# Install medcat
-! pip install medcat~=1.12.0
+! pip install medcat~=1.12.0
try:
from medcat.cat import CAT
except:
- print("WARNING: Runtime will restart automatically and please run other cells thereafter.")
+ print("WARNING: Runtime will restart automatically and please run other cells thereafter.")
exit()
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Collecting medcat==1.3.0 Downloading medcat-1.3.0-py3-none-any.whl (133 kB) @@ -13334,9 +14848,10 @@
WARNING: Runtime will restart automatically and please run other cells thereafter.
import gensim
import pandas as pd
import numpy as np
@@ -13371,48 +14890,59 @@
from gensim.models import Word2Vec
DATA_DIR = "./data_p4.1/"
-! DATA_DIR="./data_p4.1/"
+
+In [2]:
+
+
+DATA_DIR = "./data_p4.1/"
+! DATA_DIR="./data_p4.1/"
-
+
+
!mkdir ./models
-!wget -N https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/noteevents.csv -P $DATA_DIR
+
+In [3]:
+
+
+!mkdir ./models
+!wget -N https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/noteevents.csv -P $DATA_DIR
-
+
mkdir: cannot create directory ‘./data’: File exists mkdir: cannot create directory ‘./models’: File exists --2022-08-25 11:42:26-- https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/noteevents.csv @@ -13431,12 +14961,16 @@
To train meta-annotations (e.g. Experiencer, Negation...) we need two additional models:
# To train the tokenizer we will use all the data we have from our dummy dataset.
-df = pd.read_csv(DATA_DIR + "noteevents.csv")
+df = pd.read_csv(DATA_DIR + "noteevents.csv")
df.head()
# The tokenizers from huggingface require us to save all the text used for
#training into one/multiple text files.
-f = open(DATA_DIR + "tok_data.txt", 'w')
-for text in df['text'].values:
- #We'll remove new lines, so that we have one document in one line
- text = text.strip().replace("\n", ' ')
+f = open(DATA_DIR + "tok_data.txt", 'w')
+for text in df['text'].values:
+ #We'll remove new lines, so that we have one document in one line
+ text = text.strip().replace("\n", ' ')
f.write(text.lower()) # Lowercase text to remove noise
- f.write("\n")
+ f.write("\n")
f.close()
# Create, train and save the tokenizer
tokenizer = ByteLevelBPETokenizer()
-tokenizer.train(DATA_DIR + "tok_data.txt")
-tokenizer.save("./models/bbpe")
+tokenizer.train(DATA_DIR + "tok_data.txt")
+tokenizer.save("./models/bbpe")
# Now we tokenize all the text we have and train word2vec
-f = open(DATA_DIR + "tok_data.txt", 'r')
+f = open(DATA_DIR + "tok_data.txt", 'r')
# Note that if you have a very large dataset, use iterators that
#read the text line by line from the file, do not load the whole file
#into memory.
@@ -13681,36 +15232,44 @@ Meta Annotations with MedCATw2v = Word2Vec(data, vector_size=300, min_count=1)
# Check is word2vec trained, Ġ - for this tokenizer denotes start of word (a space)
-w2v.wv.most_similar('Ġcancer')
+w2v.wv.most_similar('Ġcancer')
[('Ġmetastatic', 0.7546937465667725),
('Ġcolon', 0.7531586289405823),
('Ġbreast', 0.7017560601234436),
@@ -13726,14 +15285,17 @@ Meta Annotations with MedCAT
+
+
-
-
-In [9]:
-
-
+
+In [9]:
+
+
# Now we just have to create the embeddings matrix
embeddings = []
for i in range(tokenizer.get_vocab_size()):
@@ -13746,30 +15308,35 @@ Meta Annotations with MedCATembeddings.append(np.random.rand(300))
-
+
+
+
+
+
-
-
-In [10]:
-
-
+
+In [10]:
+
+
# Save the embeddings
-np.save(open("./models/embeddings.npy", 'wb'), np.array(embeddings))
+np.save(open("./models/embeddings.npy", 'wb'), np.array(embeddings))
-
+
+
-
-
-
+
+
+
+
diff --git a/notebooks/introductory/Part_4_1_ByteLevelBPETokenizer_and_Embeddings.ipynb b/notebooks/introductory/Part_4_1_ByteLevelBPETokenizer_and_Embeddings.ipynb
index 2700ba6..2d512e2 100644
--- a/notebooks/introductory/Part_4_1_ByteLevelBPETokenizer_and_Embeddings.ipynb
+++ b/notebooks/introductory/Part_4_1_ByteLevelBPETokenizer_and_Embeddings.ipynb
@@ -1,5 +1,12 @@
{
"cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### NOTE: This tutorial is applicable for BiLSTM model not BERT as BERT model uses its pre-trained tokenizer.
When using BERT model for MetaCAT, directly move on to Tutorial 4.2."
+ ]
+ },
{
"cell_type": "code",
"execution_count": 1,
diff --git a/notebooks/introductory/Part_4_2_Supervised_Training_and_Meta_annotations.html b/notebooks/introductory/Part_4_2_Supervised_Training_and_Meta_annotations.html
index e28da27..b4bb367 100644
--- a/notebooks/introductory/Part_4_2_Supervised_Training_and_Meta_annotations.html
+++ b/notebooks/introductory/Part_4_2_Supervised_Training_and_Meta_annotations.html
@@ -1,11249 +1,12626 @@
+
-Part_4_2_Supervised_Training_and_Meta_annotations
+Part_4_2_Supervised_Training_and_Meta_annotations
-
-
+
+
+
+
+
+
+
+
-
+body[data-format='mobile'] .jp-OutputArea-child .jp-OutputArea-output {
+ display: table-row;
+}
-
-
-
-
-
-
+
-
-
-
-
-
-
-In [1]:
-
-
+
+
+
+
+
+
+In [ ]:
+
+
# Install medcat
-! pip install medcat~=1.12.0
+! pip install medcat~=1.12.1
# Get the spacy model
-! python -m spacy download en_core_web_md
+! python -m spacy download en_core_web_md
try:
from medcat.cat import CAT
except:
- print("WARNING: Runtime will restart automatically and please run other cells thereafter.")
+ print("WARNING: Runtime will restart automatically and please run other cells thereafter.")
exit()
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
-Collecting medcat==1.3.0
- Downloading medcat-1.3.0-py3-none-any.whl (133 kB)
- |████████████████████████████████| 133 kB 14.3 MB/s
-Collecting spacy<3.1.4,>=3.1.0
- Downloading spacy-3.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.9 MB)
- |████████████████████████████████| 5.9 MB 28.0 MB/s
-Collecting aiofiles~=0.8.0
- Downloading aiofiles-0.8.0-py3-none-any.whl (13 kB)
-Collecting psutil<6.0.0,>=5.8.0
- Downloading psutil-5.9.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (281 kB)
- |████████████████████████████████| 281 kB 104.2 MB/s
-Requirement already satisfied: click<=8.0.4 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (7.1.2)
-Collecting xxhash==3.0.0
- Downloading xxhash-3.0.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)
- |████████████████████████████████| 212 kB 58.1 MB/s
-Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (4.64.0)
-Collecting gensim~=4.1.2
- Downloading gensim-4.1.2-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (24.1 MB)
- |████████████████████████████████| 24.1 MB 1.4 MB/s
-Collecting blis<=0.7.5
- Downloading blis-0.7.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.9 MB)
- |████████████████████████████████| 9.9 MB 56.3 MB/s
-Collecting transformers~=4.19.2
- Downloading transformers-4.19.4-py3-none-any.whl (4.2 MB)
- |████████████████████████████████| 4.2 MB 64.9 MB/s
-Requirement already satisfied: scipy<=1.8.1,>=1.5.4 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (1.7.3)
-Collecting ipywidgets~=7.6.5
- Downloading ipywidgets-7.6.6-py2.py3-none-any.whl (121 kB)
- |████████████████████████████████| 121 kB 71.5 MB/s
-Collecting jsonpickle~=2.0.0
- Downloading jsonpickle-2.0.0-py2.py3-none-any.whl (37 kB)
-Collecting sklearn~=0.0
- Downloading sklearn-0.0.tar.gz (1.1 kB)
-Collecting elasticsearch<8.0.0,>=7.10
- Downloading elasticsearch-7.17.4-py2.py3-none-any.whl (385 kB)
- |████████████████████████████████| 385 kB 60.3 MB/s
-Requirement already satisfied: numpy>=1.21.4 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (1.21.6)
-Collecting py2neo==2021.2.3
- Downloading py2neo-2021.2.3-py2.py3-none-any.whl (177 kB)
- |████████████████████████████████| 177 kB 48.1 MB/s
-Requirement already satisfied: pandas<=1.4.2,>=1.1.5 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (1.3.5)
-Collecting multiprocess
- Downloading multiprocess-0.70.13-py37-none-any.whl (115 kB)
- |████████████████████████████████| 115 kB 66.8 MB/s
-Collecting datasets~=2.2.2
- Downloading datasets-2.2.2-py3-none-any.whl (346 kB)
- |████████████████████████████████| 346 kB 66.9 MB/s
-Requirement already satisfied: dill~=0.3.4 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (0.3.5.1)
-Requirement already satisfied: torch>=1.0 in /usr/local/lib/python3.7/dist-packages (from medcat==1.3.0) (1.12.1+cu113)
-Requirement already satisfied: urllib3 in /usr/local/lib/python3.7/dist-packages (from py2neo==2021.2.3->medcat==1.3.0) (1.24.3)
-Requirement already satisfied: pygments>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from py2neo==2021.2.3->medcat==1.3.0) (2.6.1)
-Requirement already satisfied: six>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from py2neo==2021.2.3->medcat==1.3.0) (1.15.0)
-Collecting interchange~=2021.0.4
- Downloading interchange-2021.0.4-py2.py3-none-any.whl (28 kB)
-Collecting pansi>=2020.7.3
- Downloading pansi-2020.7.3-py2.py3-none-any.whl (10 kB)
-Requirement already satisfied: certifi in /usr/local/lib/python3.7/dist-packages (from py2neo==2021.2.3->medcat==1.3.0) (2022.6.15)
-Requirement already satisfied: packaging in /usr/local/lib/python3.7/dist-packages (from py2neo==2021.2.3->medcat==1.3.0) (21.3)
-Collecting monotonic
- Downloading monotonic-1.6-py2.py3-none-any.whl (8.2 kB)
-Collecting dill~=0.3.4
- Downloading dill-0.3.4-py2.py3-none-any.whl (86 kB)
- |████████████████████████████████| 86 kB 5.8 MB/s
-Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.7/dist-packages (from datasets~=2.2.2->medcat==1.3.0) (4.12.0)
-Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.7/dist-packages (from datasets~=2.2.2->medcat==1.3.0) (2.23.0)
-Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.7/dist-packages (from datasets~=2.2.2->medcat==1.3.0) (2022.7.1)
-Requirement already satisfied: pyarrow>=6.0.0 in /usr/local/lib/python3.7/dist-packages (from datasets~=2.2.2->medcat==1.3.0) (6.0.1)
-Requirement already satisfied: aiohttp in /usr/local/lib/python3.7/dist-packages (from datasets~=2.2.2->medcat==1.3.0) (3.8.1)
-Collecting responses<0.19
- Downloading responses-0.18.0-py3-none-any.whl (38 kB)
-Collecting huggingface-hub<1.0.0,>=0.1.0
- Downloading huggingface_hub-0.9.0-py3-none-any.whl (120 kB)
- |████████████████████████████████| 120 kB 69.8 MB/s
-Requirement already satisfied: smart-open>=1.8.1 in /usr/local/lib/python3.7/dist-packages (from gensim~=4.1.2->medcat==1.3.0) (5.2.1)
-Requirement already satisfied: filelock in /usr/local/lib/python3.7/dist-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets~=2.2.2->medcat==1.3.0) (3.8.0)
-Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets~=2.2.2->medcat==1.3.0) (6.0)
-Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets~=2.2.2->medcat==1.3.0) (4.1.1)
-Requirement already satisfied: pytz in /usr/local/lib/python3.7/dist-packages (from interchange~=2021.0.4->py2neo==2021.2.3->medcat==1.3.0) (2022.2.1)
-Collecting widgetsnbextension~=3.5.0
- Downloading widgetsnbextension-3.5.2-py2.py3-none-any.whl (1.6 MB)
- |████████████████████████████████| 1.6 MB 51.4 MB/s
-Requirement already satisfied: traitlets>=4.3.1 in /usr/local/lib/python3.7/dist-packages (from ipywidgets~=7.6.5->medcat==1.3.0) (5.1.1)
-Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.7/dist-packages (from ipywidgets~=7.6.5->medcat==1.3.0) (7.9.0)
-Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.7/dist-packages (from ipywidgets~=7.6.5->medcat==1.3.0) (5.3.4)
-Requirement already satisfied: nbformat>=4.2.0 in /usr/local/lib/python3.7/dist-packages (from ipywidgets~=7.6.5->medcat==1.3.0) (5.4.0)
-Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.7/dist-packages (from ipywidgets~=7.6.5->medcat==1.3.0) (0.2.0)
-Collecting jupyterlab-widgets<3,>=1.0.0
- Downloading jupyterlab_widgets-1.1.1-py3-none-any.whl (245 kB)
- |████████████████████████████████| 245 kB 52.8 MB/s
-Requirement already satisfied: jupyter-client in /usr/local/lib/python3.7/dist-packages (from ipykernel>=4.5.1->ipywidgets~=7.6.5->medcat==1.3.0) (6.1.12)
-Requirement already satisfied: tornado>=4.2 in /usr/local/lib/python3.7/dist-packages (from ipykernel>=4.5.1->ipywidgets~=7.6.5->medcat==1.3.0) (5.1.1)
-Requirement already satisfied: prompt-toolkit<2.1.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (2.0.10)
-Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (57.4.0)
-Requirement already satisfied: backcall in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.2.0)
-Collecting jedi>=0.10
- Downloading jedi-0.18.1-py2.py3-none-any.whl (1.6 MB)
- |████████████████████████████████| 1.6 MB 45.4 MB/s
-Requirement already satisfied: decorator in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (4.4.2)
-Requirement already satisfied: pickleshare in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.7.5)
-Requirement already satisfied: pexpect in /usr/local/lib/python3.7/dist-packages (from ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (4.8.0)
-Requirement already satisfied: parso<0.9.0,>=0.8.0 in /usr/local/lib/python3.7/dist-packages (from jedi>=0.10->ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.8.3)
-Requirement already satisfied: jupyter-core in /usr/local/lib/python3.7/dist-packages (from nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (4.11.1)
-Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.7/dist-packages (from nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (2.16.1)
-Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.7/dist-packages (from nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (4.3.3)
-Requirement already satisfied: attrs>=17.4.0 in /usr/local/lib/python3.7/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (22.1.0)
-Requirement already satisfied: importlib-resources>=1.4.0 in /usr/local/lib/python3.7/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (5.9.0)
-Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.7/dist-packages (from jsonschema>=2.6->nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.18.1)
-Requirement already satisfied: zipp>=3.1.0 in /usr/local/lib/python3.7/dist-packages (from importlib-resources>=1.4.0->jsonschema>=2.6->nbformat>=4.2.0->ipywidgets~=7.6.5->medcat==1.3.0) (3.8.1)
-Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging->py2neo==2021.2.3->medcat==1.3.0) (3.0.9)
-Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas<=1.4.2,>=1.1.5->medcat==1.3.0) (2.8.2)
-Requirement already satisfied: wcwidth in /usr/local/lib/python3.7/dist-packages (from prompt-toolkit<2.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.2.5)
-Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->datasets~=2.2.2->medcat==1.3.0) (3.0.4)
-Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests>=2.19.0->datasets~=2.2.2->medcat==1.3.0) (2.10)
-Collecting urllib3
- Downloading urllib3-1.25.11-py2.py3-none-any.whl (127 kB)
- |████████████████████████████████| 127 kB 57.1 MB/s
-Requirement already satisfied: scikit-learn in /usr/local/lib/python3.7/dist-packages (from sklearn~=0.0->medcat==1.3.0) (1.0.2)
-Collecting typing-extensions>=3.7.4.3
- Downloading typing_extensions-3.10.0.2-py3-none-any.whl (26 kB)
-Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.8 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (3.0.10)
-Requirement already satisfied: wasabi<1.1.0,>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (0.10.1)
-Collecting pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4
- Downloading pydantic-1.8.2-cp37-cp37m-manylinux2014_x86_64.whl (10.1 MB)
- |████████████████████████████████| 10.1 MB 68.6 MB/s
-Requirement already satisfied: jinja2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (2.11.3)
-Requirement already satisfied: typer<0.5.0,>=0.3.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (0.4.2)
-Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (3.0.7)
-Collecting thinc<8.1.0,>=8.0.9
- Downloading thinc-8.0.17-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (660 kB)
- |████████████████████████████████| 660 kB 81.8 MB/s
-Requirement already satisfied: pathy>=0.3.5 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (0.6.2)
-Requirement already satisfied: srsly<3.0.0,>=2.4.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (2.4.4)
-Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (2.0.8)
-Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (2.0.6)
-Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.1.4,>=3.1.0->medcat==1.3.0) (1.0.8)
-Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.7/dist-packages (from transformers~=4.19.2->medcat==1.3.0) (2022.6.2)
-Collecting tokenizers!=0.11.3,<0.13,>=0.11.1
- Downloading tokenizers-0.12.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (6.6 MB)
- |████████████████████████████████| 6.6 MB 46.8 MB/s
-Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.7/dist-packages (from widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (5.3.1)
-Requirement already satisfied: nbconvert in /usr/local/lib/python3.7/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (5.6.1)
-Requirement already satisfied: terminado>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.13.3)
-Requirement already satisfied: Send2Trash in /usr/local/lib/python3.7/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (1.8.0)
-Requirement already satisfied: pyzmq>=13 in /usr/local/lib/python3.7/dist-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets~=7.6.5->medcat==1.3.0) (23.2.1)
