saving work

p_jr_d1.py

@@ -372,4 +372,33 @@ print(pipe2.classification_report (y_test, np.argmax(predicted, axis = 1)))
 enc = preprocessing.OneHotEncoder()
 enc.fit(X_train)
 enc.transform(X_train).toarray()
+#%%
+from sklearn.metrics import mean_squared_error, make_scorer
+from sklearn.model_selection import cross_validate
+from sklearn.linear_model import LinearRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import MinMaxScaler
+boston = load_boston()
 
+X_train, y_train = pd.DataFrame(boston.data, columns = boston.feature_names), boston.target
+
+model1 = Pipeline(steps = [
+    ('pre', MinMaxScaler()),
+    ('reg', LinearRegression())])
+
+score_fn = make_scorer(mean_squared_error)
+scores = cross_validate(model1, X_train, y_train
+                        , scoring = score_fn
+                        , cv = 10)
+
+from itertools import combinations
+def train(X):
+    return cross_validate(model1, X, y_train
+                          , scoring = score_fn
+                          #, return_train_score = False)
+                          , return_estimator = True)['test_score']
+
+scores = [train(X_train.loc[:,vars]) for vars in combinations(X_train.columns, 12)]
+means = [score.mean() for score in scores]
+means