问Sci学习:调查不正确的分类数据

EN

# take a sample of our original data
data=tweet_df[0:100]['texts']
y=tweet_df[0:100]['truth']

# create the feature vectors
vec=TfidfVectorizer(analyzer="char",ngram_range=(1,2))
X=vec.fit_transform(data) # this is now feature matrix

# split the feature matrix into train/test subsets, keeping the indices back into the original X using the
# array indices
indices = np.arange(X.shape[0])
X_train, X_test, y_train, y_test,idx_train,idx_test=train_test_split(X,y,indices,test_size=0.2,random_state=state)

# fit and test a model
forest=RandomForestClassifier()
forest.fit(X_train,y_train)
predictions=forest.predict(X_test)

# get the indices for false_negatives and false_positives in the test set
false_neg, false_pos=tweet_fns.check_predictions(predictions,y_test)

# map the false negative indices in the test set (which is features) back to it's original data (text)
print "False negatives: \n"
pd.options.display.max_colwidth = 140
for i in false_neg:
    original_index=idx_test[i]
    print data.iloc[original_index]

def check_predictions(predictions,truth):
    # take a 1-dim array of predictions from a model, and a 1-dim truth vector and calculate similarity
    # returns the indices of the false negatives and false positives in the predictions. 

    truth=truth.astype(bool)
    predictions=predictions.astype(bool)
    print sum(predictions == truth), 'of ', len(truth), "or ", float(sum(predictions == truth))/float(len(truth))," match"

    # false positives
    print "false positives: ", sum(predictions & ~truth)
    # false negatives
    print "false negatives: ",sum( ~predictions & truth)
    false_neg=np.nonzero(~predictions & truth) # these are tuples of arrays
    false_pos=np.nonzero(predictions & ~truth)
    return false_neg[0], false_pos[0] # we just want the arrays to return