【LightGBM】LightGBM实战分类小实验

打天池时突然意识到自己不是很了解LightGBM，所以根据教程，做了个LightGBM的实战小实验。

基本包，没有的pip install。

import datetime
import numpy as np
import pandas as pd
import lightgbm as lgb
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

为了打印方便，声明一个打印str的函数

def printlog(info):
    nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    print("n"+"=========="*8 + "%s" % nowtime)
    print(info+'...nn')

直接使用sklearn封装好的乳腺癌数据。

printlog("step1: reading data...")

# 读取dftrain,dftest
breast = datasets.load_breast_cancer()
df = pd.Dataframe(breast.data,columns = [x.replace(' ','_') for x in breast.feature_names])
df['label'] = breast.target
df['mean_radius'] = df['mean_radius'].apply(lambda x:int(x))
df['mean_texture'] = df['mean_texture'].apply(lambda x:int(x))
dftrain,dftest = train_test_split(df)

categorical_features = ['mean_radius','mean_texture']
lgb_train = lgb.Dataset(dftrain.drop(['label'],axis = 1),label=dftrain['label'],
                        categorical_feature = categorical_features)

lgb_valid = lgb.Dataset(dftest.drop(['label'],axis = 1),label=dftest['label'],
                        categorical_feature = categorical_features,
                        reference=lgb_train)

printlog("step2: setting parameters...")
                               
boost_round = 50                   
early_stop_rounds = 10

params = {
    'boosting_type': 'gbdt',
    'objective':'binary',
    'metric': ['auc'],
    'num_leaves': 31,   
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
}

printlog("step3: training model...")

results = {}
gbm = lgb.train(params,
                lgb_train,
                num_boost_round= boost_round,
                valid_sets=(lgb_valid, lgb_train),
                valid_names=('validate','train'),
                early_stopping_rounds = early_stop_rounds,
                evals_result= results)

printlog("step4: evaluating model ...")

y_pred_train = gbm.predict(dftrain.drop('label',axis = 1), num_iteration=gbm.best_iteration)
y_pred_test = gbm.predict(dftest.drop('label',axis = 1), num_iteration=gbm.best_iteration)

print('train accuracy: {:.5} '.format(accuracy_score(dftrain['label'],y_pred_train>0.5)))
print('valid accuracy: {:.5} n'.format(accuracy_score(dftest['label'],y_pred_test>0.5)))

lgb.plot_metric(results)
lgb.plot_importance(gbm,importance_type = "gain")

效果很不错，96%左右的准确率。

printlog("step5: saving model ...")

model_dir = "./gbm.model"
print("model_dir: %s"%model_dir)
gbm.save_model("data/gbm.model")