-Requirement already satisfied: ptyprocess in /usr/local/lib/python3.7/dist-packages (from terminado>=0.8.1->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.7.0)
-Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (1.2.0)
-Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (1.3.1)
-Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (6.0.2)
-Requirement already satisfied: asynctest==0.13.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (0.13.0)
-Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (1.8.1)
-Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (2.1.0)
-Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets~=2.2.2->medcat==1.3.0) (4.0.2)
-Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.7/dist-packages (from jinja2->spacy<3.1.4,>=3.1.0->medcat==1.3.0) (2.0.1)
-Collecting multiprocess
- Downloading multiprocess-0.70.12.2-py37-none-any.whl (112 kB)
- |████████████████████████████████| 112 kB 72.5 MB/s
-Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (1.5.0)
-Requirement already satisfied: bleach in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (5.0.1)
-Requirement already satisfied: defusedxml in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.7.1)
-Requirement already satisfied: entrypoints>=0.2.2 in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.4)
-Requirement already satisfied: testpath in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.6.0)
-Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.8.4)
-Requirement already satisfied: webencodings in /usr/local/lib/python3.7/dist-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets~=7.6.5->medcat==1.3.0) (0.5.1)
-Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn->sklearn~=0.0->medcat==1.3.0) (1.1.0)
-Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn->sklearn~=0.0->medcat==1.3.0) (3.1.0)
-Building wheels for collected packages: sklearn
- Building wheel for sklearn (setup.py) ... done
- Created wheel for sklearn: filename=sklearn-0.0-py2.py3-none-any.whl size=1310 sha256=0fb409a925dd6e7ddc0cdc8d7911f2d6e3889472ad56bfe48302496b0fffc20d
- Stored in directory: /root/.cache/pip/wheels/46/ef/c3/157e41f5ee1372d1be90b09f74f82b10e391eaacca8f22d33e
-Successfully built sklearn
-Installing collected packages: typing-extensions, jedi, urllib3, pydantic, dill, blis, xxhash, widgetsnbextension, tokenizers, thinc, responses, pansi, multiprocess, monotonic, jupyterlab-widgets, interchange, huggingface-hub, transformers, spacy, sklearn, py2neo, psutil, jsonpickle, ipywidgets, gensim, elasticsearch, datasets, aiofiles, medcat
- Attempting uninstall: typing-extensions
- Found existing installation: typing-extensions 4.1.1
- Uninstalling typing-extensions-4.1.1:
- Successfully uninstalled typing-extensions-4.1.1
- Attempting uninstall: urllib3
- Found existing installation: urllib3 1.24.3
- Uninstalling urllib3-1.24.3:
- Successfully uninstalled urllib3-1.24.3
- Attempting uninstall: pydantic
- Found existing installation: pydantic 1.9.2
- Uninstalling pydantic-1.9.2:
- Successfully uninstalled pydantic-1.9.2
- Attempting uninstall: dill
- Found existing installation: dill 0.3.5.1
- Uninstalling dill-0.3.5.1:
- Successfully uninstalled dill-0.3.5.1
- Attempting uninstall: blis
- Found existing installation: blis 0.7.8
- Uninstalling blis-0.7.8:
- Successfully uninstalled blis-0.7.8
- Attempting uninstall: widgetsnbextension
- Found existing installation: widgetsnbextension 3.6.1
- Uninstalling widgetsnbextension-3.6.1:
- Successfully uninstalled widgetsnbextension-3.6.1
- Attempting uninstall: thinc
- Found existing installation: thinc 8.1.0
- Uninstalling thinc-8.1.0:
- Successfully uninstalled thinc-8.1.0
- Attempting uninstall: jupyterlab-widgets
- Found existing installation: jupyterlab-widgets 3.0.2
- Uninstalling jupyterlab-widgets-3.0.2:
- Successfully uninstalled jupyterlab-widgets-3.0.2
- Attempting uninstall: spacy
- Found existing installation: spacy 3.4.1
- Uninstalling spacy-3.4.1:
- Successfully uninstalled spacy-3.4.1
- Attempting uninstall: psutil
- Found existing installation: psutil 5.4.8
- Uninstalling psutil-5.4.8:
- Successfully uninstalled psutil-5.4.8
- Attempting uninstall: ipywidgets
- Found existing installation: ipywidgets 7.7.1
- Uninstalling ipywidgets-7.7.1:
- Successfully uninstalled ipywidgets-7.7.1
- Attempting uninstall: gensim
- Found existing installation: gensim 3.6.0
- Uninstalling gensim-3.6.0:
- Successfully uninstalled gensim-3.6.0
-ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
-en-core-web-sm 3.4.0 requires spacy<3.5.0,>=3.4.0, but you have spacy 3.1.3 which is incompatible.
-Successfully installed aiofiles-0.8.0 blis-0.7.5 datasets-2.2.2 dill-0.3.4 elasticsearch-7.17.4 gensim-4.1.2 huggingface-hub-0.9.0 interchange-2021.0.4 ipywidgets-7.6.6 jedi-0.18.1 jsonpickle-2.0.0 jupyterlab-widgets-1.1.1 medcat-1.3.0 monotonic-1.6 multiprocess-0.70.12.2 pansi-2020.7.3 psutil-5.9.1 py2neo-2021.2.3 pydantic-1.8.2 responses-0.18.0 sklearn-0.0 spacy-3.1.3 thinc-8.0.17 tokenizers-0.12.1 transformers-4.19.4 typing-extensions-3.10.0.2 urllib3-1.25.11 widgetsnbextension-3.5.2 xxhash-3.0.0
-
+
+
-
+
+
+
-
+
+
+
+
+
+
+
+
+
+Collecting medcat~=1.12.1
+ Downloading medcat-1.12.1-py3-none-any.whl.metadata (8.9 kB)
+Collecting numpy<1.26.0,>=1.22.0 (from medcat~=1.12.1)
+ Downloading numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.6 kB)
+Requirement already satisfied: pandas>=1.4.2 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (2.1.4)
+Requirement already satisfied: gensim<5.0.0,>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (4.3.3)
+Requirement already satisfied: spacy<4.0.0,>=3.6.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (3.7.5)
+Collecting scipy~=1.9.2 (from medcat~=1.12.1)
+ Downloading scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (58 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.4/58.4 kB 549.0 kB/s eta 0:00:00
+Requirement already satisfied: transformers<5.0.0,>=4.34.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (4.42.4)
+Requirement already satisfied: accelerate>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (0.32.1)
+Requirement already satisfied: torch<3.0.0,>=1.13.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (2.3.1+cu121)
+Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (4.66.5)
+Requirement already satisfied: scikit-learn<2.0.0,>=1.1.3 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (1.3.2)
+Collecting dill<1.0.0,>=0.3.6 (from medcat~=1.12.1)
+ Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)
+Collecting datasets<3.0.0,>=2.2.2 (from medcat~=1.12.1)
+ Downloading datasets-2.21.0-py3-none-any.whl.metadata (21 kB)
+Requirement already satisfied: jsonpickle>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (3.2.2)
+Requirement already satisfied: psutil>=5.8.0 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (5.9.5)
+Collecting multiprocess~=0.70.12 (from medcat~=1.12.1)
+ Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)
+Collecting aiofiles>=0.8.0 (from medcat~=1.12.1)
+ Downloading aiofiles-24.1.0-py3-none-any.whl.metadata (10 kB)
+Requirement already satisfied: ipywidgets>=7.6.5 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (7.7.1)
+Collecting xxhash>=3.0.0 (from medcat~=1.12.1)
+ Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)
+Requirement already satisfied: blis<1.0.0,>=0.7.5 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (0.7.11)
+Requirement already satisfied: click>=8.0.4 in /usr/local/lib/python3.10/dist-packages (from medcat~=1.12.1) (8.1.7)
+Collecting pydantic<2.0,>=1.10.0 (from medcat~=1.12.1)
+ Downloading pydantic-1.10.17-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (151 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 151.6/151.6 kB 1.4 MB/s eta 0:00:00
+Collecting humanfriendly~=10.0 (from medcat~=1.12.1)
+ Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)
+Collecting peft>=0.8.2 (from medcat~=1.12.1)
+ Downloading peft-0.12.0-py3-none-any.whl.metadata (13 kB)
+Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.23.0->medcat~=1.12.1) (24.1)
+Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.23.0->medcat~=1.12.1) (6.0.2)
+Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.23.0->medcat~=1.12.1) (0.23.5)
+Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.23.0->medcat~=1.12.1) (0.4.4)
+Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (3.15.4)
+Collecting pyarrow>=15.0.0 (from datasets<3.0.0,>=2.2.2->medcat~=1.12.1)
+ Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.3 kB)
+Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.10/dist-packages (from datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (2.32.3)
+Requirement already satisfied: fsspec<=2024.6.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from fsspec[http]<=2024.6.1,>=2023.1.0->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (2024.6.1)
+Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (3.10.2)
+Requirement already satisfied: smart-open>=1.8.1 in /usr/local/lib/python3.10/dist-packages (from gensim<5.0.0,>=4.3.0->medcat~=1.12.1) (7.0.4)
+Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (5.5.6)
+Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (0.2.0)
+Requirement already satisfied: traitlets>=4.3.1 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (5.7.1)
+Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (3.6.8)
+Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (7.34.0)
+Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets>=7.6.5->medcat~=1.12.1) (3.0.11)
+Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.4.2->medcat~=1.12.1) (2.8.2)
+Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.4.2->medcat~=1.12.1) (2024.1)
+Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.4.2->medcat~=1.12.1) (2024.1)
+Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<2.0,>=1.10.0->medcat~=1.12.1) (4.12.2)
+Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn<2.0.0,>=1.1.3->medcat~=1.12.1) (1.4.2)
+Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn<2.0.0,>=1.1.3->medcat~=1.12.1) (3.5.0)
+Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (3.0.12)
+Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.0.5)
+Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.0.10)
+Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (2.0.8)
+Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (3.0.9)
+Requirement already satisfied: thinc<8.3.0,>=8.2.2 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (8.2.5)
+Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.1.3)
+Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (2.4.8)
+Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (2.0.10)
+Requirement already satisfied: weasel<0.5.0,>=0.1.0 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (0.4.1)
+Requirement already satisfied: typer<1.0.0,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (0.12.3)
+Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (3.1.4)
+Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (71.0.4)
+Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (3.4.0)
+Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch<3.0.0,>=1.13.0->medcat~=1.12.1) (1.13.1)
+Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch<3.0.0,>=1.13.0->medcat~=1.12.1) (3.3)
+Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
+Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
+Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
+Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
+Collecting nvidia-cublas-cu12==12.1.3.1 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
+Collecting nvidia-cufft-cu12==11.0.2.54 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
+Collecting nvidia-curand-cu12==10.3.2.106 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)
+Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
+Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)
+Collecting nvidia-nccl-cu12==2.20.5 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)
+Collecting nvidia-nvtx-cu12==12.1.105 (from torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)
+Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch<3.0.0,>=1.13.0->medcat~=1.12.1) (2.3.1)
+Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch<3.0.0,>=1.13.0->medcat~=1.12.1)
+ Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
+Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->medcat~=1.12.1) (2024.5.15)
+Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->medcat~=1.12.1) (0.19.1)
+Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (2.3.5)
+Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (1.3.1)
+Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (24.2.0)
+Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (1.4.1)
+Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (6.0.5)
+Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (1.9.4)
+Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (4.0.3)
+Requirement already satisfied: jupyter-client in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets>=7.6.5->medcat~=1.12.1) (6.1.12)
+Requirement already satisfied: tornado>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipykernel>=4.5.1->ipywidgets>=7.6.5->medcat~=1.12.1) (6.3.3)
+Collecting jedi>=0.16 (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1)
+ Using cached jedi-0.19.1-py2.py3-none-any.whl.metadata (22 kB)
+Requirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.4.2)
+Requirement already satisfied: pickleshare in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.7.5)
+Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (3.0.47)
+Requirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (2.16.1)
+Requirement already satisfied: backcall in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.2.0)
+Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.1.7)
+Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.9.0)
+Requirement already satisfied: language-data>=1.2 in /usr/local/lib/python3.10/dist-packages (from langcodes<4.0.0,>=3.2.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.2.0)
+Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas>=1.4.2->medcat~=1.12.1) (1.16.0)
+Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (3.3.2)
+Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (3.7)
+Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (2.0.7)
+Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets<3.0.0,>=2.2.2->medcat~=1.12.1) (2024.7.4)
+Requirement already satisfied: wrapt in /usr/local/lib/python3.10/dist-packages (from smart-open>=1.8.1->gensim<5.0.0,>=4.3.0->medcat~=1.12.1) (1.16.0)
+Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from thinc<8.3.0,>=8.2.2->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (0.1.5)
+Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.5.4)
+Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (13.7.1)
+Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from weasel<0.5.0,>=0.1.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (0.18.1)
+Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.10/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (6.5.5)
+Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (2.1.5)
+Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch<3.0.0,>=1.13.0->medcat~=1.12.1) (1.3.0)
+Requirement already satisfied: parso<0.9.0,>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.8.4)
+Requirement already satisfied: marisa-trie>=0.7.7 in /usr/local/lib/python3.10/dist-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (1.2.0)
+Requirement already satisfied: pyzmq<25,>=17 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (24.0.1)
+Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (23.1.0)
+Requirement already satisfied: jupyter-core>=4.6.1 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (5.7.2)
+Requirement already satisfied: nbformat in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (5.10.4)
+Requirement already satisfied: nbconvert>=5 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (6.5.4)
+Requirement already satisfied: nest-asyncio>=1.5 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.6.0)
+Requirement already satisfied: Send2Trash>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.8.3)
+Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.18.1)
+Requirement already satisfied: prometheus-client in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.20.0)
+Requirement already satisfied: nbclassic>=0.4.7 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.1.0)
+Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.10/dist-packages (from pexpect>4.3->ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.7.0)
+Requirement already satisfied: wcwidth in /usr/local/lib/python3.10/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=4.0.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.2.13)
+Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (3.0.0)
+Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.10/dist-packages (from jupyter-core>=4.6.1->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.2.2)
+Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<4.0.0,>=3.6.0->medcat~=1.12.1) (0.1.2)
+Requirement already satisfied: notebook-shim>=0.2.3 in /usr/local/lib/python3.10/dist-packages (from nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.2.4)
+Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.9.4)
+Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.12.3)
+Requirement already satisfied: bleach in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (6.1.0)
+Requirement already satisfied: defusedxml in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.7.1)
+Requirement already satisfied: entrypoints>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.4)
+Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.3.0)
+Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.8.4)
+Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.10.0)
+Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.5.1)
+Requirement already satisfied: tinycss2 in /usr/local/lib/python3.10/dist-packages (from nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.3.0)
+Requirement already satisfied: fastjsonschema>=2.15 in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (2.20.0)
+Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (4.23.0)
+Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.10/dist-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (21.2.0)
+Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (2023.12.1)
+Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.35.1)
+Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.20.0)
+Requirement already satisfied: jupyter-server<3,>=1.8 in /usr/local/lib/python3.10/dist-packages (from notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.24.0)
+Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.17.0)
+Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (2.5)
+Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from bleach->nbconvert>=5->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (0.5.1)
+Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (2.22)
+Requirement already satisfied: anyio<4,>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (3.7.1)
+Requirement already satisfied: websocket-client in /usr/local/lib/python3.10/dist-packages (from jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.8.0)
+Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.3.1)
+Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4,>=3.1.0->jupyter-server<3,>=1.8->notebook-shim>=0.2.3->nbclassic>=0.4.7->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets>=7.6.5->medcat~=1.12.1) (1.2.2)
+Downloading medcat-1.12.1-py3-none-any.whl (235 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 235.5/235.5 kB 3.5 MB/s eta 0:00:00
+Downloading aiofiles-24.1.0-py3-none-any.whl (15 kB)
+Downloading datasets-2.21.0-py3-none-any.whl (527 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 527.3/527.3 kB 8.8 MB/s eta 0:00:00
+Downloading dill-0.3.8-py3-none-any.whl (116 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 116.3/116.3 kB 6.4 MB/s eta 0:00:00
+Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 86.8/86.8 kB 1.7 MB/s eta 0:00:00
+Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 134.8/134.8 kB 6.7 MB/s eta 0:00:00
+Downloading numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18.2/18.2 MB 29.9 MB/s eta 0:00:00
+Downloading peft-0.12.0-py3-none-any.whl (296 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 296.4/296.4 kB 13.4 MB/s eta 0:00:00
+Downloading pydantic-1.10.17-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.1/3.1 MB 54.3 MB/s eta 0:00:00
+Downloading scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.7 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 33.7/33.7 MB 35.2 MB/s eta 0:00:00
+Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)
+Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)
+Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)
+Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)
+Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)
+Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)
+Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)
+Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)
+Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)
+Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)
+Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)
+Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 194.1/194.1 kB 341.2 kB/s eta 0:00:00
+Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (39.9 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 39.9/39.9 MB 12.0 MB/s eta 0:00:00
+Using cached jedi-0.19.1-py2.py3-none-any.whl (1.6 MB)
+Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl (19.7 MB)
+Installing collected packages: xxhash, pydantic, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, jedi, humanfriendly, dill, aiofiles, scipy, pyarrow, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, nvidia-cusolver-cu12, datasets, peft, medcat
+ Attempting uninstall: pydantic
+ Found existing installation: pydantic 2.8.2
+ Uninstalling pydantic-2.8.2:
+ Successfully uninstalled pydantic-2.8.2
+ Attempting uninstall: numpy
+ Found existing installation: numpy 1.26.4
+ Uninstalling numpy-1.26.4:
+ Successfully uninstalled numpy-1.26.4
+ Attempting uninstall: scipy
+ Found existing installation: scipy 1.13.1
+ Uninstalling scipy-1.13.1:
+ Successfully uninstalled scipy-1.13.1
+ Attempting uninstall: pyarrow
+ Found existing installation: pyarrow 14.0.2
+ Uninstalling pyarrow-14.0.2:
+ Successfully uninstalled pyarrow-14.0.2
+ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
+albumentations 1.4.13 requires pydantic>=2.7.0, but you have pydantic 1.10.17 which is incompatible.
+albumentations 1.4.13 requires scipy>=1.10.0, but you have scipy 1.9.3 which is incompatible.
+cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 17.0.0 which is incompatible.
+ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 17.0.0 which is incompatible.
+pandas-stubs 2.1.4.231227 requires numpy>=1.26.0; python_version < "3.13", but you have numpy 1.25.2 which is incompatible.
+Successfully installed aiofiles-24.1.0 datasets-2.21.0 dill-0.3.8 humanfriendly-10.0 jedi-0.19.1 medcat-1.12.1 multiprocess-0.70.16 numpy-1.25.2 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.6.20 nvidia-nvtx-cu12-12.1.105 peft-0.12.0 pyarrow-17.0.0 pydantic-1.10.17 scipy-1.9.3 xxhash-3.4.1
+
+
+
+
+
+
-
-
-
+
-
-Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
-Collecting en-core-web-md==3.1.0
- Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.1.0/en_core_web_md-3.1.0-py3-none-any.whl (45.4 MB)
- |████████████████████████████████| 45.4 MB 99.1 MB/s
-Requirement already satisfied: spacy<3.2.0,>=3.1.0 in /usr/local/lib/python3.7/dist-packages (from en-core-web-md==3.1.0) (3.1.3)
-Requirement already satisfied: blis<0.8.0,>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (0.7.5)
-Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (4.64.0)
-Requirement already satisfied: jinja2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.11.3)
-Requirement already satisfied: wasabi<1.1.0,>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (0.10.1)
-Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (21.3)
-Requirement already satisfied: srsly<3.0.0,>=2.4.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.4.4)
-Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (1.8.2)
-Requirement already satisfied: thinc<8.1.0,>=8.0.9 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (8.0.17)
-Requirement already satisfied: typing-extensions<4.0.0.0,>=3.7.4 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.10.0.2)
-Requirement already satisfied: typer<0.5.0,>=0.3.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (0.4.2)
-Requirement already satisfied: pathy>=0.3.5 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (0.6.2)
-Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.0.7)
-Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (1.0.8)
-Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (57.4.0)
-Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.0.6)
-Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.8 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.0.10)
-Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.23.0)
-Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.0.8)
-Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (1.21.6)
-Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from catalogue<2.1.0,>=2.0.6->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.8.1)
-Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.0.9)
-Requirement already satisfied: smart-open<6.0.0,>=5.2.1 in /usr/local/lib/python3.7/dist-packages (from pathy>=0.3.5->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (5.2.1)
-Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.10)
-Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2022.6.15)
-Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (1.25.11)
-Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (3.0.4)
-Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.7/dist-packages (from typer<0.5.0,>=0.3.0->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (7.1.2)
-Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.7/dist-packages (from jinja2->spacy<3.2.0,>=3.1.0->en-core-web-md==3.1.0) (2.0.1)
+
+
+
+
+
+
+
+Collecting en-core-web-md==3.7.1
+ Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.7.1/en_core_web_md-3.7.1-py3-none-any.whl (42.8 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.8/42.8 MB 16.1 MB/s eta 0:00:00
+Requirement already satisfied: spacy<3.8.0,>=3.7.2 in /usr/local/lib/python3.10/dist-packages (from en-core-web-md==3.7.1) (3.7.5)
+Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.12)
+Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.0.5)
+Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.0.10)
+Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.8)
+Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.9)
+Requirement already satisfied: thinc<8.3.0,>=8.2.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (8.2.5)
+Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.1.3)
+Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.4.8)
+Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.10)
+Requirement already satisfied: weasel<0.5.0,>=0.1.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.4.1)
+Requirement already satisfied: typer<1.0.0,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.12.3)
+Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (4.66.5)
+Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.32.3)
+Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.10.17)
+Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.1.4)
+Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (71.0.4)
+Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (24.1)
+Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.4.0)
+Requirement already satisfied: numpy>=1.19.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.25.2)
+Requirement already satisfied: language-data>=1.2 in /usr/local/lib/python3.10/dist-packages (from langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.2.0)
+Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (4.12.2)
+Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.3.2)
+Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.7)
+Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.7)
+Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2024.7.4)
+Requirement already satisfied: blis<0.8.0,>=0.7.8 in /usr/local/lib/python3.10/dist-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.7.11)
+Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.1.5)
+Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (8.1.7)
+Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.5.4)
+Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (13.7.1)
+Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.18.1)
+Requirement already satisfied: smart-open<8.0.0,>=5.2.1 in /usr/local/lib/python3.10/dist-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (7.0.4)
+Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.1.5)
+Requirement already satisfied: marisa-trie>=0.7.7 in /usr/local/lib/python3.10/dist-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.2.0)
+Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.0)
+Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.16.1)
+Requirement already satisfied: wrapt in /usr/local/lib/python3.10/dist-packages (from smart-open<8.0.0,>=5.2.1->weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.16.0)
+Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.1.2)
Installing collected packages: en-core-web-md
-Successfully installed en-core-web-md-3.1.0
+Successfully installed en-core-web-md-3.7.1
✔ Download and installation successful
You can now load the package via spacy.load('en_core_web_md')
+⚠ Restart to reload dependencies
+If you are in a Jupyter or Colab notebook, you may need to restart Python in
+order to load all the package's dependencies. You can do this by selecting the
+'Restart kernel' or 'Restart runtime' option.
WARNING: Runtime will restart automatically and please run other cells thereafter.
+
-
-
-
+
+
+
+
+
+
Restart the runtime if on colab, sometimes necessary after installing models
-
-
-In [1]:
-
-
+
+
+
+
+
+In [ ]:
+
+
+! python -m spacy download en_core_web_md
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Collecting en-core-web-md==3.7.1
+ Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.7.1/en_core_web_md-3.7.1-py3-none-any.whl (42.8 MB)
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.8/42.8 MB 11.2 MB/s eta 0:00:00
+Requirement already satisfied: spacy<3.8.0,>=3.7.2 in /usr/local/lib/python3.10/dist-packages (from en-core-web-md==3.7.1) (3.7.5)
+Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.12)
+Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.0.5)
+Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.0.10)
+Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.8)
+Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.9)
+Requirement already satisfied: thinc<8.3.0,>=8.2.2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (8.2.5)
+Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.1.3)
+Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.4.8)
+Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.10)
+Requirement already satisfied: weasel<0.5.0,>=0.1.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.4.1)
+Requirement already satisfied: typer<1.0.0,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.12.3)
+Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (4.66.5)
+Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.32.3)
+Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.10.17)
+Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.1.4)
+Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (71.0.4)
+Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (24.1)
+Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.4.0)
+Requirement already satisfied: numpy>=1.19.0 in /usr/local/lib/python3.10/dist-packages (from spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.25.2)
+Requirement already satisfied: language-data>=1.2 in /usr/local/lib/python3.10/dist-packages (from langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.2.0)
+Requirement already satisfied: typing-extensions>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (4.12.2)
+Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.3.2)
+Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.7)
+Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.0.7)
+Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2024.7.4)
+Requirement already satisfied: blis<0.8.0,>=0.7.8 in /usr/local/lib/python3.10/dist-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.7.11)
+Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from thinc<8.3.0,>=8.2.2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.1.5)
+Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (8.1.7)
+Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.5.4)
+Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (13.7.1)
+Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.18.1)
+Requirement already satisfied: smart-open<8.0.0,>=5.2.1 in /usr/local/lib/python3.10/dist-packages (from weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (7.0.4)
+Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.1.5)
+Requirement already satisfied: marisa-trie>=0.7.7 in /usr/local/lib/python3.10/dist-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.2.0)
+Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (3.0.0)
+Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (2.16.1)
+Requirement already satisfied: wrapt in /usr/local/lib/python3.10/dist-packages (from smart-open<8.0.0,>=5.2.1->weasel<0.5.0,>=0.1.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (1.16.0)
+Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy<3.8.0,>=3.7.2->en-core-web-md==3.7.1) (0.1.2)
+✔ Download and installation successful
+You can now load the package via spacy.load('en_core_web_md')
+⚠ Restart to reload dependencies
+If you are in a Jupyter or Colab notebook, you may need to restart Python in
+order to load all the package's dependencies. You can do this by selecting the
+'Restart kernel' or 'Restart runtime' option.
