from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from time import time

def accuracy_summary(pipeline, x_train, y_train, x_test, y_test):
    if len(x_test[y_test == 0]) / (len(x_test)*1.) > 0.5:
        null_accuracy = len(x_test[y_test == 0]) / (len(x_test)*1.)
    else:
        null_accuracy = 1. - (len(x_test[y_test == 0]) / (len(x_test)*1.))
    t0 = time()
    sentiment_fit = pipeline.fit(x_train, y_train)
    y_pred = sentiment_fit.predict(x_test)
    train_test_time = time() - t0
    accuracy = accuracy_score(y_test, y_pred)
    print "null accuracy: {0:.2f}%".format(null_accuracy*100)
    print "accuracy score: {0:.2f}%".format(accuracy*100)
    if accuracy > null_accuracy:
        print "model is {0:.2f}% more accurate than null accuracy".format((accuracy-null_accuracy)*100)
    elif accuracy == null_accuracy:
        print "model has the same accuracy with the null accuracy"
    else:
        print "model is {0:.2f}% less accurate than null accuracy".format((null_accuracy-accuracy)*100)
    print "train and test time: {0:.2f}s".format(train_test_time)
    print "-"*80
    return accuracy, train_test_time

cvec = CountVectorizer()
lr = LogisticRegression()
n_features = np.arange(10000,100001,10000)

def nfeature_accuracy_checker(vectorizer=cvec, n_features=n_features, stop_words=None, ngram_range=(1, 1), classifier=lr):
    result = []
    print (classifier)
    print "\n"
    for n in n_features:
        vectorizer.set_params(stop_words=stop_words, max_features=n, ngram_range=ngram_range)
        checker_pipeline = Pipeline([
            ('vectorizer', vectorizer),
            ('classifier', classifier)
        ])
        print "Validation result for {} features".format(n)
        nfeature_accuracy,tt_time = accuracy_summary(checker_pipeline, x_train, y_train, x_validation, y_validation)
        result.append((n,nfeature_accuracy,tt_time))
    return result

from sklearn.feature_extraction.text import TfidfVectorizer
tvec = TfidfVectorizer()

feature_result_ugt = nfeature_accuracy_checker(vectorizer=tvec)
feature_result_bgt = nfeature_accuracy_checker(vectorizer=tvec,ngram_range=(1, 2))
feature_result_tgt = nfeature_accuracy_checker(vectorizer=tvec,ngram_range=(1, 3))


nfeatures_plot_tgt = pd.DataFrame(feature_result_tgt,columns=['nfeatures','validation_accuracy','train_test_time'])
nfeatures_plot_bgt = pd.DataFrame(feature_result_bgt,columns=['nfeatures','validation_accuracy','train_test_time'])
nfeatures_plot_ugt = pd.DataFrame(feature_result_ugt,columns=['nfeatures','validation_accuracy','train_test_time'])
plt.figure(figsize=(8,6))
plt.plot(nfeatures_plot_tgt.nfeatures, nfeatures_plot_tgt.validation_accuracy,label='trigram tfidf vectorizer',color='royalblue')
plt.plot(nfeatures_plot_tg.nfeatures, nfeatures_plot_tg.validation_accuracy,label='trigram count vectorizer',linestyle=':', color='royalblue')
plt.plot(nfeatures_plot_bgt.nfeatures, nfeatures_plot_bgt.validation_accuracy,label='bigram tfidf vectorizer',color='orangered')
plt.plot(nfeatures_plot_bg.nfeatures, nfeatures_plot_bg.validation_accuracy,label='bigram count vectorizer',linestyle=':',color='orangered')
plt.plot(nfeatures_plot_ugt.nfeatures, nfeatures_plot_ugt.validation_accuracy, label='unigram tfidf vectorizer',color='gold')
plt.plot(nfeatures_plot_ug.nfeatures, nfeatures_plot_ug.validation_accuracy, label='unigram count vectorizer',linestyle=':',color='gold')
plt.title("N-gram(1~3) test result : Accuracy")
plt.xlabel("Number of features")
plt.ylabel("Validation set accuracy")
plt.legend()