global_func/load_file.py

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_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 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
            for i in range(0,10):
                df[i] = df['Lineup'].str.split(',').str[i].str.strip()
                # Remove position indicators from the beginning of each entry
                df[i] = df[i].str.replace(r'^(' + '|'.join(pos_values) + r')\s+', '', regex=True)
            position_dict = dict(zip(df['Player'], df['Pos']))
            ownership_dict = dict(zip(df['Player'], df['Own']))
            entry_list = list(set(df['EntryName']))
            entry_list.sort()
            
            return df, position_dict, ownership_dict, entry_list
        except Exception as e:
            st.error(f'Error loading file: {str(e)}')
            return None
    return None