Merge pull request #968 from matouma/pending-version-change/1.0.0

Starting new release cycle after cutoff 1.0.0
IBM · Jan 24, 2025 · 38039f6 · 38039f6
2 parents 84b081a + 8e927bd
commit 38039f6
Show file tree

Hide file tree

Showing 5 changed files with 22 additions and 24 deletions.
diff --git a/.make.versions b/.make.versions
@@ -63,4 +63,4 @@ endif
 #
 # If you change the versions numbers, be sure to run "make set-versions" to 
 # update version numbers across the transform (e.g., pyproject.toml).
-TRANSFORMS_PKG_VERSION=1.0.0a0
+TRANSFORMS_PKG_VERSION=1.0.1.dev0
diff --git a/release-notes.md b/release-notes.md
@@ -1,5 +1,19 @@
 # Data Prep Kit Release notes
 
+## Release 1.0.0 - 1/24/2025
+
+## General
+
+1. Refactored all language transforms and implemented simplified APIs for the refactored transforms
+1. Added notebook examples for each of the transforms 
+1. Streamlined documentation and added tutorial for developers who want to build new transforms 
+1. Other minor enhancements and bug fixes were done for transforms, workflow pipelines, and CI/CD makefiles
+
+### Transforms
+
+1. Added new similarity transform (for detecting confidentiality, copyright, and/or plagiarism in documents)
+
+
 ## Release 0.2.3 - 12/15/2024
 
 ## General

diff --git a/transforms/pyproject.toml b/transforms/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_transforms"
-version = "1.0.0a6"
+version = "1.0.1.dev0"
 requires-python = ">=3.10,<3.13"
 keywords = ["transforms", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
 description = "Data Preparation Toolkit Transforms using Ray"

diff --git a/transforms/transforms-1.0-lang-ray.ipynb b/transforms/transforms-1.0-lang-ray.ipynb
@@ -21,7 +21,7 @@
    "outputs": [],
    "source": [
     "%%capture\n",
-    "!pip install 'data-prep-toolkit-transforms[ray, language]==1.0.0a4'\n",
+    "!pip install 'data-prep-toolkit-transforms[ray,language]'\n",
     "import pyarrow.parquet as pq\n",
     "import pandas as pd"
    ]
@@ -335,8 +335,8 @@
    "outputs": [],
    "source": [
     "##### **** To explote the output from eDedup, run the code below\n",
-    "table = pq.read_table('files-ededup/arxiv_org_2408.09869v5.pdf_application.parquet')\n",
-    "table.to_pandas()"
+    "#table = pq.read_table('files-ededup/arxiv_org_2408.09869v5.pdf_application.parquet')\n",
+    "#table.to_pandas()"
    ]
   },
   {
@@ -595,22 +595,6 @@
     "#import glob\n",
     "#glob.glob(\"files-fdedup/*\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "36c243b7-5097-4a3c-bd4e-45c3b8273a90",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "52d85768-7a15-46bc-8c46-6782dba53d69",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

diff --git a/transforms/transforms-1.0-lang.ipynb b/transforms/transforms-1.0-lang.ipynb
@@ -20,7 +20,7 @@
    "outputs": [],
    "source": [
     "%%capture\n",
-    "!pip install 'data-prep-toolkit-transforms[language]==1.0.0a1'\n",
+    "!pip install 'data-prep-toolkit-transforms[language]'\n",
     "import pyarrow.parquet as pq\n",
     "import pandas as pd"
    ]
@@ -330,8 +330,8 @@
    "outputs": [],
    "source": [
     "##### **** To explote the output from eDedup, run the code below\n",
-    "table = pq.read_table('files-ededup/arxiv_org_2408.09869v5.pdf_application.parquet')\n",
-    "table.to_pandas()"
+    "#table = pq.read_table('files-ededup/arxiv_org_2408.09869v5.pdf_application.parquet')\n",
+    "#table.to_pandas()"
    ]
   },
   {