model auto trainer

.gitignore

+__pycache__/
\ No newline at end of file

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="5">
+            <item index="0" class="java.lang.String" itemvalue="pandas" />
+            <item index="1" class="java.lang.String" itemvalue="scipy" />
+            <item index="2" class="java.lang.String" itemvalue="pydantic" />
+            <item index="3" class="java.lang.String" itemvalue="pytz" />
+            <item index="4" class="java.lang.String" itemvalue="simplejson" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="scripts.core.data.data_import.KairosQueryBuilder.input_tag" />
+          <option value="scripts.core.data.data_import.KairosQueryBuilder.metric_name" />
+          <option value="scripts.core.data.data_import.KairosQueryBuilder.aggregation_name" />
+          <option value="scripts.core.data.data_import.DataPuller.postgres_engine" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (KBase)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/model_auto_trainer.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.9 (KBase)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/model_auto_trainer.iml" filepath="$PROJECT_DIR$/.idea/model_auto_trainer.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

app.py

+import pandas as pd
+
+from mlflow_util import ModelReTrainer
+
+if __name__ == "__main__":
+    df = pd.read_csv('mlflow-test.csv')
+    obj = ModelReTrainer(df, 'instantaneous_export', 'Dalmia Solar Forecasting V2', 'Forecasting_kadapa_v1', 'versioning')
+    obj.get_latest_model()

pycaret_util.py

+from pycaret import regression
+from loguru import logger
+
+
+class GetBestModel:
+    def __init__(self, df, target_col_list, list_of_models, no_of_models=1):
+        self.df = df
+        self.target_col_list = target_col_list
+        self.no_of_models = no_of_models
+        self.list_of_models = list_of_models
+
+    def compare_get_best_model(self, fine_tune_tech, comparison_metric):
+        try:
+            logger.info("Using Pycaret to train mentioned models")
+            regression.setup(data=self.df, target=self.target_col_list)
+            logger.info(f"Selecting the best model using the metric {comparison_metric}")
+            best_model = regression.compare_models(include=self.list_of_models, sort=comparison_metric,
+                                                   n_select=self.no_of_models)
+            logger.info("Tuning the Model")
+            tuned_model = regression.tune_model(best_model, optimize=comparison_metric, search_library=fine_tune_tech)
+            results = regression.pull()
+            get_best_model_row = results.iloc[0]
+            best_metrics = get_best_model_row.to_dict()
+            best_metrics.pop('Model', None)
+            model_name = str(tuned_model).split('(')[0]
+            hyper_params = tuned_model.get_params()
+            logger.info("Model Training Completed")
+            return tuned_model, model_name, best_metrics, hyper_params
+        except Exception as e:
+            logger.info(f"Unable to select the best model - {e}")