贷款利润最大化——利用随机森林和逻辑回归进行分类

1.数据读取

这里有一份贷款数据，包括与贷款相关信息，现有主要任务：对贷款人借贷状态（全额借贷、不予借贷）进行分类，从而实现贷款利润最大化。

import pandas as pd
loans_2007 = pd.read_csv('LoanStats3a.csv', skiprows=1)
half_count = len(loans_2007) / 2
#删除空值记录
loans_2007 = loans_2007.dropna(thresh=half_count, axis=1)
#舍弃无关字段
loans_2007 = loans_2007.drop(['desc', 'url'],axis=1)
#将清理的数据集存入新的csv文件中
loans_2007.to_csv('loans_2007.csv', index=False)
import pandas as pd
loans_2007 = pd.read_csv("loans_2007.csv")
print(loans_2007.iloc[0])
print(loans_2007.shape[1])

输出结果显示共有52个字段，其中部分字段为无关字段，应该舍弃。

2.数据清洗及分析

loans_2007 = loans_2007.drop(["id", "member_id", "funded_amnt", "funded_amnt_inv", "grade", "sub_grade", "emp_title", "issue_d"], axis=1)
loans_2007 = loans_2007.drop(["zip_code", "out_prncp", "out_prncp_inv", "total_pymnt", "total_pymnt_inv", "total_rec_prncp"], axis=1)
loans_2007 = loans_2007.drop(["total_rec_int", "total_rec_late_fee", "recoveries", "collection_recovery_fee", "last_pymnt_d", "last_pymnt_amnt"], axis=1)
print(loans_2007.iloc[0])
print(loans_2007.shape[1])

删除无关字段后，剩余32个字段

#统计不同还款状态对应的样本数量——标签类分析
print(loans_2007['loan_status'].value_counts())

统计结果显示，共有9种借贷状态，其中我们仅分析"Fully Paid"（全额借款）和"Charged Off"（不借款）这两种状态。

#筛选出要分类的标签值，其中"Fully Paid"状态值为1，"Charged Off"状态值为0
loans_2007 = loans_2007[(loans_2007['loan_status'] == "Fully Paid") | (loans_2007['loan_status'] == "Charged Off")]

status_replace = {
    "loan_status" : {
        "Fully Paid": 1,
        "Charged Off": 0,
    }
}

loans_2007 = loans_2007.replace(status_replace)

在进行数据分析时，部分字段对应的值只有一个，应删除这些无关字段

orig_columns = loans_2007.columns
drop_columns = []
for col in orig_columns:
    col_series = loans_2007[col].dropna().unique()
    #如果字段值都一样，删除该字段
    if len(col_series) == 1:
        drop_columns.append(col)
loans_2007 = loans_2007.drop(drop_columns, axis=1)
print(drop_columns)
print loans_2007.shape
#将清洗后数据存入一个新的文件中
loans_2007.to_csv('filtered_loans_2007.csv', index=False)

输出结果如下

import pandas as pd
loans = pd.read_csv('filtered_loans_2007.csv')
loans = loans.drop("pub_rec_bankruptcies", axis=1)
#删除包含空值的记录
loans = loans.dropna(axis=0)
print(loans.dtypes.value_counts())
loans = loans.drop("pub_rec_bankruptcies", axis=1)
loans = loans.dropna(axis=0)
#统计不同数据类型下的字段总和
print(loans.dtypes.value_counts())

输出结果如下图，12个列所对应的数据类型为字符型，应转化为数值型。

#输出数据类型为字符型的字段
object_columns_df = loans.select_dtypes(include=["object"])
print(object_columns_df.iloc[0])
#对字符型数据进行分组计数
cols = ['home_ownership', 'verification_status', 'emp_length', 'term', 'addr_state']
for c in cols:
    print(loans[c].value_counts())
print(loans["purpose"].value_counts())
print(loans["title"].value_counts())

进一步进行数据清洗

#将"emp_length"字段转化为字符型数据
mapping_dict = {
    "emp_length": {
        "10+ years": 10,
        "9 years": 9,
        "8 years": 8,
        "7 years": 7,
        "6 years": 6,
        "5 years": 5,
        "4 years": 4,
        "3 years": 3,
        "2 years": 2,
        "1 year": 1,
        "< 1 year": 0,
        "n/a": 0
    }
}
loans = loans.drop(["last_credit_pull_d", "earliest_cr_line", "addr_state", "title"], axis=1)
#将百分比类型转化为浮点型（小数类型）
loans["int_rate"] = loans["int_rate"].str.rstrip("%").astype("float")
loans["revol_util"] = loans["revol_util"].str.rstrip("%").astype("float")
loans = loans.replace(mapping_dict)

cat_columns = ["home_ownership", "verification_status", "emp_length", "purpose", "term"]
dummy_df = pd.get_dummies(loans[cat_columns])
loans = pd.concat([loans, dummy_df], axis=1)
loans = loans.drop(cat_columns, axis=1)
loans = loans.drop("pymnt_plan", axis=1)
loans.to_csv('cleaned_loans2007.csv', index=False)
import pandas as pd
#读取最终清洗的数据
loans = pd.read_csv("cleaned_loans2007.csv")
print(loans.info())

