def setUp(self):
windows = [Window(7, 7, 2, 2, 0, 0),
Window(11, 11, 2, 2, 0, 0)]
rf1 = ExtraRandomForestConfig(n_estimators=40, min_samples_leaf=10)
rf2 = RandomForestConfig(n_estimators=40, min_samples_leaf=10)
est_for_windows = [[rf1, rf2],
[rf1, rf2]]
self.mgs = MultiGrainScanLayer(windows=windows,
est_for_windows=est_for_windows,
n_class=10)
pools = [[MaxPooling(), MaxPooling()],
[MaxPooling(), MaxPooling()]]
self.poolayer = PoolingLayer(pools=pools)
self.concat_layer = ConcatLayer()
self.est_configs = [
ExtraRandomForestConfig(n_estimators=40),
ExtraRandomForestConfig(n_estimators=40),
RandomForestConfig(n_estimators=40),
RandomForestConfig(n_estimators=40)
]
self.cascade = CascadeLayer(est_configs=self.est_configs,
n_classes=10,
keep_in_mem=True,
data_save_dir=osp.join(get_data_save_base(), 'test_layer', 'cascade'))
self.auto_cascade = AutoGrowingCascadeLayer(est_configs=self.est_configs,
early_stopping_rounds=3,
data_save_rounds=4,
stop_by_test=True,
n_classes=10,
data_save_dir=osp.join(get_data_save_base(),
'test_layer', 'auto_cascade'))
def _init(self, distribute=False):
self.est_configs = [
ExtraRandomForestConfig(n_estimators=20),
ExtraRandomForestConfig(n_estimators=20),
RandomForestConfig(n_estimators=20),
RandomForestConfig(n_estimators=20)
]
gc = CascadeLayer(est_configs=self.est_configs,
n_classes=2,
data_save_dir=osp.join(get_data_save_base(), 'test_layer', 'cascade'),
distribute=distribute)
agc = AutoGrowingCascadeLayer(est_configs=self.est_configs,
early_stopping_rounds=2,
stop_by_test=False,
data_save_rounds=4,
n_classes=2,
data_save_dir=osp.join(get_data_save_base(),
'test_layer', 'auto_cascade'),
distribute=distribute)
return gc, agc
def _init(self):
self.est_configs = [
ExtraRandomForestConfig(n_estimators=40),
ExtraRandomForestConfig(n_estimators=40),
RandomForestConfig(n_estimators=40),
RandomForestConfig(n_estimators=40)
]
windows = [Window(7, 7, 2, 2, 0, 0), Window(11, 11, 2, 2, 0, 0)]
rf1 = ExtraRandomForestConfig(min_samples_leaf=10)
rf2 = RandomForestConfig(min_samples_leaf=10)
est_for_windows = [[rf1, rf2], [rf1, rf2]]
mgs = MultiGrainScanLayer(dtype=np.float32,
windows=windows,
est_for_windows=est_for_windows,
n_class=10)
pools = [[Pooling(2, 2, "max"),
Pooling(2, 2, "max")],
[Pooling(2, 2, "max"),
Pooling(2, 2, "max")]]
poolayer = PoolingLayer(pools=pools)
concat_layer = ConcatLayer()
auto_cascade = AutoGrowingCascadeLayer(
est_configs=self.est_configs,
early_stopping_rounds=2,
stop_by_test=False,
data_save_rounds=4,
n_classes=10,
data_save_dir=osp.join(get_data_save_base(), 'test_graph',
'auto_cascade'))
return mgs, poolayer, concat_layer, auto_cascade
print('x_test.shape: {}'.format(x_test.shape))
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'uci_yeast')
model_save_dir = osp.join(get_model_save_base(), 'uci_yeast')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=10,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=False,
seed=0)
model = Graph()
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
print("time cost: {}".format(time.time() - start_time))
"""
