import arboretum
import numpy as np
from sklearn.datasets import load_boston
import xgboost
def rmse(y, y_hat):
diff = np.power(y - y_hat, 2)
return np.sqrt(np.sum(diff))
# load test data
boston = load_boston()
n = 10000
# create data matrix
data = arboretum.DMatrix(boston.data[0:n], y=boston.target[0:n])
y = boston.target[0:n]
# init model
model = arboretum.Garden('reg:linear', data, 6, 2, 1, 0.5)
# grow trees
for i in xrange(5):
model.grow_tree()
# predict on train data set
pred = model.predict(data)
# print first n records
print pred[0:10]
import arboretum
import numpy as np
from sklearn.datasets import load_iris
import xgboost
import json
# load test data
iris = load_iris()
n = 10000
index = iris.target != 2
y = iris.target[index][0:n]
# create data matrix
data = arboretum.DMatrix(iris.data[index, 0:n], y=y)
config = json.dumps({
'objective': 1,
'verbose': {
'gpu': True
},
'tree': {
'eta': 0.2,
'max_depth': 6,
'gamma': 0.0,
'min_child_weight': 2.0,
'min_leaf_size': 0,
'colsample_bytree': 1.0,
'colsample_bylevel': 1.0,
'lambda': 0.0,
'alpha': 0.0
'tree':
{
'eta': 0.01,
'max_depth': 10,
'gamma': 0.0,
'min_child_weight': 20.0,
'min_leaf_size': 0,
'colsample_bytree': 0.6,
'colsample_bylevel': 0.6,
'lambda': 0.1,
'gamma_relative': 0.0001
}})
print(config)
data = arboretum.DMatrix(data, data_category=data_categoties, y=labels)
data_val = arboretum.DMatrix(data_val, data_category=data_categoties_val)
model = arboretum.Garden(config, data)
print('training...')
# grow trees
for i in range(7400):
print('tree', i)
model.grow_tree()
model.append_last_tree(data_val)
if i % 20 == 0:
pred = model.get_y(data)
print('train', sklearn.metrics.log_loss(labels, pred, eps=1e-6), roc_auc_score(labels, pred))
# load test data
boston = load_boston()
n = 4000
categoties = [3]
data_categories = []
for item in categoties:
data_categories.append(convert2category(boston.data[:, item]))
data_categories = np.stack(data_categories, axis=-1)
data_source = boston.data[:, 4:5]
# create data matrix
data = arboretum.DMatrix(data_source[0:n],
data_category=data_categories,
y=boston.target[0:n])
y = boston.target[0:n]
config = json.dumps({
'objective': 0,
'internals': {
'double_precision': True,
'compute_overlap': 2
},
'verbose': {
'gpu': True
},
'tree': {
'eta': 0.5,
'max_depth': 10,
import arboretum
import numpy as np
from sklearn.datasets import load_iris
import xgboost
import json
# load test data
iris = load_iris()
n = 10000
y = iris.target[0:n]
# create data matrix
data = arboretum.DMatrix(iris.data[:, 0:n], labels=y)
config = json.dumps({
'objective': 3,
'verbose': {
'gpu': True,
'booster': True
},
'tree': {
'labels_count': 3,
'eta': 0.2,
'max_depth': 6,
'gamma': 0.0,
'min_child_weight': 2.0,
'min_leaf_size': 0,
'colsample_bytree': 1.0,
'colsample_bylevel': 1.0,
'lambda': 0.0,
'alpha': 0.0,
import arboretum
import numpy as np
from sklearn.datasets import load_iris
import xgboost
import json
# load test data
iris = load_iris()
n = 10000
index = iris.target != 2
y = iris.target[index][0:n]
# create data matrix
data = arboretum.DMatrix(iris.data[index, 0:n], y=y)
config = json.dumps({
'objective': 1,
'verbose': {
'gpu': True
},
'tree': {
'eta': 0.2,
'max_depth': 6,
'gamma': 0.0,
'min_child_weight': 2.0,
'min_leaf_size': 0,
'colsample_bytree': 1.0,
'colsample_bylevel': 1.0,
'lambda': 0.0,
'alpha': 0.0