贷款违约预测-Task2 数据分析（下）

plt.figure(figsize=(8, 8))
sns.barplot(data_train["employmentLength"].value_counts(dropna=False)[:20],
            data_train["employmentLength"].value_counts(dropna=False).keys()[:20])
plt.show()

train_loan_fr = data_train.loc[data_train['isDefault'] == 1]
train_loan_nofr = data_train.loc[data_train['isDefault'] == 0]

fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, figsize=(15, 8))
train_loan_fr.groupby('grade')['grade'].count().plot(kind='barh', ax=ax1, title='Count of grade fraud')
train_loan_nofr.groupby('grade')['grade'].count().plot(kind='barh', ax=ax2, title='Count of grade non-fraud')
train_loan_fr.groupby('employmentLength')['employmentLength'].count().plot(kind='barh', ax=ax3, title='Count of employmentLength fraud')
train_loan_nofr.groupby('employmentLength')['employmentLength'].count().plot(kind='barh', ax=ax4, title='Count of employmentLength non-fraud')
plt.show()

fig, ((ax1, ax2)) = plt.subplots(1, 2, figsize=(15, 6))
data_train.loc[data_train['isDefault'] == 1] \
    ['loanAmnt'].apply(np.log) \
    .plot(kind='hist',
          bins=100,
          title='Log Loan Amt - Fraud',
          color='r',
          xlim=(-3, 10),
         ax= ax1)
data_train.loc[data_train['isDefault'] == 0] \
    ['loanAmnt'].apply(np.log) \
    .plot(kind='hist',
          bins=100,
          title='Log Loan Amt - Not Fraud',
          color='b',
          xlim=(-3, 10),
         ax=ax2)

<matplotlib.axes._subplots.AxesSubplot at 0x126a44b50>

total = len(data_train)
total_amt = data_train.groupby(['isDefault'])['loanAmnt'].sum().sum()
plt.figure(figsize=(12,5))
plt.subplot(121)##1代表行，2代表列，所以一共有2个图，1代表此时绘制第一个图。
plot_tr = sns.countplot(x='isDefault',data=data_train)#data_train‘isDefault’这个特征每种类别的数量**
plot_tr.set_title("Fraud Loan Distribution \n 0: good user | 1: bad user", fontsize=14)
plot_tr.set_xlabel("Is fraud by count", fontsize=16)
plot_tr.set_ylabel('Count', fontsize=16)
for p in plot_tr.patches:
    height = p.get_height()
    plot_tr.text(p.get_x()+p.get_width()/2.,
            height + 3,
            '{:1.2f}%'.format(height/total*100),
            ha="center", fontsize=15) 
percent_amt = (data_train.groupby(['isDefault'])['loanAmnt'].sum())
percent_amt = percent_amt.reset_index()
plt.subplot(122)
plot_tr_2 = sns.barplot(x='isDefault', y='loanAmnt',  dodge=True, data=percent_amt)
plot_tr_2.set_title("Total Amount in loanAmnt  \n 0: good user | 1: bad user", fontsize=14)
plot_tr_2.set_xlabel("Is fraud by percent", fontsize=16)
plot_tr_2.set_ylabel('Total Loan Amount Scalar', fontsize=16)
for p in plot_tr_2.patches:
    height = p.get_height()
    plot_tr_2.text(p.get_x()+p.get_width()/2.,
            height + 3,
            '{:1.2f}%'.format(height/total_amt * 100),
            ha="center", fontsize=15)

#转化成时间格式  issueDateDT特征表示数据日期离数据集中日期最早的日期（2007-06-01）的天数
data_train['issueDate'] = pd.to_datetime(data_train['issueDate'],format='%Y-%m-%d')
startdate = datetime.datetime.strptime('2007-06-01', '%Y-%m-%d')
data_train['issueDateDT'] = data_train['issueDate'].apply(lambda x: x-startdate).dt.days

#转化成时间格式
data_test_a['issueDate'] = pd.to_datetime(data_train['issueDate'],format='%Y-%m-%d')
startdate = datetime.datetime.strptime('2007-06-01', '%Y-%m-%d')
data_test_a['issueDateDT'] = data_test_a['issueDate'].apply(lambda x: x-startdate).dt.days

plt.hist(data_train['issueDateDT'], label='train');
plt.hist(data_test_a['issueDateDT'], label='test');
plt.legend();
plt.title('Distribution of issueDateDT dates');
#train 和 test issueDateDT 日期有重叠 所以使用基于时间的分割进行验证是不明智的

#透视图 索引可以有多个，“columns（列）”是可选的，聚合函数aggfunc最后是被应用到了变量“values”中你所列举的项目上。
pivot = pd.pivot_table(data_train, index=['grade'], columns=['issueDateDT'], values=['loanAmnt'], aggfunc=np.sum)

pivot

import pandas_profiling

pfr = pandas_profiling.ProfileReport(data_train)
pfr.to_file("./example.html")