最终数据包含的字段如下：

loan_amnt	38428 non-null float64
installment	38428 non-null float64
int_rate	38428 non-null float64
annual_inc	38428 non-null float64
loan_status	38428 non-null float64
dti	38428 non-null float64
delinq_2yrs	38428 non-null float64
inq_last_6mths	38428 non-null float64
open_acc	38428 non-null float64
pub_rec	38428 non-null float64
revol_bal	38428 non-null float64
revol_util	38428 non-null float64
total_acc	38428 non-null float64
home_ownership_MORTGAGE	38428 non-null float64
home_ownership_NONE	38428 non-null float64
``````	```````

3.建立逻辑回归模型，预测是否借贷

在这里我们分别建立了三个模型，比较不同模型的训练效果

#利用逻辑回归模型对0-1标签进行分类
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import cross_val_predict, KFold
lr = LogisticRegression()
kf = KFold(features.shape[0], random_state=1)
predictions = cross_val_predict(lr, features, target, cv=kf)
predictions = pd.Series(predictions)
#负例预测为正例
fp_filter = (predictions == 1) & (loans["loan_status"] == 0)
fp = len(predictions[fp_filter])
# 正例预测为正例
tp_filter = (predictions == 1) & (loans["loan_status"] == 1)
tp = len(predictions[tp_filter])
# 负例预测为正例
fn_filter = (predictions == 0) & (loans["loan_status"] == 1)
fn = len(predictions[fn_filter])
# 负例预测为负例
tn_filter = (predictions == 0) & (loans["loan_status"] == 0)
tn = len(predictions[tn_filter])
# 统计指标：tpr和fpr，其中tpr越大越好，fpr越小越好
tpr = tp / float((tp + fn))
fpr = fp / float((fp + tn))
print(tpr)
print(fpr)
print(predictions[:20])

输出如下：

此时tpr和fpr比例均较高，不满足要求；进一步调整参数class_weight，使得正负样本比例得到均衡

#在正负样本比例均衡条件下训练模型，统计相关指标
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import cross_val_predict
lr = LogisticRegression(class_weight="balanced")
kf = KFold(features.shape[0], random_state=1)
predictions = cross_val_predict(lr, features, target, cv=kf)
predictions = pd.Series(predictions)
#负例预测为正例
fp_filter = (predictions == 1) & (loans["loan_status"] == 0)
fp = len(predictions[fp_filter])
# 正例预测为正例
tp_filter = (predictions == 1) & (loans["loan_status"] == 1)
tp = len(predictions[tp_filter])
# 负例预测为正例
fn_filter = (predictions == 0) & (loans["loan_status"] == 1)
fn = len(predictions[fn_filter])
# 负例预测为负例
tn_filter = (predictions == 0) & (loans["loan_status"] == 0)
tn = len(predictions[tn_filter])
# 统计指标：tpr和fpr，其中tpr越大越好，fpr越小越好
tpr = tp / float((tp + fn))
fpr = fp / float((fp + tn))
print(tpr)
print(fpr)
print(predictions[:20])

from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import cross_val_predict
#因为这里负例样本数量远远小于正例样本数量，我们可以调整正负样本的权重，使得正负样本比例均衡
penalty = {
    0: 5,
    1: 1
}
lr = LogisticRegression(class_weight=penalty)
kf = KFold(features.shape[0], random_state=1)
predictions = cross_val_predict(lr, features, target, cv=kf)
predictions = pd.Series(predictions)
#负例预测为正例
fp_filter = (predictions == 1) & (loans["loan_status"] == 0)
fp = len(predictions[fp_filter])
# 正例预测为正例
tp_filter = (predictions == 1) & (loans["loan_status"] == 1)
tp = len(predictions[tp_filter])
# 负例预测为正例
fn_filter = (predictions == 0) & (loans["loan_status"] == 1)
fn = len(predictions[fn_filter])
# 负例预测为负例
tn_filter = (predictions == 0) & (loans["loan_status"] == 0)
tn = len(predictions[tn_filter])
# 统计指标：tpr和fpr，其中tpr越大越好，fpr越小越好
tpr = tp / float((tp + fn))
fpr = fp / float((fp + tn))
print(tpr)
print(fpr)
print(predictions[:20])

4.建立随机森林模型

from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import cross_val_predict
rf = RandomForestClassifier(n_estimators=10,class_weight="balanced", random_state=1)
#print help(RandomForestClassifier)
kf = KFold(features.shape[0], random_state=1)
predictions = cross_val_predict(rf, features, target, cv=kf)
predictions = pd.Series(predictions)
# False positives.
fp_filter = (predictions == 1) & (loans["loan_status"] == 0)
fp = len(predictions[fp_filter])
# True positives.
tp_filter = (predictions == 1) & (loans["loan_status"] == 1)
tp = len(predictions[tp_filter])
# False negatives.
fn_filter = (predictions == 0) & (loans["loan_status"] == 1)
fn = len(predictions[fn_filter])
# True negatives
tn_filter = (predictions == 0) & (loans["loan_status"] == 0)
tn = len(predictions[tn_filter])
# Rates
tpr = tp / float((tp + fn))
fpr = fp / float((fp + tn))

输出结果如下

在这里我们得到随机森林模型效果劣于逻辑回归模型的效果

相关数据集如下：链接：https://pan.baidu.com/s/1CezGYZAR1Zs-8_WIo2-TrA
提取码：wmvq