Python sklearn 模块，feature_extraction() 实例源码

def rand_forest_train(self):
        # ??????????
        users = pd.read_csv('names.csv')
        # ??similarity?platform?reputation?entropy????????????
        X = users[['similarity', 'platform', 'reputation', 'entropy']]
        y = users['human_or_machine']

        # ?????????? 25%???????
        from sklearn.cross_validation import train_test_split
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=33)

        # ????????????????
        from sklearn.feature_extraction import DictVectorizer
        vec = DictVectorizer(sparse=False)
        X_train = vec.fit_transform(X_train.to_dict(orient='record'))
        X_test = vec.transform(X_test.to_dict(orient='record'))

        # ?????????????????????
        from sklearn.tree import DecisionTreeClassifier
        dtc = DecisionTreeClassifier()
        dtc.fit(X_train, y_train)
        dtc_y_pred = dtc.predict(X_test)

        # ???????????????????????
        from sklearn.ensemble import RandomForestClassifier
        rfc = RandomForestClassifier()
        rfc.fit(X_train, y_train)
        rfc_y_pred = rfc.predict(X_test)

        # ???????????????????????
        from sklearn.ensemble import GradientBoostingClassifier
        gbc = GradientBoostingClassifier()
        gbc.fit(X_train, y_train)
        gbc_y_pred = gbc.predict(X_test)

        from sklearn.metrics import classification_report
        # ??????????????????? ?????????? ??? F1??
        print("??????????", dtc.score(X_test, y_test))
        print(classification_report(dtc_y_pred, y_test))

        # ??????????????????????????????? ??? F1??
        print("????????????", rfc.score(X_test, y_test))
        print(classification_report(rfc_y_pred, y_test))

        # ??????????????????????????????? ??? F1??
        print("????????????", gbc.score(X_test, y_test))
        print(classification_report(gbc_y_pred, y_test))


        users = pd.read_csv('values.csv')

        # ??????????
        X = users[['similarity', 'platform', 'reputation', 'entropy']]
        X = vec.transform(X.to_dict(orient='record'))
        print(rfc.predict(X))

        self.dtc = dtc
        self.rfc = rfc
        self.gbc = gbc