classify.py 文件源码

def validation(self, X, Y, wv_X, kind):
        """
        2-fold validation
        :param X: train text
        :param Y: train label
        :param wv_X: train wv_vec
        :param kind: age/gender/education
        :return: mean score of 2-fold validation
        """
        print '????...'
        X=np.array(X)
        fold_n=2
        folds = list(StratifiedKFold(Y, n_folds=fold_n, shuffle=False,random_state=0))
        score = np.zeros(fold_n)
        for j, (train_idx, test_idx) in enumerate(folds):
            print j+1,'-fold'

            X_train = X[train_idx]
            y_train = Y[train_idx]
            X_test = X[test_idx]
            y_test = Y[test_idx]

            wv_X_train =wv_X[train_idx]
            wv_X_test = wv_X[test_idx]

            vec = TfidfVectorizer(use_idf=True,sublinear_tf=False, max_features=50000, binary=True)
            vec.fit(X_train, y_train)
            X_train = vec.transform(X_train)
            X_test = vec.transform(X_test)

            print 'shape',X_train.shape

            ypre = self.stacking(X_train,y_train,X_test,wv_X_train,wv_X_test,kind)
            cur = sum(y_test == ypre) * 1.0 / len(ypre)
            score[j] = cur

        print score
        print score.mean(),kind
        return score.mean()