我正在尝试解决一个Twitter情感分析问题。我使用的代码如下：

print()print("正在导入")print()#导入from __future__ import print_functionimport pandas as pdimport numpy as npimport reimport nltknltk.download('stopwords')from nltk.corpus import stopwordsfrom nltk.stem.porter import PorterStemmerfrom sklearn.feature_extraction.text import CountVectorizerfrom sklearn import metricsfrom sklearn import model_selectionfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.decomposition import PCAfrom sklearn.cross_validation import train_test_splitfrom sklearn.model_selection import GridSearchCVdef getting_data(train_dataset_name, test_dataset_name):    print()    print("正在获取数据")    print()    #参数名称自解释 - 数据集的文件名    #假设您在包含数据集的目录中执行此代码语句    train = pd.read_csv(train_dataset_name).values    train_y = train[:,1]    train_x = train[:,2]    test = pd.read_csv(test_dataset_name).values    test = test[:,1]    test = np.reshape(test,(test.shape[0],1))    return train_x,train_y,testdef bagOfWords(test,train_x):    print()    print("正在创建词袋模型")    print()    #创建并返回测试和训练x的词袋版本    #训练转换    corpus_train = []    for i in range(0,train_x.shape[0]):        review = re.sub('[^a-zA-Z]', ' ', train_x[i])        review = review.lower().split()        ps = PorterStemmer()        review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]        review = ' '.join(review)        corpus_train.append(review)    #测试转换    corpus_test = []    for i in range(0,test.shape[0]):        review = re.sub('[^a-zA-Z]', ' ', test[i][0])        review = review.lower().split()        ps = PorterStemmer()        review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]        review = ' '.join(review)        corpus_test.append(review)    return corpus_train,corpus_testdef dimensionality_reduction(corpus_train,corpus_test, return_ratio, components):    print()    print("正在进行降维")    print()    #CountVectorizer    cv = CountVectorizer(max_features = 1500)    train_x = cv.fit_transform(corpus_train).toarray()    #PCA    pca = PCA(n_components=components)    train_x = pca.fit_transform(train_x)    explained_variance = pca.explained_variance_ratio_    test = cv.transform(corpus_test).toarray()    test = pca.transform(test)    test = test.astype('float32')    if (return_ratio):        return train_x,test, explained_variance    else:        return train_x,testdef getOptimumParameters(train_x,train_y, return_stats):    print()    print("正在获取最佳参数")    print("此优化算法可能需要一些时间，请耐心等待。")    print("请在运行期间不要进行其他任务。")    print()    train_x = train_x.astype('float32')    train_y = train_y.astype('float32')    classifier = KNeighborsClassifier()     classifier.fit(train_x,train_y)    #为了我的程序，我使用了自己的参数列表。    #如果您使用此代码，请更改它们    neighbor_list = [1,3,6,9,12,15,18,21,25]    algorithm_list = ['brute', 'kd_tree', 'ball_tree']    weights_list = ['uniform', 'distance']    p_list = [1] #p_list = [1,2,3,4]    leaf_list = [10,15,20,25,30,35,40,45,50]    parameters = [{'n_neighbors':neighbor_list, 'weights':weights_list, 'algorithm':algorithm_list, 'p':p_list, 'leaf_size':leaf_list}]    clf = GridSearchCV(estimator=classifier, param_grid = parameters, cv=5,refit=True, error_score=0, n_jobs = -1)    clf = clf.fit(train_x,train_y)    bc = clf.best_score_    bp = clf.best_params_    if return_stats:        return clf, bc, bp    else:        return clfdef predictions(classifier, train_x, train_y, test, ratio):    print()    print("正在进行预测")    print()    #更改类型以与分类器一起使用    train_x= train_x.astype('float32')    train_y = train_y.astype('float32')    #将训练集拆分为训练集和开发集    train_x,dev_x,train_y,dev_y = train_test_split(train_x,train_y,test_size = ratio, random_state=0)    #进行预测    test = test.astype('float32')    pred = classifier.predict(test)    return preddef convertPredToCsv(pred, csv_name):    df = pd.DataFrame(pred)    df.index.name = 'id'    df.columns = ['label']    df.to_csv("predictions.csv")def main():    #获取数据    train_x,train_y,test = getting_data('train.csv', 'test_tweets.csv')    #构建词袋模型    corpus_train,corpus_test = bagOfWords(test,train_x)    #进行降维    train_x,test = dimensionality_reduction(corpus_train,corpus_test,False,350)    #获取最佳分类器    classifier= getOptimumParameters(train_x,train_y, False)    #预测并转换为csv    pred = predictions(classifier, train_x, train_y, test, 0.1)    convertPredToCsv(pred, 'predictions.csv')if __name__ == "__main__":    main()

每次运行到getOptimumParameters函数时，我都会遇到许多错误。有些错误提示是属性错误，但大多数错误我找不到错误名称。我认为大多数其他错误都是为了引导我找到属性错误。我无法弄清楚为什么会发生这个错误。我知道我的GridSearch有问题，但我不知道是参数有问题（我已经三次检查过了，没有发现任何问题），还是有其他问题。任何帮助都将不胜感激。谢谢。

D:\Anaconda\lib\site-packages\numpy\core\fromnumeric.py in _wrapfunc(obj=array([[ 0.        , 30.70562651, 27.84020028, .... 38.11465899,        25.22553572,  0.        ]]), method='argpartition', *args=(0,), **kwds={'axis': 1, 'kind': 'introselect', 'order': None})     47     return result     48      49      50 def _wrapfunc(obj, method, *args, **kwds):     51     try:---> 52         return getattr(obj, method)(*args, **kwds)        obj = array([[ 0.        , 30.70562651, 27.84020028, .... 38.11465899,        25.22553572,  0.        ]])        method = 'argpartition'        args = (0,)        kwds = {'axis': 1, 'kind': 'introselect', 'order': None}     53      54     # 如果对象的类中没有这样的方法，会发生属性错误     55     # 内存错误： 

数据来自我的analyticsvidhya问题。这里是训练数据的下载链接 – 这是一个Dropbox链接。https://www.dropbox.com/s/w4tagiewcuoxgkt/train.csv?dl=0

这是测试数据的链接：https://www.dropbox.com/s/qiitwlpnkbs2c3m/test_tweets.csv?dl=0

谢谢。

回答：

我知道已经过了一段时间，很抱歉。

只是想让大家知道，对于长时间的网格搜索，至少对于Windows用户来说，导入的是

sklearn.model_selection.GridSearchCV

而实际上应该导入的是

sklearn.grid_search.GridSearchCV

前者几乎总是会抛出内存错误，而后者即使在长时间的网格搜索中也能正常工作。