Learning missing options

pythonCode/med_libs/GoExecutionScript.py

@@ -72,6 +72,10 @@ def __init__(self, json_params: dict, _id: str = "default_id", debug: bool = Fal
         self._progress = {"now": 0, "currentLabel": ""}
         self._id = _id
         self._debug = debug
+        if self._debug:
+            # save json_params_dict to a file
+            with open('json_params_dict.json', 'w') as f:
+                json.dump(json_params, f, indent=4)
 
     def start(self):
         """

pythonCode/med_libs/MEDml/MEDexperiment_learning.py

@@ -114,6 +114,13 @@ def setup_dataset(self, node: Node):
             elif kwargs['use_gpu'] == "False":
                 kwargs['use_gpu'] = False
 
+        if 'index' in kwargs:
+            if kwargs['index'] == "True":
+                kwargs['index'] = True
+            elif kwargs['index'] == "False":
+                kwargs['index'] = False
+
+
         # add the imports
         node.CodeHandler.add_import("import numpy as np")
         node.CodeHandler.add_import("import pandas as pd")
@@ -137,9 +144,15 @@ def setup_dataset(self, node: Node):
         medml_logger = MEDml_logger()
 
         # setup the experiment
-        pycaret_exp.setup(temp_df, log_experiment=medml_logger, **kwargs)
-        node.CodeHandler.add_line(
-            "code", f"pycaret_exp.setup(temp_df, {node.CodeHandler.convert_dict_to_params(kwargs)})")
+        if 'test_data' in kwargs:
+            test_data_df = pd.read_csv(kwargs['test_data']['path'])
+            node.CodeHandler.add_line("code", f"test_data_df = pd.read_csv('{kwargs['test_data']}'")
+            node.CodeHandler.add_line("code", f"pycaret_exp.setup(temp_df, test_data=test_data_df, {node.CodeHandler.convert_dict_to_params(kwargs)})")
+            del kwargs['test_data']
+            pycaret_exp.setup(temp_df, test_data=test_data_df, log_experiment=medml_logger, **kwargs)
+        else:
+            pycaret_exp.setup(temp_df, log_experiment=medml_logger, **kwargs)
+            node.CodeHandler.add_line("code", f"pycaret_exp.setup(temp_df, {node.CodeHandler.convert_dict_to_params(kwargs)})")
         node.CodeHandler.add_line(
             "code", f"dataset = pycaret_exp.get_config('X').join(pycaret_exp.get_config('y'))")
         dataset_metaData = {

pythonCode/med_libs/MEDml/utils/settings_generator/settings_generator.py

@@ -12,6 +12,10 @@
 import dpath.util as dp
 from collections.abc import MutableMapping
 
+# EXAMPLE USAGE
+# cd pythonCode/med_libs/MEDml/utils/settings_generator
+# python settings_generator.py --ml_type classification 
+
 # python scripts arguments
 import argparse
 parser = argparse.ArgumentParser(description='Script so useful.')
@@ -360,6 +364,39 @@ def specific_case(dict_settings: dict) -> dict:
     del dict_settings['analyze']['interpret_model']['options']['save']
     del dict_settings['load_model']['options']['model_name']
 
+    # NOT SUPPORTED
+    del dict_settings['dataset']['options']['data_func']
+    del dict_settings['dataset']['options']['ordinal_features']
+    del dict_settings['dataset']['options']['encoding_method']
+    del dict_settings['dataset']['options']['group_features']
+    del dict_settings['dataset']['options']['custom_pipeline']
+    del dict_settings['dataset']['options']['experiment_custom_tags']
+    del dict_settings['dataset']['options']['engine']
+    del dict_settings['dataset']['options']['memory']
+    del dict_settings['dataset']['options']['profile']
+    del dict_settings['dataset']['options']['profile_kwargs']
+    del dict_settings['compare_models']['options']['engine']
+    del dict_settings['compare_models']['options']['fit_kwargs']
+    del dict_settings['create_model']['options']['engine']
+    del dict_settings['create_model']['options']['fit_kwargs']
+    del dict_settings['create_model']['options']['experiment_custom_tags']
+    del dict_settings['analyze']['plot_model']['options']['fit_kwargs']
+    del dict_settings['analyze']['plot_model']['options']['plot_kwargs']
+    del dict_settings['analyze']['dashboard']['options']['dashboard_kwargs']
+    del dict_settings['analyze']['dashboard']['options']['run_kwargs']
+    del dict_settings['finalize']['options']['fit_kwargs']
+    del dict_settings['finalize']['options']['experiment_custom_tags']
+    del dict_settings['load_model']['options']['platform']
+    del dict_settings['load_model']['options']['authentication']
+    del dict_settings['tune_model']['options']['custom_grid']
+    del dict_settings['tune_model']['options']['custom_scorer']
+    del dict_settings['tune_model']['options']['fit_kwargs']
+    del dict_settings['ensemble_model']['options']['fit_kwargs']
+    del dict_settings['blend_models']['options']['fit_kwargs']
+    del dict_settings['stack_models']['options']['fit_kwargs']
+    if ml_type == "classification":
+        del dict_settings['calibrate_model']['options']['fit_kwargs']
+
     return dict_settings