Update app.py

app.py

@@ -1,73 +1,281 @@
-import requests
+import pulp
+import numpy as np
 import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestRegressor
-from sklearn.metrics import mean_absolute_error
-from flask import Flask, request, jsonify
-
-# Step 1: Data Collection
-def fetch_data():
-    api_key = 'itku7CjwJv5bfrwAvGlwR3nYv'  # Replace with your SportsData.io API key
-    response = requests.get(f"https://api.sportsdata.io/v3/nba/stats/json/PlayerSeasonStats/2023?key={api_key}")
-
-    # Check if the response is valid
-    if response.status_code != 200:
-        raise ValueError(f"Error fetching data: {response.status_code}, {response.text}")
-
-    data = response.json()
-    
-    # Check if the response is a list of dictionaries
-    if not isinstance(data, list) or not all(isinstance(i, dict) for i in data):
-        raise ValueError("API response is not in the expected format (list of dictionaries)")
-
-    return pd.DataFrame(data)
-
-# Step 2: Data Preprocessing
-def preprocess_data(df):
-    df = df.dropna()  # Remove rows with missing values
-    df = df[df['Minutes'] > 0]  # Filter players with playing time
-    df['PointsPerGame'] = df['Points'] / df['Games']
-    return df
-
-# Step 3: Feature Engineering
-def engineer_features(df):
-    df['RecentForm'] = df['PointsPerGame'].rolling(window=5).mean().fillna(0)
-    df['HomeAdvantage'] = df['HomeGames'] / df['TotalGames']
-    return df
-
-# Step 4: Model Training
-def train_model(df):
-    X = df[['RecentForm', 'HomeAdvantage']]
-    y = df['PointsPerGame']
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-    model = RandomForestRegressor(n_estimators=100, random_state=42)
-    model.fit(X_train, y_train)
-
-    y_pred = model.predict(X_test)
-    mae = mean_absolute_error(y_test, y_pred)
-    print(f"Mean Absolute Error: {mae}")
-    
-    return model
-
-# Step 5: Deployment with Flask
-app = Flask(__name__)
-
-@app.route('/predict', methods=['POST'])
-def predict():
-    data = request.json
-    input_features = [data['RecentForm'], data['HomeAdvantage']]
-    prediction = model.predict([input_features])[0]
-    return jsonify({'prediction': prediction})
-
-if __name__ == '__main__':
-    # Fetch and preprocess data
-    df = fetch_data()
-    df = preprocess_data(df)
-    df = engineer_features(df)
-    
-    # Train the model
-    model = train_model(df)
-    
-    # Run the Flask app
-    app.run(debug=True, host='0.0.0.0', port=5000)
+import streamlit as st
+import gspread
+
+scope = ['https://www.googleapis.com/auth/spreadsheets',
+          "https://www.googleapis.com/auth/drive"]
+
+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"
+}
+
+gc = gspread.service_account_from_dict(credentials)
+
+st.set_page_config(layout="wide")
+
+roo_format = {'Win%': '{:.2%}', 'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_finish': '{:.2%}',
+              '60+%': '{:.2%}','5x%': '{:.2%}','6x%': '{:.2%}','7x%': '{:.2%}','Own': '{:.2%}','LevX': '{:.2%}'}
+stat_format = {'Odds%': '{:.2%}'}
+table_format = {'Odds': '{:.2%}'}
+
+csgo_overall = 'CSGO_Overall_Proj'
+csgo_rpl = 'CSGO_RPL_Proj'
+csgo_neutral = 'CSGO_Neutral_Proj'
+csgo_wins = 'CSGO_Win_Proj'
+csgo_losses = 'CSGO_Loss_Proj'
+overall_odds = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+RPL_odds = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+csgo_bo1 = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+two_map = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+csgo_bo3 = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+csgo_bo5 = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+player_baselines = 'https://docs.google.com/spreadsheets/d/1aLVN4izjSuqZGRyz73Kip6U1q3rubh6v9GrckgEqbfs/edit?pli=1#gid=1545712013'
+
+@st.cache_data
+def load_roo_model(URL):
+    sh = gc.open(URL)
+    worksheet = sh.get_worksheet(0)
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    try:
+          raw_display["Salary"] = raw_display["Salary"].replace("$", "", regex=True).astype(float)
+    except:
+          pass
+    try:
+          raw_display['Win%'] = raw_display['Win%'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['Top_finish'] = raw_display['Top_finish'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['Top_5_finish'] = raw_display['Top_5_finish'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['Top_10_finish'] = raw_display['Top_10_finish'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try: 
