Refactor app.py to integrate MongoDB for data storage and retrieval, replacing Google Sheets API calls. Added caching for connection initialization and improved tab styling in Streamlit.

app.py

@@ -3,26 +3,37 @@ import pandas as pd
 import streamlit as st
 import gspread
 import plotly.figure_factory as ff
+import pymongo
 
-scope = ['https://www.googleapis.com/auth/spreadsheets',
-          "https://www.googleapis.com/auth/drive"]
+st.set_page_config(layout="wide")
 
-credentials = {
-  "type": "service_account",
-  "project_id": "sheets-api-connect-378620",
-  "private_key_id": "1005124050c80d085e2c5b344345715978dd9cc9",
-  "private_key": "-----BEGIN PRIVATE KEY-----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\nJuElxA33rFEjbgbzdyrE768=\n-----END PRIVATE KEY-----\n",
-  "client_email": "gspread-connection@sheets-api-connect-378620.iam.gserviceaccount.com",
-  "client_id": "106625872877651920064",
-  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
-  "token_uri": "https://oauth2.googleapis.com/token",
-  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
-  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gspread-connection%40sheets-api-connect-378620.iam.gserviceaccount.com"
-}
+@st.cache_resource
+def init_conn():
+    scope = ['https://www.googleapis.com/auth/spreadsheets',
+            "https://www.googleapis.com/auth/drive"]
 
-gc = gspread.service_account_from_dict(credentials)
+    credentials = {
+    "type": "service_account",
+    "project_id": "sheets-api-connect-378620",
+    "private_key_id": "1005124050c80d085e2c5b344345715978dd9cc9",
+    "private_key": "-----BEGIN PRIVATE KEY-----\nMIIEvQIBADANBgkqhkiG9w0BAQEFAASCBKcwggSjAgEAAoIBAQCtKa01beXwc88R\nnPZVQTNPVQuBnbwoOfc66gW3547ja/UEyIGAF112dt/VqHprRafkKGmlg55jqJNt\na4zceLKV+wTm7vBu7lDISTJfGzCf2TrxQYNqwMKE2LOjI69dBM8u4Dcb4k0wcp9v\ntW1ZzLVVuwTvmrg7JBHjiSaB+x5wxm/r3FOiJDXdlAgFlytzqgcyeZMJVKKBQHyJ\njEGg/1720A0numuOCt71w/2G0bDmijuj1e6tH32MwRWcvRNZ19K9ssyDz2S9p68s\nYDhIxX69OWxwScTIHLY6J2t8txf/XMivL/636fPlDADvBEVTdlT606n8CcKUVQeq\npUVdG+lfAgMBAAECggEAP38SUA7B69eTfRpo658ycOs3Amr0JW4H/bb1rNeAul0K\nZhwd/HnU4E07y81xQmey5kN5ZeNrD5EvqkZvSyMJHV0EEahZStwhjCfnDB/cxyix\nZ+kFhv4y9eK+kFpUAhBy5nX6T0O+2T6WvzAwbmbVsZ+X8kJyPuF9m8ldcPlD0sce\ntj8NwVq1ys52eosqs7zi2vjt+eMcaY393l4ls+vNq8Yf27cfyFw45W45CH/97/Nu\n5AmuzlCOAfFF+z4OC5g4rei4E/Qgpxa7/uom+BVfv9G0DIGW/tU6Sne0+37uoGKt\nW6DzhgtebUtoYkG7ZJ05BTXGp2lwgVcNRoPwnKJDxQKBgQDT5wYPUBDW+FHbvZSp\nd1m1UQuXyerqOTA9smFaM8sr/UraeH85DJPEIEk8qsntMBVMhvD3Pw8uIUeFNMYj\naLmZFObsL+WctepXrVo5NB6RtLB/jZYxiKMatMLUJIYtcKIp+2z/YtKiWcLnwotB\nWdCjVnPTxpkurmF2fWP/eewZ+wKBgQDRMtJg7etjvKyjYNQ5fARnCc+XsI3gkBe1\nX9oeXfhyfZFeBXWnZzN1ITgFHplDznmBdxAyYGiQdbbkdKQSghviUQ0igBvoDMYy\n1rWcy+a17Mj98uyNEfmb3X2cC6WpvOZaGHwg9+GY67BThwI3FqHIbyk6Ko09WlTX\nQpRQjMzU7QKBgAfi1iflu+q0LR+3a3vvFCiaToskmZiD7latd9AKk2ocsBd3Woy9\n+hXXecJHPOKV4oUJlJgvAZqe5HGBqEoTEK0wyPNLSQlO/9ypd+0fEnArwFHO7CMF\nycQprAKHJXM1eOOFFuZeQCaInqdPZy1UcV5Szla4UmUZWkk1m24blHzXAoGBAMcA\nyH4qdbxX9AYrC1dvsSRvgcnzytMvX05LU0uF6tzGtG0zVlub4ahvpEHCfNuy44UT\nxRWW/oFFaWjjyFxO5sWggpUqNuHEnRopg3QXx22SRRTGbN45li/+QAocTkgsiRh1\nqEcYZsO4mPCsQqAy6E2p6RcK+Xa+omxvSnVhq0x1AoGAKr8GdkCl4CF6rieLMAQ7\nLNBuuoYGaHoh8l5E2uOQpzwxVy/nMBcAv+2+KqHEzHryUv1owOi6pMLv7A9mTFoS\n18B0QRLuz5fSOsVnmldfC9fpUc6H8cH1SINZpzajqQA74bPwELJjnzrCnH79TnHG\nJuElxA33rFEjbgbzdyrE768=\n-----END PRIVATE KEY-----\n",
+    "client_email": "gspread-connection@sheets-api-connect-378620.iam.gserviceaccount.com",
+    "client_id": "106625872877651920064",
+    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+    "token_uri": "https://oauth2.googleapis.com/token",
+    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+    "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gspread-connection%40sheets-api-connect-378620.iam.gserviceaccount.com"
+    }
 
