def test_estimator():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
from alphaml.datasets.cls_dataset.dataset_loader import load_data
from alphaml.utils.constants import MAX_INT
rep_num = args.rep
run_count = args.run_count
datasets = args.datasets.split(',')
print(rep_num, run_count, datasets)
for dataset in datasets:
dataset_id = dataset.split('_')[0]
result_dir = 'data/' + dataset_id
if not os.path.exists(result_dir):
os.mkdir(result_dir)
task_format = dataset + '_est_%d'
X, y, _ = load_data(dataset)
dm = DataManager(X, y)
seed = np.random.random_integers(MAX_INT)
for optimizer in ['smbo']:
cls = Classifier(include_models=['gradient_boosting'],
optimizer=optimizer,
seed=seed).fit(dm,
metric='accuracy',
runcount=run_count,
task_name=task_format)
print(cls.predict(X))
def test_hyperspace():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
from alphaml.datasets.cls_dataset.dataset_loader import load_data
from alphaml.utils.constants import MAX_INT
try:
for dataset in datasets:
for run_id in range(start_run, rep_num):
X, y, _ = load_data(dataset)
dm = DataManager(X, y)
seed = np.random.random_integers(MAX_INT)
for update_mode in [2, 3]:
task_format = dataset + '_mode_%d_%d' % (update_mode,
run_id)
cls = Classifier(optimizer='ts_smbo',
seed=seed).fit(dm,
metric='accuracy',
runcount=run_count,
task_name=task_format,
update_mode=update_mode)
print(cls.predict(X))
except Exception as e:
print(e)
print('Exit!')
def test_cash_module():
df = pd.read_csv("data/cls_data/santander/train.csv")
df = df.drop(columns=["ID"])
cls = Classifier(include_models=['xgboost', 'random_forest', 'decision_tree'],
optimizer='baseline',
ensemble_method='ensemble_selection',
ensemble_size=30,
).fit(df, metric='auc', runcount=1)
df = pd.read_csv("data/cls_data/santander/test.csv")
data = df.values
df = df.drop(columns=["ID"])
pred2 = cls.predict(df)
print(pred2)
import csv
with open('data/cls_data/santander/submission.csv', 'w', newline='') as f:
writer = csv.writer(f)
writer.writerow(['ID', 'TARGET'])
for i in range(len(pred2)):
line = [int(data[i, 0]), pred2[i]]
writer.writerow(line)
def test_no_free_lunch():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
from alphaml.datasets.cls_dataset.dataset_loader import load_data
for dataset in datasets:
seeds = get_seeds(dataset, rep_num)
for run_id in range(rep_num):
seed = seeds[run_id]
# Dataset partition.
X, y, _ = load_data(dataset)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
dm = DataManager(X_train, y_train)
for algo in algo_list:
for optimizer in ['smbo']:
task_format = dataset + '_' + algo + '_%d_%d'
cls = Classifier(
include_models=[algo], optimizer=optimizer, seed=seed).fit(
dm, metric='accuracy', runcount=run_count, task_name=task_format % (run_count, run_id))
print(cls.predict(X))
def test_hyperspace():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
from alphaml.datasets.cls_dataset.dataset_loader import load_data
from alphaml.utils.constants import MAX_INT
try:
for dataset in datasets:
for run_id in range(start_run, rep_num):
X, y, _ = load_data(dataset)
dm = DataManager(X, y)
seed = np.random.random_integers(MAX_INT)
for n_est in [1, 2, 4, 8, 12]:
algos = algo_list[:n_est]
task_format = dataset + '_hp_%d_%d' % (n_est, run_id)
cls = Classifier(
include_models=algos, optimizer='smbo', seed=seed).fit(
dm, metric='accuracy', runcount=run_count, task_name=task_format)
print(cls.predict(X))
except Exception as e:
print(e)
print('Exit!')
def test_claim():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
from alphaml.datasets.cls_dataset.dataset_loader import load_data
from alphaml.utils.constants import MAX_INT
perfs_list = list()
for dataset in datasets:
for run_id in range(rep_num):
X, y, _ = load_data(dataset)
dm = DataManager(X, y)
seed = np.random.random_integers(MAX_INT)
task_format = dataset + '_claim_%d'
for optimizer in ['smbo']:
cls = Classifier(optimizer=optimizer,
seed=seed).fit(dm,
metric='accuracy',
runcount=run_count,
task_name=task_format % run_id)
print(cls.predict(X))
file_id = 'data/%s/%s_claim_%d_%s.data' % (dataset, dataset,
run_id, 'smac')
with open(file_id, 'rb') as f:
data = pickle.load(f)
best_id = np.argmax(data['perfs'])
best_value = data['perfs'][best_id]
if data['perfs'].count(best_value) > 1:
stats = dict()
for conf, perf in zip(data['configs'], data['perfs']):
if perf == best_value:
est = conf['estimator']
if est not in stats:
stats[est] = 0
stats[est] += 1
tmp_id = np.argmax(stats.values())
best_estimator = list(stats.keys())[tmp_id]
print('=' * 20, best_value, stats)
else:
best_estimator = data['configs'][best_id]['estimator']
print('=' * 20, data['perfs'][best_id],
data['configs'][best_id])
run_cnts = len([
item for item in data['configs']
if item['estimator'] == best_estimator
])
task_format = dataset + '_claim_single_%d'
cls = Classifier(include_models=[best_estimator],
optimizer=optimizer,
seed=seed).fit(dm,
metric='accuracy',
runcount=run_cnts,
task_name=task_format % run_id)
print(cls.predict(X))
file_id = 'data/%s/%s_claim_single_%d_%s.data' % (
dataset, dataset, run_id, 'smac')
with open(file_id, 'rb') as f:
data_s = pickle.load(f)
print('=' * 20 + 'single', max(data_s['perfs']))
perfs_list.append((data['perfs'], data_s['perfs']))
for item in perfs_list:
item1, item2 = item
print(len(item1), max(item1), len(item2), max(item2))
print('=' * 50)
print(perfs_list)
df["Sex"] = df["Sex"].replace(["male", "female"], [0, 1])
df.drop(columns="Ticket", axis=1, inplace=True)
for i in range(df.shape[0]):
if df["Cabin"][i] == "C23 C25 C27":
df["Cabin"][i] = 0
else:
df["Cabin"][i] = 1
df["Cabin"] = df["Cabin"].astype("float")
df = pd.get_dummies(df)
x = df.values
x_train = x[:train_size]
x_test = x[train_size:]
dm = DataManager()
dm.train_X = x_train
dm.train_y = y_train
clf = Classifier(optimizer="smbo")
clf.fit(dm, metric="accuracy", runcount=200)
submission = pd.read_csv(home_path + "/datasets/titanic/gender_submission.csv")
submission["Survived"] = clf.predict(x_test)
submission.to_csv(home_path + "/datasets/titanic/xgboost.csv", index=False)