additional cleanup

model_data/analysis/SapModel.py

@@ -12,6 +12,9 @@ from sklearn.inspection import permutation_importance
 
 from statsmodels.stats.outliers_influence import variance_inflation_factor
 from tqdm import tqdm
+from model_data.utils import setup_logger
+
+logger = setup_logger()
 
 with open("all_data.pkl", "rb") as f:
     all_data = pickle.load(f)
@@ -271,6 +274,7 @@ class SapModel:
         return model_data
 
     def create_dataset(self):
+        logger.info("Creating modelling dataset")
         model_data = self.df[[self.RESPONSE] + self.COMPONENT_FEATURES + self.BASE_FEATURES]
         model_data = model_data.reset_index(drop=True)
         model_data["idx"] = model_data.index.copy()
@@ -353,7 +357,6 @@ class SapModel:
     def fit_model(self):
         """
         Main function to fit the model and produce accuracy metrics
-        :return:
         """
 
         x = pd.get_dummies(self.model_data, columns=self.CATEGORICAL_COLS + self.BUCKET_VARIABLES, drop_first=True)
@@ -369,6 +372,7 @@ class SapModel:
         # Create the training and test sets for each run
         self.make_training_test(x)
         self.train_x, self.test_x = self.remove_zero_std_cols(self.train_x, self.test_x)
+        logger.info("Detecting multi-collinearity in training dataset")
         self.detect_multi_collinearity()
 
         # Add a constant to the independent value
@@ -379,6 +383,7 @@ class SapModel:
         train_x = train_x.drop(columns=["idx"])
         test_x = test_x.drop(columns=["idx"])
 
+        logger.info("Fitting testing model")
         # make regression model
         model = sm.OLS(self.train_y, train_x)
         # fit model and print results
@@ -429,7 +434,7 @@ class SapModel:
         # We're now ready to fit the final model
         # For the momeent, the pre-processing at the top of this function merely removes columns, so we
         # just need to remove the columns that were removed from the training data from the final model
-
+        logger.info("Fitting final model")
         x = sm.add_constant(x)
         y = x[self.RESPONSE]
         x = x[self.train_x.columns]