-st.set_page_config(layout="wide")
+    uri = st.secrets['mongo_uri']
+    client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
+    db = client["NHL_Database"]
+
+    gc = gspread.service_account_from_dict(credentials)
+
+    return db, gc
+
+db, gc = init_conn()
 
 game_format = {'Win Percentage': '{:.2%}','Cover Spread Percentage': '{:.2%}', 'First Inning Lead Percentage': '{:.2%}',
               'Fifth Inning Lead Percentage': '{:.2%}'}
@@ -30,52 +41,79 @@ american_format = {'First Inning Lead Percentage': '{:.2%}', 'Fifth Inning Lead
 
 master_hold = 'https://docs.google.com/spreadsheets/d/1f42Ergav8K1VsOLOK9MUn7DM_MLMvv4GR2Fy7EfnZTc/edit#gid=340831852'
 
+st.markdown("""
+<style>
+    /* Tab styling */
+    .stTabs [data-baseweb="tab-list"] {
+        gap: 8px;
+        padding: 4px;
+    }
+    .stTabs [data-baseweb="tab"] {
+        height: 50px;
+        white-space: pre-wrap;
+        background-color: #DAA520;
+        color: white;
+        border-radius: 10px;
+        gap: 1px;
+        padding: 10px 20px;
+        font-weight: bold;
+        transition: all 0.3s ease;
+    }
+    .stTabs [aria-selected="true"] {
+        background-color: #DAA520;
+        border: 3px solid #FFD700;
+        color: white;
+    }
+    .stTabs [data-baseweb="tab"]:hover {
+        background-color: #FFD700;
+        cursor: pointer;
+    }
+</style>""", unsafe_allow_html=True)
+
 @st.cache_resource(ttl = 300)
 def init_baselines():
-          sh = gc.open_by_url(master_hold)
-          worksheet = sh.worksheet('Pitcher_Stats')
-          props_frame_hold = pd.DataFrame(worksheet.get_all_records())
-          props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
-          props_frame_hold = props_frame_hold[['Player', 'Team', 'BB', 'Hits', 'HRs', 'ERs', 'Ks', 'Outs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
-          pitcher_stats = props_frame_hold.drop_duplicates(subset='Player')
-          
-          worksheet = sh.worksheet('Timestamp')
-          raw_stamp = worksheet.acell('a1').value
-          
-          t_stamp = f"Last update was at {raw_stamp}"
-          
-          worksheet = sh.worksheet('Hitter_Stats')
-          props_frame_hold = pd.DataFrame(worksheet.get_all_records())
-          props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
-          props_frame_hold = props_frame_hold[['Player', 'Team', 'Walks', 'Steals', 'Hits', 'Singles', 'Doubles', 'HRs', 'RBIs', 'Runs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
-          props_frame_hold['Total Bases'] = props_frame_hold['Singles'] + (props_frame_hold['Doubles'] * 2) + (props_frame_hold['HRs'] * 4)
-          props_frame_hold['Hits + Runs + RBIs'] = props_frame_hold['Hits'] + props_frame_hold['Runs'] + props_frame_hold['RBIs']
-          hitter_stats = props_frame_hold.drop_duplicates(subset='Player')
-          
-          worksheet = sh.worksheet('Game_Betting_Model')
-          team_frame = pd.DataFrame(worksheet.get_all_records())
-          team_frame = team_frame.drop_duplicates(subset='Names')
-          team_frame['Win Percentage'] = team_frame['Win Percentage'].str.replace('%', '').astype('float')/100
-          team_frame['Cover Spread Percentage'] = team_frame['Cover Spread Percentage'].str.replace('%', '').astype('float')/100
-          team_frame['ML_Value'] = team_frame['ML_Value'].str.replace('%', '').astype('float')/100
-          team_frame['Spread_Value'] = team_frame['Spread_Value'].str.replace('%', '').astype('float')/100
-          
