Uploaded files

Author: hardikkamboj

my_encoder/my_encoder.py

@@ -0,0 +1,32 @@
+from sklearn.preprocessing import OneHotEncoder
+import pandas as pd
+from sklearn.base import BaseEstimator, TransformerMixin
+
+
+class Myencoder(BaseEstimator, TransformerMixin):
+   
+    def __init__(self,drop = 'first',sparse=False):
+        self.encoder = OneHotEncoder(drop = drop,sparse = sparse)
+        self.features_to_encode = []
+        self.columns = []
+    
+    def fit(self,X_train,features_to_encode):
+        
+        data = X_train.copy()
+        self.features_to_encode = features_to_encode
+        data_to_encode = data[self.features_to_encode]
+        self.columns = pd.get_dummies(data_to_encode,drop_first = True).columns
+        self.encoder.fit(data_to_encode)
+        return self.encoder
+    
+    def transform(self,X_test):
+        
+        data = X_test.copy()
+        data.reset_index(drop = True,inplace =True)
+        data_to_encode = data[self.features_to_encode]
+        data_left = data.drop(self.features_to_encode,axis = 1)
+        
+        data_encoded = pd.DataFrame(self.encoder.transform(data_to_encode),columns = self.columns)
+        
+        return pd.concat([data_left,data_encoded],axis = 1)
+