test

app.py

@@ -1,27 +1,31 @@
+
+import os, shutil
+
 import streamlit as st
 import pandas as pd
 import numpy as np
-import os, shutil
 import joblib
+import os
 from huggingface_hub import hf_hub_download
 from sklearn.preprocessing import LabelEncoder, StandardScaler
+from catboost import Pool
 
 # Hugging Face Model Repo
 MODEL_REPO = "chagu13/is_click_predictor"
 MODEL_DIR = "models"
-os.makedirs(MODEL_DIR, exist_ok=True)  # Ensure directory exists
+os.makedirs(MODEL_DIR, exist_ok=True)
 
-# Model Filenames (on Hugging Face)
+# Model Filenames
 CATBOOST_MODEL_FILENAME = "models/catboost_model.pkl"
 XGB_MODEL_FILENAME = "models/xgb_model.pkl"
 RF_MODEL_FILENAME = "models/rf_model.pkl"
 
-# Expected Local Paths
+# Local Paths
 CATBOOST_MODEL_PATH = os.path.join(MODEL_DIR, "catboost_model.pkl")
 XGB_MODEL_PATH = os.path.join(MODEL_DIR, "xgb_model.pkl")
 RF_MODEL_PATH = os.path.join(MODEL_DIR, "rf_model.pkl")
 
-# Define feature lists
+# Define Features
 CATEGORICAL_COLUMNS = ["gender", "product", "campaign_id", "webpage_id"]
 NUMERICAL_COLUMNS = [
     "age_level", "city_development_index", "user_group_id", "user_depth", "var_1",
@@ -33,75 +37,23 @@ NUMERICAL_COLUMNS = [
 
 FEATURE_COLUMNS = CATEGORICAL_COLUMNS + NUMERICAL_COLUMNS
 
-def preprocess_input(input_df, train_df=None, model_type="catboost"):
-    """
-    Preprocess input data before passing it to ML models.
-    - Removes DateTime columns
-    - Computes aggregations
-    - Ensures categorical variables are properly encoded
-    - Normalizes numerical features
-    - Selects only required features for the given model
-    """
 
-    # 🚀 Step 1: Drop DateTime Columns
-    datetime_columns = input_df.select_dtypes(include=["datetime", "object"]).columns
-    for col in datetime_columns:
-        try:
-            input_df[col] = pd.to_datetime(input_df[col])
-            input_df.drop(columns=[col], inplace=True)
-        except Exception:
-            continue
+def preprocess_input(input_df):
+    """Ensure proper preprocessing, handling duplicates, missing values, and encoding."""
 
-    # 🚀 Step 2: Fill missing values before aggregations
-    input_df.fillna(0, inplace=True)
+    # Drop duplicates in columns
+    input_df = input_df.loc[:, ~input_df.columns.duplicated()]
 
-    # 🚀 Step 3: Compute Aggregations (Requires a reference training dataset)
-    if train_df is not None:
-        input_df = apply_aggregations(input_df, train_df)
+    # Fill missing values
+    input_df.fillna(0, inplace=True)
 
-    # 🚀 Step 4: Ensure Categorical Features Stay as Strings
-    categorical_columns = ["gender", "product", "campaign_id", "webpage_id"]
-    for col in categorical_columns:
+    # Convert categorical to string
+    for col in CATEGORICAL_COLUMNS:
         input_df[col] = input_df[col].astype(str).fillna("missing")
 
-    # 🚀 Step 5: Ensure Consistent Label Encoding
-    label_encoders = {}
-    for col in categorical_columns:
-        le = LabelEncoder()
-        input_df[col] = input_df[col].astype(str)
-        le.fit(input_df[col].unique())
-        label_encoders[col] = le
-        input_df[col] = input_df[col].map(lambda x: le.transform([x])[0] if x in le.classes_ else -1)
-
-    # 🚀 Step 6: Normalize Numerical Features
-    numerical_columns = [
-        "age_level", "city_development_index", "user_group_id", "user_depth", "var_1",
-        "click_sum_age_sex_prod", "click_count_age_sex_prod",
-        "unique_campaigns_age_sex_prod", "unique_webpages_age_sex_prod",
-        "click_sum_city_age_prod", "click_count_city_age_prod",
-        "unique_campaigns_city_age_prod", "unique_webpages_city_age_prod"
-    ]
-
-    # Check if all numerical columns exist
-    numerical_columns = [col for col in numerical_columns if col in input_df.columns]
+    # Normalize numerical columns
     scaler = StandardScaler()
-    input_df[numerical_columns] = scaler.fit_transform(input_df[numerical_columns])
-
-    # 🚀 Step 7: Select Features Based on Model Type
-    model_features = {
-        "catboost": ["age_level", "gender", "product", "campaign_id", "webpage_id"] + numerical_columns,
-        "xgboost": ["age_level", "gender", "product", "campaign_id", "webpage_id"] + numerical_columns,
-        "random_forest": [
-            "age_level", "gender", "product", "campaign_id", "webpage_id",
-            "product_category_1", "product_category_2", "user_group_id",
-            "user_depth", "city_development_index", "var_1"
-        ] + numerical_columns
-    }
-
-    selected_features = model_features.get(model_type, input_df.columns)
-
-    # 🚀 Ensure only required features are passed to the model
-    input_df = input_df[selected_features]
+    input_df[NUMERICAL_COLUMNS] = scaler.fit_transform(input_df[NUMERICAL_COLUMNS])
 
     return input_df