XGBoost、LightGBM和CatBoost的同与不同

from catboost import CatBoostRegressor
cat_feature = [0,1,2]
train_data = [['a','b',1,4,5,6],['a','b',4,5,6,7],['c','d',30,40,50,60]]
test_data = [['a','b',2,4,6,8],['a','d',1,4,50,60]]
train_labels = [10,20,30]
model = CatBoostRegressor(iteration = 2,learning_rate = 1,depth = 2)
model.fit(train_data,train_labels,cat_feature)

import pandas as pd, numpy as np, time
from sklearn.model_selection import train_test_split
path = '../input/'
data = pd.read_csv(path +"flights.csv")
data = data.sample(frac = 0.1, random_state=10)
#提取所需字段
data=data[["MONTH","DAY","DAY_OF_WEEK","AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT","ORIGIN_AIRPORT","AIR_TIME","DEPARTURE_TIME","DISTANCE","ARRIVAL_DELAY"]]

data.dropna(inplace=True)
data["ARRIVAL_DELAY"] = (data["ARRIVAL_DELAY"]>10)*1
cols = ["AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT","ORIGIN_AIRPORT"]
for item in cols:
    data[item] = data[item].astype("category").cat.codes +1
# 数据划分
train, test, y_train,y_test=train_test_split(data.drop(["ARRIVAL_DELAY"], axis=1), data["ARRIVAL_DELAY"],random_state=10, test_size=0.25)

import xgboost as xgb
from sklearn.metrics import roc_auc_score
from sklearn.grid_search import GridSearchCV
# auc
def auc(m, train, test):
	train_auc = roc_auc_score(y_train,m.predict_proba(train)[:,1]
	test_auc  = roc_auc_score(y_test,m.predict_proba(test)[:,1]
	return (train_auc,test_auc)

# Parameter Tuning
model = xgb.XGBClassifier()
# 参数空间
param_dist = {"max_depth": [10,30,50],
              "min_child_weight" : [1,3,6],
              "n_estimators": [200],
              "learning_rate": [0.05, 0.1,0.16],}
# cv调参
grid_search=GridSearchCV(model,
						param_grid=param_dist,
						cv=3,
						verbose=10,
						n_jobs=-1)
grid_search.fit(train, y_train)
# 返回最佳迭代
print(grid_search.best_estimator_)
# 拟合训练数据
model = xgb.XGBClassifier(max_depth=50,
						  min_child_weight=1,
						  n_estimators=200,
                          n_jobs=-1 ,
                          verbose=1,
                          learning_rate=0.16)
model.fit(train,y_train)
print(auc(model, train, test))

import lightgbm as lgb
from sklearn import metrics

def auc2(m, train, test):
	train_auc = roc_auc_score(y_train,m.predict(train))
	test_auc  = roc_auc_score(y_test,m.predict(test))
	return (train_auc,test_auc)
# 初始化lgb函数
lg = lgb.LGBMClassifier(silent=False)
param_dist = {"max_depth": [25,50, 75],
              "learning_rate" : [0.01,0.05,0.1],
              "num_leaves": [300,900,1200],
              "n_estimators": [200]
             }
grid_search = GridSearchCV(lg,
							n_jobs=-1,
							param_grid=param_dist,
							cv = 3,
							scoring="roc_auc",
							verbose=5)
grid_search.fit(train,y_train)
print(grid_search.best_estimator_)
d_train = lgb.Dataset(train, label=y_train)
# 参数空间
params = {"max_depth": 50,
		"learning_rate" : 0.1,
		"num_leaves": 900,
        "n_estimators": 300}

# Without Categorical Features
model2 = lgb.train(params, d_train)
print(auc2(model2, train, test))

#With Catgeorical Features
cate_features_name = ["MONTH","DAY","DAY_OF_WEEK","AIRLINE","DESTINATION_AIRPORT",
 "ORIGIN_AIRPORT"]
model2 = lgb.train(params, d_train, categorical_feature = cate_features_name)

import catboost as cb
cat_features_index = [0,1,2,3,4,5,6]

def auc(m, train, test):
	train_auc = roc_auc_score(y_train,m.predict_proba(train)[:,1])
	test_auc  = roc_auc_score(y_test,m.predict_proba(test)[:,1])
	return (train_auc,test_auc)
# 参数空间
params = {'depth': [4, 7, 10],
          'learning_rate' : [0.03, 0.1, 0.15],
         'l2_leaf_reg': [1,4,9],
         'iterations': [300]}
cb = cb.CatBoostClassifier()
cb_model = GridSearchCV(cb, params, scoring="roc_auc", cv = 3)
cb_model.fit(train, y_train)

#With Categorical features
clf = cb.CatBoostClassifier(eval_metric="AUC", depth=10, iterations= 500, l2_leaf_reg= 9, learning_rate= 0.15)
clf.fit(train,y_train)
auc(clf, train, test)

#With Categorical features
clf = cb.CatBoostClassifier(eval_metric="AUC",
							one_hot_max_size=31,
                            depth=10,
                            iterations= 500,
                            l2_leaf_reg= 9,
                            learning_rate= 0.15)
clf.fit(train,y_train, cat_features= cat_features_index)
print(auc(clf, train, test))