import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import phik


import warnings

def download(path):
    try:
        df = pd.read_csv('c:/users/norfolk/documents/python' + path, index_col=['customerID'])
    except:
        df = pd.read_csv(path)
    display(df.head(5))
    print('\n')
    print(df.info())
    return df

df_contract = download('/datasets/contract_new.csv')


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7043 entries, 0 to 7042
Data columns (total 8 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   customerID        7043 non-null   object 
 1   BeginDate         7043 non-null   object 
 2   EndDate           7043 non-null   object 
 3   Type              7043 non-null   object 
 4   PaperlessBilling  7043 non-null   object 
 5   PaymentMethod     7043 non-null   object 
 6   MonthlyCharges    7043 non-null   float64
 7   TotalCharges      7043 non-null   object 
dtypes: float64(1), object(7)
memory usage: 440.3+ KB
None

df_personal = download('/datasets/personal_new.csv')


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7043 entries, 0 to 7042
Data columns (total 5 columns):
 #   Column         Non-Null Count  Dtype 
---  ------         --------------  ----- 
 0   customerID     7043 non-null   object
 1   gender         7043 non-null   object
 2   SeniorCitizen  7043 non-null   int64 
 3   Partner        7043 non-null   object
 4   Dependents     7043 non-null   object
dtypes: int64(1), object(4)
memory usage: 275.2+ KB
None

df_internet = download('/datasets/internet_new.csv')


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5517 entries, 0 to 5516
Data columns (total 8 columns):
 #   Column            Non-Null Count  Dtype 
---  ------            --------------  ----- 
 0   customerID        5517 non-null   object
 1   InternetService   5517 non-null   object
 2   OnlineSecurity    5517 non-null   object
 3   OnlineBackup      5517 non-null   object
 4   DeviceProtection  5517 non-null   object
 5   TechSupport       5517 non-null   object
 6   StreamingTV       5517 non-null   object
 7   StreamingMovies   5517 non-null   object
dtypes: object(8)
memory usage: 344.9+ KB
None

df_phone = download('/datasets/phone_new.csv')


<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6361 entries, 0 to 6360
Data columns (total 2 columns):
 #   Column         Non-Null Count  Dtype 
---  ------         --------------  ----- 
 0   customerID     6361 non-null   object
 1   MultipleLines  6361 non-null   object
dtypes: object(2)
memory usage: 99.5+ KB
None

def ncol(df):
    df = df.rename(columns = {'customerID':'CustomerId'})
    df.columns = df.columns.str.replace(r"([A-Z])", r" \1").str.lower().str.replace(' ', '_').str[1:]
    print(list(df.columns),'\n')
    return df

warnings.filterwarnings('ignore')

df_personal = df_personal.rename(columns = {'gender':'Gender'})
df_personal = ncol(df_personal) 

df_contract = ncol(df_contract)

df_internet = ncol(df_internet)

df_phone = ncol(df_phone)

['gender', 'senior_citizen', 'partner', 'dependents'] 

['begin_date', 'end_date', 'type', 'paperless_billing', 'payment_method', 'monthly_charges', 'total_charges'] 

['internet_service', 'online_security', 'online_backup', 'device_protection', 'tech_support', 'streaming_t_v', 'streaming_movies'] 

['multiple_lines']

not_categorical = ['monthly_charges','total_charges','begin_date', 'end_date']
def cat_1(df):
    for i in df.columns:
        if i not in not_categorical:
            print(df[i].describe(),'\n')
            print('Пропуски',df[i].isna().sum(),'\n')
cat_1(df_personal)
print('\n*****************')
cat_1(df_contract)
print('\n*****************')
cat_1(df_internet)
print('\n*****************')
cat_1(df_phone)

count     7043
unique       2
top       Male
freq      3555
Name: gender, dtype: object 

Пропуски 0 

count    7043.000000
mean        0.162147
std         0.368612
min         0.000000
25%         0.000000
50%         0.000000
75%         0.000000
max         1.000000
Name: senior_citizen, dtype: float64 

Пропуски 0 

count     7043
unique       2
top         No
freq      3641
Name: partner, dtype: object 

Пропуски 0 

count     7043
unique       2
top         No
freq      4933
Name: dependents, dtype: object 

Пропуски 0 


*****************
count               7043
unique                 3
top       Month-to-month
freq                3875
Name: type, dtype: object 

Пропуски 0 

count     7043
unique       2
top        Yes
freq      4171
Name: paperless_billing, dtype: object 

Пропуски 0 

count                 7043
unique                   4
top       Electronic check
freq                  2365
Name: payment_method, dtype: object 

Пропуски 0 


*****************
count            5517
unique              2
top       Fiber optic
freq             3096
Name: internet_service, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      3498
Name: online_security, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      3088
Name: online_backup, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      3095
Name: device_protection, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      3473
Name: tech_support, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      2810
Name: streaming_t_v, dtype: object 

Пропуски 0 

count     5517
unique       2
top         No
freq      2785
Name: streaming_movies, dtype: object 

