MultiModalData class improvement (#789)

* MultiModalData class improvement

Now csv files with text and table data can be read just in one motion

- from_csv method added
- MultiModalData detection module is added
- text fields are defined automatically
- tests are added
- some refactoring of preprocessing.py

examples/advanced/multimodal_text_num_example.py

@@ -1,49 +1,33 @@
-import os
+from pathlib import Path
 
 from fedot.api.main import Fedot
 
-from fedot.core.data.data import InputData
 from fedot.core.data.data_split import train_test_data_setup
 from fedot.core.data.multi_modal import MultiModalData
-from fedot.core.repository.dataset_types import DataTypesEnum
-from fedot.core.repository.tasks import Task, TaskTypesEnum
 from fedot.core.utils import fedot_project_root
 
 
-def prepare_multi_modal_data(files_path: str, task: Task) -> MultiModalData:
+def run_multi_modal_example(file_path: str, is_visualise=True) -> float:
     """
-    Imports data from 2 different sources (table and text)
-
-    :param files_path: path to data
-    :param task: task to solve
-    :return: MultiModalData object which contains table and text data
+    This is an example of FEDOT use on multimodal data.
+    The data is taken and adapted from Wine Reviews dataset (winemag-data_first150k):
+    https://www.kaggle.com/datasets/zynicide/wine-reviews
+    and contains information about wine country, region, price, etc.
+    Column that contains text features is 'description'.
+    Other columns contain numerical and categorical features.
+    The aim is to predict wine variety, so it's a classification task.
+
+    :param file_path: path to the file with multimodal data
+    :param is_visualise: if True, then final pipeline will be visualised
+
+    :return: F1 metrics of the model
     """
-
-    path = os.path.join(str(fedot_project_root()), files_path)
-
-    # import of table data
-    path_table = os.path.join(path, 'multimodal_wine_table.csv')
-    data_num = InputData.from_csv(path_table, task=task, target_columns='variety')
-
-    # import of text data
-    path_text = os.path.join(path, 'multimodal_wine_text.csv')
-    data_text = InputData.from_csv(path_text, data_type=DataTypesEnum.text, task=task, target_columns='variety')
-
-    data = MultiModalData({
-        'data_source_table': data_num,
-        'data_source_text': data_text
-    })
-
-    return data
-
-
-def run_multi_modal_example(files_path: str, is_visualise=True) -> float:
-    task = Task(TaskTypesEnum.classification)
-
-    data = prepare_multi_modal_data(files_path, task)
+    task = 'classification'
+    path = Path(fedot_project_root(), file_path)
+    data = MultiModalData.from_csv(file_path=path, task=task, target_columns='variety', index_col=None)
     fit_data, predict_data = train_test_data_setup(data, shuffle_flag=True, split_ratio=0.7)
 
-    automl_model = Fedot(problem='classification', timeout=10)
+    automl_model = Fedot(problem=task, timeout=10)
     automl_model.fit(features=fit_data,
                      target=fit_data.target)
 
@@ -59,4 +43,4 @@ def run_multi_modal_example(files_path: str, is_visualise=True) -> float:
 
 
 if __name__ == '__main__':
-    run_multi_modal_example(files_path='examples/data/multimodal_wine', is_visualise=True)
+    run_multi_modal_example(file_path='examples/data/multimodal_wine.csv', is_visualise=True)