Create app.py

app.py

@@ -0,0 +1,63 @@
+import requests
+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 = 'YOUR_API_KEY'  # Replace with your SportsData.io API key
+    response = requests.get(f"https://api.sportsdata.io/v3/nba/stats/json/PlayerSeasonStats/2023?key={api_key}")
+    data = response.json()
+    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)