+          raw_display['60+%'] = raw_display['60+%'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['5x%'] = raw_display['5x%'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['6x%'] = raw_display['6x%'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['7x%'] = raw_display['7x%'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['Own'] = raw_display['Own'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+    try:
+          raw_display['LevX'] = raw_display['LevX'].str.replace('%', '').astype(float)/100
+    except:
+          pass
+
+    return raw_display
+
+@st.cache_data
+def load_overall_odds(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('Overall_Vegas')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display['Odds'] = raw_display['Odds'].str.replace('%', '').astype(float)/100
+
+    return raw_display
+
+@st.cache_data
+def load_rpl_odds(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('RPL_Vegas')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display['Odds'] = raw_display['Odds'].str.replace('%', '').astype(float)/100
+    raw_display['Vegas'] = raw_display['Vegas'].str.replace('%', '').astype(float)/100
+    raw_display = raw_display[['Team', 'Opponent', 'RPL', 'Opp_RPL', 'RPL_Diff', 'Vegas', 'Odds', 'P Rounds']]
+
+    return raw_display
+
+@st.cache_data
+def load_bo1_proj_model(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('Overall_BO1_Projections')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display.rename(columns={"Name": "Player"}, inplace = True)
+    raw_display['Odds%'] = raw_display['Odds%'].str.replace('%', '').astype(float)/100
+    raw_display = raw_display.sort_values(by='Kills', ascending=False)
+
+    return raw_display
+
+@st.cache_data
+def two_map_load(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('2_map_projections')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display.rename(columns={"Name": "Player"}, inplace = True)
+    raw_display['Odds%'] = raw_display['Odds%'].str.replace('%', '').astype(float)/100
+    raw_display = raw_display.sort_values(by='Kills', ascending=False)
+
+    return raw_display
+
+@st.cache_data
+def load_bo3_proj_model(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('Overall_BO3_Projections')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display.rename(columns={"Name": "Player"}, inplace = True)
+    raw_display['Odds%'] = raw_display['Odds%'].str.replace('%', '').astype(float)/100
+    raw_display = raw_display.sort_values(by='Kills', ascending=False)
+
+    return raw_display
+
+@st.cache_data
+def load_bo5_proj_model(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('Overall_BO5_Projections')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display.rename(columns={"Name": "Player"}, inplace = True)
+    raw_display['Odds%'] = raw_display['Odds%'].str.replace('%', '').astype(float)/100
+    raw_display = raw_display.sort_values(by='Kills', ascending=False)
+          
+    return raw_display  
+
+@st.cache_data
+def load_slate_baselines(URL):
+    sh = gc.open_by_url(URL)
+    worksheet = sh.worksheet('Player_Data')
+    raw_display = pd.DataFrame(worksheet.get_all_records())
+    raw_display.rename(columns={"Name": "Player"}, inplace = True)
+    raw_display = raw_display.sort_values(by='Kills/Round', ascending=False)
+
+    return raw_display    
+
+hold_display = load_roo_model(csgo_overall)
+
+tab1, tab2, tab3, tab4, tab5 = st.tabs(["CSGO Odds Tables", "CSGO Range of Outcomes", "CSGO Player Stat Projections", "CSGO Slate Baselines", '2-map Projections'])
+
+def convert_df_to_csv(df):
+    return df.to_csv().encode('utf-8')
+
+with tab1:
+    if st.button("Reset Data", key='reset4'):
+              # Clear values from *all* all in-memory and on-disk data caches:
+              # i.e. clear values from both square and cube
+              st.cache_data.clear()
+    odds_choice = st.radio("What table would you like to display?", ('Overall', 'RPL'), key='odds_table')
+    if odds_choice == 'Overall':
+        hold_display = load_overall_odds(overall_odds)
+    elif odds_choice == 'RPL':