+
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
import pandas as pd
import numpy as np
import seaborn as sns
-import json
+import json
from matplotlib import pyplot as plt
from medcat.cat import CAT
@@ -13423,382 +15048,468 @@
from medcat.vocab import Vocab
from medcat.meta_cat import MetaCAT
from medcat.config_meta_cat import ConfigMetaCAT
-from medcat.preprocessing.tokenizers import TokenizerWrapperBPE, TokenizerWrapperBERT
+from medcat.preprocessing.tokenizers import TokenizerWrapperBPE
+from medcat.tokenizers.meta_cat_tokenizers import TokenizerWrapperBERT
from tokenizers import ByteLevelBPETokenizer
-
+
+
-
-
+
+
+
+
+
-
+
-
+
+
-
-/usr/local/lib/python3.7/dist-packages/medcat/cat.py:18: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)
- from tqdm.autonotebook import tqdm, trange
+
+/usr/local/lib/python3.10/dist-packages/medcat/cat.py:17: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)
+ from tqdm.autonotebook import tqdm, trange
+
+
+
+
-
-
-In [2]:
-
-
-DATA_DIR = "./data_p4.2/"
-! DATA_DIR="./data_p4.2/"
-vocab_path = DATA_DIR + "vocab.dat"
-cdb_path = DATA_DIR + "cdb-medmen-v1.dat"
+
+In [ ]:
+
+
+DATA_DIR = "./data_p4.2/"
+! DATA_DIR="./data_p4.2/"
+vocab_path = DATA_DIR + "vocab.dat"
+cdb_path = DATA_DIR + "cdb-medmen-v1.dat"
-
+
+
+
+
+
-
-
-In [3]:
-
-
+
+In [ ]:
+
+
# Download the models and required data
-!wget -N https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/MedCAT_Export.json -P $DATA_DIR
+!wget -N https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/MedCAT_Export.json -P $DATA_DIR
# You can also use the models created in Part 4.1 of the Tutorial
-!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/mc_status.zip -P $DATA_DIR
+!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/mc_status.zip -P $DATA_DIR
# Get MedCAT models components (Alternatively you can use a previously created MedCAT model packs)
-!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/vocab.dat -P $DATA_DIR
-!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/cdb-medmen-v1.dat -P $DATA_DIR
+!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/vocab.dat -P $DATA_DIR
+!wget -N https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/cdb-medmen-v1.dat -P $DATA_DIR
-
+
+
+
+
+
+
-
-
+
-
+
-
+
+
-
---2022-08-25 12:02:19-- https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/MedCAT_Export.json
+
+--2024-08-16 08:23:54-- https://raw.githubusercontent.com/CogStack/MedCATtutorials/main/notebooks/introductory/data/MedCAT_Export.json
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 272538 (266K) [text/plain]
-Saving to: ‘./data/MedCAT_Export.json’
+Saving to: ‘./data_p4.2/MedCAT_Export.json’
-MedCAT_Export.json 100%[===================>] 266.15K --.-KB/s in 0.01s
+MedCAT_Export.json 100%[===================>] 266.15K --.-KB/s in 0.04s
-2022-08-25 12:02:19 (19.3 MB/s) - ‘./data/MedCAT_Export.json’ saved [272538/272538]
+Last-modified header missing -- time-stamps turned off.
+2024-08-16 08:23:54 (6.82 MB/s) - ‘./data_p4.2/MedCAT_Export.json’ saved [272538/272538]
---2022-08-25 12:02:19-- https://medcat.rosalind.kcl.ac.uk/media/mc_status.zip
-Resolving medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)... 193.61.202.225
-Connecting to medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)|193.61.202.225|:443... connected.
+--2024-08-16 08:23:54-- https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/mc_status.zip
+Resolving cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)... 52.95.150.170, 3.5.246.110, 3.5.244.200, ...
+Connecting to cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)|52.95.150.170|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 37947480 (36M) [application/zip]
-Saving to: ‘./data/mc_status.zip’
+Saving to: ‘./data_p4.2/mc_status.zip’
-mc_status.zip 100%[===================>] 36.19M 46.6MB/s in 0.8s
+mc_status.zip 100%[===================>] 36.19M 20.9MB/s in 1.7s
-2022-08-25 12:02:20 (46.6 MB/s) - ‘./data/mc_status.zip’ saved [37947480/37947480]
+2024-08-16 08:23:57 (20.9 MB/s) - ‘./data_p4.2/mc_status.zip’ saved [37947480/37947480]
---2022-08-25 12:02:20-- https://medcat.rosalind.kcl.ac.uk/media/vocab.dat
-Resolving medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)... 193.61.202.225
-Connecting to medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)|193.61.202.225|:443... connected.
+--2024-08-16 08:23:57-- https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/vocab.dat
+Resolving cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)... 52.95.150.170, 3.5.246.110, 3.5.244.200, ...
+Connecting to cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)|52.95.150.170|:443... connected.
HTTP request sent, awaiting response... 200 OK
-Length: 274445907 (262M) [application/octet-stream]
-Saving to: ‘./data/vocab.dat’
+Length: 274445907 (262M) [binary/octet-stream]
+Saving to: ‘./data_p4.2/vocab.dat’
-vocab.dat 100%[===================>] 261.73M 48.8MB/s in 5.5s
+vocab.dat 100%[===================>] 261.73M 32.6MB/s in 8.8s
-2022-08-25 12:02:26 (47.6 MB/s) - ‘./data/vocab.dat’ saved [274445907/274445907]
+2024-08-16 08:24:06 (29.6 MB/s) - ‘./data_p4.2/vocab.dat’ saved [274445907/274445907]
---2022-08-25 12:02:26-- https://medcat.rosalind.kcl.ac.uk/media/cdb-medmen-v1_2.dat
-Resolving medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)... 193.61.202.225
-Connecting to medcat.rosalind.kcl.ac.uk (medcat.rosalind.kcl.ac.uk)|193.61.202.225|:443... connected.
+--2024-08-16 08:24:06-- https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/cdb-medmen-v1.dat
+Resolving cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)... 52.95.142.38, 3.5.246.238, 52.95.149.2, ...
+Connecting to cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com (cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com)|52.95.142.38|:443... connected.
HTTP request sent, awaiting response... 200 OK
-Length: 356502941 (340M) [application/octet-stream]
-Saving to: ‘./data/cdb-medmen-v1_2.dat’
+Length: 356087008 (340M) [binary/octet-stream]
+Saving to: ‘./data_p4.2/cdb-medmen-v1.dat’
-cdb-medmen-v1_2.dat 100%[===================>] 339.99M 67.2MB/s in 6.4s
+cdb-medmen-v1.dat 100%[===================>] 339.59M 31.5MB/s in 12s
-2022-08-25 12:02:32 (53.4 MB/s) - ‘./data/cdb-medmen-v1_2.dat’ saved [356502941/356502941]
+2024-08-16 08:24:18 (29.4 MB/s) - ‘./data_p4.2/cdb-medmen-v1.dat’ saved [356087008/356087008]
+
-
-
-
+
+
+
+
+
+
MedCATtrainer Export¶
-
-
-In [4]:
-
-
+
+
+
+
+
+In [ ]:
+
+
#@title
-data = json.load(open(DATA_DIR + "MedCAT_Export.json"))
+data = json.load(open(DATA_DIR + "MedCAT_Export.json"))
-
+
+
+
+
+
-
-
-In [5]:
-
-
+
+In [ ]:
+
+
#@title
print(data.keys())
-
+
+
-
-
+
+
+
+
+
-
+
-
+
+
-
+
dict_keys(['projects'])
+
+
+
+
-
-
-In [6]:
-
-
+
+In [ ]:
+
+
#@title
-data['projects'][0].keys()
+data['projects'][0].keys()
-
+
+
-
-
+
+
+
+
+
-
+
- Out[6]:
+
+ Out[ ]:
-
+
dict_keys(['name', 'id', 'cuis', 'tuis', 'documents'])
+
+
+
+
-
-
-In [7]:
-
-
+
+In [ ]:
+
+
#@title
-data['projects'][0]['documents'][0].keys()
+data['projects'][0]['documents'][0].keys()
-
+
+
-
-
+
+
+
+
+
-
+
- Out[7]:
+
+ Out[ ]:
-
+
dict_keys(['id', 'name', 'text', 'last_modified', 'annotations'])
+
+
+
+
-
-
-In [8]:
-
-
+
+In [ ]:
+
+
#@title
-data['projects'][0]['documents'][0]['annotations'][0].keys()
+data['projects'][0]['documents'][0]['annotations'][0].keys()
-
+
+
-
-
+
+
+
+
+
-
+
- Out[8]:
+
+ Out[ ]:
-
+
dict_keys(['id', 'user', 'cui', 'value', 'start', 'end', 'validated', 'correct', 'deleted', 'alternative', 'killed', 'last_modified', 'manually_created', 'acc', 'meta_anns'])
+
+
+
+
-
-
-In [9]:
-
-
+
+In [ ]:
+
+
#@title
-data['projects'][0]['documents'][0]['annotations'][0]['meta_anns'][0].keys()
+data['projects'][0]['documents'][0]['annotations'][0]['meta_anns'][0].keys()
-
+
+
-
-
+
+
+
+
+
-
+
- Out[9]:
+
+ Out[ ]:
-
+
dict_keys(['name', 'value', 'acc', 'validated'])
+
-
-
-
-Fine-tuning the NER+L model¶
+
+
+
+
+
+
+Fine-tuning the NER+L model¶
-
-
-
+
+
+
+
+
+
+
First we load the existing MedCAT models that we will fine-tune.
-
-
-In [10]:
-
-
+
+
+
+
+
+In [ ]:
+
+
# Create and load the CDB (Concept Database)
cdb = CDB.load(cdb_path)
# NOTE: CDBs saved prior to medcat 1.10 will also load a config
-# as part of the CDB, but below we'll be changing that anyway
+# as part of the CDB, but below we'll be changing that anyway
# Create and load the Vocabulary
vocab = Vocab.load(vocab_path)
# Setup config
config = Config()
-config.general['spacy_model'] = 'en_core_web_md'
+config.general['spacy_model'] = 'en_core_web_md'
# Create CAT - the main class from medcat used for concept annotation
cat = CAT(cdb=cdb, config=config, vocab=vocab)
-
+
+
-
-
+
+
+
+
+
-
+
-
+
+
-
-WARNING:medcat.cdb:The CDB was exported by an unknown version of MedCAT.
+
+WARNING:medcat.utils.saving.serializer:Found config in CDB for model (./data_p4.2). This is an old format. Please re-save the model in the new format to avoid potential issues
+WARNING:medcat.cdb:The CDB was exported by an unknown version of MedCAT.
+
-
-
-
+
+
+
+
+
+
-
-
-In [11]:
-
-
-cat.train_supervised_from_json(data_path=DATA_DIR + "MedCAT_Export.json",
+
+
+
+
+
+In [ ]:
+
+
+cat.train_supervised_from_json(data_path=DATA_DIR + "MedCAT_Export.json",
nepochs=1,
reset_cui_count=False,
- print_stats=True,
- use_filters=True)
+ print_stats=True,
+ use_filters=True)
-
+
+
-
-
+
+
+
+
+
-
+
-
+
+
-
+
INFO:medcat:Running without a test set, or train==test
-
+
-
+
+
-
-
-
-
-
-
-
+
+Stats project: 0%| | 0/1 [00:00<?, ?it/s]
-
-
-
+
+
+
-
-
-
-
-
-
+
+Stats document: 0%| | 0/27 [00:00<?, ?it/s]
-
+
-
+
+
-
+
Epoch: 0, Prec: 0.7948717948717948, Rec: 0.7828282828282829, F1: 0.7888040712468194
Docs with false positives: 2124; 1383; 516; 1734; 96; 1577; 1881; 1687; 899; 688
@@ -13953,122 +15657,83 @@ Fine-tuning the NER+L model
-
+
-
+
+
-
-
-
-
-
-
-
+
+Epoch: 0%| | 0/1 [00:00<?, ?it/s]
-
-
-
+
+
+
-
-
-
-
-
-
+
+Project: 0%| | 0/1 [00:00<?, ?it/s]
-
+
-
+
+
-
-
-
-
-
-
-
+
+Document: 0%| | 0/27 [00:00<?, ?it/s]
-
-
-
+
+
+
-
-
-
-
-
-
+
+Stats project: 0%| | 0/1 [00:00<?, ?it/s]
-
+
-
+
+
-
-
-
-
-
-
-
+
+Stats document: 0%| | 0/27 [00:00<?, ?it/s]
-
+
-
+
+
-
+
Epoch: 1, Prec: 0.8439024390243902, Rec: 0.8737373737373737, F1: 0.858560794044665
Docs with false positives: 2124; 1383; 516; 96; 1577; 1881; 1687; 688; 1737; 716
@@ -14123,14 +15788,15 @@ Fine-tuning the NER+L model
-
+
- Out[11]:
+
+ Out[ ]:
-
+
({'C0011847': 15,
'C0020538': 5,
'C0011849': 4,
@@ -17399,1903 +19065,3476 @@ Fine-tuning the NER+L model
+
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# If we want to know the F1, P, R for each cui, we can call the stats method
+data = json.load(open(DATA_DIR + "MedCAT_Export.json"))
+fps, fns, tps, cui_prec, cui_rec, cui_f1, cui_counts, examples = cat._print_stats(data, extra_cui_filter=True)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Stats project: 0%| | 0/1 [00:00<?, ?it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+Stats document: 0%| | 0/27 [00:00<?, ?it/s]
+
+
+
+
+
+
+
+
+
+
+
+Epoch: 0, Prec: 0.07726965532777652, Rec: 0.8511166253101737, F1: 0.1416769929781082
+
+Docs with false positives: 2124; 1383; 1734; 516; 73; 96; 1577; 1881; 1070; 1687
+
+Docs with false negatives: 1383; 73; 96; 1577; 1881; 1070; 688; 1737; 716; 496
+
+
+
+False Positives
+
+Patients - C0030705 - 200
+Normal - C0205307 - 67
+Medical History - C0262926 - 57
+Daily - C0332173 - 46
+year - C0439234 - 41
+Bilateral - C0238767 - 40
+Right - C0205090 - 33
+Pain - C0030193 - 28
+Physical Examination - C0031809 - 27
+Lung - C0024109 - 25
+
+
+False Negatives
+
+Diabetes Mellitus, Non-Insulin-Dependent - C0011860 - 9
+Diabetes Mellitus - C0011849 - 7
+disorder lesions skin - C0037284 - 4
+Pseudomonas aeruginosa infection - C0854135 - 3
+Pulmonary Embolism - C0034065 - 3
+Coronary heart disease - C0010068 - 2
+Arthritis - C0003864 - 2
+C1561826 - C1561826 - 2
+Syndrome - C0039082 - 2
+Ulcer - C0041582 - 2
+
+
+True Positives
+
+Hypertensive disease - C0020538 - 43
+disorder lesions skin - C0037284 - 17
+Hyperlipidemia - C0020473 - 12
+Coronary Arteriosclerosis - C0010054 - 10
+Lymphadenopathy - C0497156 - 10
+Mental Depression - C0011570 - 10
+Erythema - C0041834 - 9
+Congestive heart failure - C0018802 - 8
+Chronic Obstructive Airway Disease - C0024117 - 7
+Renal Insufficiency - C1565489 - 7
+**************************************************************************************************************
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+K-fold metrics¶
K-fold cross-validation offers a more robust evaluation of your model's performance by dividing your dataset into k subsets, or folds.
+Unlike a single evaluation on the entire dataset (like cat._print_stats), the k-fold approach ensures that every data point is used for both training and validation, thereby reducing the risk of bias and providing a more reliable estimate of the model's generalization capabilities.
+This method is particularly beneficial for assessing the fine-tuned performance of your model on specific datasets, as it accounts for variability and offers a comprehensive understanding of how the model might perform on unseen data.
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# you need to import the module to use it
+from medcat.stats.kfold import get_k_fold_stats
+fps, fns, tps, cui_prec, cui_rec, cui_f1, cui_counts, examples = get_k_fold_stats(cat, data)
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# Now we can check F1/P/R for a cui using
+cui = "C0020538" # Hypertension
+print(cui_f1[cui], cui_prec[cui], cui_rec[cui])
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+0.9662921348314606 0.9347826086956522 1.0
+
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# inspect fn, fp examples for specific CUIs of interest...