Пропуски 0 


*****************
count     6361
unique       2
top         No
freq      3390
Name: multiple_lines, dtype: object 

Пропуски 0

# используем фунцию т.к. категориальных данных много, а остальные обработаем вручную
def type_new(df):
    for i in df.columns:
        if i not in not_categorical:
            df[i] = df[i].astype('category')
    return df

df_contract = type_new(df_contract)
df_contract['total_charges'] = df_contract['total_charges'].replace(' ','0')
df_contract['total_charges'] = df_contract['total_charges'].astype('float')
df_contract['monthly_charges'] = df_contract['monthly_charges'].astype('float')

df_contract['begin_date']=pd.to_datetime(df_contract['begin_date'], format='%Y-%m-%d')
df_contract['end_date'] = df_contract['end_date'].replace('No',np.nan)
df_contract['end_date']=pd.to_datetime(df_contract['end_date'], format='%Y-%m-%d')
df_contract['end_date'] = df_contract['end_date'].fillna('2020-02-01')

df_contract.info()

<class 'pandas.core.frame.DataFrame'>
Index: 7043 entries, 7590-VHVEG to 3186-AJIEK
Data columns (total 7 columns):
 #   Column             Non-Null Count  Dtype         
---  ------             --------------  -----         
 0   begin_date         7043 non-null   datetime64[ns]
 1   end_date           7043 non-null   datetime64[ns]
 2   type               7043 non-null   category      
 3   paperless_billing  7043 non-null   category      
 4   payment_method     7043 non-null   category      
 5   monthly_charges    7043 non-null   float64       
 6   total_charges      7043 non-null   float64       
dtypes: category(3), datetime64[ns](2), float64(2)
memory usage: 296.2+ KB

df_personal = type_new(df_personal)
df_personal.info()

<class 'pandas.core.frame.DataFrame'>
Index: 7043 entries, 7590-VHVEG to 3186-AJIEK
Data columns (total 4 columns):
 #   Column          Non-Null Count  Dtype   
---  ------          --------------  -----   
 0   gender          7043 non-null   category
 1   senior_citizen  7043 non-null   category
 2   partner         7043 non-null   category
 3   dependents      7043 non-null   category
dtypes: category(4)
memory usage: 83.0+ KB

df_internet = type_new(df_internet)
df_internet.info()

<class 'pandas.core.frame.DataFrame'>
Index: 5517 entries, 7590-VHVEG to 3186-AJIEK
Data columns (total 7 columns):
 #   Column             Non-Null Count  Dtype   
---  ------             --------------  -----   
 0   internet_service   5517 non-null   category
 1   online_security    5517 non-null   category
 2   online_backup      5517 non-null   category
 3   device_protection  5517 non-null   category
 4   tech_support       5517 non-null   category
 5   streaming_t_v      5517 non-null   category
 6   streaming_movies   5517 non-null   category
dtypes: category(7)
memory usage: 81.7+ KB

df_phone = type_new(df_phone)
df_phone.info()

<class 'pandas.core.frame.DataFrame'>
Index: 6361 entries, 5575-GNVDE to 3186-AJIEK
Data columns (total 1 columns):
 #   Column          Non-Null Count  Dtype   
---  ------          --------------  -----   
 0   multiple_lines  6361 non-null   category
dtypes: category(1)
memory usage: 56.0+ KB

# используем функцию как и раньше для категорий и отдельно сотрим не бинарные данные
def plotting(df):
    for i in df.columns:
        if i not in not_categorical:
            plt.title('Распределение по значениям '+i, color ='brown')
            plt.xlabel(i)
            plt.ylabel('Количество клиентов')
            plt.xticks(rotation = 45)
            df[i].hist(figsize=(5,2), grid = True);
            plt.show()

plotting(df_personal)

plotting(df_contract)

plt.title('Распределение по расходам в месяц ', color ='brown')
plt.xlabel('Расход')
plt.ylabel('Количество')
df_contract['monthly_charges'].hist(bins = 50, figsize=(5,2), grid = True);
plt.show()

plt.title('Распределение расходов за все время ', color ='brown')
plt.xlabel('Расход')
plt.ylabel('Количество')
df_contract['total_charges'].hist(bins = 50, figsize=(5,2), grid = True);

plotting(df_internet)

plotting(df_phone)

sns.heatmap(df_contract.phik_matrix(), annot =True);

interval columns not set, guessing: ['monthly_charges', 'total_charges']

Содержание

Телеком — задача проекта¶

Оператор предоставляет два основных типа услуг:¶

Также доступны такие услуги:¶

Данные состоят из файлов, полученных из разных источников:¶

Загрузка данных¶

Переименуем колонки¶

Приведем типы колонок в соответсвие¶

Визуализирум наши датасеты¶

План работы¶

	customerID	BeginDate	EndDate	Type	PaperlessBilling	PaymentMethod	MonthlyCharges	TotalCharges
0	7590-VHVEG	2020-01-01	No	Month-to-month	Yes	Electronic check	29.85	31.04
1	5575-GNVDE	2017-04-01	No	One year	No	Mailed check	56.95	2071.84
2	3668-QPYBK	2019-10-01	No	Month-to-month	Yes	Mailed check	53.85	226.17
3	7795-CFOCW	2016-05-01	No	One year	No	Bank transfer (automatic)	42.30	1960.6
4	9237-HQITU	2019-09-01	No	Month-to-month	Yes	Electronic check	70.70	353.5

	customerID	gender	Partner	Dependents
0	7590-VHVEG	Female	Yes	No
1	5575-GNVDE	Male	No	No
2	3668-QPYBK	Male	No	No
3	7795-CFOCW	Male	No	No
4	9237-HQITU	Female	No	No