机器学习——pandas

╰+哭是因爲堅強的太久メ 2022-12-25 05:58 149阅读 0赞

import numpy as np
    import pandas as pd
    import warnings
    
    #加载模块绘制图形
    import matplotlib.pyplot as plt
    import seaborn as sns
    
    warnings.filterwarnings('ignore')
    df = pd.read_csv('https://labfile.oss.aliyuncs.com/courses/1283/telecom_churn.csv')
    df.head()#显示前五行数据
    df.shape#查看数据库维度
    df.columns#打印列名
    #df.info()#输出DataFrame的一些总体信息
    df.describe()#显示数值特征的基本统计学特性
    df.describe(include=['object','bool'])#查看非数值特征的统计数据
    df['Churn'].value_counts()#查看类别（object）和bool值得特征
    df['Churn'].value_counts(normalize=True)#以比例的形式呈现
    
    #排序
    df.sort_values(by='Total day charge',ascending=False).head()#根据每日消费额倒叙排序,默认是正序从小到大
    df.sort_values(by=['Churn','Total day charge'],ascending=[True,False]).head()#以Churn正序，以Total day charge倒序
    
    #索引和获取数据
    df['Churn'].mean()#离网率
    df[df['Churn']==1].mean()#离网用户数值变量的均值
    df[df['Churn']==1]['Total day minutes'].mean()#离网用户白天打电话的时长是多少
    df[(df['Churn']==0)&(df['International plan']=='No')]['Total intl minutes'].max()#未使用国际套餐的忠实用户所打的国际长途是多久
    
    df.loc[0:5,'State':'Area code']#输出0至5行，state至area code区号的数据
    df.iloc[0:5,0:3]#输出前五行，前三列的数据
    
    df[:1]#首行
    df[-1:]#末行
    
    #应用函数到单元格、列、行
    df.apply(np.max)#输出每列的最大值
    df[df['State'].apply(lambda state:state[0]=='W')].head()#选中以w开头的州
    
    #替换
    d = { 'No':False,'Yes':True}
    df['International plan']=df['International plan'].map(d)
    df.head()
    
    df = df.replace({ 'Voice mail plan':d})
    df.head()
    
    #分组（groupby）
    columns_to_show = ['Total day minutes','Total eve minutes','Total night minutes']
    df.groupby(['Churn'])[columns_to_show].describe(percentiles=[])
    
    df.groupby(['Churn'])[columns_to_show].agg([np.mean,np.std,np.min,np.max])
    
    #汇总表
    #透视表
    df.pivot_table(['Total day calls','Total eve calls','Total night calls'],['Area code'],aggfunc='mean')
    #交叉表
    pd.crosstab(df['Churn'],df['International plan'])
    pd.crosstab(df['Churn'],df['Voice mail plan'],normalize=True)
    
    #增加DataFrame的行列
    total_calls = df['Total day calls']+df['Total eve calls']+df['Total night calls']+df['Total intl calls']
    #loc参数是插入series对象后选择的列数
    #设置为len(df.columns)将计算后的Total calls粘贴到最后一列
    df.insert(loc=len(df.columns),column='Total calls',value=total_calls)
    df.head()
    #other way
    #df['Total calls'] = df['Total day calls']+df['Total eve calls']+df['Total night calls']+df['Total intl calls']
    
    #删除列和行，drop()
    df.drop(['Total calls'],axis=1,inplace=True)#删除列,axis=1，inplace=True表示修改当前DataFrame
    df.drop([1,2]).head()#删除行,axis=0默认
    
    sns.countplot(x='International plan',hue='Churn',data=df)
    
    pd.crosstab(df['Churn'], df['Customer service calls'], margins=True)
    sns.countplot(x='Customer service calls',hue='Churn',data=df)