+examples['fn']['C0010068']
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Out[ ]:
+
+
+
+
+
+[{'text': ' appendectomy, oophorectomy.,FAMILY HISTORY: , Positive for coronary artery disease in her father and brother in their 40s.,SOCIAL HISTORY: , S',
+ 'cui': 'C0010068',
+ 'source value': 'coronary artery disease',
+ 'acc': 1,
+ 'project index': 0,
+ 'document inedex': 1},
+ {'text': 'on fraction of 20%-25% in December 2005, COPD, mild diffuse coronary artery disease, and renal insufficiency.,ALLERGIES:, NO KNOWN DRUG ALLERGI',
+ 'cui': 'C0010068',
+ 'source value': 'coronary artery disease',
+ 'acc': 1,
'project index': 0,
- 'document inedex': 23},
- {'text': 'is primarily bilateral recess, intermittent lower extremity radiculopathy, DJD of both knees, bilateral pes anserinus bursitis, and c',
- 'cui': 'C0700594',
- 'source value': 'radiculopathy',
+ 'document inedex': 25}]
+
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# annotations inside first projects...
+[anno for d in data['projects'][0]['documents'] for anno in d['annotations']][0:5]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Out[ ]:
+
+
+
+
+
+[{'id': 45580,
+ 'user': 'wish',
+ 'cui': 'C0017168',
+ 'value': 'gastroesophageal reflux',
+ 'start': 332,
+ 'end': 355,
+ 'validated': True,
+ 'correct': True,
+ 'deleted': False,
+ 'alternative': False,
+ 'killed': False,
+ 'last_modified': '2020-04-01 22:06:34.303633+00:00',
+ 'manually_created': False,
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24},
- {'text': ' primarily lateral recess with intermittent lower extremity radiculopathy, stable.,8. Degenerative disc disease of both knees, sympt',
- 'cui': 'C0700594',
- 'source value': 'radiculopathy',
+ 'meta_anns': [{'name': 'Status',
+ 'value': 'Other',
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24}],
- 'C0041582': [{'text': ' reveal any additional scars, rashes, cafe au lait spots or ulcers. No significant lymphadenopathy noted.,Spine: Examination',
- 'cui': 'C0041582',
- 'source value': 'ulcers',
- 'acc': 0.33016347633031534,
- 'project index': 0,
- 'document inedex': 23},
- {'text': ' reveal any additional scars, rashes, cafe au lait spots or ulcers. No significant lymphadenopathy noted.,Spine: Examination',
- 'cui': 'C0041582',
- 'source value': 'ulcers',
- 'acc': 0.32397186541676487,
- 'project index': 0,
- 'document inedex': 24}],
- 'C0158266': [{'text': 'sian female who had seen Dr. XYZ with low back pain, lumbar degenerative disc disease, lumbar spondylosis, facet and sacroiliac joint syndrome, l',
- 'cui': 'C0158266',
- 'source value': 'degenerative disc disease',
+ 'validated': True}]},
+ {'id': 45581,
+ 'user': 'wish',
+ 'cui': 'C0020538',
+ 'value': 'hypertension',
+ 'start': 255,
+ 'end': 267,
+ 'validated': True,
+ 'correct': True,
+ 'deleted': False,
+ 'alternative': False,
+ 'killed': False,
+ 'last_modified': '2020-04-01 22:06:30.394941+00:00',
+ 'manually_created': False,
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24},
- {'text': 'ponent to it.,IMPRESSION:,1. Low back syndrome with lumbar degenerative disc disease, lumbar spinal stenosis, and facet joint syndrome on the ri',
- 'cui': 'C0158266',
- 'source value': 'degenerative disc disease',
+ 'meta_anns': [{'name': 'Status',
+ 'value': 'Confirmed',
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24},
- {'text': 'ith intermittent lower extremity radiculopathy, stable.,8. Degenerative disc disease of both knees, symptomatic.,9. Pes anserinus bursitis, bil',
- 'cui': 'C0158266',
- 'source value': 'Degenerative disc disease',
+ 'validated': True}]},
+ {'id': 45582,
+ 'user': 'wish',
+ 'cui': 'C0012634',
+ 'value': 'disorder',
+ 'start': 356,
+ 'end': 364,
+ 'validated': True,
+ 'correct': False,
+ 'deleted': False,
+ 'alternative': False,
+ 'killed': True,
+ 'last_modified': '2020-04-01 22:06:48.174475+00:00',
+ 'manually_created': False,
+ 'acc': 0.364258020093567,
+ 'meta_anns': [{'name': 'Status',
+ 'value': 'Other',
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24}],
- 'C0006444': [{'text': 'y radiculopathy, DJD of both knees, bilateral pes anserinus bursitis, and chronic pain syndrome. Dr. XYZ had performed right an',
- 'cui': 'C0006444',
- 'source value': 'bursitis',
+ 'validated': True}]},
+ {'id': 45583,
+ 'user': 'wish',
+ 'cui': 'C0038454',
+ 'value': 'stroke',
+ 'start': 276,
+ 'end': 282,
+ 'validated': True,
+ 'correct': True,
+ 'deleted': False,
+ 'alternative': False,
+ 'killed': False,
+ 'last_modified': '2020-04-01 22:06:33.410261+00:00',
+ 'manually_created': False,
+ 'acc': 0.39498916376357734,
+ 'meta_anns': [{'name': 'Status',
+ 'value': 'Confirmed',
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24},
- {'text': ' disc disease of both knees, symptomatic.,9. Pes anserinus bursitis, bilaterally symptomatic.,10. Chronic pain syndrome.,RECOM',
- 'cui': 'C0006444',
- 'source value': 'bursitis',
+ 'validated': True}]},
+ {'id': 45584,
+ 'user': 'wish',
+ 'cui': 'C0007787',
+ 'value': 'TIA',
+ 'start': 272,
+ 'end': 275,
+ 'validated': True,
+ 'correct': True,
+ 'deleted': False,
+ 'alternative': False,
+ 'killed': False,
+ 'last_modified': '2020-04-01 22:06:32.727096+00:00',
+ 'manually_created': False,
+ 'acc': 0.43553226241827225,
+ 'meta_anns': [{'name': 'Status',
+ 'value': 'Confirmed',
'acc': 1.0,
- 'project index': 0,
- 'document inedex': 24}],
- 'C0024003': [{'text': 'denopathy noted.,Spine: Examination shows decreased lumbar lordosis with tenderness that seems to be in her right sacroiliac jo',
- 'cui': 'C0024003',
- 'source value': 'lordosis',
- 'acc': 0.502686235070267,
- 'project index': 0,
- 'document inedex': 24}]}})
+ 'validated': True}]}]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+MetaAnnotations¶
During the annotation process we have created only one meta-annotation called "Status". Here we are going to train a BiLSTM to detect that meta-annotation.
+
+
+
+
+
+
+
+
+
+
+
+MetaCAT¶
The class we are going to use to train meta-annotations is called MetaCAT. As input it takes:
+tokenizer - BBPE tokenizer from huggingface and BERT tokenizer
+embeddings - The precalculated embeddings for the tokens produced by the tokenizer. Can be anything from Word2Vec to BERT. This is a numpy matrix, or python list of embeddings (only for Bi-LSTM).
+cntx_left - Size of context from the left side of the entity that will be taken into account.
+cntx_right - Size of context from the right side of the entity that will be taken into account.
+save_dir - Where do we want to save the trained models.
+pad_id - Padding index in the embeddings matrix.
+device - On which device to run this cpu or cuda
+
+
+
+
+
+
+
+
+
+
+
+You can choose to train BERT or Bi-LSTM model for MetaCAT.
+In this tutorial, we'll demonstrate:
+
+- continuing training for a previously trained
Bi-LSTM model (on NHS data)
+- training
BERT without loading a previously trained model (on NHS data)
+
+
+
+
+
+
+
+
+
+
+
+
+Run the model setup, config and train sections for either BERT or Bi-LSTM
+
+
+
+
+
+
+
+
+
+
+
+BERT¶
+
+
+
+
+
+
+
+
+
+
+Model setup¶
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# training BERT without loading previous model pack
+
+config_metacat = ConfigMetaCAT()
+config_metacat.model['model_name'] = 'bert'
+
+# add category name
+config_metacat.general['category_name'] = 'Status'
+# add number of classes
+config_metacat.model['nclasses'] = 2
+
+tokenizer = TokenizerWrapperBERT.load("", config_metacat.model['model_variant'])
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+WARNING:root:Could not load tokenizer from path due to error: bert-tokenizer is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
+If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`. Loading from library for model variant: bert-base-uncased
+
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+mc = MetaCAT(tokenizer=tokenizer, embeddings=None, config=config_metacat)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+WARNING:medcat.utils.meta_cat.models:
+Input size for bert-base-uncased model should be 768, provided input size is 300 Input size changed to 768
+INFO:medcat.meta_cat:BERT model used for classification
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+MetaCAT configuration¶
For a full list of all the configurable parameter. Follow this link.
+Some noteable parameters:
+category_name - What is the name of this meta-annotation (same as the name in the MedCATtrainer)
+model_name - bert or lstm
+model_variant - Only for BERT: Specifies the model variant to be used
+lr - Learning rate
+test_size - Proportion of the test set
+bach_size - Batch size
+model_freeze_layers - Only for BERT: Freeze BERT's layers or train using LoRA
+metric - What metric should be used for choosing the best model.
+nepochs - Number of epochs to run for
+lowercase - Do you want to lowercase the text
+class_weights - Pytorch parameter for unbalanced classes
+compute_class_weights - Do you want the classes weights to be computed automatically based on the data
+ignore_cpos - The position of the entity will be ignored, do not use this.
+auto_save_model - This will autosave the top performing epoch during the training process
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+# Example of how to change parameters
+mc.config.model['input_size'] = 768
+mc.config.model['hidden_size'] = 300
+
+mc.config.train.lr = 5e-4
+mc.config.model.dropout = 0.2
+
+mc.config.model['model_freeze_layers'] = False
+mc.config.train['nepochs'] = 55
+mc.config.train['auto_save_model'] = True
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Train MetaCAT¶
To run the training we use the train_from_json method that allows us to specify:
+json_path: Path to a MedCATtrainer export containing the meta_annotations we want to train for.
+save_dir_path: (optional, defaults to None): In case we have auto_save_model (meaning during the training the best model will be saved) we need to set a save path.
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+import logging
+logging.basicConfig(level=logging.INFO,force=True)
+
+
+
+
+
+
+
+
+
+
+
+
+In [ ]:
+
+
+mc.train_from_json(json_path=DATA_DIR+"MedCAT_Export.json", save_dir_path='status_bert')
+# Saving the model this way will only save the model epoch with the best performance
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+INFO:medcat.utils.meta_cat.data_utils:Updated label_data: {0: 128, 1: 128}
+/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:591: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+ warnings.warn(
+INFO:medcat.utils.meta_cat.ml_utils:Total steps for optimizer: 200
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 0 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.69 0.64 0.66 251
+ 1 0.31 0.36 0.33 114
+
+ accuracy 0.55 365
+ macro avg 0.50 0.50 0.50 365
+weighted avg 0.57 0.55 0.56 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 0 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.63 0.63 0.63 27
+ 1 0.29 0.29 0.29 14
+
+ accuracy 0.51 41
+ macro avg 0.46 0.46 0.46 41
+weighted avg 0.51 0.51 0.51 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 0 and macro avg/f1-score: 0.4576719576719577 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 1 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.68 0.60 0.64 251
+ 1 0.31 0.39 0.34 114
+
+ accuracy 0.53 365
+ macro avg 0.49 0.49 0.49 365
+weighted avg 0.57 0.53 0.55 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 1 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.65 0.63 0.64 27
+ 1 0.33 0.36 0.34 14
+
+ accuracy 0.54 41
+ macro avg 0.49 0.49 0.49 41
+weighted avg 0.54 0.54 0.54 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 1 and macro avg/f1-score: 0.4931685100845803 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 2 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.68 0.61 0.64 251
+ 1 0.30 0.38 0.34 114
+
+ accuracy 0.53 365
+ macro avg 0.49 0.49 0.49 365
+weighted avg 0.56 0.53 0.55 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 2 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.68 0.63 0.65 27
+ 1 0.38 0.43 0.40 14
+
+ accuracy 0.56 41
+ macro avg 0.53 0.53 0.53 41
+weighted avg 0.58 0.56 0.57 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 2 and macro avg/f1-score: 0.5269230769230769 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 3 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.69 0.58 0.63 251
+ 1 0.32 0.44 0.37 114
+
+ accuracy 0.53 365
+ macro avg 0.51 0.51 0.50 365
+weighted avg 0.58 0.53 0.55 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 3 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.70 0.59 0.64 27
+ 1 0.39 0.50 0.44 14
+
+ accuracy 0.56 41
+ macro avg 0.54 0.55 0.54 41
+weighted avg 0.59 0.56 0.57 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 3 and macro avg/f1-score: 0.53875 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 4 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.73 0.60 0.66 251
+ 1 0.37 0.52 0.43 114
+
+ accuracy 0.57 365
+ macro avg 0.55 0.56 0.54 365
+weighted avg 0.62 0.57 0.59 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 4 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.70 0.59 0.64 27
+ 1 0.39 0.50 0.44 14
+
+ accuracy 0.56 41
+ macro avg 0.54 0.55 0.54 41
+weighted avg 0.59 0.56 0.57 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 5 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.72 0.57 0.64 251
+ 1 0.35 0.51 0.42 114
+
+ accuracy 0.55 365
+ macro avg 0.54 0.54 0.53 365
+weighted avg 0.60 0.55 0.57 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 5 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.67 0.59 0.63 27
+ 1 0.35 0.43 0.39 14
+
+ accuracy 0.54 41
+ macro avg 0.51 0.51 0.51 41
+weighted avg 0.56 0.54 0.55 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 6 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.75 0.67 0.70 251
+ 1 0.40 0.50 0.45 114
-
+ accuracy 0.61 365
+ macro avg 0.57 0.58 0.58 365
+weighted avg 0.64 0.61 0.62 365
-
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 6 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
-In [12]:
-
-
-# If we want to know the F1, P, R for each cui, we can call the stats method
-data = json.load(open(DATA_DIR + "MedCAT_Export.json"))
-fps, fns, tps, cui_prec, cui_rec, cui_f1, cui_counts, examples = cat._print_stats(data, extra_cui_filter=True)
-
+ 0 0.74 0.63 0.68 27
+ 1 0.44 0.57 0.50 14
-
-
-
+ accuracy 0.61 41
+ macro avg 0.59 0.60 0.59 41
+weighted avg 0.64 0.61 0.62 41
-
-
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 6 and macro avg/f1-score: 0.5900000000000001 #####
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 7 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.75 0.68 0.71 251
+ 1 0.42 0.51 0.46 114
-
+ accuracy 0.62 365
+ macro avg 0.58 0.59 0.59 365
+weighted avg 0.65 0.62 0.63 365
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 7 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.79 0.70 0.75 27
+ 1 0.53 0.64 0.58 14
+ accuracy 0.68 41
+ macro avg 0.66 0.67 0.66 41
+weighted avg 0.70 0.68 0.69 41
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 7 and macro avg/f1-score: 0.6628716002530045 #####
-
-
-
-
-
-
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 8 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.80 0.70 0.74 251
+ 1 0.48 0.61 0.54 114
-
+ accuracy 0.67 365
+ macro avg 0.64 0.66 0.64 365
+weighted avg 0.70 0.67 0.68 365
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 8 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.80 0.74 0.77 27
+ 1 0.56 0.64 0.60 14
+ accuracy 0.71 41
+ macro avg 0.68 0.69 0.68 41
+weighted avg 0.72 0.71 0.71 41
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 8 and macro avg/f1-score: 0.6846153846153846 #####
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 9 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
-
-
-
-
+ 0 0.83 0.74 0.78 251
+ 1 0.54 0.68 0.60 114
-
+ accuracy 0.72 365
+ macro avg 0.69 0.71 0.69 365
+weighted avg 0.74 0.72 0.73 365
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 9 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.81 0.78 0.79 27
+ 1 0.60 0.64 0.62 14
+ accuracy 0.73 41
+ macro avg 0.70 0.71 0.71 41
+weighted avg 0.74 0.73 0.73 41
-
-Epoch: 0, Prec: 0.07726965532777652, Rec: 0.8511166253101737, F1: 0.1416769929781082
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 9 and macro avg/f1-score: 0.7065712426805465 #####
-Docs with false positives: 2124; 1383; 1734; 516; 73; 96; 1577; 1881; 1070; 1687
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 10 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Docs with false negatives: 1383; 73; 96; 1577; 1881; 1070; 688; 1737; 716; 496
+ 0 0.84 0.80 0.82 251
+ 1 0.61 0.67 0.64 114
+ accuracy 0.76 365
+ macro avg 0.72 0.74 0.73 365
+weighted avg 0.77 0.76 0.76 365
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 10 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-False Positives
