added one main

main.py

 import sys
 import warnings
-
 import mlflow
 from sklearn import metrics
 from sklearn.model_selection import train_test_split
+import math
+import traceback
+from datetime import datetime
 
-# from scripts.constants.constants import RawConstants
-# from scripts.core.model_loader import ModelLoader
-# from scripts.section_utils.bof_section import preprocess_bof_section
-# from scripts.section_utils.extruder_section import preprocess_extruder_section
-# from scripts.section_utils.material_section import preprocess_viscosity_section
-# from scripts.section_utils.mixer_section import preprocess_mixer_section
-# from scripts.section_utils.pickup_section import preprocess_pickup_section
-# from scripts.section_utils.sheet_supply_section import preprocess_sheet_section
-
-warnings.filterwarnings("ignore")
-
-import warnings
-
-# from scripts.constants.constants import ExtruderConstants
-
-warnings.filterwarnings("ignore")
-
-import warnings
-
-# from scripts.constants.constants import ViscosityConstants
-
-warnings.filterwarnings("ignore")
-
-import warnings
-
-# from scripts.constants.constants import MixerConstants
-
-warnings.filterwarnings("ignore")
-
-import warnings
-
-# from scripts.constants.constants import PickupConstants
-
-warnings.filterwarnings("ignore")
-
-import warnings
-
-# from scripts.constants.constants import SheetConstants
+import numpy as np
+import pandas as pd
+from loguru import logger
 
 warnings.filterwarnings("ignore")
 
-
 def preprocess_sheet_section(df, index_number):
     sheet_supply_column = SheetConstants.sheet_supply_column
     sheet_supply_df = df[sheet_supply_column]
@@ -724,6 +690,8 @@ def preprocess_viscosity_section(viscosity_df, index_number):
     viscosity_df['batch-date'] = 'Batch_' + viscosity_df['Batch No.'].astype(str) + '_' + viscosity_df['date'].astype(
         str)
     viscosity_df = viscosity_df[viscosity_df['Index No'] == index_number]
+    if viscosity_df.empty:
+        raise Exception(f"Size Index No {index_number} not found pls check the file")
     rubber_cols = ViscosityConstants.rubber_cols
     # Replace '-' with 0 for numerical and float columns
     viscosity_df[rubber_cols] = viscosity_df[rubber_cols].replace('-', 0)
@@ -1057,58 +1025,6 @@ def preprocess_extruder_section(df, index_number, vis_df):
     return df_extruder_grouped
 
 
-import math
-import warnings
-import traceback
-from datetime import datetime
-
-import numpy as np
-import pandas as pd
-from loguru import logger
-
-from scripts.constants.constants import BofConstants
-
-warnings.filterwarnings("ignore")
-
-
-def mixer_section_start_end_time(raw_df, index_no):
-    try:
-        mixer_cols = BofConstants.bof_mixer_cols
-        mixer_df = raw_df[mixer_cols]
-        mixer_df['Time Stamp'] = pd.to_datetime(mixer_df['Time Stamp'])
-        mixer_df = mixer_df.sort_values(by='Time Stamp')
-        numeric_cols = mixer_df.select_dtypes(include=['int', 'float']).columns
-
-        # Convert numeric columns to float
-        mixer_df[numeric_cols] = mixer_df[numeric_cols].astype(float)
-        mixer_df['day'] = mixer_df['Time Stamp'].dt.date
-        mixer_df = mixer_df[mixer_df["Size No (INDEX No).3"] == index_no]
-        mixer_df = mixer_df[mixer_df["Mixing batch number"] != 0]
-        mixer_df['time_min'] = mixer_df['Time Stamp']
-        mixer_df['time_max'] = mixer_df['Time Stamp']
-        aggregation_dict = {
-            'time_min': 'min',
-            'time_max': 'max',
-        }
-        group_by = ['day', 'Mixing batch number']
-        df_mixer_grouped = mixer_df.groupby(group_by).agg(aggregation_dict).reset_index()
-        df_mixer_grouped['mixer_section_time_diff_second'] = df_mixer_grouped['time_max'] - df_mixer_grouped['time_min']
-        df_mixer_grouped['mixer_section_time_diff_second'] = df_mixer_grouped[
-            'mixer_section_time_diff_second'].dt.total_seconds()
-        df_mixer_grouped['batch-date'] = 'Batch_' + df_mixer_grouped['Mixing batch number'].astype(str) + '_' + \
-                                         df_mixer_grouped['day'].astype(str)
-        date_dict = {}
-        batch_lis = list(df_mixer_grouped['batch-date'].unique())
-        for each_bt in batch_lis:
-            df_nw = df_mixer_grouped[df_mixer_grouped['batch-date'] == each_bt]
-            date_dict[each_bt] = {"start_time": str(list(df_nw['time_min'])[0]),
-                                  'end_time': str(list(df_nw['time_max'])[0])}
-        return date_dict
-    except Exception as err:
-        logger.error(f'Error in fetching mixer batch date dictionary: {str(err)}')
-        logger.error(traceback.format_exc())
-        raise Exception(str(err))
-
 
 def return_batch_no_df(raw_df, viscosity_df, date_dict, index_number):
     try:
@@ -1988,8 +1904,8 @@ def start_prediction(raw_path, viscosity_path, index_no, raw_skip_rows, viscosit
     df_grouped = merged_all_sections(df_sheet_grouped, df_mixer_grouped, df_extruder_grouped, df_bof_grouped,
                                      df_pickup_grouped, viscosity_df)
 
-    load_and_predict(df_grouped, index_no, model_path)
-    # model_trainer(df_grouped, index_no, model_path)
+    # load_and_predict(df_grouped, index_no, model_path)
+    model_trainer(df_grouped, index_no, model_path)
 
 
 if __name__ == "__main__":