def main():
print('Explore dataset')
train = Dataset.from_train()
u = train.pca()
print('U shape: ' + str(u.shape))
X = train.get_pca_features(u)
print(X.shape)
def train_nn(restore):
print('Training neural net')
encoder = AutoEncoder()
encoder.restore_session()
train_data = Dataset.from_train()
X = encoder.encode(train_data.get_features())
y = train_data.get_labels()
nn = NeuralNet()
nn.fit(X, y)
def prepare_solution():
train = Dataset.from_train()
X = train.get_features()
Y = train.get_labels()
rf = RandomForestRegressor(n_jobs=-1)
model = rf.fit(X, Y)
print('Train dataset score: %f' % loss(Y, model.predict(X)))
test = Dataset.from_test()
X2 = test.get_features()
Y2 = model.predict(X2)
save_predictions(Y2, test.df)
def prepare_solution():
train = Dataset.from_train()
X = train.get_features()
Y = train.get_labels()
rf = RandomForestRegressor(n_jobs=-1)
model = rf.fit(X, Y)
print('Train score: %f' % loss(Y, model.predict(X)))
test = Dataset.from_test()
X2 = test.get_features()
Y2 = model.predict(X2)
save_predictions(Y2, test)
def submission():
print('Cross validate K-Means model')
train = Dataset.from_train()
test = Dataset.from_test()
X = train.get_features()
Y = train.get_labels()
X2 = test.get_features()
kmeans = KMeans(n_clusters=8)
clf = kmeans.fit(X, train.get_multi_labels())
score = check_score(Y, to_labels(clf.predict(X)))
print("Train dataset score %f" % (score/len(X)))
Y2 = to_labels(clf.predict(X2))
save_predictions(Y2, test.df)
def submission():
print('Cross validate K-Means model')
train = Dataset.from_train()
test = Dataset.from_test()
X = train.get_features()
Y = train.get_labels()
X2 = test.get_features()
kmeans = KMeans(n_clusters=8)
clf = kmeans.fit(X, train.get_multi_labels())
score = check_score(Y, to_labels(clf.predict(X)))
print("Train dataset score %f" % (score / len(X)))
Y2 = to_labels(clf.predict(X2))
save_predictions(Y2, test.df)
def submission():
print('Cross validate bayes model')
train = Dataset.from_train()
test = Dataset.from_test()
X = train.get_features()
Y = train.get_labels()
X2 = test.get_features()
gnb = bayes.MultinomialNB()
clf = gnb.fit(X, train.get_multi_labels())
score = check_score(Y, to_labels(clf.predict(X)))
print("Train dataset score %f" % (score / len(X)))
Y2 = to_labels(clf.predict(X2))
save_predictions(Y2, test.df)
def submission():
print('Cross validate bayes model')
train = Dataset.from_train()
test = Dataset.from_test()
X = train.get_features()
Y = train.get_labels()
X2 = test.get_features()
gnb = bayes.MultinomialNB()
clf = gnb.fit(X, train.get_multi_labels())
score = check_score(Y, to_labels(clf.predict(X)))
print("Train dataset score %f" % (score/len(X)))
Y2 = to_labels(clf.predict(X2))
save_predictions(Y2, test.df)
def prepare_submission(params):
print('Prepare submission with params')
print(params)
network = NeuralNetwork(params)
train = Dataset.from_train()
u = train.pca()
if params.pca:
X = train.get_pca_features(u)
else:
X = train.get_features()
Y = train.get_labels()
network.fit(X, Y)
score = network.check_score(X, Y)
print('Train dataset score %f' % (score / len(X)))
make_submission(network, params, u)
def prepare_submission(params):
print('Prepare submission with params')
print(params)
network = NeuralNetwork(params)
train = Dataset.from_train()
u = train.pca()
if params.pca:
X = train.get_pca_features(u)
else:
X = train.get_features()
Y = train.get_labels()
network.fit(X, Y)
score = network.check_score(X, Y)
print('Train dataset score %f' % (score/len(X)))
make_submission(network, params, u)
def train_auto_encoder(restore):
print('Training auto encoder')
network = AutoEncoder()
train_data = Dataset.from_train()
test_data = Dataset.from_test()
network.fit_encoder(train_data, test_data, restore=restore)
