Upload predictionpipeline.py

This is the prediction pipeline of the model.

predictionpipeline.py

@@ -0,0 +1,106 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import roc_auc_score
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
+import mlflow
+import joblib
+
+
+def load_data():
+    df = pd.read_csv("customer_marketing_data.csv")
+
+    # Simple data quality checks
+    if df.shape[0] == 0:
+        raise pd.errors.EmptyDataError("Empty dataset")
+    if "converted" not in df.columns:
+        raise KeyError("Target missing")
+
+    return df
+
+
+def feature_engineering(df):
+    df["engagement_score"] = (
+            df["app_logins_last30"]
+            + df["emails_opened_last30"]
+            + df["feature_usage_last30"]
+    )
+
+    features = [
+        "tenure_months",
+        "vehicle_age",
+        "engagement_score",
+        "service_visits_last12"
+    ]
+
+    X = df[features]
+    y = df["converted"]
+
+    return X, y
+
+
+def train_model(X, y):
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
+
+    X_train, X_test, y_train, y_test = train_test_split(
+        X_scaled, y, test_size=0.2, random_state=42
+    )
+
+    model = LogisticRegression()
+    model.fit(X_train, y_train)
+
+    preds = model.predict_proba(X_test)[:, 1]
+    auc = roc_auc_score(y_test, preds)
+
+    print("Validation AUC:", auc)
+
+    return model, scaler, auc
+
+def log_model(model, scaler, auc):
+    with mlflow.start_run():
+        mlflow.log_metric("auc", auc)
+        mlflow.sklearn.log_model(model, "conversion_model")
+        joblib.dump(scaler, "scaler.pkl")
+        mlflow.log_artifact("scaler.pkl")
+
+
+def score_customers(model, scaler):
+    new_data = pd.read_csv("daily_customer_scoring_data.csv")
+
+    new_data["engagement_score"] = (
+            new_data["app_logins_last30"]
+            + new_data["emails_opened_last30"]
+            + new_data["feature_usage_last30"]
+    )
+
+    features = [
+        "tenure_months",
+        "vehicle_age",
+        "engagement_score",
+        "service_visits_last12"
+    ]
+
+    X = scaler.transform(new_data[features])
+
+    new_data["conversion_probability"] = model.predict_proba(X)[:, 1]
+
+    new_data.to_csv("scored_output.csv", index=False)
+
+
+def monitoring_check(scored_df):
+    avg_score = scored_df["conversion_probability"].mean()
+
+    if avg_score < 0.05:
+        raise ValueError("Prediction distribution abnormal — investigate pipeline")
+
+
+if __name__ == "__main__":
+    df = load_data()
+    X, y = feature_engineering(df)
+
+    model, scaler, auc = train_model(X, y)
+    log_model(model, scaler, auc)
+
+    score_customers(model, scaler)