+ 0 0.81 0.78 0.79 27
+ 1 0.60 0.64 0.62 14
-Patients - C0030705 - 200
-Normal - C0205307 - 67
-Medical History - C0262926 - 57
-Daily - C0332173 - 46
-year - C0439234 - 41
-Bilateral - C0238767 - 40
-Right - C0205090 - 33
-Pain - C0030193 - 28
-Physical Examination - C0031809 - 27
-Lung - C0024109 - 25
+ accuracy 0.73 41
+ macro avg 0.70 0.71 0.71 41
+weighted avg 0.74 0.73 0.73 41
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 11 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-False Negatives
+ 0 0.87 0.80 0.83 251
+ 1 0.62 0.73 0.67 114
+
+ accuracy 0.78 365
+ macro avg 0.75 0.76 0.75 365
+weighted avg 0.79 0.78 0.78 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 11 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.81 0.78 0.79 27
+ 1 0.60 0.64 0.62 14
+
+ accuracy 0.73 41
+ macro avg 0.70 0.71 0.71 41
+weighted avg 0.74 0.73 0.73 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 12 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.92 0.81 0.86 251
+ 1 0.67 0.85 0.75 114
+
+ accuracy 0.82 365
+ macro avg 0.80 0.83 0.81 365
+weighted avg 0.85 0.82 0.83 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 12 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.74 0.78 27
+ 1 0.59 0.71 0.65 14
+
+ accuracy 0.73 41
+ macro avg 0.71 0.73 0.71 41
+weighted avg 0.75 0.73 0.74 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 12 and macro avg/f1-score: 0.7147375079063883 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 13 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.91 0.83 0.87 251
+ 1 0.69 0.82 0.75 114
+
+ accuracy 0.83 365
+ macro avg 0.80 0.83 0.81 365
+weighted avg 0.84 0.83 0.83 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 13 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.81 0.78 0.79 27
+ 1 0.60 0.64 0.62 14
+
+ accuracy 0.73 41
+ macro avg 0.70 0.71 0.71 41
+weighted avg 0.74 0.73 0.73 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 14 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.93 0.85 0.89 251
+ 1 0.73 0.87 0.79 114
+
+ accuracy 0.86 365
+ macro avg 0.83 0.86 0.84 365
+weighted avg 0.87 0.86 0.86 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 14 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.81 0.78 0.79 27
+ 1 0.60 0.64 0.62 14
+
+ accuracy 0.73 41
+ macro avg 0.70 0.71 0.71 41
+weighted avg 0.74 0.73 0.73 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 15 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.93 0.84 0.89 251
+ 1 0.72 0.87 0.79 114
+
+ accuracy 0.85 365
+ macro avg 0.83 0.86 0.84 365
+weighted avg 0.87 0.85 0.86 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 15 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.81 0.81 0.81 27
+ 1 0.64 0.64 0.64 14
+
+ accuracy 0.76 41
+ macro avg 0.73 0.73 0.73 41
+weighted avg 0.76 0.76 0.76 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 15 and macro avg/f1-score: 0.7288359788359788 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 16 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.95 0.90 0.92 251
+ 1 0.80 0.89 0.84 114
+
+ accuracy 0.89 365
+ macro avg 0.87 0.89 0.88 365
+weighted avg 0.90 0.89 0.89 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 16 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.82 0.85 0.84 27
+ 1 0.69 0.64 0.67 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.75 0.75 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 16 and macro avg/f1-score: 0.7515151515151515 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 17 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.95 0.88 0.91 251
+ 1 0.77 0.89 0.83 114
+
+ accuracy 0.88 365
+ macro avg 0.86 0.89 0.87 365
+weighted avg 0.89 0.88 0.88 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 17 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.82 0.85 0.84 27
+ 1 0.69 0.64 0.67 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.75 0.75 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 18 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.95 0.90 0.92 251
+ 1 0.80 0.89 0.84 114
+
+ accuracy 0.89 365
+ macro avg 0.87 0.89 0.88 365
+weighted avg 0.90 0.89 0.89 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 18 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.82 0.85 0.84 27
+ 1 0.69 0.64 0.67 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.75 0.75 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 19 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.95 0.91 0.93 251
+ 1 0.81 0.89 0.85 114
+
+ accuracy 0.90 365
+ macro avg 0.88 0.90 0.89 365
+weighted avg 0.90 0.90 0.90 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 19 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.82 0.85 0.84 27
+ 1 0.69 0.64 0.67 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.75 0.75 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 20 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.97 0.91 0.94 251
+ 1 0.83 0.93 0.88 114
+
+ accuracy 0.92 365
+ macro avg 0.90 0.92 0.91 365
+weighted avg 0.92 0.92 0.92 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 20 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 20 and macro avg/f1-score: 0.7747252747252749 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 21 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.96 0.94 0.95 251
+ 1 0.87 0.91 0.89 114
+
+ accuracy 0.93 365
+ macro avg 0.91 0.92 0.92 365
+weighted avg 0.93 0.93 0.93 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 21 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 22 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.96 0.94 0.95 251
+ 1 0.88 0.92 0.90 114
+
+ accuracy 0.93 365
+ macro avg 0.92 0.93 0.92 365
+weighted avg 0.94 0.93 0.93 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 22 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 23 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.96 0.92 0.94 251
+ 1 0.85 0.92 0.88 114
+
+ accuracy 0.92 365
+ macro avg 0.90 0.92 0.91 365
+weighted avg 0.93 0.92 0.92 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 23 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.92 0.85 0.88 27
+ 1 0.75 0.86 0.80 14
+
+ accuracy 0.85 41
+ macro avg 0.83 0.85 0.84 41
+weighted avg 0.86 0.85 0.86 41
+
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_bert/model.dat at epoch: 23 and macro avg/f1-score: 0.8423076923076922 #####
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 24 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.97 0.94 0.96 251
+ 1 0.88 0.93 0.91 114
+
+ accuracy 0.94 365
+ macro avg 0.93 0.94 0.93 365
+weighted avg 0.94 0.94 0.94 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 24 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.92 0.81 0.86 27
+ 1 0.71 0.86 0.77 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.84 0.82 41
+weighted avg 0.84 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 25 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.95 0.96 251
+ 1 0.89 0.95 0.92 114
+
+ accuracy 0.95 365
+ macro avg 0.93 0.95 0.94 365
+weighted avg 0.95 0.95 0.95 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 25 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.92 0.81 0.86 27
+ 1 0.71 0.86 0.77 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.84 0.82 41
+weighted avg 0.84 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 26 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.96 0.94 0.95 251
+ 1 0.87 0.91 0.89 114
+
+ accuracy 0.93 365
+ macro avg 0.91 0.92 0.92 365
+weighted avg 0.93 0.93 0.93 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 26 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.92 0.81 0.86 27
+ 1 0.71 0.86 0.77 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.84 0.82 41
+weighted avg 0.84 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 27 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.94 0.96 251
+ 1 0.89 0.96 0.92 114
+
+ accuracy 0.95 365
+ macro avg 0.94 0.95 0.94 365
+weighted avg 0.95 0.95 0.95 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 27 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.85 0.81 0.83 27
+ 1 0.67 0.71 0.69 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.76 0.76 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 28 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.94 0.96 251
+ 1 0.88 0.96 0.92 114
+
+ accuracy 0.95 365
+ macro avg 0.93 0.95 0.94 365
+weighted avg 0.95 0.95 0.95 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 28 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.85 0.81 0.83 27
+ 1 0.67 0.71 0.69 14
+
+ accuracy 0.78 41
+ macro avg 0.76 0.76 0.76 41
+weighted avg 0.78 0.78 0.78 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 29 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.95 0.97 251
+ 1 0.90 0.96 0.93 114
+
+ accuracy 0.95 365
+ macro avg 0.94 0.95 0.95 365
+weighted avg 0.95 0.95 0.95 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 29 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.86 0.89 0.87 27
+ 1 0.77 0.71 0.74 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.80 0.81 41
+weighted avg 0.83 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 30 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 30 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.85 0.85 0.85 27
+ 1 0.71 0.71 0.71 14
+
+ accuracy 0.80 41
+ macro avg 0.78 0.78 0.78 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 31 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 31 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.85 0.85 0.85 27
+ 1 0.71 0.71 0.71 14
+
+ accuracy 0.80 41
+ macro avg 0.78 0.78 0.78 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 32 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 32 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.88 0.85 0.87 27
+ 1 0.73 0.79 0.76 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.82 0.81 41
+weighted avg 0.83 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 33 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 33 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.88 0.85 0.87 27
+ 1 0.73 0.79 0.76 14
+
+ accuracy 0.83 41
+ macro avg 0.81 0.82 0.81 41
+weighted avg 0.83 0.83 0.83 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 34 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.95 0.97 251
+ 1 0.90 0.96 0.93 114
+
+ accuracy 0.96 365
+ macro avg 0.94 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 34 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.85 0.85 0.85 27
+ 1 0.71 0.71 0.71 14
+
+ accuracy 0.80 41
+ macro avg 0.78 0.78 0.78 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 35 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.91 0.96 0.93 114
+
+ accuracy 0.96 365
+ macro avg 0.94 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 35 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 36 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.97 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 36 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 37 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.96 0.97 251
+ 1 0.92 0.97 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.97 0.96 365
+weighted avg 0.97 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 37 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 38 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.95 0.97 251
+ 1 0.90 0.97 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 38 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 39 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 39 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 40 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.96 0.97 251
+ 1 0.92 0.97 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.97 0.96 365
+weighted avg 0.97 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 40 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.89 0.86 27
+ 1 0.75 0.64 0.69 14
+
+ accuracy 0.80 41
+ macro avg 0.79 0.77 0.77 41
+weighted avg 0.80 0.80 0.80 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 41 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.97 0.98 251
+ 1 0.93 0.96 0.95 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.96 365
+weighted avg 0.97 0.97 0.97 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 41 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 42 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.97 0.98 251
+ 1 0.93 0.97 0.95 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 42 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 43 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.97 0.98 251
+ 1 0.93 0.97 0.95 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 43 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 44 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 44 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 45 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.97 0.98 251
+ 1 0.94 0.97 0.96 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 45 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 46 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
+
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.95 365
+weighted avg 0.96 0.96 0.96 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 46 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 47 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.99 0.96 0.98 251
+ 1 0.93 0.97 0.95 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.96 365
+weighted avg 0.97 0.97 0.97 365
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 47 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 48 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+
+ 0 0.98 0.97 0.98 251
+ 1 0.93 0.96 0.95 114
+
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.96 365
+weighted avg 0.97 0.97 0.97 365
-Diabetes Mellitus, Non-Insulin-Dependent - C0011860 - 9
-Diabetes Mellitus - C0011849 - 7
-disorder lesions skin - C0037284 - 4
-Pseudomonas aeruginosa infection - C0854135 - 3
-Pulmonary Embolism - C0034065 - 3
-Coronary heart disease - C0010068 - 2
-Arthritis - C0003864 - 2
-C1561826 - C1561826 - 2
-Syndrome - C0039082 - 2
-Ulcer - C0041582 - 2
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 48 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
-True Positives
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
-Hypertensive disease - C0020538 - 43
-disorder lesions skin - C0037284 - 17
-Hyperlipidemia - C0020473 - 12
-Coronary Arteriosclerosis - C0010054 - 10
-Lymphadenopathy - C0497156 - 10
-Mental Depression - C0011570 - 10
-Erythema - C0041834 - 9
-Congestive heart failure - C0018802 - 8
-Chronic Obstructive Airway Disease - C0024117 - 7
-Renal Insufficiency - C1565489 - 7
-**************************************************************************************************************
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 49 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
+ 0 0.99 0.97 0.98 251
+ 1 0.93 0.97 0.95 114
-
-
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
-
-
-
-
-K-fold metrics¶
K-fold cross-validation offers a more robust evaluation of your model's performance by dividing your dataset into k subsets, or folds.
-Unlike a single evaluation on the entire dataset (like cat._print_stats), the k-fold approach ensures that every data point is used for both training and validation, thereby reducing the risk of bias and providing a more reliable estimate of the model's generalization capabilities.
-This method is particularly beneficial for assessing the fine-tuned performance of your model on specific datasets, as it accounts for variability and offers a comprehensive understanding of how the model might perform on unseen data.
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 49 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
-
-
-In [ ]:
-
-
-# you need to import the module to use it
-from medcat.stats.kfold import get_k_fold_stats
-fps, fns, tps, cui_prec, cui_rec, cui_f1, cui_counts, examples = get_k_fold_stats(cat, data)
-
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
-
-
-
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
-
-
-
-In [13]:
-
-
-# Now we can check F1/P/R for a cui using
-cui = "C0020538" # Hypertension
-print(cui_f1[cui], cui_prec[cui], cui_rec[cui])
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 50 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
+ 0 0.99 0.97 0.98 251
+ 1 0.94 0.97 0.96 114
-
-
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 50 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
-
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 51 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-0.9662921348314606 0.9347826086956522 1.0
-
-
-
+ 0 0.99 0.96 0.97 251
+ 1 0.92 0.97 0.94 114
-
-
+ accuracy 0.96 365
+ macro avg 0.95 0.97 0.96 365
+weighted avg 0.97 0.96 0.96 365
-
-
-
-In [14]:
-
-
-# inspect fn, fp examples for specific CUIs of interest...
