Python实现gcForest模型

# 导入必要的模块
from gcforest.gcforest import GCForest

# 初始化一个gcForest对象
gc = GCForest(config) # config是一个字典结构

# gcForest模型最后一层每个估计器预测的概率concatenated的结果
X_train_enc = gc.fit_transform(X_train,y_train)

# 测试集的预测
y_pred = gc.predict(X_test)

# 导入必要的模块

import argparse # 命令行参数调用模块
import numpy as np 
import sys
from keras.datasets import mnist # MNIST数据集
import pickle
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
sys.path.insert(0, "lib")

from gcforest.gcforest import GCForest
from gcforest.utils.config_utils import load_json


def parse_args():
	'''
	解析终端命令行参数(model)
	'''
    parser = argparse.ArgumentParser()
    parser.add_argument("--model", dest="model", type=str, default=None, 
	help="gcfoest Net Model File")
    args = parser.parse_args()
    return args


def get_toy_config():
	'''
	生成级联结构的相关结构
	'''
    config = {}
    ca_config = {}
    ca_config["random_state"] = 0
    ca_config["max_layers"] = 100
    ca_config["early_stopping_rounds"] = 3
    ca_config["n_classes"] = 10
    ca_config["estimators"] = []
    ca_config["estimators"].append(
            {"n_folds": 5, "type": "XGBClassifier", "n_estimators": 10, 
		"max_depth": 5,"objective": "multi:softprob", "silent": 
		True, "nthread": -1, "learning_rate": 0.1} )
    ca_config["estimators"].append({"n_folds": 5, "type": "RandomForestClassifier", 
	"n_estimators": 10, "max_depth": None, "n_jobs": -1})
    ca_config["estimators"].append({"n_folds": 5, "type": "ExtraTreesClassifier",
	 "n_estimators": 10, "max_depth": None, "n_jobs": -1})
    ca_config["estimators"].append({"n_folds": 5, "type": "LogisticRegression"})
    config["cascade"] = ca_config
    return config

# get_toy_config()生成的结构，如下所示：

'''
{
"cascade": {
    "random_state": 0,
    "max_layers": 100,
    "early_stopping_rounds": 3,
    "n_classes": 10,
    "estimators": [
        {"n_folds":5,"type":"XGBClassifier","n_estimators":10,"max_depth":5,
		"objective":"multi:softprob", "silent":true, 
		"nthread":-1, "learning_rate":0.1},
        {"n_folds":5,"type":"RandomForestClassifier","n_estimators":10,
		"max_depth":null,"n_jobs":-1},
        {"n_folds":5,"type":"ExtraTreesClassifier","n_estimators":10,
		"max_depth":null,"n_jobs":-1},
        {"n_folds":5,"type":"LogisticRegression"}
    ]
}
}
'''

if __name__ == "__main__":
    args = parse_args()
    if args.model is None:
        config = get_toy_config()
    else:
        config = load_json(args.model)

    gc = GCForest(config)
    # 如果模型消耗太大内存，可以使用如下命令使得gcforest不保存在内存中
    # gc.set_keep_model_in_mem(False), 默认情况下是True.

    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    # X_train, y_train = X_train[:2000], y_train[:2000]
    # np.newaxis相当于增加了一个维度
    X_train = X_train[:, np.newaxis, :, :]
    X_test = X_test[:, np.newaxis, :, :]


    X_train_enc = gc.fit_transform(X_train, y_train)
    # X_enc是gcForest模型最后一层每个估计器预测的概率concatenated的结果
    # X_enc.shape =
    #   (n_datas, n_estimators * n_classes): 如果是级联结构
    #   (n_datas, n_estimators * n_classes, dimX, dimY): 如果只有多粒度扫描结构

    # 可以在fit_transform方法中加入X_test,y_test,这样测试数据的准确率在训练的过程中
    # 也会被记录下来。
    # X_train_enc, X_test_enc = 
	gc.fit_transform(X_train, y_train, X_test=X_test, y_test=y_test)

    # 注意: 如果设置了gc.set_keep_model_in_mem(True),必须使用
    # gc.fit_transform(X_train, y_train, X_test=X_test, y_test=y_test)
    # 评估模型

    # 测试集预测与评估
    y_pred = gc.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print("Test Accuracy of GcForest = {:.2f} %".format(acc * 100))

    # 可以使用gcForest得到的X_enc数据进行其他模型的训练比如xgboost/RF
    # 数据的concat
    X_test_enc = gc.transform(X_test)
    X_train_enc = X_train_enc.reshape((X_train_enc.shape[0], -1))
    X_test_enc = X_test_enc.reshape((X_test_enc.shape[0], -1))
    X_train_origin = X_train.reshape((X_train.shape[0], -1))
    X_test_origin = X_test.reshape((X_test.shape[0], -1))
    X_train_enc = np.hstack((X_train_origin, X_train_enc))
    X_test_enc = np.hstack((X_test_origin, X_test_enc))

    print("X_train_enc.shape={}, X_test_enc.shape={}".format(X_train_enc.shape,
	 X_test_enc.shape))

    # 训练一个RF
    clf = RandomForestClassifier(n_estimators=1000, max_depth=None, n_jobs=-1)
    clf.fit(X_train_enc, y_train)
    y_pred = clf.predict(X_test_enc)
    acc = accuracy_score(y_test, y_pred)
    print("Test Accuracy of Other classifier using 
	gcforest's X_encode = {:.2f} %".format(acc * 100))

    # 模型写入pickle文件
    with open("test.pkl", "wb") as f:
        pickle.dump(gc, f, pickle.HIGHEST_PROTOCOL)

    # 加载训练的模型
    with open("test.pkl", "rb") as f:
        gc = pickle.load(f)
    y_pred = gc.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print("Test Accuracy of GcForest (save and load) = {:.2f} %".format(acc * 100))

config = load_json(your_json_file)
gc = GCForest(config)