LightGBM实战
数据集地址
- 分类:http://archive.ics.uci.edu/ml/datasets/Iris
部分数据:
- 回归:利用sklearn函数直接生成
基于原生LightGBM的分类
首先得安装相关的库:pip install lightgbm
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
import lightgbm as lgb
import numpy as np
# 以分隔符,读取文件,得到的是一个二维列表
iris = np.loadtxt('iris.data', dtype=str, delimiter=',', unpack=False, encoding='utf-8')
# 前4列是特征
data = iris[:, :4].astype(np.float)
# 最后一列是标签,我们将其转换为二维列表
target = iris[:, -1][:, np.newaxis]
# 对标签进行onehot编码后还原成数字
enc = OneHotEncoder()
target = enc.fit_transform(target).astype(np.int).toarray()
target = [list(oh).index(1) for oh in target]
# 划分训练数据和测试数据
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1)
# 转换为Dataset数据格式
train_data = lgb.Dataset(X_train, label=y_train)
validation_data = lgb.Dataset(X_test, label=y_test)
# 参数
params = {
'learning_rate': 0.1,
'lambda_l1': 0.1,
'lambda_l2': 0.2,
'max_depth': 4,
'objective': 'multiclass', # 目标函数
'num_class': 3,
}
# 模型训练
gbm = lgb.train(params, train_data, valid_sets=[validation_data])
# 模型预测
y_pred = gbm.predict(X_test)
y_pred = [list(x).index(max(x)) for x in y_pred]
print(y_pred)
# 模型评估
print(accuracy_score(y_test, y_pred))
结果
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[99] valid_0's multi_logloss: 0.264218
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[100] valid_0's multi_logloss: 0.264481
[0, 1, 1, 0, 2, 1, 2, 0, 0, 2, 1, 0, 2, 1, 1, 0, 1, 1, 0, 0, 1, 1, 2, 0, 2, 1, 0, 0, 1, 2]
0.9666666666666667
基于sklearn接口的分类
使用基本参数进行分类
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from lightgbm import LGBMClassifier
from sklearn.externals import joblib
import numpy as np
# 以分隔符,读取文件,得到的是一个二维列表
iris = np.loadtxt('iris.data', dtype=str, delimiter=',', unpack=False, encoding='utf-8')
# 前4列是特征
data = iris[:, :4].astype(np.float)
# 最后一列是标签,我们将其转换为二维列表
target = iris[:, -1][:, np.newaxis]
# 对标签进行onehot编码后还原成数字
enc = OneHotEncoder()
target = enc.fit_transform(target).astype(np.int).toarray()
target = [list(oh).index(1) for oh in target]
# 划分训练数据和测试数据
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1)
# 模型训练
gbm = LGBMClassifier(num_leaves=31, learning_rate=0.05, n_estimators=20)
gbm.fit(X_train, y_train, eval_set=[(X_test, y_test)], early_stopping_rounds=5)
# 模型存储
joblib.dump(gbm, 'loan_model.pkl')
# 模型加载
gbm = joblib.load('loan_model.pkl')
# 模型预测
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)
# 模型评估
print('The accuracy of prediction is:', accuracy_score(y_test, y_pred))
# 特征重要度
print('Feature importances:', list(gbm.feature_importances_))
结果
[1] valid_0's multi_logloss: 1.04105
Training until validation scores don't improve for 5 rounds
[2] valid_0's multi_logloss: 0.969489
[3] valid_0's multi_logloss: 0.903964
[4] valid_0's multi_logloss: 0.845211
[5] valid_0's multi_logloss: 0.793714
[6] valid_0's multi_logloss: 0.742919
[7] valid_0's multi_logloss: 0.698058
[8] valid_0's multi_logloss: 0.659407
[9] valid_0's multi_logloss: 0.621686
[10] valid_0's multi_logloss: 0.588324
[11] valid_0's multi_logloss: 0.556705
[12] valid_0's multi_logloss: 0.52607
[13] valid_0's multi_logloss: 0.501139
[14] valid_0's multi_logloss: 0.476254
[15] valid_0's multi_logloss: 0.454358
[16] valid_0's multi_logloss: 0.433247
[17] valid_0's multi_logloss: 0.41494
[18] valid_0's multi_logloss: 0.395876
[19] valid_0's multi_logloss: 0.378817
[20] valid_0's multi_logloss: 0.364502
Did not meet early stopping. Best iteration is:
[20] valid_0's multi_logloss: 0.364502
The accuracy of prediction is: 0.9333333333333333
Feature importances: [12, 15, 129, 56]
使用参数搜索进行分类
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import OneHotEncoder
from lightgbm import LGBMClassifier
from sklearn.externals import joblib
import numpy as np
# 以分隔符,读取文件,得到的是一个二维列表
iris = np.loadtxt('iris.data', dtype=str, delimiter=',', unpack=False, encoding='utf-8')
# 前4列是特征
data = iris[:, :4].astype(np.float)
# 最后一列是标签,我们将其转换为二维列表
target = iris[:, -1][:, np.newaxis]
