天池更新了一次数据 所以上一篇博文可能有一点点失准的地方.之后的博文会基于更新之后的数据.
读取数据和套路的头文件
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import datetime
import warnings
warnings.filterwarnings('ignore')
data_train = pd.read_csv('./train.csv')
data_test_a = pd.read_csv('./testA.csv')
基操
data_test_a.shape
data_test_a.columns
data_test_a.info()
data_test_a.describe()
print(f'There are {data_train.isnull().any().sum()} columns in train dataset with missing values.')
# 查看缺失值
注意到单值变量在训练集中并没有额外的信息,可以找到之后drop掉.
one_value_fea = [col for col in data_train.columns if data_train[col].nunique() <= 1]
# 查看单值变量
print(one_value_fea)
这里假定离散型变量最多只有十类.也可以适当调整.
max_type = 10
#数值型
numerical_fea = list(data_train.select_dtypes(exclude=['object']).columns)
#种类型
category_fea = list(filter(lambda x: x not in numerical_fea,list(data_train.columns)))
#过滤数值型类别特征
def get_numerical_serial_fea(data,feas):
numerical_serial_fea = []
numerical_noserial_fea = []
for fea in feas:
temp = data[fea].nunique()
if temp <= max_type:
numerical_noserial_fea.append(fea)
continue
numerical_serial_fea.append(fea)
return numerical_serial_fea,numerical_noserial_fea
numerical_serial_fea,numerical_noserial_fea = get_numerical_serial_fea(data_train,numerical_fea)
返回的列表是离散和连续变量的列名构成的列表
data_train['term'].value_counts()#离散型变量
离散型变量一般用去考虑一共有多少值,值的分布如何
#每个数字特征的分布可视化
f = pd.melt(data_train, value_vars=numerical_serial_fea)
g = sns.FacetGrid(f, col="variable", col_wrap=2, sharex=False, sharey=False)
g = g.map(sns.distplot, "value")
这个要跑久一点,然后举个例子是这样
data_train['grade'].value_counts()
非数值型就一般这么处理
#Ploting Transaction Amount Values Distribution
plt.figure(figsize=(16,12))
plt.suptitle('Transaction Values Distribution', fontsize=22)
plt.subplot(221)
sub_plot_1 = sns.distplot(data_train['loanAmnt'])
sub_plot_1.set_title("loanAmnt Distribuition", fontsize=18)
sub_plot_1.set_xlabel("")
sub_plot_1.set_ylabel("Probability", fontsize=15)
plt.subplot(222)
sub_plot_2 = sns.distplot(np.log(data_train['loanAmnt']))
sub_plot_2.set_title("loanAmnt (Log) Distribuition", fontsize=18)
sub_plot_2.set_xlabel("")
sub_plot_2.set_ylabel("Probability", fontsize=15)
太偏向一边的或者没有Normal Distribution可以试着做个log运算,或者Normalize,不要让数据太偏就可以了
然后是数据可视化
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()
可以选择若干不同变量做cross看一下彼此之间有没有比较显著的关系
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()
对于分类型的变量和别的变量做cross的时候可以把数据先分类,然后在每类的基础上去绘图.
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)
分类型的变量可以计算各类分布画柱状图
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)
时间格式的分析
#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
聚合函数和索引的应用
#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)
reference:
Task2 数据分析