-          worksheet = sh.worksheet('prop_frame')
-          raw_display = pd.DataFrame(worksheet.get_all_records())
-          raw_display.replace('', np.nan, inplace=True)
-          prop_frame = raw_display.dropna(subset='Team')
-          
-          worksheet = sh.worksheet('Prop_results')
-          raw_display = pd.DataFrame(worksheet.get_all_records())
-          raw_display.replace('', np.nan, inplace=True)
-          betsheet_frame = raw_display.dropna(subset='proj')
-          
-          worksheet = sh.worksheet('Pick6_ingest')
-          raw_display = pd.DataFrame(worksheet.get_all_records())
-          raw_display.replace('', np.nan, inplace=True)
-          pick_frame = raw_display.dropna(subset='Player')
-          
-          return pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp
+        collection = db["Pitcher_Stats"] 
+        cursor = collection.find()
+        raw_display = pd.DataFrame(cursor)
+        props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
+        props_frame_hold = props_frame_hold[['Player', 'Team', 'BB', 'Hits', 'HRs', 'ERs', 'Ks', 'Outs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
+        pitcher_stats = props_frame_hold.drop_duplicates(subset='Player')
+        
+        collection = db['Hitter_Stats']
+        cursor = collection.find()
+        raw_display = pd.DataFrame(cursor)
+        props_frame_hold.rename(columns={"Names": "Player"}, inplace = True)
+        props_frame_hold = props_frame_hold[['Player', 'Team', 'Walks', 'Steals', 'Hits', 'Singles', 'Doubles', 'HRs', 'RBIs', 'Runs', 'Fantasy', 'FD_Fantasy', 'PrizePicks']]
+        props_frame_hold['Total Bases'] = props_frame_hold['Singles'] + (props_frame_hold['Doubles'] * 2) + (props_frame_hold['HRs'] * 4)
+        props_frame_hold['Hits + Runs + RBIs'] = props_frame_hold['Hits'] + props_frame_hold['Runs'] + props_frame_hold['RBIs']
+        hitter_stats = props_frame_hold.drop_duplicates(subset='Player')
+        
+        collection = db['Game_Betting_Model']
+        cursor = collection.find()
+        raw_display = pd.DataFrame(cursor)
+        team_frame = raw_display.drop_duplicates(subset='Names')
+        team_frame['Win Percentage'] = team_frame['Win Percentage'].str.replace('%', '').astype('float')/100
+        team_frame['Cover Spread Percentage'] = team_frame['Cover Spread Percentage'].str.replace('%', '').astype('float')/100
+        team_frame['ML_Value'] = team_frame['ML_Value'].str.replace('%', '').astype('float')/100
+        team_frame['Spread_Value'] = team_frame['Spread_Value'].str.replace('%', '').astype('float')/100
+        
+        sh = gc.open_by_url(master_hold)
+        worksheet = sh.worksheet('prop_frame')
+        raw_display = pd.DataFrame(worksheet.get_all_records())
+        raw_display.replace('', np.nan, inplace=True)
+        prop_frame = raw_display.dropna(subset='Team')
+        
+        worksheet = sh.worksheet('Prop_results')
+        raw_display = pd.DataFrame(worksheet.get_all_records())
+        raw_display.replace('', np.nan, inplace=True)
+        betsheet_frame = raw_display.dropna(subset='proj')
+        
+        worksheet = sh.worksheet('Pick6_ingest')
+        raw_display = pd.DataFrame(worksheet.get_all_records())
+        raw_display.replace('', np.nan, inplace=True)
+        pick_frame = raw_display.dropna(subset='Player')
+        
+        return pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp
 
 pitcher_stats, hitter_stats, team_frame, prop_frame, betsheet_frame, pick_frame, t_stamp = init_baselines()