from sklearn.feature_extraction.text import CountVectorizer
from sklearn.cross_validation import train_test_split
from sklearn.naive_bayes import MultinomialNB

X = vectorizer.fit_transform(df.quote)
X = X.tocsc()
Y = (df.fresh == 'fresh').values.astype(np.int)

xtrain, xtest, ytrain, ytest = train_test_split(X, Y)

clf = MultinomialNB().fit(xtrain, ytrain)

new_review = ['this is a new review, movie was awesome']
new_review = vectorizer.fit_transform(new_review)

print df.quote[15]
print(clf.predict(df.quote[10])) #predict existing review in dataframe
print(clf.predict(new_review)) #predict new review


Technically, Toy Story is nearly flawless.
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-91-27a0698bbd1f> in <module>()
     15
     16 print df.quote[15]
---> 17 print(clf.predict(df.quote[10])) #predict existing quote in dataframe
     18 print(clf.predict(new_review)) #predict new review

//anaconda/lib/python2.7/site-packages/sklearn/naive_bayes.pyc in predict(self, X)
     60             Predicted target values for X
     61         """
---> 62         jll = self._joint_log_likelihood(X)
     63         return self.classes_[np.argmax(jll, axis=1)]
     64

//anaconda/lib/python2.7/site-packages/sklearn/naive_bayes.pyc in _joint_log_likelihood(self, X)
    439         """Calculate the posterior log probability of the samples X"""
    440         X = atleast2d_or_csr(X)
--> 441         return (safe_sparse_dot(X, self.feature_log_prob_.T)
    442                 + self.class_log_prior_)
    443

//anaconda/lib/python2.7/site-packages/sklearn/utils/extmath.pyc in safe_sparse_dot(a, b, dense_output)
    178         return ret
    179     else:
--> 180         return fast_dot(a, b)
    181
    182

TypeError: Cannot cast array data from dtype('float64') to dtype('S32') according to the rule 'safe'