-examples['fn']['C0010068']
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 51 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
-
-
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 52 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.98 0.97 0.98 251
+ 1 0.94 0.96 0.95 114
- Out[14]:
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 52 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
-
-[{'text': ' appendectomy, oophorectomy.,FAMILY HISTORY: , Positive for coronary artery disease in her father and brother in their 40s.,SOCIAL HISTORY: , S',
- 'cui': 'C0010068',
- 'source value': 'coronary artery disease',
- 'acc': 1,
- 'project index': 0,
- 'document inedex': 1},
- {'text': 'on fraction of 20%-25% in December 2005, COPD, mild diffuse coronary artery disease, and renal insufficiency.,ALLERGIES:, NO KNOWN DRUG ALLERGI',
- 'cui': 'C0010068',
- 'source value': 'coronary artery disease',
- 'acc': 1,
- 'project index': 0,
- 'document inedex': 25}]
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 53 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.98 0.96 0.97 251
+ 1 0.92 0.96 0.94 114
-
-
+ accuracy 0.96 365
+ macro avg 0.95 0.96 0.96 365
+weighted avg 0.97 0.96 0.96 365
-
-
-
-In [15]:
-
-
-# annotations inside first projects...
-[anno for d in data['projects'][0]['documents'] for anno in d['annotations']][0:5]
-
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 53 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
-
-
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
-
-
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 54 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-
+ 0 0.98 0.97 0.98 251
+ 1 0.94 0.96 0.95 114
- Out[15]:
+ accuracy 0.97 365
+ macro avg 0.96 0.97 0.97 365
+weighted avg 0.97 0.97 0.97 365
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 54 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.83 0.93 0.88 27
+ 1 0.82 0.64 0.72 14
+ accuracy 0.83 41
+ macro avg 0.83 0.78 0.80 41
+weighted avg 0.83 0.83 0.82 41
-
-[{'id': 45580,
- 'user': 'wish',
- 'cui': 'C0017168',
- 'value': 'gastroesophageal reflux',
- 'start': 332,
- 'end': 355,
- 'validated': True,
- 'correct': True,
- 'deleted': False,
- 'alternative': False,
- 'killed': False,
- 'last_modified': '2020-04-01 22:06:34.303633+00:00',
- 'manually_created': False,
- 'acc': 1.0,
- 'meta_anns': [{'name': 'Status',
- 'value': 'Other',
- 'acc': 1.0,
- 'validated': True}]},
- {'id': 45581,
- 'user': 'wish',
- 'cui': 'C0020538',
- 'value': 'hypertension',
- 'start': 255,
- 'end': 267,
- 'validated': True,
- 'correct': True,
- 'deleted': False,
- 'alternative': False,
- 'killed': False,
- 'last_modified': '2020-04-01 22:06:30.394941+00:00',
- 'manually_created': False,
- 'acc': 1.0,
- 'meta_anns': [{'name': 'Status',
- 'value': 'Confirmed',
- 'acc': 1.0,
- 'validated': True}]},
- {'id': 45582,
- 'user': 'wish',
- 'cui': 'C0012634',
- 'value': 'disorder',
- 'start': 356,
- 'end': 364,
- 'validated': True,
- 'correct': False,
- 'deleted': False,
- 'alternative': False,
- 'killed': True,
- 'last_modified': '2020-04-01 22:06:48.174475+00:00',
- 'manually_created': False,
- 'acc': 0.364258020093567,
- 'meta_anns': [{'name': 'Status',
- 'value': 'Other',
- 'acc': 1.0,
- 'validated': True}]},
- {'id': 45583,
- 'user': 'wish',
- 'cui': 'C0038454',
- 'value': 'stroke',
- 'start': 276,
- 'end': 282,
- 'validated': True,
- 'correct': True,
- 'deleted': False,
- 'alternative': False,
- 'killed': False,
- 'last_modified': '2020-04-01 22:06:33.410261+00:00',
- 'manually_created': False,
- 'acc': 0.39498916376357734,
- 'meta_anns': [{'name': 'Status',
- 'value': 'Confirmed',
- 'acc': 1.0,
- 'validated': True}]},
- {'id': 45584,
- 'user': 'wish',
- 'cui': 'C0007787',
- 'value': 'TIA',
- 'start': 272,
- 'end': 275,
- 'validated': True,
- 'correct': True,
- 'deleted': False,
- 'alternative': False,
- 'killed': False,
- 'last_modified': '2020-04-01 22:06:32.727096+00:00',
- 'manually_created': False,
- 'acc': 0.43553226241827225,
- 'meta_anns': [{'name': 'Status',
- 'value': 'Confirmed',
- 'acc': 1.0,
- 'validated': True}]}]
+
+
+
+
+
+ Out[ ]:
+
+
+
+
+
+{'confusion_matrix': array([[0.85185185, 0.14814815],
+ [0.14285714, 0.85714286]]),
+ 'report': {'0': {'precision': 0.92,
+ 'recall': 0.8518518518518519,
+ 'f1-score': 0.8846153846153846,
+ 'support': 27.0},
+ '1': {'precision': 0.75,
+ 'recall': 0.8571428571428571,
+ 'f1-score': 0.7999999999999999,
+ 'support': 14.0},
+ 'accuracy': 0.8536585365853658,
+ 'macro avg': {'precision': 0.835,
+ 'recall': 0.8544973544973544,
+ 'f1-score': 0.8423076923076922,
+ 'support': 41.0},
+ 'weighted avg': {'precision': 0.8619512195121952,
+ 'recall': 0.8536585365853658,
+ 'f1-score': 0.8557223264540337,
+ 'support': 41.0}},
+ 'report_train': {'0': {'precision': 0.9626556016597511,
+ 'recall': 0.9243027888446215,
+ 'f1-score': 0.9430894308943089,
+ 'support': 251.0},
+ '1': {'precision': 0.8467741935483871,
+ 'recall': 0.9210526315789473,
+ 'f1-score': 0.8823529411764707,
+ 'support': 114.0},
+ 'accuracy': 0.9232876712328767,
+ 'macro avg': {'precision': 0.9047148976040691,
+ 'recall': 0.9226777102117845,
+ 'f1-score': 0.9127211860353898,
+ 'support': 365.0},
+ 'weighted avg': {'precision': 0.9264625043318182,
+ 'recall': 0.9232876712328767,
+ 'f1-score': 0.9241196779413401,
+ 'support': 365.0}},
+ 'epoch': 23}
+
-
-
-
-MetaAnnotations¶
During the annotation process we have created only one meta-annotation called "Status". Here we are going to train a BiLSTM to detect that meta-annotation.
+
+
+
+
+
+Bi-LSTM¶
+
+
+
+
+
+
+
+
+
+
+Model setup¶
-
-
-
-MetaCAT¶
The class we are going to use to train meta-annotations is called MetaCAT. As input it takes:
-tokenizer - A BBPE tokenizer from huggingface
-embeddings - The precalculated embeddings for the tokens produced by the tokenizer. Can be anything from Word2Vec to BERT. This is a numpy matrix, or python list of embeddings.
-cntx_left - Size of context from the left side of the entity that will be taken into account.
-cntx_right - Size of context from the right side of the entity that will be taken into account.
-save_dir - Where do we want to save the trained models.
-pad_id - Padding index in the embeddings matrix.
-device - On which device to run this cpu or cuda
-
+
+
+
-
-
-In [16]:
-
-
-!unzip $DATA_DIR/mc_status.zip
+
+In [ ]:
+
+
+!unzip $DATA_DIR/mc_status.zip
-
+
+
+
+
+
+
-
-
+
-
+
-
+
+
-
-Archive: data/mc_status.zip
- creating: Status/
- inflating: Status/model.dat
- inflating: Status/config.json
- inflating: Status/bbpe-vocab.json
- inflating: Status/bbpe-merges.txt
+
+Archive: ./data_p4.2//mc_status.zip
+ creating: Status/
+ inflating: Status/model.dat
+ inflating: Status/config.json
+ inflating: Status/bbpe-vocab.json
+ inflating: Status/bbpe-merges.txt
+
+
+
+
-
-
-In [17]:
-
-
+
+In [ ]:
+
+
# Get the required tokenizer (note that we have already downloaded the required models)
-mc = MetaCAT.load('Status')
+mc = MetaCAT.load('Status')
-
+
+
-
-
-
-MetaCAT configuration¶
For a full list of all the configurable parameter. Follow this link.
+
+
+
+
+
+
+MetaCAT configuration¶
For a full list of all the configurable parameter. Follow this link.
Some noteable parameters:
category_name - What is the name of this meta-annotation (same as the name in the MedCATtrainer)
-model_name - for now only lstm
+model_name - bert or lstm
+model_variant - Only for BERT: Specifies the model variant to be used
lr - Learning rate
test_size - Proportion of the test set
bach_size - Batch size
+model_freeze_layers - Only for BERT: Freeze BERT's layers or train using LoRA
+metric - What metric should be used for choosing the best model.
nepochs - Number of epochs to run for
lowercase - Do you want to lowercase the text
-class_weights - Pytorch LSTM parameter for unbalanced classes
+class_weights - Pytorch parameter for unbalanced classes
+compute_class_weights - Do you want the classes weights to be computed automatically based on the data
ignore_cpos - The position of the entity will be ignored, do not use this.
auto_save_model - This will autosave the top performing epoch during the training process
-
-
-In [18]:
-
-
+
+
+
+
+
+In [ ]:
+
+
# Example of how to change parameters
-mc.config.model['input_size'] = 768
-mc.config.model['hidden_size'] = 300
+mc.config.model['input_size'] = 768
+mc.config.model['hidden_size'] = 300
+mc.config.general['category_value2id'] = {'Other':1,'Confirmed':0}
+
+mc.config.train['test_size'] = 0.2
-mc.config.train['nepochs'] = 55
-mc.config.train['auto_save_model'] = True
+mc.config.model['nclasses'] = 2
+mc.config.train['nepochs'] = 55
+mc.config.train['auto_save_model'] = True
-
+
+
-
-
-
-Train MetaCAT¶
To run the training we use the train method that allows us to specify:
+
+
+
+
+
+
+Train MetaCAT¶
To run the training we use the train_from_json method that allows us to specify:
json_path: Path to a MedCATtrainer export containing the meta_annotations we want to train for.
save_dir_path: (optional, defaults to None): In case we have auto_save_model (meaning during the training the best model will be saved) we need to set a save path.
-
-
-In [19]:
-
-
-mc.train_from_json(json_path= DATA_DIR+"MedCAT_Export.json", save_dir_path='status')
-# Saving the model this way will only save the model epoch with the best performance
+
+
+
+
+
+In [ ]:
+
+
+import logging
+logging.basicConfig(level=logging.INFO,force=True)
-
+
-
-
-
-
-
-
-
-
-
-
-
-WARNING:medcat:The number of classes set in the config is not the same as the one found in the data: 2 vs 3
-WARNING:medcat:Auto-setting the nclasses value in config and rebuilding the model.
-
-
-
-
-
-
-
-
-Epoch: 0 ************************************************** Train
- precision recall f1-score support
-
- 0 0.00 0.00 0.00 0
- 1 0.46 0.49 0.47 113
- 2 0.77 0.70 0.74 253
-
- accuracy 0.64 366
- macro avg 0.41 0.40 0.40 366
-weighted avg 0.68 0.64 0.65 366
-
-Epoch: 0 ************************************************** Test
- precision recall f1-score support
-
- 1 1.00 0.27 0.42 15
- 2 0.69 1.00 0.82 25
-
- accuracy 0.73 40
- macro avg 0.85 0.63 0.62 40
-weighted avg 0.81 0.72 0.67 40
-
-
-##### Model saved to status/model.dat at epoch: 0 and weighted avg/f1-score: 0.6701898188093184 #####
+
+
+
+
+
+In [ ]:
+
+
+mc.train_from_json(json_path= DATA_DIR+"MedCAT_Export.json", save_dir_path='status_lstm')
+# Saving the model this way will only save the model epoch with the best performance
+
-
+
-
-
-
-
-
-
-
-/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py:1318: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
- _warn_prf(average, modifier, msg_start, len(result))
-/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py:1318: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
- _warn_prf(average, modifier, msg_start, len(result))
-/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py:1318: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
- _warn_prf(average, modifier, msg_start, len(result))
-
+
+
+
-
-
+
+
-
-Epoch: 1 ************************************************** Train
- precision recall f1-score support
+
+
- 1 1.00 0.18 0.30 113
- 2 0.73 1.00 0.84 253
- accuracy 0.75 366
- macro avg 0.87 0.59 0.57 366
-weighted avg 0.81 0.75 0.68 366
+
+INFO:medcat.utils.meta_cat.data_utils:Updated label_data: {1: 128, 0: 128}
+WARNING:medcat.utils.meta_cat.ml_utils:Class weights not provided and compute_class_weights parameter is set to False. No class weights used for training.
