我正在尝试按照《Building Machine Learning Systems in Python》一书的第6章对Twitter数据进行情感分析。
我使用的数据集是：https://raw.githubusercontent.com/zfz/twitter_corpus/master/full-corpus.csv
我使用了tfidf向量化器和朴素贝叶斯分类器的管道作为估计器。
然后我使用GridSearchCV()来查找估计器的最佳参数。
代码如下：
from load_data import load_datafrom sklearn.cross_validation import ShuffleSplitfrom sklearn.grid_search import GridSearchCVfrom sklearn.metrics import f1_scorefrom sklearn.naive_bayes import MultinomialNBfrom sklearn.feature_extraction.text import TfidfVectorizerfrom sklearn.pipeline import Pipelinedef pipeline_tfidf_nb(): tfidf_vect = TfidfVectorizer( analyzer = "word") naive_bayes_clf = MultinomialNB() return Pipeline([('vect', tfidf_vect),('nbclf',naive_bayes_clf)])input_file = "full-corpus.csv"X,y = load_data(input_file)print X.shape,y.shapeclf = pipeline_tfidf_nb()cv = ShuffleSplit(n = len(X), test_size = .3, n_iter = 1, random_state = 0)clf_param_grid = dict(vect__ngram_range = [(1,1),(1,2),(1,3)], vect__min_df = [1,2], vect__smooth_idf = [False, True], vect__use_idf = [False, True], vect__sublinear_tf = [False, True], vect__binary = [False, True], nbclf__alpha = [0, 0.01, 0.05, 0.1, 0.5, 1], )grid_search = GridSearchCV(estimator = clf, param_grid = clf_param_grid, cv = cv, scoring = f1_score)grid_search.fit(X, y)print grid_search.best_estimator_load_data()从csv文件中提取带有正面或负面情感的值。
X是一个字符串数组（TweetText），y是一个布尔值数组（正面情感为True）。
错误信息如下：
runfile('C:/Users/saurabh.s1/Downloads/Python_ml/ch6/main.py', wdir='C:/Users/saurabh.s1/Downloads/Python_ml/ch6')Reloaded modules: load_datanegative : 572positive : 519(1091,) (1091,)Traceback (most recent call last): File "<ipython-input-25-823b07c4ff26>", line 1, in <module> runfile('C:/Users/saurabh.s1/Downloads/Python_ml/ch6/main.py', wdir='C:/Users/saurabh.s1/Downloads/Python_ml/ch6') File "C:\anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile execfile(filename, namespace) File "C:\anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 87, in execfile exec(compile(scripttext, filename, 'exec'), glob, loc) File "C:/Users/saurabh.s1/Downloads/Python_ml/ch6/main.py", line 31, in <module> grid_search.fit(X, y) File "C:\anaconda2\lib\site-packages\sklearn\grid_search.py", line 804, in fit return self._fit(X, y, ParameterGrid(self.param_grid)) File "C:\anaconda2\lib\site-packages\sklearn\grid_search.py", line 553, in _fit for parameters in parameter_iterable File "C:\anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 800, in __call__ while self.dispatch_one_batch(iterator): File "C:\anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 658, in dispatch_one_batch self._dispatch(tasks) File "C:\anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 566, in _dispatch job = ImmediateComputeBatch(batch) File "C:\anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 180, in __init__ self.results = batch() File "C:\anaconda2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 72, in __call__ return [func(*args, **kwargs) for func, args, kwargs in self.items] File "C:\anaconda2\lib\site-packages\sklearn\cross_validation.py", line 1550, in _fit_and_score test_score = _score(estimator, X_test, y_test, scorer) File "C:\anaconda2\lib\site-packages\sklearn\cross_validation.py", line 1606, in _score score = scorer(estimator, X_test, y_test) File "C:\anaconda2\lib\site-packages\sklearn\metrics\classification.py", line 639, in f1_score sample_weight=sample_weight) File "C:\anaconda2\lib\site-packages\sklearn\metrics\classification.py", line 756, in fbeta_score sample_weight=sample_weight) File "C:\anaconda2\lib\site-packages\sklearn\metrics\classification.py", line 956, in precision_recall_fscore_support y_type, y_true, y_pred = _check_targets(y_true, y_pred) File "C:\anaconda2\lib\site-packages\sklearn\metrics\classification.py", line 72, in _check_targets check_consistent_length(y_true, y_pred) File "C:\anaconda2\lib\site-packages\sklearn\utils\validation.py", line 173, in check_consistent_length uniques = np.unique([_num_samples(X) for X in arrays if X is not None]) File "C:\anaconda2\lib\site-packages\sklearn\utils\validation.py", line 112, in _num_samples 'estimator %s' % x)TypeError: Expected sequence or array-like, got estimator Pipeline(steps=[('vect', TfidfVectorizer(analyzer='word', binary=False, decode_error=u'strict', dtype=<type 'numpy.int64'>, encoding=u'utf-8', input=u'content', lowercase=True, max_df=1.0, max_features=None, min_df=1, ngram_range=(1, 1), norm=u'l2', preprocessor=None, smooth_i...e_idf=False, vocabulary=None)), ('nbclf', MultinomialNB(alpha=0, class_prior=None, fit_prior=True))])我已经尝试过重塑X,y，但这不起作用。
如果您需要更多数据，或者我遗漏了什么，请告诉我。
谢谢！
回答：
