record['mean_acc'] = scores.mean()
# predict on the test set
fn = SelectPercentile(f_classif, percentile).fit(train_x, train_y)
train_x = fn.transform(train_x)
test_x = fn.transform(test_x)
scaler = StandardScaler().fit(train_x)
train_x = scaler.transform(train_x)
test_x = scaler.transform(test_x)
model.fit(train_x, train_y)
ids = data['test_ids']
preds = model.predict(test_x)
record['test_preds'] = [(id_, pred) for id_, pred in zip(ids, preds)]
def finalize(config, experiment):
experiment.records = top_k(experiment.records, 'mean_acc', 30)
experiment['exp_name'] = config['exp_name']
pip = Pipeline(config, load_yaml('exp.yaml'), workers=4, save=True)
pip.load = load
# pip.model_iterator = model_iterator
pip.model_iterator = model_iterator_autosklearn
pip.train = train
pip.finalize = finalize
pip()
scoring='accuracy')
record['mean_acc'] = scores.mean()
# predict on the test set
fn = SelectPercentile(f_classif, percentile).fit(train_x, train_y)
train_x = fn.transform(train_x)
test_x = fn.transform(test_x)
scaler = StandardScaler().fit(train_x)
train_x = scaler.transform(train_x)
test_x = scaler.transform(test_x)
model.fit(train_x, train_y)
ids = data['test_ids']
preds = model.predict(test_x)
record['test_preds'] = [(id_, pred) for id_, pred in zip(ids, preds)]
def finalize(config, experiment):
experiment.records = top_k(experiment.records, 'mean_acc', 10)
experiment['exp_name'] = config['exp_name']
pip = Pipeline(config, load_yaml('exp.yaml'), workers=10, save=True)
pip.load = load
pip.model_iterator = model_iterator
pip.train = train
pip.finalize = finalize
pip()