# 对标签进行onehot编码后还原成数字
enc = OneHotEncoder()
target = enc.fit_transform(target).astype(np.int).toarray()
target = [list(oh).index(1) for oh in target]
# 划分训练数据和测试数据
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=1)
# 网格搜索,参数优化
estimator = LGBMClassifier(num_leaves=31)
param_grid = {
'learning_rate': [0.01, 0.1, 1],
'n_estimators': [20, 40]
}
gbm = GridSearchCV(estimator, param_grid)
gbm.fit(X_train, y_train)
print('Best parameters found by grid search are:', gbm.best_params_)
结果
Best parameters found by grid search are: {'learning_rate': 0.1, 'n_estimators': 20}
基于原生LightGBM的回归
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
import lightgbm as lgb
from sklearn.metrics import mean_absolute_error
X, y = make_regression(n_samples=100, n_features=1, noise=20)
print(X,y)
# 切分训练集、测试集
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.25, random_state=1)
# 转换为Dataset数据格式
lgb_train = lgb.Dataset(train_X, train_y)
lgb_eval = lgb.Dataset(test_X, test_y, reference=lgb_train)
# 参数
params = {
'task': 'train',
'boosting_type': 'gbdt', # 设置提升类型
'objective': 'regression', # 目标函数
'metric': {'l2', 'auc'}, # 评估函数
'num_leaves': 31, # 叶子节点数
'learning_rate': 0.05, # 学习速率
'feature_fraction': 0.9, # 建树的特征选择比例
'bagging_fraction': 0.8, # 建树的样本采样比例
'bagging_freq': 5, # k 意味着每 k 次迭代执行bagging
'verbose': 1 # <0 显示致命的, =0 显示错误 (警告), >0 显示信息
}
# 调用LightGBM模型,使用训练集数据进行训练(拟合)
# Add verbosity=2 to print messages while running boosting
my_model = lgb.train(params, lgb_train, num_boost_round=20, valid_sets=lgb_eval, early_stopping_rounds=5)
# 使用模型对测试集数据进行预测
predictions = my_model.predict(test_X, num_iteration=my_model.best_iteration)
# 对模型的预测结果进行评判(平均绝对误差)
print("Mean Absolute Error : " + str(mean_absolute_error(predictions, test_y)))
结果
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[9] valid_0's auc: 0.873377 valid_0's l2: 1521.21
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[10] valid_0's auc: 0.873377 valid_0's l2: 1448
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[11] valid_0's auc: 0.873377 valid_0's l2: 1394.27
Early stopping, best iteration is:
[6] valid_0's auc: 0.873377 valid_0's l2: 1796.72
Mean Absolute Error : 32.371899328245405
基于sklearn接口的回归
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
import lightgbm as lgb
from sklearn.metrics import mean_absolute_error
X, y = make_regression(n_samples=100, n_features=1, noise=20)
# 切分训练集、测试集
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.25, random_state=1)
# 调用LightGBM模型,使用训练集数据进行训练(拟合)
# Add verbosity=2 to print messages while running boosting
my_model = lgb.LGBMRegressor(objective='regression', num_leaves=31, learning_rate=0.05, n_estimators=20,
verbosity=2)
my_model.fit(train_X, train_y, verbose=False)
# 使用模型对测试集数据进行预测
predictions = my_model.predict(test_X)
# 对模型的预测结果进行评判(平均绝对误差)
print("Mean Absolute Error : " + str(mean_absolute_error(predictions, test_y)))
结果
[LightGBM] [Debug] Dataset::GetMultiBinFromAllFeatures: sparse rate 0.000000
[LightGBM] [Debug] init for col-wise cost 0.000011 seconds, init for row-wise cost 0.000109 seconds
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000126 seconds.
You can set force_col_wise=true
to remove the overhead.
[LightGBM] [Info] Total Bins 27
[LightGBM] [Info] Number of data points in the train set: 75, number of used features: 1
[LightGBM] [Info] Start training from score 10.744539
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 2 and max_depth = 1
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 2 and max_depth = 1
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 2 and max_depth = 1
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 2 and max_depth = 1
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 2 and max_depth = 1
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Debug] Trained a tree with leaves = 3 and max_depth = 2
Mean Absolute Error : 18.71203698086779