learn_two

import pandas as pd
import numpy as np

读取文件

df = pd.read_csv(
    'https://labfile.oss.aliyuncs.com/courses/1283/telecom_churn.csv')
df.head()

df.info() #DataFrame 的一些总体信息。

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3333 entries, 0 to 3332
Data columns (total 20 columns):
State                     3333 non-null object
Account length            3333 non-null int64
Area code                 3333 non-null int64
International plan        3333 non-null object
Voice mail plan           3333 non-null object
Number vmail messages     3333 non-null int64
Total day minutes         3333 non-null float64
Total day calls           3333 non-null int64
Total day charge          3333 non-null float64
Total eve minutes         3333 non-null float64
Total eve calls           3333 non-null int64
Total eve charge          3333 non-null float64
Total night minutes       3333 non-null float64
Total night calls         3333 non-null int64
Total night charge        3333 non-null float64
Total intl minutes        3333 non-null float64
Total intl calls          3333 non-null int64
Total intl charge         3333 non-null float64
Customer service calls    3333 non-null int64
Churn                     3333 non-null bool
dtypes: bool(1), float64(8), int64(8), object(3)
memory usage: 498.1+ KB

df.shape #形状大小

(3333, 20)

df.columns #列名

Index(['State', 'Account length', 'Area code', 'International plan',
       'Voice mail plan', 'Number vmail messages', 'Total day minutes',
       'Total day calls', 'Total day charge', 'Total eve minutes',
       'Total eve calls', 'Total eve charge', 'Total night minutes',
       'Total night calls', 'Total night charge', 'Total intl minutes',
       'Total intl calls', 'Total intl charge', 'Customer service calls',
       'Churn'],
      dtype='object')

df['Churn'] = df['Churn'].astype('int64')  #将Churn列修改数据类型
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3333 entries, 0 to 3332
Data columns (total 20 columns):
State                     3333 non-null object
Account length            3333 non-null int64
Area code                 3333 non-null int64
International plan        3333 non-null object
Voice mail plan           3333 non-null object
Number vmail messages     3333 non-null int64
Total day minutes         3333 non-null float64
Total day calls           3333 non-null int64
Total day charge          3333 non-null float64
Total eve minutes         3333 non-null float64
Total eve calls           3333 non-null int64
Total eve charge          3333 non-null float64
Total night minutes       3333 non-null float64
Total night calls         3333 non-null int64
Total night charge        3333 non-null float64
Total intl minutes        3333 non-null float64
Total intl calls          3333 non-null int64
Total intl charge         3333 non-null float64
Customer service calls    3333 non-null int64
Churn                     3333 non-null int64
dtypes: float64(8), int64(9), object(3)
memory usage: 520.9+ KB

df.describe() #显示数值特征（int64 和 float64）的基本统计学特性

df.describe(include=['object', 'bool']) #通过 include 参数显式指定包含的数据类型，可以查看非数值特征的统计数据

df['Churn'].value_counts() #如其名

0    2850
1     483
Name: Churn, dtype: int64

df['Churn'].value_counts(normalize=True) #传入参数显示比例

0    0.855086
1    0.144914
Name: Churn, dtype: float64

df.sort_values(by='Total day charge', ascending=False).head() #根据Total day charge列进行排序 ascending=False为倒序排序

df.sort_values(by=['Churn', 'Total day charge'],
               ascending=[True, False]).head() #先按 Churn 离网率 升序排列，再按 Total day charge 每日总话费 降序排列

df[df['Churn'] == 1].mean()

Account length            102.664596
Area code                 437.817805
Number vmail messages       5.115942
Total day minutes         206.914079
Total day calls           101.335404
Total day charge           35.175921
Total eve minutes         212.410145
Total eve calls           100.561077
Total eve charge           18.054969
Total night minutes       205.231677
Total night calls         100.399586
Total night charge          9.235528
Total intl minutes         10.700000
Total intl calls            4.163561
Total intl charge           2.889545
Customer service calls      2.229814
Churn                       1.000000
dtype: float64

df[df['Churn'] == 1]['Total day minutes'].mean()

206.91407867494814

df.loc[0:5, 'State':'Area code'] #通过标签来选取

df.iloc[0:5, 0:3] #通过索引来选取，类似于python的切片操作

df.apply(max) #应用到每一列

State                        WY
Account length              243
Area code                   510
International plan          Yes
Voice mail plan             Yes
Number vmail messages        51
Total day minutes         350.8
Total day calls             165
Total day charge          59.64
Total eve minutes         363.7
Total eve calls             170
Total eve charge          30.91
Total night minutes         395
Total night calls           175
Total night charge        17.77
Total intl minutes           20
Total intl calls             20
Total intl charge           5.4
Customer service calls        9
Churn                         1
dtype: object

df[df['State'].apply(lambda state: state[0] == 'W')].head() #获取首字母为W的州 

d = {'No': False, 'Yes': True}
df['International plan'] = df['International plan'].map(d) #将No转换为False Yes转换为True
df.head()

df = df.replace({'Voice mail plan': d}) #用replace也可以达到相同的目的
df.head()

汇总表

pd.crosstab(df['Churn'], df['International plan'])

pd.crosstab(df['Churn'], df['Voice mail plan'], normalize=True)

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)以便将计算后的 Total calls 粘贴到最后一列
df.insert(loc=len(df.columns), column='Total calls', value=total_calls)

df.head()

df['Total charge'] = df['Total day charge'] + df['Total eve charge'] + \
    df['Total night charge'] + df['Total intl charge'] #不创造实例的情况下直接插入
df.head()