from sklearn.svm import LinearSVC
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

names = [
         "Naive Bayes",
         "Linear SVM",
         "Logistic Regression",
         "Random Forest",
         "Multilayer Perceptron"
        ]

classifiers = [
    MultinomialNB(),
    LinearSVC(),
    LogisticRegression(),
    RandomForestClassifier(),
    MLPClassifier()
]

parameters = [
              {'vect__ngram_range': [(1, 1), (1, 2)],
              'clf__alpha': (1e-2, 1e-3)},
              {'vect__ngram_range': [(1, 1), (1, 2)],
              'clf__C': (np.logspace(-5, 1, 5))},
              {'vect__ngram_range': [(1, 1), (1, 2)],
              'clf__C': (np.logspace(-5, 1, 5))},
              {'vect__ngram_range': [(1, 1), (1, 2)],
              'clf__max_depth': (1, 2)},
              {'vect__ngram_range': [(1, 1), (1, 2)],
              'clf__alpha': (1e-2, 1e-3)}
             ]

for name, classifier, params in zip(names, classifiers, parameters):
    clf_pipe = Pipeline([
        ('vect', TfidfVectorizer(stop_words='english')),
        ('clf', classifier),
    ])
    gs_clf = GridSearchCV(clf_pipe, param_grid=params, n_jobs=-1)
    clf = gs_clf.fit(X_train, y_train)
    score = clf.score(X_test, y_test)
    print("{} score: {}".format(name, score))