From 00d6dfe725e6e2bb6aff237179afc01cef663b70 Mon Sep 17 00:00:00 2001
From: Piotrek <pplonski86@gmail.com>
Date: Wed, 9 Sep 2020 11:18:00 +0200
Subject: [PATCH] :pencil2: fix typos

---
 examples/scripts/binary_classifier_Titanic.py | 36 +++----------------
 supervised/base_automl.py                     |  6 ++--
 2 files changed, 7 insertions(+), 35 deletions(-)

diff --git a/examples/scripts/binary_classifier_Titanic.py b/examples/scripts/binary_classifier_Titanic.py
index d408dd10..0e659774 100644
--- a/examples/scripts/binary_classifier_Titanic.py
+++ b/examples/scripts/binary_classifier_Titanic.py
@@ -5,44 +5,16 @@
 
 from sklearn.metrics import accuracy_score
 
-"""
-obj_array = np.array([1, 2, "A"], dtype=object)
-y = pd.DataFrame(obj_array)
-X = y.copy()
-
-print(X)
-print(np.unique(y[~pd.isnull(y)]))
-for col in X.columns:
-    print(col, X[col].dtype)
-
-a = AutoML(total_time=30)
-
-a.fit(X, y)
-"""
-
 df = pd.read_csv("tests/data/Titanic/train.csv")
 
 X = df[df.columns[2:]]
 y = df["Survived"]
 
-automl = AutoML(mode="Perform", explain_level=2, total_time_limit=1*6, feature_selection=True)
+automl = AutoML(mode="Explain")
 automl.fit(X, y)
 pred = automl.predict(X)
 
-print("Train accuracy", accuracy_score(y, pred)) #["label"]))
-
+print("Train accuracy", accuracy_score(y, pred))
 test = pd.read_csv("tests/data/Titanic/test_with_Survived.csv")
-test_cols = [
-    "Parch",
-    "Ticket",
-    "Fare",
-    "Pclass",
-    "Name",
-    "Sex",
-    "Age",
-    "SibSp",
-    "Cabin",
-    "Embarked",
-]
-pred = automl.predict_all(test[test_cols])
-print("Test accuracy", accuracy_score(test["Survived"], pred["label"]))
+pred = automl.predict(test)
+print("Test accuracy", accuracy_score(test["Survived"], pred))
diff --git a/supervised/base_automl.py b/supervised/base_automl.py
index 4a256ab4..cfed5a8b 100644
--- a/supervised/base_automl.py
+++ b/supervised/base_automl.py
@@ -468,7 +468,7 @@ def _validate_X_predict(self, X):
         n_features = X.shape[1]
         if self.n_features_in_ != n_features:
             raise ValueError(
-                f"Number of features of the model must match the input. Model n_features is {self.n_features_in_}%s and input n_features is {n_features} %s. Reshape your data."
+                f"Number of features of the model must match the input. Model n_features_in_ is {self.n_features_in_} and input n_features is {n_features}. Reshape your data."
             )
 
     # This method builds pandas.Dataframe from input. The input can be numpy.ndarray, matrix, or pandas.Dataframe
@@ -712,8 +712,7 @@ def _check_is_fitted(self):
 
     def _base_predict(self, X):
         self._check_is_fitted()
-        self._validate_X_predict(X)
-
+        
         X = self._build_dataframe(X)
         if not isinstance(X.columns[0], str):
             X.columns = [str(c) for c in X.columns]
@@ -726,6 +725,7 @@ def _base_predict(self, X):
                 )
 
         X = X[self._data_info["columns"]]
+        self._validate_X_predict(X)
 
         # is stacked model
         if self._best_model._is_stacked: