In [1]:

    

import pandas as pd


    

In [2]:

    

review = pd.read_csv('../../../data/interim/US_cities_only/review_US.csv')


    

In [45]:

    

review.head()


    

    
Out[45]:






  

    

      

      
business_id
      
cool
      
date
      
funny
      
review_id
      
stars
      
text
      
type
      
useful
      
user_id
    
  
  

    

      
0
      
2aFiy99vNLklCx3T_tGS9A
      
0
      
2011-10-10
      
0
      
NxL8SIC5yqOdnlXCg18IBg
      
5.0
      
If you enjoy service by someone who is as comp...
      
review
      
0
      
KpkOkG6RIf4Ra25Lhhxf1A
    
    

      
1
      
2aFiy99vNLklCx3T_tGS9A
      
0
      
2010-12-29
      
0
      
pXbbIgOXvLuTi_SPs1hQEQ
      
5.0
      
After being on the phone with Verizon Wireless...
      
review
      
1
      
bQ7fQq1otn9hKX-gXRsrgA
    
    

      
2
      
2aFiy99vNLklCx3T_tGS9A
      
0
      
2011-04-29
      
0
      
wslW2Lu4NYylb1jEapAGsw
      
5.0
      
Great service! Corey is very service oriented....
      
review
      
0
      
r1NUhdNmL6yU9Bn-Yx6FTw
    
    

      
3
      
2LfIuF3_sX6uwe-IR-P0jQ
      
1
      
2014-07-14
      
0
      
GP6YEearUWrzPtQYSF1vVg
      
5.0
      
Highly recommended. Went in yesterday looking ...
      
review
      
0
      
aW3ix1KNZAvoM8q-WghA3Q
    
    

      
4
      
2LfIuF3_sX6uwe-IR-P0jQ
      
0
      
2014-01-15
      
0
      
25RlYGq2s5qShi-pn3ufVA
      
4.0
      
I walked in here looking for a specific piece ...
      
review
      
0
      
YOo-Cip8HqvKp_p9nEGphw
    
  

In [44]:

    

review.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3457015 entries, 0 to 3457014
Data columns (total 10 columns):
business_id    object
cool           int64
date           datetime64[ns]
funny          int64
review_id      object
stars          float64
text           object
type           object
useful         int64
user_id        object
dtypes: datetime64[ns](1), float64(1), int64(3), object(5)
memory usage: 263.7+ MB

In [38]:

    

review.describe()


    

    
Out[38]:






  

    

      

      
cool
      
funny
      
stars
      
useful
    
  
  

    

      
count
      
3.457015e+06
      
3.457015e+06
      
3.457015e+06
      
3.457015e+06
    
    

      
mean
      
5.461839e-01
      
4.455893e-01
      
3.741661e+00
      
1.048886e+00
    
    

      
std
      
2.035434e+00
      
1.832262e+00
      
1.428476e+00
      
2.744492e+00
    
    

      
min
      
0.000000e+00
      
0.000000e+00
      
1.000000e+00
      
0.000000e+00
    
    

      
25%
      
0.000000e+00
      
0.000000e+00
      
3.000000e+00
      
0.000000e+00
    
    

      
50%
      
0.000000e+00
      
0.000000e+00
      
4.000000e+00
      
0.000000e+00
    
    

      
75%
      
0.000000e+00
      
0.000000e+00
      
5.000000e+00
      
1.000000e+00
    
    

      
max
      
5.130000e+02
      
6.320000e+02
      
5.000000e+00
      
1.125000e+03
    
  

In [3]:

    

# Cleaning the 'date' column

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


    

In [4]:

    

# Cleaning the 'useful' column

review['useful'] = review['useful'].fillna(0)
review['useful'] = review['useful'].map(int)


    

In [13]:

    

# Reading clean vegas_three_years reviews and writing 2016 reviews

review = pd.read_csv('../../../data/interim/clean_US_cities/reviews_vegas_threeyears.csv')
review['date'] = pd.to_datetime(review['date'])
review = review.loc[review['date'] > '2015-12-31']
review.to_csv('../../../data/interim/clean_US_cities/2016_review.csv', encoding='utf-8', index=False)


    

In [46]:

    

# Writing clean 'review' dataframe to csv

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