基于xgboost 的贷款风险预测

 现在我们用传说中的xgboost 对这个数据集进行计算

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Aug 19 13:19:26 2017

@author: luogan
"""

import pandas as pd
df = pd.read_csv('loans.csv')

from sklearn.preprocessing import LabelEncoder
from collections import defaultdict
d = defaultdict(LabelEncoder)
dff =df.apply(lambda df: d[df.name].fit_transform(df))
dff.to_excel('dff.xls')



import pandas as pd
import numpy as np
import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn import cross_validation, metrics   #Additional     scklearn functions
from sklearn.grid_search import GridSearchCV   #Perforing grid search

import matplotlib.pylab as plt
#%matplotlib inline
from matplotlib.pylab import rcParams
rcParams['figure.figsize'] = 12, 4

train = pd.read_excel('dff.xls')
target = 'safe_loans'
IDcol = 'id'


def modelfit(alg, dtrain, 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)
        cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
            metrics='auc', early_stopping_rounds=early_stopping_rounds)
        alg.set_params(n_estimators=cvresult.shape[0])

    #Fit the algorithm on the data
    alg.fit(dtrain[predictors], dtrain['safe_loans'],eval_metric='auc')

    #Predict training set:
    dtrain_predictions = alg.predict(dtrain[predictors])
    dtrain_predprob = alg.predict_proba(dtrain[predictors])[:,1]
    from pandas import DataFrame
    '''
    gg=DataFrame(dtrain_predictions)
    gg.to_excel('dtrain_predictions.xls')   

    tt=DataFrame(dtrain_predprob)
    tt.to_excel('dtrain_predprob.xls')
    '''

    print(alg)
    #Print model report:
    print ("\nModel Report")
    print ("Accuracy : %.4g" % metrics.accuracy_score(dtrain['safe_loans'].values, dtrain_predictions))
    print ("AUC Score (Train): %f" % metrics.roc_auc_score(dtrain['safe_loans'], dtrain_predprob))

    ww=(alg.feature_importances_)
    print(ww)            
    feat_imp = pd.Series(ww).sort_values(ascending=False)

    #print(feat_imp)

    feat_imp.plot(kind='bar', title='Feature Importances')
    plt.ylabel('Feature Importance Score')

    """
    model=alg
    featureImportance = model.get_score() 
    features = pd.DataFrame() 
    features['features'] = featureImportance.keys() 
    features['importance'] = featureImportance.values() 
    features.sort_values(by=['importance'],ascending=False,inplace=True) 
    fig,ax= plt.subplots() 
    fig.set_size_inches(20,10) 
    plt.xticks(rotation=60) 
    #sn.barplot(data=features.head(30),x="features",y="importance",ax=ax,orient="v") 
    """


#Choose all predictors except target & IDcols
predictors = [x for x in train.columns if x not in [target, IDcol]]
xgb1 = XGBClassifier(
                learning_rate =0.1,
                n_estimators=1000,
                max_depth=18,
                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, predictors)     

• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• 51
• 52
• 53
• 54
• 55
• 56
• 57
• 58
• 59
• 60
• 61
• 62
• 63
• 64
• 65
• 66
• 67
• 68
• 69
• 70
• 71
• 72
• 73
• 74
• 75
• 76
• 77
• 78
• 79
• 80
• 81
• 82
• 83
• 84
• 85
• 86
• 87
• 88
• 89
• 90
• 91
• 92
• 93
• 94
• 95
• 96
• 97
• 98
• 99
• 100
• 101
• 102
• 103
• 104
• 105
• 106
• 107
• 108
• 109
• 110
• 111

Model Report
Accuracy : 0.9533
AUC Score (Train): 0.990971

• 1
• 2
• 3

    正确率95%,甩决策树和BP网几条街啊！ 
可见传说中的xgboost果然厉害，难怪工业实践中xgboost 应用如痴的广泛 
下图显示了每个 feature的重要性,里面有两个文件，请运行xgboost.py