def setUp(self):
l1 = log(low=-3, high=5, base=10)
l2 = log(low=-2, high=3, base=10)
u = uniform(low=-1, high=1)
qu = quantized_uniform(low=1, high=20, step=1)
self.space = Space([{
"algo": {
"svm": {
"C": l1,
"kernel": {
"linear": None,
"rbf": {
"gamma": l2
}
},
"cond2": {
"aa": None,
"bb": {
"abc": u
}
}
},
"knn": {
"n_neighbors": qu
}
}
}, {
"cond3": 0,
"p": l1,
"p2": qu
}])
def init_choco_sampler(args):
conn = choco.SQLiteConnection(args['sqlite_dbase'])
space = {
"lr": choco.log(low=-5, high=-3, base=10),
"lr_decay": choco.uniform(high=1, low=0),
"reg_scale": choco.uniform(low=0, high=1),
"last_reg_scale": choco.uniform(low=0, high=1),
"weight": choco.uniform(low=1, high=50),
"weight_decay": choco.uniform(low=0, high=1),
"contrast": choco.uniform(low=-100, high=100)
}
sampler = choco.CMAES(conn, space)
return (sampler, conn)
def create_space():
space = {
"learning_rate":
choco.log(low=-5, high=-2, base=10),
"dropout_keep_prob":
choco.quantized_uniform(low=0.0, high=0.95, step=0.05),
"num_filters":
choco.quantized_uniform(low=50, high=200, step=10),
"batch_size":
choco.quantized_uniform(low=64, high=256, step=16),
"num_epochs":
choco.quantized_uniform(low=100, high=200, step=10),
"l2_reg_lambda":
choco.quantized_uniform(low=0.0, high=10.0, step=0.5),
"eps":
choco.quantized_uniform(low=1.0, high=10.0, step=0.02),
"dev_sample_percentage":
choco.quantized_uniform(low=0.1, high=0.3, step=0.01)
}
return space
def convert_param_to_choco(param):
"""Convert a single search parameter suitably for ``chocolate``.
"""
from math import log10
import chocolate as choco
if param['type'] == 'BOOL':
return choco.choice([False, True])
if param['type'] == 'INT':
return choco.quantized_uniform(low=param['min'],
high=param['max'] + 1,
step=1)
if param['type'] == 'STRING':
return choco.choice(param['options'])
if param['type'] == 'FLOAT':
return choco.uniform(low=param['min'], high=param['max'])
if param['type'] == 'FLOAT_EXP':
return choco.log(low=log10(param['min']),
high=log10(param['max']),
base=10)
else:
raise ValueError("Didn't understand space {}.".format(param))
from utils import read_data, write_data, metrics, submit
from sklearn.svm import SVC
from param_config import config
import chocolate as choco
from utils import metrics
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
np.random.seed(config.set_seed)
TOTAL_RUNS = 5000
c_d = np.logspace(-4, 6, TOTAL_RUNS)
g_d = np.logspace(-5, 6, TOTAL_RUNS)
param_grid = {
"C": choco.log(-4, 6, base=10),
"gamma": choco.log(-5, 6, base=10)
}
def model_train(x_train, y_train, x_val, y_val, params):
svc = SVC(kernel='rbf', verbose=True, **params)
svc.fit(x_train, y_train)
y_hat = svc.predict(x_val)
f1 = metrics(y_val, y_hat)
return -f1
def split(X, y):
x_train, x_val, y_train, y_val = train_test_split(
def f1_score_model(trn_x, trn_y, tst_x, tst_y, model, **params):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
m = models[model](**params)
m.fit(trn_x, trn_y)
y_pred = m.predict(tst_x)
return -1*skm.f1_score(tst_y, y_pred, average='macro')
space = [
# {'model': 'RandomForestClassifier',
# "max_depth" : choco.quantized_uniform(2, 32, 2),
# "min_samples_split": choco.quantized_uniform(2, 600, 2),
# "n_estimators" : choco.quantized_uniform(125, 800, 25),},
{'model': 'SVC',
"gamma": 'auto',
"C": choco.log(-3, 3, 10),
"kernel": choco.choice(['linear', 'poly', 'rbf', 'sigmoid', 'precomputed']),
"tol": choco.log(-5, -2, 10),},
{'model': 'XGBClassifier',
"learning_rate" : choco.uniform(0.001, 0.1),
"max_depth" : choco.quantized_uniform(2, 16, 2),
"min_child_weight": choco.quantized_uniform(2, 10, 2),
"subsample" : choco.quantized_uniform(0.7, 1.05, 0.05),
"n_estimators" : choco.quantized_uniform(25, 525, 25),},
{'model': 'LogisticRegression',
"penalty" : choco.choice(['l1', 'l2']),
"C" : choco.log(-2, 1, 10),},
]
models = {
'RandomForestClassifier': RandomForestClassifier,
self.validation_error = 100000.0
if __name__ == '__main__':
if len(sys.argv) == 1:
# original params from article
model=LatentAttention(frac_train=0.99, n_z=20, batchsize=100,
learning_rate=0.001, max_epochs=10,
e_h1=16, e_h2=32, d_h1=32, d_h2=16, run_id=-1);
model.train()
print("loss={}".format(float(model.validation_error)))
exit(0)
# Params from optimizer
search_space = {
"n_z": choco.quantized_uniform(5, 100, 1),
"learning_rate": choco.log(-20, -8, 2),
"max_epochs": choco.quantized_uniform(5, 200, 1),
"e_h1": choco.quantized_uniform(16, 256, 1),
"e_h2": choco.quantized_uniform(16, 256, 1),
"d_h1": choco.quantized_uniform(16, 256, 1),
"d_h2": choco.quantized_uniform(16, 256, 1),
}
connection = choco.SQLiteConnection("sqlite:///no_labels_results.sqlite3")
sampler = choco.Bayes(connection, search_space)
token, sample = sampler.next()
print("Parameters: {} Token: {}".format(sample, token))
run_id = token['_chocolate_id']
model = LatentAttention(0.99, batchsize=150, run_id=run_id, **sample)
model.train()
sampler.update(token, float(model.validation_error))
return func
def f1_score_model(trn_x, trn_y, tst_x, tst_y, model, **params):
m = models[model](**params)
m.fit(trn_x, trn_y)
y_pred = m.predict(tst_x)
return -1 * skm.f1_score(tst_y, y_pred, average='macro')
space = [
{
'model': 'SVC',
"gamma": 'auto',
"C": choco.log(-3, 3, 10),
"kernel":
choco.choice(['linear', 'poly', 'rbf', 'sigmoid', 'precomputed']),
"tol": choco.log(-5, -2, 10),
},
{
'model': 'XGBClassifier',
"learning_rate": choco.uniform(0.001, 0.1),
"max_depth": choco.quantized_uniform(2, 16, 2),
"min_child_weight": choco.quantized_uniform(2, 10, 2),
"subsample": choco.quantized_uniform(0.7, 1.05, 0.05),
"n_estimators": choco.quantized_uniform(25, 525, 25),
},
{
'model': 'RandomForestClassifier',
"max_depth": choco.quantized_uniform(2, 10, 2),