In [1]:
import pandas as pd
import numpy as np
import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn import cross_validation, metrics
from sklearn.grid_search import GridSearchCV
import matplotlib.pylab as plt
%matplotlib inline
from matplotlib.pylab import rcParams
rcParams['figure.figsize'] = 12, 4
上一个ipython notebook已经做了下面这些数据特征预处理
In [2]:
train = pd.read_csv('train_modified.csv')
test = pd.read_csv('test_modified.csv')
In [3]:
train.shape, test.shape
Out[3]:
In [4]:
target='Disbursed'
IDcol = 'ID'
In [5]:
train['Disbursed'].value_counts()
Out[5]:
In [11]:
#test_results = pd.read_csv('test_results.csv')
def modelfit(alg, dtrain, dtest, predictors,useTrainCV=True, cv_folds=5, early_stopping_rounds=50):
if useTrainCV:
xgb_param = alg.get_xgb_params()
xgtrain = xgb.DMatrix(dtrain[predictors].values, label=dtrain[target].values)
xgtest = xgb.DMatrix(dtest[predictors].values)
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
early_stopping_rounds=early_stopping_rounds, show_progress=False)
alg.set_params(n_estimators=cvresult.shape[0])
#建模
alg.fit(dtrain[predictors], dtrain['Disbursed'],eval_metric='auc')
#对训练集预测
dtrain_predictions = alg.predict(dtrain[predictors])
dtrain_predprob = alg.predict_proba(dtrain[predictors])[:,1]
#输出模型的一些结果
print "\n关于现在这个模型"
print "准确率 : %.4g" % metrics.accuracy_score(dtrain['Disbursed'].values, dtrain_predictions)
print "AUC 得分 (训练集): %f" % metrics.roc_auc_score(dtrain['Disbursed'], dtrain_predprob)
feat_imp = pd.Series(alg.booster().get_fscore()).sort_values(ascending=False)
feat_imp.plot(kind='bar', title='Feature Importances')
plt.ylabel('Feature Importance Score')
In [12]:
predictors = [x for x in train.columns if x not in [target, IDcol]]
xgb1 = XGBClassifier(
learning_rate =0.1,
n_estimators=1000,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective= 'binary:logistic',
nthread=4,
scale_pos_weight=1,
seed=27)
modelfit(xgb1, train, test, predictors)
In [13]:
#对subsample 和 max_features 用grid search查找最好的参数
param_test1 = {
'max_depth':range(3,10,2),
'min_child_weight':range(1,6,2)
}
gsearch1 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=140, max_depth=5,
min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1, seed=27),
param_grid = param_test1, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch1.fit(train[predictors],train[target])
Out[13]:
In [14]:
gsearch1.grid_scores_, gsearch1.best_params_, gsearch1.best_score_
Out[14]:
In [11]:
# 对于max_depth和min_child_weight查找最好的参数
param_test2 = {
'max_depth':[4,5,6],
'min_child_weight':[4,5,6]
}
gsearch2 = GridSearchCV(estimator = XGBClassifier( learning_rate=0.1, n_estimators=140, max_depth=5,
min_child_weight=2, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test2, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch2.fit(train[predictors],train[target])
Out[11]:
In [12]:
gsearch2.grid_scores_, gsearch2.best_params_, gsearch2.best_score_
Out[12]:
In [13]:
#交叉验证对min_child_weight寻找最合适的参数
param_test2b = {
'min_child_weight':[6,8,10,12]
}
gsearch2b = GridSearchCV(estimator = XGBClassifier( learning_rate=0.1, n_estimators=140, max_depth=4,
min_child_weight=2, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test2b, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch2b.fit(train[predictors],train[target])
Out[13]:
In [14]:
gsearch2b.grid_scores_, gsearch2b.best_params_, gsearch2b.best_score_
Out[14]:
In [17]:
#Grid seach选择合适的gamma
param_test3 = {
'gamma':[i/10.0 for i in range(0,5)]
}
gsearch3 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=140, max_depth=4,
min_child_weight=6, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test3, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch3.fit(train[predictors],train[target])
Out[17]:
In [18]:
gsearch3.grid_scores_, gsearch3.best_params_, gsearch3.best_score_
Out[18]:
In [19]:
predictors = [x for x in train.columns if x not in [target, IDcol]]
xgb2 = XGBClassifier(
learning_rate =0.1,
n_estimators=1000,
max_depth=4,
min_child_weight=6,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective= 'binary:logistic',
nthread=4,
scale_pos_weight=1,
seed=27)
modelfit(xgb2, train, test, predictors)
Tune subsample and colsample_bytree
In [20]:
#对subsample 和 colsample_bytree用grid search寻找最合适的参数
param_test4 = {
'subsample':[i/10.0 for i in range(6,10)],
'colsample_bytree':[i/10.0 for i in range(6,10)]
}
gsearch4 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=177, max_depth=4,
min_child_weight=6, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test4, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch4.fit(train[predictors],train[target])
Out[20]:
In [21]:
gsearch4.grid_scores_, gsearch4.best_params_, gsearch4.best_score_
Out[21]:
tune subsample:
In [22]:
# 同上
param_test5 = {
'subsample':[i/100.0 for i in range(75,90,5)],
'colsample_bytree':[i/100.0 for i in range(75,90,5)]
}
gsearch5 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=177, max_depth=4,
min_child_weight=6, gamma=0, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test5, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch5.fit(train[predictors],train[target])
Out[22]:
In [25]:
gsearch5.grid_scores_, gsearch5.best_params_, gsearch5.best_score_
Out[25]:
对正则化做交叉验证
In [24]:
#对reg_alpha用grid search寻找最合适的参数
param_test6 = {
'reg_alpha':[1e-5, 1e-2, 0.1, 1, 100]
}
gsearch6 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=177, max_depth=4,
min_child_weight=6, gamma=0.1, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test6, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch6.fit(train[predictors],train[target])
Out[24]:
In [26]:
gsearch6.grid_scores_, gsearch6.best_params_, gsearch6.best_score_
Out[26]:
In [27]:
# 换一组参数对reg_alpha用grid search寻找最合适的参数
param_test7 = {
'reg_alpha':[0, 0.001, 0.005, 0.01, 0.05]
}
gsearch7 = GridSearchCV(estimator = XGBClassifier( learning_rate =0.1, n_estimators=177, max_depth=4,
min_child_weight=6, gamma=0.1, subsample=0.8, colsample_bytree=0.8,
objective= 'binary:logistic', nthread=4, scale_pos_weight=1,seed=27),
param_grid = param_test7, scoring='roc_auc',n_jobs=4,iid=False, cv=5)
gsearch7.fit(train[predictors],train[target])
Out[27]:
In [28]:
gsearch7.grid_scores_, gsearch7.best_params_, gsearch7.best_score_
Out[28]:
In [29]:
xgb3 = XGBClassifier(
learning_rate =0.1,
n_estimators=1000,
max_depth=4,
min_child_weight=6,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
reg_alpha=0.005,
objective= 'binary:logistic',
nthread=4,
scale_pos_weight=1,
seed=27)
modelfit(xgb3, train, test, predictors)
In [30]:
xgb4 = XGBClassifier(
learning_rate =0.01,
n_estimators=5000,
max_depth=4,
min_child_weight=6,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
reg_alpha=0.005,
objective= 'binary:logistic',
nthread=4,
scale_pos_weight=1,
seed=27)
modelfit(xgb4, train, test, predictors)
In [ ]: