python打卡DAY7

import pandas as pd

data=pd.read_csv(r'data.csv')

#查看基本信息与缺失值

print(f'{data.info()}\n{data.isnull().sum()}\n{data.head()}')

#图像绘制

import seaborn as sns

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif']=['STHeiti']

plt.rcParams['axes.unicode_minus']=True

# plt.figure(figsize=(6,4))

# sns.boxplot(x=data['Annual Income'])

# plt.title('annual income photo')

# plt.xlabel('annual income')

# plt.tight_layout()

# plt.show()

 

# plt.figure(figsize=(6,4))

# sns.boxplot(x=data['Annual Income'])

# plt.title('年收入箱线图')

# plt.xlabel('年收入')

# plt.tight_layout()

# plt.show()

# plt.figure(figsize=(6,4))

# sns.boxplot(x='Credit Default',y='Annual Income',data=data)

# plt.title('annual income vs.credit default')

# plt.xlabel('credit default')

# plt.ylabel('annual income')

# plt.xticks([0,1],['否','是'])

# plt.tight_layout()

# plt.show()

# plt.figure(figsize=(6,4))

# sns.histplot(x='Annual Income',

# hue='Credit Default',

# data=data,

# kde=True,

# element='step')

# #kde 是 "Kernel Density Estimation"（核密度估计）的缩写

# plt.title('annual income')

# plt.xlabel('annual income')

# plt.ylabel('count')

# plt.legend(labels=['否','是'])

# plt.tight_layout()

# plt.show()

# plt.figure(figsize=(6,4))

# sns.countplot(x='Number of Open Accounts',

# hue='Credit Default',

# data=data)

# plt.xticks(rotation=45,ha='right')

# plt.xlabel('number of open account')

# plt.ylabel('count')

# plt.legend(labels=['否','是'])

# plt.tight_layout()

# plt.show()

# print(data.info())

# data['Open Accounts Group']=pd.cut(data['Number of Open Accounts'],

# bins=[0,5,10,15,20,float('inf')],

# labels=['0-5','6-10','11-15','16-20','20+'])

# plt.figure(figsize=(6,4))

# sns.countplot(x='Open Accounts Group',hue='Credit Default',data=data)

# plt.title('number of open accounts(grouped) vs. Credit Default')

# plt.xlabel('nimber of open account group')

# plt.ylabel('count')

# plt.legend(labels=['否','是'])

# plt.tight_layout()

# plt.show()

 

#填补缺失值

for i in data.columns:

if data[i].dtype!='object':

data.isnull().sum()>0

data[i].fillna(data[i].mean(),inplace=True)

if data[i].dtype=='object':

data[i].isnull().sum()>0

data[i].fillna(data[i].mode()[0],inplace=True)

#数据编码

mapping={

'10+ years':0,

'9 years':1,

'8 years':2,

'7 years':3,

'6 years':4,

'5 years':5,

'4 years':6,

'3 years':7,

'2 years':8,

'< 1 year':9

}

data['Years in current job']=data['Years in current job'].map(mapping)

data=pd.get_dummies(data,drop_first=True)

dummies_list=[]

data2=pd.read_csv(r'data.csv')

for i in data.columns:

if i not in data2.columns:

dummies_list.append(i)

for i in dummies_list:

data[i]=data[i].astype(int)

print(data.head())

# #绘制热力图&子图

# print(f'{data.columns}\n{data.info()}\n{data.head()}')

# continuous_features=[

# 'Annual Income', 'Years in current job', 'Tax Liens',

# 'Number of Open Accounts', 'Years of Credit History',

# 'Maximum Open Credit', 'Number of Credit Problems',

# 'Months since last delinquent', 'Bankruptcies', 'Current Loan Amount',

# 'Current Credit Balance', 'Monthly Debt', 'Credit Score'

# ]

# correlation_matrix=data[continuous_features].corr()

# plt.rcParams['figure.dpi']=100

# plt.figure(figsize=(12,10))

# sns.heatmap(correlation_matrix,annot=True,cmap='coolwarm',vmin=-1,vmax=1)

# plt.title('相关热力图')

# plt.xticks(rotation=45,ha='right')

# plt.tight_layout()

# plt.show()

# features=['Annual Income','Years in current job','Tax Liens','Number of Open Accounts']

# plt.rcParams['figure.dpi']=100

# fig,axes=plt.subplots(2,2,figsize=(12,10))

# i=0

# feature=features[i]

# axes[0,0].boxplot(data[feature].dropna())

# axes[0,0].set_title(f'boxplot of {feature}')

# axes[0,0].set_ylabel(feature)

# i=1

# feature=features[i]

# axes[0,1].boxplot(data[feature].dropna())

# axes[0,1].set_title(f'boxplot of {feature}')

# axes[0,1].set_ylabel(feature)

# i=2

# feature=features[i]

# axes[1,0].boxplot(data[feature].dropna())

# axes[1,0].set_title(f'boxplot of {feature}')

# axes[1,0].set_ylabel(feature)

# i=3

# feature=features[i]

# axes[1,1].boxplot(data[feature].dropna())

# axes[1,1].set_title(f'boxplot of {feature}')

# axes[1,1].set_ylabel(feature)

# plt.tight_layout()

# plt.show()

# features=['Annual Income', 'Years in current job', 'Tax Liens', 'Number of Open Accounts']

# plt.rcParams['figure.dpi']=100

# fig,axes=plt.subplots(2,2,figsize=(12,8))

# for i in range(len(features)):

# row=i//2

# col=i%2

# feature=features[i]

# axes[row,col].boxplot(data[feature].dropna())

# axes[row,col].set_title(f'boxplot of {feature}')

# axes[row,col].set_ylabel(feature)

# plt.tight_layout()

# plt.show()

# features=['Annual Income', 'Years in current job', 'Tax Liens', 'Number of Open Accounts']

# for i,feature in enumerate(features):

# print(f'索引{i}对应的特征是：{feature}')

# features=['Annual Income', 'Years in current job', 'Tax Liens', 'Number of Open Accounts']

# plt.rcParams['figure.dpi']=100

# fig,axes=plt.subplots(2,2,figsize=(12,8))

# for i,feature in enumerate(features):

# row=i//2

# col=i%2

# axes[row,col].boxplot(data[feature].dropna())

# axes[row,col].set_title(f'boxplot of {feature}')

# axes[row,col].set_ylabel(feature)

# plt.tight_layout()

# plt.show()