+/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:591: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+ warnings.warn(
+INFO:medcat.utils.meta_cat.ml_utils:Total steps for optimizer: 178
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 0 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Epoch: 1 ************************************************** Test
- precision recall f1-score support
+ 0 0.89 0.93 0.91 222
+ 1 0.83 0.75 0.79 102
- 1 1.00 0.20 0.33 15
- 2 0.68 1.00 0.81 25
+ accuracy 0.87 324
+ macro avg 0.86 0.84 0.85 324
+weighted avg 0.87 0.87 0.87 324
- accuracy 0.70 40
- macro avg 0.84 0.60 0.57 40
-weighted avg 0.80 0.70 0.63 40
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 0 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Epoch: 2 ************************************************** Train
- precision recall f1-score support
+ 0 0.85 0.84 0.85 56
+ 1 0.67 0.69 0.68 26
- 1 1.00 0.35 0.52 113
- 2 0.78 1.00 0.87 253
+ accuracy 0.79 82
+ macro avg 0.76 0.77 0.76 82
+weighted avg 0.79 0.79 0.79 82
- accuracy 0.80 366
- macro avg 0.89 0.68 0.70 366
-weighted avg 0.85 0.80 0.77 366
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_lstm/model.dat at epoch: 0 and weighted avg/f1-score: 0.7937048875843168 #####
-Epoch: 2 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 1 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+ 0 0.95 0.96 0.96 222
+ 1 0.92 0.88 0.90 102
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ accuracy 0.94 324
+ macro avg 0.93 0.92 0.93 324
+weighted avg 0.94 0.94 0.94 324
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 1 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-##### Model saved to status/model.dat at epoch: 2 and weighted avg/f1-score: 0.8154545454545457 #####
+ 0 0.87 0.84 0.85 56
+ 1 0.68 0.73 0.70 26
-Epoch: 3 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.80 82
+ macro avg 0.77 0.79 0.78 82
+weighted avg 0.81 0.80 0.81 82
- 1 0.90 0.88 0.89 113
- 2 0.95 0.96 0.95 253
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_lstm/model.dat at epoch: 1 and weighted avg/f1-score: 0.8067175823273386 #####
- accuracy 0.93 366
- macro avg 0.92 0.92 0.92 366
-weighted avg 0.93 0.93 0.93 366
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 2 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Epoch: 3 ************************************************** Test
- precision recall f1-score support
+ 0 0.96 0.98 0.97 222
+ 1 0.95 0.90 0.92 102
- 1 0.83 0.67 0.74 15
- 2 0.82 0.92 0.87 25
+ accuracy 0.95 324
+ macro avg 0.95 0.94 0.95 324
+weighted avg 0.95 0.95 0.95 324
- accuracy 0.82 40
- macro avg 0.83 0.79 0.80 40
-weighted avg 0.83 0.82 0.82 40
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 2 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.87 0.84 0.85 56
+ 1 0.68 0.73 0.70 26
-##### Model saved to status/model.dat at epoch: 3 and weighted avg/f1-score: 0.820230607966457 #####
+ accuracy 0.80 82
+ macro avg 0.77 0.79 0.78 82
+weighted avg 0.81 0.80 0.81 82
-Epoch: 4 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 3 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.96 0.89 0.93 113
- 2 0.95 0.98 0.97 253
+ 0 0.96 0.97 0.97 222
+ 1 0.93 0.92 0.93 102
- accuracy 0.96 366
- macro avg 0.96 0.94 0.95 366
-weighted avg 0.96 0.96 0.96 366
+ accuracy 0.95 324
+ macro avg 0.95 0.95 0.95 324
+weighted avg 0.95 0.95 0.95 324
-Epoch: 4 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 3 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.92 0.73 0.81 15
- 2 0.86 0.96 0.91 25
+ 0 0.92 0.86 0.89 56
+ 1 0.73 0.85 0.79 26
- accuracy 0.88 40
- macro avg 0.89 0.85 0.86 40
-weighted avg 0.88 0.88 0.87 40
+ accuracy 0.85 82
+ macro avg 0.83 0.85 0.84 82
+weighted avg 0.86 0.85 0.86 82
+INFO:medcat.utils.meta_cat.ml_utils:
+##### Model saved to status_lstm/model.dat at epoch: 3 and weighted avg/f1-score: 0.8561749903213317 #####
-##### Model saved to status/model.dat at epoch: 4 and weighted avg/f1-score: 0.8715932914046121 #####
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 4 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Epoch: 5 ************************************************** Train
- precision recall f1-score support
+ 0 0.98 1.00 0.99 222
+ 1 0.99 0.96 0.98 102
- 1 0.96 0.99 0.97 113
- 2 1.00 0.98 0.99 253
+ accuracy 0.98 324
+ macro avg 0.99 0.98 0.98 324
+weighted avg 0.98 0.98 0.98 324
- accuracy 0.98 366
- macro avg 0.98 0.99 0.98 366
-weighted avg 0.98 0.98 0.98 366
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 4 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-Epoch: 5 ************************************************** Test
- precision recall f1-score support
+ 0 0.90 0.84 0.87 56
+ 1 0.70 0.81 0.75 26
- 1 0.81 0.87 0.84 15
- 2 0.92 0.88 0.90 25
+ accuracy 0.83 82
+ macro avg 0.80 0.82 0.81 82
+weighted avg 0.84 0.83 0.83 82
- accuracy 0.88 40
- macro avg 0.86 0.87 0.87 40
-weighted avg 0.88 0.88 0.88 40
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 5 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
+ 0 0.99 0.99 0.99 222
+ 1 0.97 0.97 0.97 102
-##### Model saved to status/model.dat at epoch: 5 and weighted avg/f1-score: 0.8757406188281764 #####
+ accuracy 0.98 324
+ macro avg 0.98 0.98 0.98 324
+weighted avg 0.98 0.98 0.98 324
-Epoch: 6 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 5 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.98 1.00 0.99 113
- 2 1.00 0.99 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.99 366
- macro avg 0.99 1.00 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 6 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 6 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+ 0 0.99 1.00 0.99 222
+ 1 1.00 0.97 0.99 102
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
-Epoch: 7 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 6 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.99 0.85 0.91 113
- 2 0.94 1.00 0.97 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.95 366
- macro avg 0.96 0.92 0.94 366
-weighted avg 0.95 0.95 0.95 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 7 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 7 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+ 0 0.99 1.00 0.99 222
+ 1 0.99 0.98 0.99 102
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
-Epoch: 8 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 7 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 1.00 0.97 0.99 113
- 2 0.99 1.00 0.99 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 8 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 8 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.76 0.87 0.81 15
- 2 0.91 0.84 0.87 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
- accuracy 0.85 40
- macro avg 0.84 0.85 0.84 40
-weighted avg 0.86 0.85 0.85 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 9 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 8 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.92 1.00 0.96 113
- 2 1.00 0.96 0.98 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.97 366
- macro avg 0.96 0.98 0.97 366
-weighted avg 0.97 0.97 0.97 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 9 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 9 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.72 0.87 0.79 15
- 2 0.91 0.80 0.85 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
- accuracy 0.82 40
- macro avg 0.82 0.83 0.82 40
-weighted avg 0.84 0.82 0.83 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 10 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 9 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.96 1.00 0.98 113
- 2 1.00 0.98 0.99 253
+ 0 0.87 0.86 0.86 56
+ 1 0.70 0.73 0.72 26
- accuracy 0.99 366
- macro avg 0.98 0.99 0.98 366
-weighted avg 0.99 0.99 0.99 366
+ accuracy 0.82 82
+ macro avg 0.79 0.79 0.79 82
+weighted avg 0.82 0.82 0.82 82
-Epoch: 10 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 10 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.86 0.80 0.83 15
- 2 0.88 0.92 0.90 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
- accuracy 0.88 40
- macro avg 0.87 0.86 0.86 40
-weighted avg 0.87 0.88 0.87 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 11 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 10 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.87 0.86 0.86 56
+ 1 0.70 0.73 0.72 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.82 82
+ macro avg 0.79 0.79 0.79 82
+weighted avg 0.82 0.82 0.82 82
-Epoch: 11 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 11 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.91 0.67 0.77 15
- 2 0.83 0.96 0.89 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
- accuracy 0.85 40
- macro avg 0.87 0.81 0.83 40
-weighted avg 0.86 0.85 0.84 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 12 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 11 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 1.00 0.97 0.99 113
- 2 0.99 1.00 0.99 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 12 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 12 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
-Epoch: 13 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 12 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 13 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 13 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.91 0.67 0.77 15
- 2 0.83 0.96 0.89 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
- accuracy 0.85 40
- macro avg 0.87 0.81 0.83 40
-weighted avg 0.86 0.85 0.84 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 14 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 13 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 14 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 14 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.92 0.73 0.81 15
- 2 0.86 0.96 0.91 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
- accuracy 0.88 40
- macro avg 0.89 0.85 0.86 40
-weighted avg 0.88 0.88 0.87 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 15 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 14 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 15 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 15 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.67 0.80 0.73 15
- 2 0.86 0.76 0.81 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
- accuracy 0.78 40
- macro avg 0.77 0.78 0.77 40
-weighted avg 0.79 0.78 0.78 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 16 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 15 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.98 1.00 0.99 113
- 2 1.00 0.99 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 0.99 366
- macro avg 0.99 1.00 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 16 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 16 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.65 0.87 0.74 15
- 2 0.90 0.72 0.80 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
- accuracy 0.78 40
- macro avg 0.78 0.79 0.77 40
-weighted avg 0.81 0.78 0.78 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 17 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 16 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 17 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 17 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.67 0.80 0.73 15
- 2 0.86 0.76 0.81 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
- accuracy 0.78 40
- macro avg 0.77 0.78 0.77 40
-weighted avg 0.79 0.78 0.78 40
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
-Epoch: 18 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 17 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 18 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 18 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.80 0.80 0.80 15
- 2 0.88 0.88 0.88 25
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
- accuracy 0.85 40
- macro avg 0.84 0.84 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
-Epoch: 19 ************************************************** Train
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 18 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-Epoch: 19 ************************************************** Test
- precision recall f1-score support
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 19 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- 1 0.92 0.80 0.86 15
- 2 0.89 0.96 0.92 25
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
- accuracy 0.90 40
- macro avg 0.91 0.88 0.89 40
-weighted avg 0.90 0.90 0.90 40
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 19 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
-##### Model saved to status/model.dat at epoch: 19 and weighted avg/f1-score: 0.8983516483516484 #####
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 20 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 20 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
-Epoch: 20 ************************************************** Test
- precision recall f1-score support
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
- 1 0.91 0.67 0.77 15
- 2 0.83 0.96 0.89 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 20 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.87 0.81 0.83 40
-weighted avg 0.86 0.85 0.84 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 21 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 21 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 21 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 21 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 22 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.98 0.99 113
- 2 0.99 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 22 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 1.00 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 22 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 22 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 23 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 23 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 23 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 23 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 24 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 24 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 24 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 24 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 25 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 25 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 25 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.90 0.60 0.72 15
- 2 0.80 0.96 0.87 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 25 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.85 0.78 0.80 40
-weighted avg 0.84 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 26 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 26 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
-Epoch: 26 ************************************************** Test
- precision recall f1-score support
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
- 1 0.92 0.73 0.81 15
- 2 0.86 0.96 0.91 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 26 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.88 40
- macro avg 0.89 0.85 0.86 40
-weighted avg 0.88 0.88 0.87 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 27 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 27 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 27 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.92 0.73 0.81 15
- 2 0.86 0.96 0.91 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 27 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.88 40
- macro avg 0.89 0.85 0.86 40
-weighted avg 0.88 0.88 0.87 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 28 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 28 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 28 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 28 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 29 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 29 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 29 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 29 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 30 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 30 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 30 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 30 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 31 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 31 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 31 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 31 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 32 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 32 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 32 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 32 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 33 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 33 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 33 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 33 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 34 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 34 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 34 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 34 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 35 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 35 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 35 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 35 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 36 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 36 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 36 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 36 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 37 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 37 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 37 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 37 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 38 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 38 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 38 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 38 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 39 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 39 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 39 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 39 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 40 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 40 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 40 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 40 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 41 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 0.99 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 41 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 41 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 41 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 42 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 42 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
-Epoch: 42 ************************************************** Test
- precision recall f1-score support
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 42 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 43 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 43 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 43 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.85 0.73 0.79 15
- 2 0.85 0.92 0.88 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 43 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.85 40
- macro avg 0.85 0.83 0.84 40
-weighted avg 0.85 0.85 0.85 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 44 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 44 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 0.99 0.99 102
-Epoch: 44 ************************************************** Test
- precision recall f1-score support
+ accuracy 0.99 324
+ macro avg 0.99 0.99 0.99 324
+weighted avg 0.99 0.99 0.99 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 44 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 45 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 45 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 45 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 45 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 46 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 46 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 46 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 46 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 47 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 47 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 47 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 47 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 48 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 48 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 48 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 48 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 49 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 49 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 49 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 49 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 50 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 50 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 0.99 1.00 102
-Epoch: 50 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 50 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 51 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 1.00 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 51 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 51 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 51 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 52 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 52 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 0.99 1.00 1.00 102
-Epoch: 52 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.73 0.73 0.73 15
- 2 0.84 0.84 0.84 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 52 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.80 40
- macro avg 0.79 0.79 0.79 40
-weighted avg 0.80 0.80 0.80 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 53 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 1.00 1.00 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 53 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 1.00 366
- macro avg 1.00 1.00 1.00 366
-weighted avg 1.00 1.00 1.00 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 53 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 53 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
-Epoch: 54 ************************************************** Train
- precision recall f1-score support
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
- 1 0.99 0.99 0.99 113
- 2 1.00 1.00 1.00 253
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 54 ************************************************** Train
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.99 366
- macro avg 0.99 0.99 0.99 366
-weighted avg 0.99 0.99 0.99 366
+ 0 1.00 1.00 1.00 222
+ 1 1.00 1.00 1.00 102
-Epoch: 54 ************************************************** Test
- precision recall f1-score support
+ accuracy 1.00 324
+ macro avg 1.00 1.00 1.00 324
+weighted avg 1.00 1.00 1.00 324
- 1 0.79 0.73 0.76 15
- 2 0.85 0.88 0.86 25
+INFO:medcat.utils.meta_cat.ml_utils:Epoch: 54 ************************************************** Test
+INFO:medcat.utils.meta_cat.ml_utils: precision recall f1-score support
- accuracy 0.82 40
- macro avg 0.82 0.81 0.81 40
-weighted avg 0.82 0.82 0.82 40
+ 0 0.89 0.86 0.87 56
+ 1 0.71 0.77 0.74 26
+
+ accuracy 0.83 82
+ macro avg 0.80 0.81 0.81 82
+weighted avg 0.83 0.83 0.83 82
-
-
- Out[19]:
-
-
-
-
-
-{'report': {'1': {'precision': 0.9230769230769231,
- 'recall': 0.8,
- 'f1-score': 0.8571428571428571,
- 'support': 15},
- '2': {'precision': 0.8888888888888888,
- 'recall': 0.96,
- 'f1-score': 0.923076923076923,
- 'support': 25},
- 'accuracy': 0.9,
- 'macro avg': {'precision': 0.905982905982906,
- 'recall': 0.88,
- 'f1-score': 0.8901098901098901,
- 'support': 40},
- 'weighted avg': {'precision': 0.9017094017094017,
- 'recall': 0.9,
- 'f1-score': 0.8983516483516484,
- 'support': 40}},
- 'epoch': 19}
+
+
+
+ Out[ ]:
+
+
+
+
+
+{'confusion_matrix': array([[0.85714286, 0.14285714],
+ [0.15384615, 0.84615385]]),
+ 'report': {'0': {'precision': 0.9230769230769231,
+ 'recall': 0.8571428571428571,
+ 'f1-score': 0.888888888888889,
+ 'support': 56.0},
+ '1': {'precision': 0.7333333333333333,
+ 'recall': 0.8461538461538461,
+ 'f1-score': 0.7857142857142856,
+ 'support': 26.0},
+ 'accuracy': 0.8536585365853658,
+ 'macro avg': {'precision': 0.8282051282051281,
+ 'recall': 0.8516483516483516,
+ 'f1-score': 0.8373015873015872,
+ 'support': 82.0},
+ 'weighted avg': {'precision': 0.8629143214509067,
+ 'recall': 0.8536585365853658,
+ 'f1-score': 0.8561749903213317,
+ 'support': 82.0}},
+ 'report_train': {'0': {'precision': 0.9641255605381166,
+ 'recall': 0.9684684684684685,
+ 'f1-score': 0.9662921348314607,
+ 'support': 222.0},
+ '1': {'precision': 0.9306930693069307,
+ 'recall': 0.9215686274509803,
+ 'f1-score': 0.9261083743842364,
+ 'support': 102.0},
+ 'accuracy': 0.9537037037037037,
+ 'macro avg': {'precision': 0.9474093149225237,
+ 'recall': 0.9450185479597244,
+ 'f1-score': 0.9462002546078485,
+ 'support': 324.0},
+ 'weighted avg': {'precision': 0.9536005170023729,
+ 'recall': 0.9537037037037037,
+ 'f1-score': 0.9536416917277049,
+ 'support': 324.0}},
+ 'epoch': 3}
+
-
-
-
+
+
+
+
+
+
We can now save the models using the save function. It has only one argument full_save if True it will also save the embeddings and tokenizers (note that this is slightly redundant, as we no training was done on the embeddings/tokenizers).
-
-
-In [20]:
-
-
+
+
+
+
+
+In [ ]:
+
+
# Alternative way to save
-mc.save("alternative_status_metamodel")
+mc.save("alternative_status_metamodel")
-
+
+
-
-
-
+
+
+
+
+
+
Test of the whole pipeline¶
-
-
-In [21]:
-
-
+
+
+
+
+
+