In [1]:

    

import pandas as pd


    

In [2]:

    

tip = pd.read_csv('../../../data/interim/US_cities_only/tip_US.csv')


    

In [3]:

    

tip.head()


    

    
Out[3]:






  

    

      

      
business_id
      
date
      
likes
      
text
      
type
      
user_id
    
  
  

    

      
0
      
dAa0hB2yrnHzVmsCkN4YvQ
      
2014-06-20
      
0
      
Nice place. Great staff.  A fixture in the tow...
      
tip
      
oaYhjqBbh18ZhU0bpyzSuw
    
    

      
1
      
dAa0hB2yrnHzVmsCkN4YvQ
      
2016-10-12
      
0
      
Happy hour 5-7 Monday - Friday
      
tip
      
ulQ8Nyj7jCUR8M83SUMoRQ
    
    

      
2
      
SqW3igh1_Png336VIb5DUA
      
2016-07-03
      
0
      
Come early on Sunday's to avoid the rush
      
tip
      
ulQ8Nyj7jCUR8M83SUMoRQ
    
    

      
3
      
KNpcPGqDORDdvtekXd348w
      
2016-01-07
      
0
      
Love their soup!
      
tip
      
ulQ8Nyj7jCUR8M83SUMoRQ
    
    

      
4
      
KNpcPGqDORDdvtekXd348w
      
2016-05-22
      
0
      
Soups are fantastic!
      
tip
      
ulQ8Nyj7jCUR8M83SUMoRQ
    
  

In [4]:

    

# Cleaning 'date' column

tip['date'] = pd.to_datetime(tip['date'])


    

In [5]:

    

tip.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 833142 entries, 0 to 833141
Data columns (total 6 columns):
business_id    833142 non-null object
date           833142 non-null datetime64[ns]
likes          833142 non-null int64
text           833142 non-null object
type           833142 non-null object
user_id        833142 non-null object
dtypes: datetime64[ns](1), int64(1), object(4)
memory usage: 38.1+ MB

In [6]:

    

tip.describe()


    

    
Out[6]:






  

    

      

      
likes
    
  
  

    

      
count
      
833142.000000
    
    

      
mean
      
0.016962
    
    

      
std
      
0.148393
    
    

      
min
      
0.000000
    
    

      
25%
      
0.000000
    
    

      
50%
      
0.000000
    
    

      
75%
      
0.000000
    
    

      
max
      
15.000000
    
  

In [7]:

    

# Writing clean 'tip' dataframe to csv

tip.to_csv('../../../data/interim/clean_US_cities/tip_clean.csv', encoding='utf-8', index=False)