Update app.py

app.py

@@ -1,6 +1,9 @@
 import pandas as pd
 import numpy as np
 import joblib
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import QuantileTransformer, StandardScaler
+from sklearn.cluster import KMeans
 import gradio as gr
 
 # Define the feat_eng function
@@ -31,6 +34,50 @@ def feat_eng(df):
     ]
     return df[selected_features]
 
+# Custom Quantile Transformer
+class CustomQuantileTransformer(BaseEstimator, TransformerMixin):
+    def __init__(self, random_state=None):
+        self.random_state = random_state
+        self.quantile_transformer = QuantileTransformer(output_distribution='normal', random_state=self.random_state)
+
+    def fit(self, X, y=None):
+        self.quantile_transformer.fit(X)
+        return self
+
+    def transform(self, X):
+        X_transformed = self.quantile_transformer.transform(X)
+        return pd.DataFrame(X_transformed, columns=X.columns)
+
+# Custom Standard Scaler
+class CustomStandardScaler(BaseEstimator, TransformerMixin):
+    def __init__(self):
+        self.scaler = StandardScaler()
+
+    def fit(self, X, y=None):
+        self.scaler.fit(X)
+        return self
+
+    def transform(self, X):
+        X_transformed = self.scaler.transform(X)
+        return pd.DataFrame(X_transformed, columns=X.columns)
+
+# KMeans Transformer
+class KMeansTransformer(BaseEstimator, TransformerMixin):
+    def __init__(self, n_clusters=3, random_state=None):
+        self.n_clusters = n_clusters
+        self.random_state = random_state
+        self.kmeans = KMeans(n_clusters=self.n_clusters, random_state=self.random_state)
+
+    def fit(self, X, y=None):
+        self.kmeans.fit(X)
+        return self
+
+    def transform(self, X):
+        cluster_labels = self.kmeans.predict(X)
+        X_clustered = X.copy()
+        X_clustered['Cluster'] = cluster_labels
+        return X_clustered
+
 # Load the pipeline
 pipeline = joblib.load("pipeline.pkl")