Update app.py

app.py

@@ -0,0 +1,213 @@
+import gradio as gr
+import pandas as pd
+import joblib
+import numpy as np
+from sklearn.impute import SimpleImputer
+
+# -----------------------------
+# Load new tuned classification model package
+# -----------------------------
+# This file should be created from your training script:
+# joblib.dump({"model": ensemble, "threshold": best_threshold, "columns": list(X_train.columns)}, "main/final_delay_model.pkl")
+model_package = joblib.load("main/final_delay_model.pkl")
+ensemble_model = model_package["model"]
+best_threshold = model_package["threshold"]
+reference_columns = model_package["columns"]
+
+# -----------------------------
+# Load regression models and training columns
+# -----------------------------
+ridge_model = joblib.load("main/ridge_model.pkl")
+xgb_reg_model = joblib.load("main/xgb_model.pkl")
+gbr_reg_model = joblib.load("main/gbr_model.pkl")
+training_columns_reg = joblib.load("main/training_columns.pkl")
+
+# -----------------------------
+# Preprocessing for classification
+# -----------------------------
+def preprocess_classification(df):
+    categorical_cols = ['UNIQUE_CARRIER', 'CARRIER', 'ORIGIN', 'DEST',
+                        'ORIGIN_STATE_ABR', 'DEST_STATE_ABR',
+                        'DEP_TIME_BLK', 'ARR_TIME_BLK']
+    df_encoded = pd.get_dummies(df, columns=categorical_cols)
+
+    # Add missing columns from training
+    for col in reference_columns:
+        if col not in df_encoded.columns:
+            df_encoded[col] = 0
+
+    # Reorder columns
+    df_encoded = df_encoded[reference_columns]
+
+    # Impute missing values
+    imputer = SimpleImputer(strategy='median')
+    df_encoded = pd.DataFrame(imputer.fit_transform(df_encoded), columns=df_encoded.columns)
+
+    return df_encoded
+
+# -----------------------------
+# Preprocessing for regression
+# -----------------------------
+def preprocess_regression(df):
+    df_encoded = pd.get_dummies(df, columns=['time_of_day', 'wind_dir_bucket'])
+    df_encoded = df_encoded.reindex(columns=training_columns_reg, fill_value=0)
+    return df_encoded
+
+# -----------------------------
+# Delay category helper
+# -----------------------------
+def categorize_delay(minutes):
+    if minutes < 15:
+        return "Delay not considered less than 15 mins"
+    elif 15 <= minutes < 20:
+        return "Delay is Minimum"
+    elif 20 <= minutes < 30:
+        return "Flight is moderately delayed"
+    elif 30 <= minutes < 60:
+        return "Flight is highly delayed"
+    else:
+        return "Flight is delayed too much"
+
+# -----------------------------
+# Classification prediction function
+# -----------------------------
+def predict_classification(YEAR, MONTH, DAY_OF_MONTH, DAY_OF_WEEK,
+                           ORIGIN, DEST, CARRIER,
+                           ORIGIN_STATE_ABR, DEST_STATE_ABR,
+                           DEP_TIME_BLK, ARR_TIME_BLK,
+                           temp, prcp, wspd, wdir, route_delay_rate):
+
+    data = {
+        'YEAR': int(YEAR),
+        'MONTH': int(MONTH),
+        'DAY_OF_MONTH': int(DAY_OF_MONTH),
+        'DAY_OF_WEEK': int(DAY_OF_WEEK),
+        'UNIQUE_CARRIER': CARRIER,
+        'CARRIER': CARRIER,
+        'ORIGIN': ORIGIN,
+        'DEST': DEST,
+        'ORIGIN_STATE_ABR': ORIGIN_STATE_ABR,
+        'DEST_STATE_ABR': DEST_STATE_ABR,
+        'DEP_TIME_BLK': DEP_TIME_BLK,
+        'ARR_TIME_BLK': ARR_TIME_BLK,
+        'temp': float(temp),
+        'prcp': float(prcp),
+        'wspd': float(wspd),
+        'wdir': float(wdir),
+        'route_delay_rate': float(route_delay_rate)
+    }
+
+    df_input = pd.DataFrame([data])
+    X = preprocess_classification(df_input)
+
+    proba = ensemble_model.predict_proba(X)[0][1]
+    pred = int(proba >= best_threshold)
+
+    return {
