Initial commits

.gitattributes

@@ -0,0 +1,2 @@
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

app/main.py

@@ -0,0 +1,18 @@
+from fastapi import FastAPI
+import joblib
+import pandas as pd
+
+app = FastAPI()
+model = joblib.load('models/xgb_model.pkl')
+scaler = joblib.load('models/scaler.pkl')
+
+@app.get("/")
+def home():
+    return {"message": "Weather Forecast API"}
+
+@app.post("/predict/")
+def predict_weather(data: dict):
+    df = pd.DataFrame([data])
+    scaled = scaler.transform(df)
+    pred = model.predict(scaled)
+    return {"predicted_temperature": round(float(pred[0]), 2)}

scripts/predict.py

@@ -0,0 +1,19 @@
+import pandas as pd
+import joblib
+import numpy as np
+
+model = joblib.load('models/xgb_model.pkl')
+scaler = joblib.load('models/scaler.pkl')
+
+# Example: latest 7 days data (replace with real)
+latest_data = pd.DataFrame({
+    'humidity': [70, 68, 72, 71, 69, 73, 70],
+    'pressure': [1012, 1011, 1013, 1010, 1011, 1014, 1013],
+    'windspeed': [8.0, 7.9, 8.1, 8.3, 7.8, 8.2, 8.0],
+    'temp_lag1': [24.5], 'temp_lag2': [25.1], 'temp_lag3': [24.8],
+    'temp_lag4': [25.0], 'temp_lag5': [24.7], 'temp_lag6': [25.2], 'temp_lag7': [24.9]
+})
+
+scaled = scaler.transform(latest_data)
+pred = model.predict(scaled)
+print(f"Predicted temperature: {pred[0]:.2f}°C")

scripts/train_model.py

@@ -0,0 +1,45 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from xgboost import XGBRegressor
+from sklearn.metrics import mean_absolute_error, mean_squared_error
+import joblib, os
+
+# Load data
+df = pd.read_csv('data/weather.csv')
+df['date'] = pd.to_datetime(df['date'])
+df = df.sort_values('date')
+
+# Create lag features (last 7 days)
+for lag in range(1, 8):
+    df[f'temp_lag{lag}'] = df['temp'].shift(lag)
+
+df = df.dropna()
+
+X = df.drop(columns=['date', 'temp'])
+y = df['temp']
+
+# Split train/test
+X_train, X_test, y_train, y_test = train_test_split(X, y, shuffle=False, test_size=0.2)
+
+# Scale
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+
+# Train model
+model = XGBRegressor(n_estimators=300, learning_rate=0.05, max_depth=6)
+model.fit(X_train, y_train)
+
+# Evaluate
+pred = model.predict(X_test)
+mae = mean_absolute_error(y_test, pred)
+rmse = np.sqrt(mean_squared_error(y_test, pred))
+print(f"MAE: {mae:.2f}, RMSE: {rmse:.2f}")
+
+# Save model
+os.makedirs('models', exist_ok=True)
+joblib.dump(model, 'models/xgb_model.pkl')
+joblib.dump(scaler, 'models/scaler.pkl')
+print("Model saved to models/")