def LR(X_train, y_train, X_val, y_val):
linear_model = xl.LRModel(task='binary',
epoch=100,
lr=0.005,
reg_lambda=1.0,
opt='adagrad',
nthread=8,
metric='auc')
linear_model.fit(X_train, y_train, eval_set=[X_val, y_val])
y_pred = linear_model.predict(X_val)
return y_pred
def __init__(self):
self.xgb_model = xgb.XGBClassifier(max_depth=5,
learning_rate=0.01,
subsample=0.9,
colsample_bylevel=0.5,
verbosity=2)
self.lr_model = xl.LRModel(task='binary',
init=0.1,
epoch=100,
lr=0.01,
reg_lambda=0.1,
opt='sgd',
stop_window=4)
"""
Use sklearn api
"""
import xlearn as xl
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score, accuracy_score
data = load_iris()
X = data["data"]
y = data["target"] == 2
if __name__ == '__main__':
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
lr = xl.LRModel(task="binary", init=0.1, epoch=10, lr=0.1, reg_lambda=1.0, opt="sgd")
lr.fit(X_train, y_train, eval_set=[X_test, y_test], is_lock_free=False)
y_score = lr.predict(X_test)
y_pred = y_score >= 0.5
auc = roc_auc_score(y_test, y_score)
acc = accuracy_score(y_test, y_pred)
print(f"Auc.: {auc}, Acc.: {acc}")
# Load dataset
iris_data = load_iris()
X = iris_data['data']
y = (iris_data['target'] == 2)
X_train, X_val, y_train, y_val = train_test_split(X,
y,
test_size=0.3,
random_state=0)
# param:
# 0. binary classification
# 1. model scale: 0.1
# 2. epoch number: 10 (auto early-stop)
# 3. learning rate: 0.1
# 4. regular lambda: 1.0
# 5. use sgd optimization method
linear_model = xl.LRModel(task='binary',
init=0.1,
epoch=10,
lr=0.1,
reg_lambda=1.0,
opt='sgd')
# Start to train
linear_model.fit(X_train, y_train, eval_set=[X_val, y_val], is_lock_free=False)
# Generate predictions
y_pred = linear_model.predict(X_val)
import xlearn as xl
import pandas as pd
df = pd.read_csv('test/support/data.txt',
sep=' ',
names=['y', 'x0', 'x1', 'x2', 'x3'])
X = df.drop(columns=['y'])
y = df['y']
model = xl.LRModel(task='reg', nthread=1, opt='adagrad')
model.fit(X, y)
print('predict', model.predict(X)[0:6].tolist())
model = xl.LRModel(task='reg', nthread=1, opt='adagrad')
model.fit('test/support/data.txt')
print('predict txt', model.predict('test/support/data.txt')[0:6].tolist())
model = xl.LRModel(task='reg', nthread=1, opt='adagrad')
model.fit('test/support/data.csv')
print('predict csv', model.predict('test/support/data.csv')[0:6].tolist())
import xlearn as xl
model = xl.LRModel(task="reg")
model.fit("test/data/boston/boston.csv")
print(model.predict("test/data/boston/boston.csv")[:5])