# Copyright 2017 Authors NJU PASA BigData Laboratory.
# Authors: Qiu Hu <huqiu00#163.com>
# License: Apache-2.0
from __future__ import print_function
from keras.datasets import boston_housing
from forestlayer.estimators.estimator_configs import ExtraRandomForestConfig, RandomForestConfig, GBDTConfig
from forestlayer.layers.layer import AutoGrowingCascadeLayer
(x_train, y_train), (x_test, y_test) = boston_housing.load_data(test_split=0.25)
print("x_train: {}".format(x_train.shape))
print("x_test: {}".format(x_test.shape))
est_configs = [
RandomForestConfig(),
ExtraRandomForestConfig(),
GBDTConfig()
]
cascade = AutoGrowingCascadeLayer(task='regression',
est_configs=est_configs,
early_stopping_rounds=3,
keep_in_mem=False)
cascade.fit_transform(x_train, y_train, x_test, y_test)
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'uci_iris')
model_save_dir = osp.join(get_model_save_base(), 'uci_iris')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=3,
stop_by_test=False,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=False,
dis_level=0,
verbose_dis=False,
seed=0)
model = Graph()
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
print("time cost: {}".format(time.time() - start_time))
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import AdaBoostRegressor
from forestlayer.estimators.estimator_configs import RandomForestConfig, ExtraRandomForestConfig
from forestlayer.layers.layer import AutoGrowingCascadeLayer
rng = np.random.RandomState(1)
X = np.linspace(0, 6, 100)[:, np.newaxis]
y = np.sin(X).ravel() + np.sin(6 * X).ravel() + rng.normal(0, 0.1, X.shape[0])
est_configs = [RandomForestConfig(), ExtraRandomForestConfig()]
cascade = AutoGrowingCascadeLayer(task='regression',
est_configs=est_configs,
early_stopping_rounds=3,
keep_in_mem=True)
cascade.fit(X, y)
y1 = cascade.predict(X)
y1 = y1.reshape(-1)
abr = AdaBoostRegressor(DecisionTreeRegressor(max_depth=4),
n_estimators=300,
random_state=rng)
abr.fit(X, y)
y2 = abr.predict(X)
# Plot the results
plt.figure()
plt.scatter(X, y, c="k", label="training samples")
plt.plot(X, y2, c="g", label="n_estimators=300", linewidth=1.5)
rf2 = RandomForestConfig(n_folds=3, min_samples_leaf=10)
est_for_windows = [[rf1, rf2], [rf1, rf2], [rf1, rf2]]
mgs = MultiGrainScanLayer(windows=windows,
est_for_windows=est_for_windows,
n_class=6)
pools = [[MeanPooling(), MeanPooling()], [MeanPooling(),
MeanPooling()],
[MeanPooling(), MeanPooling()]]
pool_layer = PoolingLayer(pools=pools)
concat_layer = ConcatLayer()
est_configs = Basic4x2()
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=6,
look_index_cycle=[[0, 1], [2, 3],
[4, 5]])
model = Graph()
model.add(mgs)
model.add(pool_layer)
# model.add(concat_layer)
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(n_estimators=100),
RandomForestConfig(n_estimators=100),
GBDTConfig(n_estimators=100),
GBDTConfig(n_estimators=100),
# XGBRegressorConfig(),
# XGBRegressorConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'tianchi', 'intelmanu')
agc = AutoGrowingCascadeLayer(task='regression',
est_configs=est_configs,
max_layers=1,
data_save_dir=data_save_dir,
keep_test_result=True)
agc.fit_transform(feat_dim_120[:500], label, feat_dim_120[500:])
result = agc.test_results
true_A = pd.read_csv(osp.join(get_dataset_dir(), 'tianchi', 'intelmanu',
'true_A_20180114.csv'),
header=None)
true = true_A.iloc[:, 1]
print("MSE Score: {}".format(mse(result, true)))
# ret = pd.DataFrame()
print('x_train.shape', x_train.shape, x_train.dtype)
print('x_test.shape', x_test.shape, x_test.dtype)
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'imdb')
model_save_dir = osp.join(get_model_save_base(), 'imdb')
cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
stop_by_test=True,
n_classes=2,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=True,
dis_level=0,
seed=0)
cascade.fit_transform(x_train, y_train, x_test, y_test)
print("Time cost: {}".format(time.time() - start_time))
# ray.init(redis_address="192.168.x.x:6379")
(x_train, y_train, x_test, y_test) = uci_adult.load_data()
start_time = time.time()
est_configs = [
ExtraRandomForestConfig(n_jobs=-1),
ExtraRandomForestConfig(n_jobs=-1),
ExtraRandomForestConfig(n_jobs=-1),
ExtraRandomForestConfig(n_jobs=-1),
RandomForestConfig(n_jobs=-1),
RandomForestConfig(n_jobs=-1),
RandomForestConfig(n_jobs=-1),
RandomForestConfig(n_jobs=-1)
]
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=2,
distribute=True,
seed=0)
model = Graph()
model.add(auto_cascade)
model.summary()
model.fit_transform(x_train, y_train, x_test, y_test)
end_time = time.time()
print('time cost: {}'.format(end_time - start_time))