Add load_contest_file function to handle contest data loading in app.py

- Introduced a new function `load_contest_file` in `load_contest_file.py` to streamline the loading and processing of contest data from uploaded files.
- Updated `app.py` to utilize `load_contest_file` instead of `load_file`, enhancing clarity and functionality in contest data management.
- Improved error handling and data extraction logic within the new function to ensure robust processing of uploaded contest files.

app.py

@@ -8,6 +8,7 @@ import random
 
 ## import global functions
 from global_func.clean_player_name import clean_player_name
+from global_func.load_contest_file import load_contest_file
 from global_func.load_file import load_file
 from global_func.load_ss_file import load_ss_file
 from global_func.find_name_mismatches import find_name_mismatches
@@ -31,7 +32,7 @@ with tab1:
             del st.session_state['Contest']
 
         if Contest_file:
-            st.session_state['Contest'], st.session_state['ownership_dict'], st.session_state['entry_list'] = load_file(Contest_file)
+            st.session_state['Contest'], st.session_state['ownership_dict'], st.session_state['entry_list'] = load_contest_file(Contest_file)
             st.session_state['Contest'] = st.session_state['Contest'].dropna(how='all')
             st.session_state['Contest'] = st.session_state['Contest'].reset_index(drop=True)
             if st.session_state['Contest'] is not None:

global_func/load_contest_file.py

@@ -0,0 +1,57 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import time
+from fuzzywuzzy import process
+
+## import global functions
+from global_func.clean_player_name import clean_player_name
+
+def load_contest_file(upload):
+    pos_values = ['P', 'C', '1B', '2B', '3B', 'SS', 'OF']
+    if upload is not None:
+        try:
+            if upload.name.endswith('.csv'):
+                raw_df = pd.read_csv(upload)
+            elif upload.name.endswith(('.xls', '.xlsx')):
+                raw_df = pd.read_excel(upload)
+            else:
+                st.error('Please upload either a CSV or Excel file')
+                return None
+            
+            df = raw_df[['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Roster Position', '%Drafted', 'FPTS']]
+            df = df.rename(columns={'Roster Position': 'Pos', '%Drafted': 'Own'})
+            
+            # Split EntryName into base name and entry count
+            df['BaseName'] = df['EntryName'].str.replace(r'\s*\(\d+/\d+\)$', '', regex=True)
+            df['EntryCount'] = df['EntryName'].str.extract(r'\((\d+/\d+)\)')
+            df['EntryCount'] = df['EntryCount'].fillna('1/1')  # Default to 1/1 if no entry count
+            
+            # Split the lineup string by replacing position indicators with commas
+            # We need to ensure we only replace position indicators that are at the start of a player entry
+            # and not those that might appear within player names
+            df['Lineup'] = df['Lineup'].str.replace(r'\b(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
+            
+            # Split into individual columns and remove position indicators
+            # First, determine the maximum number of players in any lineup
+            max_players = int(df['Lineup'].str.split(',').str.len().max())
+            
+            if max_players <= 0:
+                st.error('No valid lineups found in the uploaded file')
+                return None
+                
+            # Create columns for each player
+            for i in range(1, max_players - 1):
+                df[i] = df['Lineup'].str.split(',').str[i].str.strip()
+                # Remove position indicators from the end of each entry
+                df[i] = df[i].str.replace(r'\s+(' + '|'.join(pos_values) + r')$', '', regex=True)
+            ownership_dict = dict(zip(df['Player'], df['Own']))
+            cleaned_df = df.drop(columns=['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Pos', 'Own', 'FPTS'])
+            entry_list = list(set(df['BaseName']))
+            entry_list.sort()
+            
+            return cleaned_df, ownership_dict, entry_list
+        except Exception as e:
+            st.error(f'Error loading file: {str(e)}')
+            return None
+    return None

global_func/load_file.py

@@ -8,49 +8,23 @@ from fuzzywuzzy import process
 from global_func.clean_player_name import clean_player_name
 
 def load_file(upload):
-    pos_values = ['P', 'C', '1B', '2B', '3B', 'SS', 'OF']
     if upload is not None:
         try:
             if upload.name.endswith('.csv'):
-                raw_df = pd.read_csv(upload)
+                df = pd.read_csv(upload)
             elif upload.name.endswith(('.xls', '.xlsx')):
-                raw_df = pd.read_excel(upload)
+                df = pd.read_excel(upload)
             else:
                 st.error('Please upload either a CSV or Excel file')
                 return None
             
-            df = raw_df[['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Roster Position', '%Drafted', 'FPTS']]
-            df = df.rename(columns={'Roster Position': 'Pos', '%Drafted': 'Own'})
+            export_df = df.copy()
             
-            # Split EntryName into base name and entry count
-            df['BaseName'] = df['EntryName'].str.replace(r'\s*\(\d+/\d+\)$', '', regex=True)
-            df['EntryCount'] = df['EntryName'].str.extract(r'\((\d+/\d+)\)')
-            df['EntryCount'] = df['EntryCount'].fillna('1/1')  # Default to 1/1 if no entry count
+            for col in df.columns:
+                if df[col].dtype == 'object':
+                    df[col] = df[col].apply(lambda x: clean_player_name(x) if isinstance(x, str) else x)
             
-            # Split the lineup string by replacing position indicators with commas
-            # We need to ensure we only replace position indicators that are at the start of a player entry
-            # and not those that might appear within player names
-            df['Lineup'] = df['Lineup'].str.replace(r'\b(' + '|'.join(pos_values) + r')\b', r'\1,', regex=True)
-            
-            # Split into individual columns and remove position indicators
-            # First, determine the maximum number of players in any lineup
-            max_players = int(df['Lineup'].str.split(',').str.len().max())
-            
-            if max_players <= 0:
-                st.error('No valid lineups found in the uploaded file')
-                return None
-                
-            # Create columns for each player
-            for i in range(1, max_players - 1):
-                df[i] = df['Lineup'].str.split(',').str[i].str.strip()
-                # Remove position indicators from the end of each entry
-                df[i] = df[i].str.replace(r'\s+(' + '|'.join(pos_values) + r')$', '', regex=True)
-            ownership_dict = dict(zip(df['Player'], df['Own']))
-            cleaned_df = df.drop(columns=['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Pos', 'Own', 'FPTS'])
-            entry_list = list(set(df['BaseName']))
-            entry_list.sort()
-            
-            return cleaned_df, ownership_dict, entry_list
+            return export_df, df
         except Exception as e:
             st.error(f'Error loading file: {str(e)}')
             return None