James McCool
Enhance salary data processing in load_file.py: add a try-except block to convert salary values to integers after removing unwanted characters, improving data integrity during file handling.
a31c2f9
| import streamlit as st | |
| import numpy as np | |
| import pandas as pd | |
| import time | |
| from fuzzywuzzy import process | |
| import re | |
| ## import global functions | |
| from global_func.clean_player_name import clean_player_name | |
| def load_file(upload): | |
| if upload is not None: | |
| try: | |
| clean_name = re.sub(r' \(\d+\)', '', upload.name) | |
| print(clean_name) | |
| print(upload.name) | |
| if clean_name.endswith('.csv'): | |
| df = pd.read_csv(upload) | |
| elif clean_name.endswith(('.xls', '.xlsx')): | |
| df = pd.read_excel(upload) | |
| else: | |
| st.error('Please upload either a CSV or Excel file') | |
| return None, None | |
| try: | |
| df['salary'] = df['salary'].astype(str).str.replace([',', '$', ' '], '', regex=True).astype(int) | |
| st.print('replaced salary symbols') | |
| except: | |
| pass | |
| export_df = df.copy() | |
| 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) | |
| return export_df, df | |
| except Exception as e: | |
| st.error(f'Error loading file: {str(e)}') | |
| return None | |
| return None |