From 068fb9f5c2cceae79c1ebbb73ecb2839bcb83686 Mon Sep 17 00:00:00 2001
From: Gian Pio Domiziani <50718324+gianpDomiziani@users.noreply.github.com>
Date: Sat, 24 Apr 2021 02:14:29 +0200
Subject: [PATCH] X.copy() in the process method (#78)

* X.copy() in the transformer method.

* update version 0.3.4
---
 flaml/data.py       | 13 ++++++++-----
 flaml/version.py    |  2 +-
 test/test_automl.py |  2 ++
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/flaml/data.py b/flaml/data.py
index f99d995655..c73c33c99b 100644
--- a/flaml/data.py
+++ b/flaml/data.py
@@ -214,6 +214,7 @@ class DataTransformer:
                         X[column] = X[column].fillna('__NAN__')
                         cat_columns.append(column)
                 else:
+                    # print(X[column].dtype.name)
                     if X[column].nunique(dropna=True) < 2:
                         X.drop(columns=column, inplace=True)
                         drop = True
@@ -236,8 +237,8 @@ class DataTransformer:
                     SimpleImputer(missing_values=np.nan, strategy='median'),
                     X_num.columns)])
                 X[num_columns] = self.transformer.fit_transform(X_num)
-            self._cat_columns, self._num_columns, self._datetime_columns = \
-                cat_columns, num_columns, datetime_columns
+            self._cat_columns, self._num_columns, self._datetime_columns = cat_columns, \
+                                                                           num_columns, datetime_columns
             self._drop = drop
 
         if task == 'regression':
@@ -249,13 +250,14 @@ class DataTransformer:
         return X, y
 
     def transform(self, X):
+        X = X.copy()
         if isinstance(X, pd.DataFrame):
-            cat_columns, num_columns, datetime_columns = \
-                self._cat_columns, self._num_columns, self._datetime_columns
+            cat_columns, num_columns, datetime_columns = self._cat_columns, \
+                self._num_columns, self._datetime_columns
+            X = X[cat_columns + num_columns].copy()
             if datetime_columns:
                 for dt_column in datetime_columns:
                     X[dt_column] = X[dt_column].map(datetime.toordinal)
-            X = X[cat_columns + num_columns].copy()
             for column in cat_columns:
                 # print(column, X[column].dtype.name)
                 if X[column].dtype.name == 'object':
@@ -273,3 +275,4 @@ class DataTransformer:
                     X_num.columns = range(X_num.shape[1])
                 X[num_columns] = self.transformer.transform(X_num)
         return X
+
diff --git a/flaml/version.py b/flaml/version.py
index e19434e2e3..334b899568 100644
--- a/flaml/version.py
+++ b/flaml/version.py
@@ -1 +1 @@
-__version__ = "0.3.3"
+__version__ = "0.3.4"
diff --git a/test/test_automl.py b/test/test_automl.py
index 4fbf8296ce..94a4452c6e 100644
--- a/test/test_automl.py
+++ b/test/test_automl.py
@@ -239,6 +239,8 @@ class TestAutoML(unittest.TestCase):
         y = np.array([0, 1])
         automl_experiment.fit(X_train=fake_df, X_val=fake_df, y_train=y, y_val=y, **automl_settings)
 
+        y_pred = automl_experiment.predict(fake_df)
+
     def test_regression(self):
 
         automl_experiment = AutoML()