from sklearn.svm import LinearSVC
from sklearn.ensemble import AdaBoostClassifier
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import RidgeClassifier
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.linear_model import Perceptron
from sklearn.neighbors import NearestCentroid
from sklearn.feature_selection import SelectFromModel

names = ["Logistic Regression", "Linear SVC", "LinearSVC with L1-based feature selection","Multinomial NB",
         "Bernoulli NB", "Ridge Classifier", "AdaBoost", "Perceptron","Passive-Aggresive", "Nearest Centroid"]
classifiers = [
    LogisticRegression(),
    LinearSVC(),
    Pipeline([
  ('feature_selection', SelectFromModel(LinearSVC(penalty="l1", dual=False))),
  ('classification', LinearSVC(penalty="l2"))]),
    MultinomialNB(),
    BernoulliNB(),
    RidgeClassifier(),
    AdaBoostClassifier(),
    Perceptron(),
    PassiveAggressiveClassifier(),
    NearestCentroid()
    ]
zipped_clf = zip(names,classifiers)

tvec = TfidfVectorizer()
def classifier_comparator(vectorizer=tvec, n_features=10000, stop_words=None, ngram_range=(1, 1), classifier=zipped_clf):
    result = []
    vectorizer.set_params(stop_words=stop_words, max_features=n_features, ngram_range=ngram_range)
    for n,c in classifier:
        checker_pipeline = Pipeline([
            ('vectorizer', vectorizer),
            ('classifier', c)
        ])
        print "Validation result for {}".format(n)
        print c
        clf_accuracy,tt_time = accuracy_summary(checker_pipeline, x_train, y_train, x_validation, y_validation)
        result.append((n,clf_accuracy,tt_time))
    return result

trigram_result = classifier_comparator(n_features=100000,ngram_range=(1,3))