def test_cash_module():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
import random
from sklearn.metrics import roc_auc_score
result = []
for i in range(1):
import xlrd
sheet = xlrd.open_workbook("lyqdata.xlsx")
sheet = sheet.sheet_by_index(0)
nrows = sheet.nrows
X_train = []
y_train = []
for i in range(2, nrows):
X_train.append(sheet.row_values(i, start_colx=1))
y_train.append(int(sheet.cell_value(i, 0)))
dm = DataManager(X_train, y_train)
cls = Classifier(
# include_models=['liblinear_svc', 'libsvm_svc', 'random_forest', 'logistic_regression', 'mlp'],
include_models=['mlp'],
optimizer='smbo',
cross_valid=False,
ensemble_method='ensemble_selection',
ensemble_size=args.ensemble_size,
save_dir='data/save_models'
)
cls.fit(dm, metric='auc', runcount=args.run_count)
sheet = xlrd.open_workbook("lyqtestdata.xlsx")
sheet = sheet.sheet_by_index(0)
nrows = sheet.nrows
X_test = []
y_test = []
for i in range(1, nrows):
X_test.append(sheet.row_values(i, start_colx=1))
y_test.append(int(sheet.cell_value(i, 0)))
pred = cls.predict_proba(X_test)
result.append(roc_auc_score(y_test, pred[:, 1:2]))
print(result)
import pickle
with open('result.pkl', 'wb') as f:
pickle.dump(result, f)
def test_cash_module():
from alphaml.engine.components.data_manager import DataManager
from alphaml.estimators.classifier import Classifier
import random
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
result = []
for i in range(1):
import xlrd
sheet = xlrd.open_workbook("ybai_Keratoconus_TJ_20190425.xlsx")
sheet = sheet.sheet_by_index(0)
nrows = sheet.nrows
X_train = []
y_train = []
for i in range(1, nrows):
X_train.append(sheet.row_values(i, start_colx=1))
y_train.append(int(sheet.cell_value(i, 0)))
encoder = OneHotEncoder()
encoder.fit(np.reshape(y_train, (len(y_train), 1)))
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, stratify=y_train)
dm = DataManager(X_train, y_train)
cls = Classifier(
# include_models=['liblinear_svc', 'libsvm_svc', 'xgboost', 'random_forest', 'logistic_regression', 'mlp'],
optimizer='smbo',
ensemble_method='bagging',
ensemble_size=args.ensemble_size,
)
cls.fit(dm, metric='auc', runcount=args.run_count)
pred = cls.predict_proba(X_test)
print(pred)
y_test = encoder.transform(np.reshape(y_test, (len(y_test), 1))).toarray()
result.append(roc_auc_score(y_test, pred))
print(result)
import pickle
with open('result.pkl', 'wb') as f:
pickle.dump(result, f)
from time import time
warnings.filterwarnings("ignore")
parser = argparse.ArgumentParser()
parser.add_argument("--generated_feature", type=int, default=1)
parser.add_argument("--dataset", type=str)
args = parser.parse_args()
x, y, c = load_data(args.dataset)
dm = DataManager(x, y)
lr = LogisticRegression()
lr.fit(dm.train_X, dm.train_y)
y_pred = lr.predict(dm.val_X)
print("original lr accu:", accuracy_score(dm.val_y, y_pred), flush=True)
if args.generated_feature > 0:
af = AutoFeature("accuracy", "auto_cross")
af.fit(dm, args.generated_feature)
dm = af.transform(dm)
clf = Classifier()
start_time = time()
clf.fit(dm, metric="accuracy", runcount=50)
print("alphaml time:", time() - start_time)
print("dataset:", args.dataset)
print("generated data:", args.generated_feature, ", alphaml score:",
clf.score(dm.val_X, dm.val_y))
