GBDT + LR 推荐算法实践

理论

包含CART、GBDT、LR，我得抽时间好好写一下。

代码

• 安装​

  ​lightgbm​

  ​
• 安装​

  ​lightgbm​

  ​​的依赖​

  ​brew install libomp​

  ​​，不安装会报错​

  ​brew install libomp​

  ​

import lightgbm as lgb
import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.datasets import  make_classification
from sklearn.linear_model import LogisticRegression

print('Load data...')
iris = load_iris()
data = iris.data
target = iris.target
print("Target:",target)
x_train,x_test,y_train,y_test = train_test_split(data,target,test_size=0.2)

lgb_train = lgb.Dataset(x_train, y_train)
lgb_eval = lgb.Dataset(x_test, y_test, reference=lgb_train)

params = {
    'task': 'train',
    'boosting_type': 'gbdt',  # 提升类型
    'objective': 'binary',  # 目标函数
    'metric': {'binary_logloss'},  # 评估函数
    'num_leaves': 31,
    'num_trees': 100,
    'learning_rate': 0.01,
    'feature_fraction': 0.9,  # 建树的样本选择比例
    'bagging_fraction': 0.8,  # 建树的样本采样比例
    'bagging_freq': 5,
    'verbose': 0
}
print('Start training...')

gbm = lgb.train(params,
                lgb_train,
                num_boost_round=100,
                valid_sets=lgb_train)

print('Save model...')
gbm.save_model('model.txt')

print('Start predicting...')

# predict and get data on leaves, training data
y_pred = gbm.predict(x_train, pred_leaf=True)
print(np.array(y_pred).shape)
print(y_pred[0])
print('Writing transformed training data')
num_leaf = 31

transformed_training_matrix = np.zeros([len(y_pred), len(y_pred[0]) * num_leaf],
                                       dtype=np.int64)  # N * num_tress * num_leafs
# 生成one-hot
for i in range(0, len(y_pred)):
    temp = np.arange(len(y_pred[0])) * num_leaf + np.array(y_pred[i])
    transformed_training_matrix[i][temp] += 1


y_pred = gbm.predict(x_test, pred_leaf=True)
print('Writing transformed testing data')
transformed_testing_matrix = np.zeros([len(y_pred), len(y_pred[0]) * num_leaf], dtype=np.int64)
for i in range(0, len(y_pred)):
    temp = np.arange(len(y_pred[0])) * num_leaf + np.array(y_pred[i])
    transformed_testing_matrix[i][temp] += 1


lm = LogisticRegression(penalty='l2',C=0.05)  # logestic model construction
lm.fit(transformed_training_matrix,y_train)  # fitting the data
y_pred_test = lm.predict_proba(transformed_testing_matrix)   # Give the probabilty on each label

print(y_pred_test)

NE = (-1) / len(y_pred_test) * sum(((1+y_test)/2 * np.log(y_pred_test[:,1]) + (1-y_test)/2 * np.log(1 - y_pred_test[:,1])))
print("Normalized Cross Entropy " + str(NE))