def main(neval=30,
nfolds=5,
ncvjobs=1,
nreps=5,
kbest=None,
ngram_hi=3,
jobs=1,
seed=1,
*event_sel):
print(locals())
#return
#event_sel=[70, 71]
#nreps=1
df = read_train()
X, y = preprocess(df, event_sel=event_sel, ngrams=(2, ngram_hi))
best = evaluate_hyper(
X,
y,
hyper_objective,
neval=neval,
nfolds=nfolds,
ncvjobs=ncvjobs,
nreps=nreps,
nbest=kbest,
njobs=jobs,
seed=seed,
)
print('Final best: {}'.format(best))
return
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.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.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.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)
def main(
kbest=46000,
ngram_hi=3,
jobs=1,
seed=1,
):
print(locals())
df_tr = read_train()
df_te = read_test()
# Przyklady pipeline
# https://github.com/sfu-natlang/typed-align/blob/3fdab03765524a93831b31c7f21f3e8a11dfe54d/srcs/LogisticRegression.py
# https://scikit-learn.org/0.18/auto_examples/hetero_feature_union.html
clf = Pipeline([
(
'union',
FeatureUnion([
# vectorized text
('vect',
Pipeline([
('selector', ItemSelector(key='text')),
('whitespace_remover',
FunctionTransformer(
lambda col: col.apply(lambda s: ''.join(s.split())),
validate=False)),
('digits_remover',
FunctionTransformer(lambda col: col.apply(
lambda s: ''.join(i for i in s if not i.isdigit())),
validate=False)),
('vec',
CountVectorizer(binary=True,
ngram_range=(2, ngram_hi),
analyzer='char',
dtype=np.uint8)),
])),
# sex
('sex',
Pipeline([
('selector', ItemSelector(key='sex')),
('less_1',
FunctionTransformer(lambda col: col.values[:, None] - 1,
validate=False)),
])),
])),
('kbest', SelectKBest(chi2, k=kbest)),
('classifier',
LinearSVC(loss='squared_hinge',
penalty='l2',
dual=False,
tol=1e-4,
verbose=0,
random_state=1,
C=0.007283075704523443))
])
# foo = clf.fit_transform(df_tr, df_tr.event)
clf.fit(df_tr, df_tr.event)
# foo = clf.transform(df_te)
yhat = clf.predict(df_te)
# print(foo.shape)
# print(foo.dtype)
# print(foo)
df_te['event'] = yhat
df_te.to_csv('solution.csv', index=False)