From ec2d5ca25b863faf887dde7b9559b5a5d19b366f Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sat, 5 Mar 2022 15:13:26 +0000
Subject: [PATCH] saving work

---
 my_data6.py | 10 ++++++----
 p_jr_d1.py  | 29 +++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/my_data6.py b/my_data6.py
index adfe017..afc887c 100644
--- a/my_data6.py
+++ b/my_data6.py
@@ -152,7 +152,7 @@ X_vars11 = my_df[x_stability_cols + X_strF + X_evolF ]
 
 #%%
 X_vars1.shape[1]
-
+X_vars5.shape[1]
 # TODO: stratified cross validate
 # Train-test Split
 
@@ -161,11 +161,13 @@ X_train, X_test, y_train, y_test = train_test_split(X_vars1,
                                                     target1, 
                                                     test_size = 0.33, 
                                                     random_state = 42)
-MultClassPipeline(X_train, X_test, y_train, y_test)
-
+t1_res = MultClassPipeline(X_train, X_test, y_train, y_test)
+t1_res
 # TARGET3
 X_train3, X_test3, y_train3, y_test3 = train_test_split(X_vars5, 
                                                     target3, 
                                                     test_size = 0.33, 
                                                     random_state = 42)
-MultClassPipeline(X_train3, X_test3, y_train3, y_test3)
+t3_res = MultClassPipeline(X_train3, X_test3, y_train3, y_test3)
+t3_res
+#%%
\ No newline at end of file
diff --git a/p_jr_d1.py b/p_jr_d1.py
index da72511..602681d 100644
--- a/p_jr_d1.py
+++ b/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
\ No newline at end of file