def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.linear_model import Perceptron
clf = Perceptron(max_iter=50, tol=1e-3, random_state=1)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.neighbors import KNeighborsClassifier
clf = KNeighborsClassifier(n_neighbors=10)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.naive_bayes import BernoulliNB, MultinomialNB
clf = BernoulliNB(alpha=.01)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.linear_model import RidgeClassifier
clf = RidgeClassifier(tol=1e-2, solver="sag", random_state=1)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.neighbors import NearestCentroid
clf = NearestCentroid()
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=event_sel)
# X_train, y_train = preprocess(df, event_sel=[31, 78])
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42, 55, 11])
X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
from lightgbm import LGBMClassifier
clf = LGBMClassifier(verbose=1, random_state=1, silent=0, n_estimators=400)
return benchmark(clf, X_train.astype(float), y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
X_train, y_train = preprocess(df, event_sel=event_sel)
from sklearn.linear_model import SGDClassifier
clf = SGDClassifier(alpha=.0001,
max_iter=50,
tol=1e-3,
penalty='l2',
random_state=1)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
X_train, y_train = preprocess(df, event_sel=event_sel)
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42, 55, 11])
# X_train, y_train = preprocess(df, event_sel=[62, 63, 60])
from sklearn.svm import LinearSVC
clf = LinearSVC(loss='squared_hinge',
penalty='l2',
dual=False,
tol=1e-3,
verbose=0,
random_state=1)
return benchmark(clf, X_train, y_train)
def main(event_sel=None):
df = read_train()
# X_train, y_train = preprocess(df, event_sel=event_sel)
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42])
# X_train, y_train = preprocess(df, event_sel=[71, 62, 42, 55, 11])
X_train, y_train = preprocess(df, event_sel=[62, 63, 60], ngrams=(2,4))
print('Extracting best features by a chi-squared test')
from sklearn.feature_selection import SelectKBest, chi2
ch2 = SelectKBest(chi2, k=12000)
X_train = ch2.fit_transform(X_train, y_train)
print('Extracting done, {}'.format(X_train.shape))
from sklearn.svm import LinearSVC
clf = LinearSVC(loss='squared_hinge', penalty='l2', dual=False, tol=1e-3, verbose=0, random_state=1)
return benchmark(clf, X_train, y_train)