Implement character normalization and enhance data export functionality in Streamlit app. Added a new function to convert accented characters to ASCII, ensuring cleaner data exports. Updated export logic to include options for both IDs and names, with filtering capabilities based on user-defined salary constraints.

src/streamlit_app.py

@@ -3,6 +3,7 @@ import numpy as np
 import pandas as pd
 import pymongo
 import os
+import unicodedata
 
 st.set_page_config(layout="wide")
 
@@ -139,15 +140,46 @@ def init_FD_lineups(type):
 
         return FD_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)
+    # 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')
 
 roo_data, sd_roo_data, timestamp = init_baselines()
+dk_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+dk_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
+fd_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+fd_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
 hold_display = roo_data
 lineup_display = []
 check_list = []
@@ -164,6 +196,10 @@ with tab1:
                 # i.e. clear values from both square and cube
                 st.cache_data.clear()
                 roo_data, sd_roo_data, timestamp = init_baselines()
+                dk_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+                dk_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
+                fd_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+                fd_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
                 dk_lineups = init_DK_lineups('Regular')
                 fd_lineups = init_FD_lineups('Regular')
                 hold_display = roo_data
@@ -213,6 +249,10 @@ with tab2:
         if st.button("Load/Reset Data", key='reset2'):
             st.cache_data.clear()
             roo_data, sd_roo_data, timestamp = init_baselines()
+            dk_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+            dk_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
+            fd_id_dict = dict(zip(roo_data['Player'], roo_data['player_id']))
+            fd_id_dict_sd = dict(zip(sd_roo_data['Player'], sd_roo_data['player_id']))
             hold_display = roo_data
             dk_lineups = init_DK_lineups('Regular')
             fd_lineups = init_FD_lineups('Regular')
@@ -223,6 +263,12 @@ with tab2:
         col1, col2, col3, col4, col5 = st.columns(5)
         with col1:      
             site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
+            if site_var1 == 'Draftkings':
+                id_dict = dk_id_dict.copy()
+                id_dict_sd = dk_id_dict_sd.copy()
+            elif site_var1 == 'Fanduel':
+                id_dict = fd_id_dict.copy()
+                id_dict_sd = fd_id_dict_sd.copy()
             
         with col2:
             slate_var1 = st.radio("Which data are you loading?", ('Regular', 'Showdown'))
@@ -281,20 +327,112 @@ with tab2:
                 salary_min_var = st.number_input("Minimum salary used", min_value = 0, max_value = 60000, value = 59000, step = 100, key = 'salary_min_var')
                 salary_max_var = st.number_input("Maximum salary used", min_value = 0, max_value = 60000, value = 60000, step = 100, key = 'salary_max_var')
 
-        if st.button("Prepare data export", key='data_export'):
-            data_export = st.session_state.working_seed.copy()
-            # if site_var1 == 'Draftkings':
-            #     for col_idx in range(6):
-            #         data_export[:, col_idx] = np.array([id_dict.get(player, player) for player in data_export[:, col_idx]])
-            # elif site_var1 == 'Fanduel':
-            #     for col_idx in range(6):
-            #         data_export[:, col_idx] = np.array([id_dict.get(player, player) for player in data_export[:, col_idx]])
-            st.download_button(
-                label="Export optimals set",
-                data=convert_df(data_export),
-                file_name='NBA_optimals_export.csv',
-                mime='text/csv',
-            )
+        reg_dl_col, filtered_dl_col, blank_dl_col = st.columns([2, 2, 6])
+        with reg_dl_col:
+            if st.button("Prepare full data export", key='data_export'):
+                name_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+                data_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+                if site_var1 == 'Draftkings':
+                    if slate_var1 == 'Regular':
+                        map_columns = ['FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'FLEX6']
+                    elif slate_var1 == 'Showdown':
+                        map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
+                elif site_var1 == 'Fanduel':
+                    if slate_var1 == 'Regular':
+                        map_columns = ['FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'FLEX6']
+                    elif slate_var1 == 'Showdown':
+                        map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
+                for col_idx in map_columns:
+                    if slate_var1 == 'Regular':
+                        data_export[col_idx] = data_export[col_idx].map(id_dict)
+                    elif slate_var1 == 'Showdown':
+                        data_export[col_idx] = data_export[col_idx].map(id_dict_sd)
+
+                pm_name_export = name_export.drop(columns=['salary', 'proj', 'Own'], axis=1)
+                pm_data_export = data_export.drop(columns=['salary', 'proj', 'Own'], axis=1)
+                reg_opt_col, pm_opt_col = st.columns(2)
+
+                with reg_opt_col:
+                    st.download_button(
+                        label="Export optimals set (IDs)",
+                        data=convert_df(data_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                    st.download_button(
+                        label="Export optimals set (Names)",
+                        data=convert_df(name_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                with pm_opt_col:
+                    st.download_button(
+                        label="Portfolio Manager Export (IDs)",
+                        data=convert_pm_df(pm_data_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                    st.download_button(
+                        label="Portfolio Manager Export (Names)",
+                        data=convert_pm_df(pm_name_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+        with filtered_dl_col:
+            if st.button("Prepare full data export (Filtered)", key='data_export_filtered'):
+                name_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+                data_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
+                if site_var1 == 'Draftkings':
+                    if slate_var1 == 'Regular':
+                        map_columns = ['FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'FLEX6']
+                    elif slate_var1 == 'Showdown':
+                        map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
+                elif site_var1 == 'Fanduel':
+                    if slate_var1 == 'Regular':
+                        map_columns = ['FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'FLEX6']
+                    elif slate_var1 == 'Showdown':
+                        map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
+                for col_idx in map_columns:
+                    if slate_var1 == 'Regular':
+                        data_export[col_idx] = data_export[col_idx].map(id_dict)
+                    elif slate_var1 == 'Showdown':
+                        data_export[col_idx] = data_export[col_idx].map(id_dict_sd)
+                data_export = data_export[data_export['salary'] >= salary_min_var]
+                data_export = data_export[data_export['salary'] <= salary_max_var]
+
+                name_export = name_export[name_export['salary'] >= salary_min_var]
+                name_export = name_export[name_export['salary'] <= salary_max_var]
+                
+                pm_name_export = name_export.drop(columns=['salary', 'proj', 'Own'], axis=1)
+                pm_data_export = data_export.drop(columns=['salary', 'proj', 'Own'], axis=1)
+
+                reg_opt_col, pm_opt_col = st.columns(2)
+                with reg_opt_col:
+                    st.download_button(
+                        label="Export optimals set (IDs)",
+                        data=convert_df(data_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                    st.download_button(
+                        label="Export optimals set (Names)",
+                        data=convert_df(name_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                with pm_opt_col:
+                    st.download_button(
+                        label="Portfolio Manager Export (IDs)",
+                        data=convert_pm_df(pm_data_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
+                    st.download_button(
+                        label="Portfolio Manager Export (Names)",
+                        data=convert_pm_df(pm_name_export),
+                        file_name='PGA_optimals_export.csv',
+                        mime='text/csv',
+                    )
         
     if site_var1 == 'Draftkings':
         if 'working_seed' in st.session_state:
@@ -353,7 +491,7 @@ with tab2:
         st.download_button(
             label="Export display optimals",
             data=convert_df(export_file),
-            file_name='NBA_display_optimals.csv',
+            file_name='PGA_display_optimals.csv',
             mime='text/csv',
         )