Add character normalization for data exports in app.py: implement a function to convert accented characters to ASCII equivalents, ensuring cleaner data output. Update CSV export functions to apply normalization, enhancing data consistency and accessibility.

app.py

@@ -4,6 +4,7 @@ import pandas as pd
 import streamlit as st
 import gspread
 import pymongo
+import unicodedata
 
 st.set_page_config(layout="wide")
 
@@ -332,18 +333,40 @@ def init_FD_SD_lineups(slate_desig: str, league: str):
 
         return DK_seed
 
+def normalize_special_characters(text):
+    """Convert accented characters to their ASCII equivalents"""
+    if pd.isna(text):
+        return text
+    # Normalize unicode characters to their closest ASCII equivalents
+    normalized = unicodedata.normalize('NFKD', str(text))
+    # Remove diacritics (accents, umlauts, etc.)
+    ascii_text = ''.join(c for c in normalized if not unicodedata.combining(c))
+    return ascii_text
+
 def convert_df_to_csv(df):
-    return df.to_csv().encode('utf-8')
+    df_clean = df.copy()
+    for col in df_clean.columns:
+        if df_clean[col].dtype == 'object':
+            df_clean[col] = df_clean[col].apply(normalize_special_characters)
+    return df_clean.to_csv(index=False).encode('utf-8')
 
 @st.cache_data
 def convert_df(array):
     array = pd.DataFrame(array, columns=column_names)
-    return array.to_csv().encode('utf-8')
+    # Normalize special characters in the dataframe before export
+    for col in array.columns:
+        if array[col].dtype == 'object':
+            array[col] = array[col].apply(normalize_special_characters)
+    return array.to_csv(index=False).encode('utf-8')
 
 @st.cache_data
 def convert_pm_df(array):
     array = pd.DataFrame(array)
-    return array.to_csv().encode('utf-8')
+    # Normalize special characters in the dataframe before export
+    for col in array.columns:
+        if array[col].dtype == 'object':
+            array[col] = array[col].apply(normalize_special_characters)
+    return array.to_csv(index=False).encode('utf-8')
 
 dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, sd_raw, dk_sd_raw, fd_sd_raw, timestamp = load_overall_stats('NBA')
 salary_dict = dict(zip(roo_raw.Player, roo_raw.Salary))