+        hold_display = load_rpl_odds(RPL_odds)
+    display = hold_display.set_index('Team')
+    st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(table_format, precision=2), use_container_width = True)
+    st.download_button(
+        label="Export Tables",
+        data=convert_df_to_csv(display),
+        file_name='CSGO_Odds_Tables_export.csv',
+        mime='text/csv',
+    )
+
+with tab2:
+    if st.button("Reset Data", key='reset1'):
+              # Clear values from *all* all in-memory and on-disk data caches:
+              # i.e. clear values from both square and cube
+              st.cache_data.clear()
+    model_choice = st.radio("What table would you like to display?", ('Overall', 'RPL', 'Neutral', 'Wins', 'Losses'), key='roo_table')
+    team_var1 = st.multiselect('View specific team?', options = hold_display['Team'].unique(), key = 'roo_teamvar')
+    if model_choice == 'Overall':
+      hold_display = load_roo_model(csgo_overall)
+    elif model_choice == 'RPL':
+      hold_display = load_roo_model(csgo_rpl)
+    elif model_choice == 'Neutral':
+      hold_display = load_roo_model(csgo_neutral)
+    elif model_choice == 'Wins':
+      hold_display = load_roo_model(csgo_wins)
+    elif model_choice == 'Losses':
+      hold_display = load_roo_model(csgo_losses)
+    hold_display['Own'] = hold_display['Own'] / 100
+    display = hold_display.set_index('Player')
+    export_display = display
+    export_display['Own'] =  export_display['Own'] *100
+    export_display['Position'] = "FLEX"
+    if team_var1:
+              display = display[display['Team'].isin(team_var1)]
+    st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(roo_format, precision=2), use_container_width = True)
+    st.download_button(
+        label="Export Range of Outcomes",
+        data=convert_df_to_csv(export_display),
+        file_name='CSGO_ROO_export.csv',
+        mime='text/csv',
+    )
+
+with tab3:
+    if st.button("Reset Data", key='reset2'):
+              # Clear values from *all* all in-memory and on-disk data caches:
+              # i.e. clear values from both square and cube
+              st.cache_data.clear()
+    gametype_choice = st.radio("What format are the games being played?", ('Best of 1', 'Best of 3', 'Best of 5'), key='player_stats')
+    team_var2 = st.multiselect('View specific team?', options = hold_display['Team'].unique(), key = 'stat_teamvar')
+    if gametype_choice == 'Best of 1':
+      hold_display = load_bo1_proj_model(csgo_bo1)
+    elif gametype_choice == 'Best of 3':
+      hold_display = load_bo3_proj_model(csgo_bo3)
+    elif gametype_choice == 'Best of 5':
+      hold_display = load_bo5_proj_model(csgo_bo5)
+    display = hold_display.set_index('Player')
+    if team_var2:
+          display = display[display['Team'].isin(team_var2)]
+    st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(stat_format, precision=2), use_container_width = True)
+    st.download_button(
+        label="Export Projections",
+        data=convert_df_to_csv(display),
+        file_name='CSGO_Projections_export.csv',
+        mime='text/csv',
+    )
+
+with tab4:
+    if st.button("Reset Data", key='reset3'):
+              # Clear values from *all* all in-memory and on-disk data caches:
+              # i.e. clear values from both square and cube
+              st.cache_data.clear()
+    hold_display = load_slate_baselines(player_baselines)
+    display = hold_display.set_index('Player')
+    st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+    st.download_button(
+        label="Export Baselines",
+        data=convert_df_to_csv(display),
+        file_name='CSGO_Baselines_export.csv',
+        mime='text/csv',
+    )
+
+with tab5:
+    if st.button("Reset Data", key='reset5'):
+              # Clear values from *all* all in-memory and on-disk data caches:
+              # i.e. clear values from both square and cube
+              st.cache_data.clear()
+    hold_display = two_map_load(two_map)
+    display = hold_display.set_index('Player')
+    st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+    st.download_button(
+        label="Export Baselines",
+        data=convert_df_to_csv(display),
+        file_name='CSGO_2_map_export.csv',
+        mime='text/csv',
+    )