+        "Prediction": "Delayed" if pred == 1 else "On Time",
+        "Confidence": round(proba, 3),
+        "Threshold": round(best_threshold, 3)
+    }
+
+# -----------------------------
+# Regression prediction function (unchanged)
+# -----------------------------
+def predict_regression_with_check(DEP_DELAY, DEP_DELAY_NEW, DEP_DEL15, DEP_DELAY_GROUP,
+                                  temp, prcp, wspd, wdir, bad_weather, wind_dir_bucket,
+                                  time_of_day, is_weekend):
+    if int(DEP_DEL15) == 0:
+        return {
+            "Status": "No delay predicted",
+            "Delay Category": None
+        }
+
+    data = {
+        'DEP_DELAY': float(DEP_DELAY),
+        'DEP_DELAY_NEW': float(DEP_DELAY_NEW),
+        'DEP_DEL15': int(DEP_DEL15),
+        'DEP_DELAY_GROUP': int(DEP_DELAY_GROUP),
+        'temp': float(temp),
+        'prcp': float(prcp),
+        'wspd': float(wspd),
+        'wdir': float(wdir),
+        'bad_weather': int(bad_weather),
+        'wind_dir_bucket': wind_dir_bucket,
+        'time_of_day': time_of_day,
+        'is_weekend': int(is_weekend)
+    }
+    df_input = pd.DataFrame([data])
+    X = preprocess_regression(df_input)
+
+    pred_ridge = ridge_model.predict(X)[0]
+    pred_xgb = xgb_reg_model.predict(X)[0]
+    pred_gbr = gbr_reg_model.predict(X)[0]
+
+    max_pred = max(pred_ridge, pred_xgb, pred_gbr)
+    category = categorize_delay(max_pred)
+
+    return {
+        "Ridge Prediction": round(pred_ridge, 2),
+        "XGBoost Prediction": round(pred_xgb, 2),
+        "Gradient Boosting Prediction": round(pred_gbr, 2),
+        "Max Prediction": round(max_pred, 2),
+        "Delay Category": category
+    }
+
+# -----------------------------
+# Gradio Interface
+# -----------------------------
+classification_inputs = [
+    gr.Number(label="YEAR"),
+    gr.Number(label="MONTH"),
+    gr.Number(label="DAY_OF_MONTH"),
+    gr.Number(label="DAY_OF_WEEK (1=Mon ... 7=Sun)"),
+    gr.Textbox(label="Origin Airport Code"),
+    gr.Textbox(label="Destination Airport Code"),
+    gr.Textbox(label="Carrier Code"),
+    gr.Textbox(label="Origin State Abbreviation"),
+    gr.Textbox(label="Destination State Abbreviation"),
+    gr.Textbox(label="Departure Time Block (e.g., 0600-0659)"),
+    gr.Textbox(label="Arrival Time Block (e.g., 0900-0959)"),
+    gr.Number(label="Temperature"),
+    gr.Number(label="Precipitation"),
+    gr.Number(label="Wind Speed"),
+    gr.Number(label="Wind Direction"),
+    gr.Number(label="Route Delay Rate (historical)")
+]
+
+regression_inputs = [
+    gr.Number(label="DEP_DELAY"),
+    gr.Number(label="DEP_DELAY_NEW"),
+    gr.Number(label="DEP_DEL15 (0 or 1)"),
+    gr.Number(label="DEP_DELAY_GROUP"),
+    gr.Number(label="Temperature"),
+    gr.Number(label="Precipitation"),
+    gr.Number(label="Wind Speed"),
+    gr.Number(label="Wind Direction"),
+    gr.Number(label="Bad Weather (0 or 1)"),
+    gr.Textbox(label="Wind Dir Bucket (North/South/East/West/etc.)"),
+    gr.Textbox(label="Time of Day (Morning/Afternoon/Evening/Night)"),
+    gr.Number(label="Is Weekend (0 or 1)")
+]
+
+classification_tab = gr.Interface(
+    fn=predict_classification,
+    inputs=classification_inputs,
+    outputs="json",
+    title="Flight Delay Classification (Tuned Ensemble)",
+    description="Predict delay classification using the tuned ensemble model with threshold optimization."
+)
+
+regression_tab = gr.Interface(
+    fn=predict_regression_with_check,
+    inputs=regression_inputs,
+    outputs="json",
+    title="Flight Delay Regression (Conditional)",
+    description="Predict arrival delay in minutes only if DEP_DEL15=1, with categorized output."
+)
+
+demo = gr.TabbedInterface([classification_tab, regression_tab],
+                          ["Classification", "Regression"])
+
+if __name__ == "__main__":
+    demo.launch()