global_func/load_contest_file.py

import streamlit as st
import pandas as pd
from rapidfuzz import process, fuzz

def load_contest_file(upload, helper = None, sport = None):
    if upload is not None:
        try:
            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
            except:
                raw_df = upload
            if helper is not None:
                helper_df = helper

            print('Made it through initial upload')
            
            # Select and rename essential columns for the actual upload
            if helper is None:
                df = raw_df[['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Roster Position', '%Drafted', 'FPTS', 'Salary', 'Team']]
            else:
                df = raw_df[['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Roster Position', '%Drafted', 'FPTS']]
            df = df.rename(columns={'Roster Position': 'Pos', '%Drafted': 'Own'})

            print('Made it through rename')
            
            # 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
            
            # Convert ownership percentage to float
            try:
                df['Own'] = df['Own'].str.replace('%', '').astype(float)
            except:
                df['Own'] = df['Own'].astype(float)

            print('Made it through ownership conversion')
            
            # Select and rename essential columns for the actual upload
            if helper is not None:
                df_helper = helper_df[['Player', 'Salary', 'Team']]
            
            print('Made it through helper')

            print(df_helper[df_helper['Player'] == 'Luis Torrens'])

            contest_names = df.Player.unique()
            if helper is not None:
                helper_names = helper_df.Player.unique()

            contest_match_dict = {}
            helper_match_dict = {}
            for names in contest_names:
                match = process.extractOne(
                    names,
                    helper_names,
                    score_cutoff = 85
                )
                if match:
                    contest_match_dict[names] = match[0]
                else:
                    contest_match_dict[names] = names
            
            for names in helper_names:
                match = process.extractOne(
                    names,
                    contest_names,
                    score_cutoff = 85
                )
                if match:
                    helper_match_dict[names] = match[0]
                else:
                    helper_match_dict[names] = names
            
            for key, value in helper_match_dict.items():
                if key not in contest_match_dict:
                    contest_match_dict[key] = value
            
            df_helper['Player'] = df_helper['Player'].map(contest_match_dict)
            df_helper = df_helper.drop_duplicates(subset='Player', keep='first')

            print(df_helper[df_helper['Player'] == 'Luis Torrens'])
            
            # Create separate dataframes for different player attributes
            if helper is not None:
                ownership_df = df[['Player', 'Own']]
                fpts_df = df[['Player', 'FPTS']]
                salary_df = df_helper[['Player', 'Salary']]
                team_df = df_helper[['Player', 'Team']]
                pos_df = df[['Player', 'Pos']]
            else:
                ownership_df = df[['Player', 'Own']]
                fpts_df = df[['Player', 'FPTS']]
                salary_df = df[['Player', 'Salary']]
                team_df = df[['Player', 'Team']]
                pos_df = df[['Player', 'Pos']]

            print('Made it through dictionaries')
            
            # Create the cleaned dataframe with just the essential columns
            cleaned_df = df[['BaseName', 'Lineup']]
            if sport == 'MLB':
                cleaned_df['Lineup'] = cleaned_df['Lineup'].replace([' P ', ' C ', '1B ', ' 2B ', ' 3B ', ' SS ', ' OF '], value=',', regex=True)
            elif sport == 'MMA':
                cleaned_df['Lineup'] = cleaned_df['Lineup'].replace([' P ', ' C ', '1B ', ' 2B ', ' 3B ', ' SS ', ' OF ', ' F ', 'F '], value=',', regex=True)
            elif sport == 'GOLF':
                cleaned_df['Lineup'] = cleaned_df['Lineup'].replace([' P ', ' C ', '1B ', ' 2B ', ' 3B ', ' SS ', ' OF ', ' G ', 'G '], value=',', regex=True)
            print(sport)
            print(cleaned_df.head(10))
            check_lineups = cleaned_df.copy()
            if sport == 'MLB':
                cleaned_df[['Remove', '1B', '2B', '3B', 'C', 'OF1', 'OF2', 'OF3', 'P1', 'P2', 'SS']] = cleaned_df['Lineup'].str.split(',', expand=True)
            elif sport == 'MMA':
                cleaned_df[['Remove', 'Guy', 'Dude', 'Pooba', 'Bub', 'Chief', 'Buddy']] = cleaned_df['Lineup'].str.split(',', expand=True)
            elif sport == 'GOLF':
                cleaned_df[['Remove', 'Guy', 'Dude', 'Pooba', 'Bub', 'Chief', 'Buddy']] = cleaned_df['Lineup'].str.split(',', expand=True)
            cleaned_df = cleaned_df.drop(columns=['Lineup', 'Remove'])
            entry_counts = cleaned_df['BaseName'].value_counts()
            cleaned_df['EntryCount'] = cleaned_df['BaseName'].map(entry_counts)
            if sport == 'MLB':
                cleaned_df = cleaned_df[['BaseName', 'EntryCount', 'P1', 'P2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']]
            elif sport == 'MMA':
                cleaned_df = cleaned_df[['BaseName', 'EntryCount', 'Guy', 'Dude', 'Pooba', 'Bub', 'Chief', 'Buddy']]
            elif sport == 'GOLF':
                cleaned_df = cleaned_df[['BaseName', 'EntryCount', 'Guy', 'Dude', 'Pooba', 'Bub', 'Chief', 'Buddy']]
            
            print('Made it through check_lineups')
            
            # Get unique entry names
            entry_list = list(set(df['BaseName']))
            entry_list.sort()
            
            return cleaned_df, ownership_df, fpts_df, entry_list, check_lineups
            
        except Exception as e:
            st.error(f'Error loading file: {str(e)}')
            return None
    return None