added dummy classifier to models

scripts/ml/dummy_classifier.py

@@ -62,6 +62,7 @@ X.columns
 
 y = df_clean.iloc[:,171] # dst
 y.value_counts()
+#########################
 
 y2 = df_clean.iloc[:,172] #dst_mode
 y2.value_counts()
@@ -107,3 +108,34 @@ acccuracy:
 TP+TN/TP+TN+FP+FN
 
 114/71
+
+######################################
+# try with CV
+
+X_eg = np.array([-1, 1, 1, 1, -2, 9, 4, 4, 1, -1, 3, 0])
+y_eg = np.array([0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1])
+dummy_clf = DummyClassifier(strategy="most_frequent")
+dummy_clf.fit(X_eg, y_eg)
+#DummyClassifier(strategy='most_frequent')
+dummy_clf.predict(X_eg)
+#dummy_clf.predict(np.array([1,1,1,1,1,1,1,1,1,1]))
+#dummy_clf.predict_proba(X_eg)
+
+dummy_clf.score(X_eg, y_eg)
+
+
+cv_DummyD = cross_validate(dummy_clf
+                      , X_eg
+                      , y_eg
+                      , cv = 5
+                      #, groups = group
+                      , scoring = scoring_fn
+                      , return_train_score = True)
+
+cv_dummyD_ALL= {}
+cv_dummyD_ALL['DUMMY'] = {}
+
+for key, value in cv_DummyD.items():
+    print('\nkey:', key, '\nvalue:', value)
+    print('\nmean value:', np.mean(value))
+    cv_dummyD_ALL['DUMMY'][key] = round(np.mean(value),2)