File size: 2,869 Bytes
d04558f 5db8a23 d04558f 5db8a23 d04558f 5db8a23 d04558f 5db8a23 1689df1 1ba31e0 a87b532 8a5c645 ffa4d02 8a5c645 ffa4d02 8a5c645 b9bf803 1ba31e0 fd9eb32 5db8a23 8a5c645 1689df1 9e80538 d04558f 8a5c645 d04558f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
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 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)
position_dict = dict(zip(df['Player'], df['Pos']))
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, position_dict, ownership_dict, entry_list
except Exception as e:
st.error(f'Error loading file: {str(e)}')
return None
return None |