In [1]:

    

%matplotlib inline

import os
import requests
import pandas as pd 
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import csv
import sys


csv.field_size_limit(sys.maxsize)

reviews = "/Users/skhederian/restaurant-health/format_reviews.csv"
data = "/Users/skhederian/restaurant-health/the_final_countdown.csv"

dfr = pd.read_csv(reviews)
dfd = pd.read_csv(data)


    

In [2]:

    

#Drop NaN Violations
dfreview = dfr.dropna(how = 'any').copy()
dfreview.shape


    

    
Out[2]:





(20377, 5)

In [3]:

    

#Load our Pickle Classifier
from sklearn.externals import joblib

filename = 'class.pkl'
clf = joblib.load(filename)


    

In [4]:

    

predict = clf.predict(dfreview['string_agg'].values)
predict.shape


    

    
Out[4]:





(20377,)

In [5]:

    

dfreview['predictions'] = predict


    

In [6]:

    

dfreview.head()


    

    
Out[6]:






  

    

      

      
business_id
      
from_date
      
thru_date
      
violations
      
string_agg
      
predictions
    
  
  

    

      
0
      
--pOlFxITWnhzc7SHSIP0A
      
2013-04-04
      
2013-07-29
      
9.0
      
My group of four visited tonight for the first...
      
Great
    
    

      
1
      
--pOlFxITWnhzc7SHSIP0A
      
2013-07-30
      
2013-10-29
      
12.0
      
My husband and I  recently ate dinner here for...
      
Great
    
    

      
2
      
--pOlFxITWnhzc7SHSIP0A
      
2013-10-30
      
2014-03-19
      
9.0
      
Our waiter Chris was excellent!!!!!!!!!! My bu...
      
Perfect
    
    

      
3
      
--pOlFxITWnhzc7SHSIP0A
      
2014-03-20
      
2014-06-11
      
6.0
      
I would like to Thank the staff at Block and G...
      
Great
    
    

      
4
      
--pOlFxITWnhzc7SHSIP0A
      
2014-06-12
      
2014-09-17
      
3.0
      
Pork Belly appetizer was to die for!  A little...
      
Perfect
    
  

In [7]:

    

df = dfreview.replace('2999-12-31','2017-01-01')


    

In [8]:

    

df.rename(columns = {'--business_id':'_id'}, inplace = True)


    

In [9]:

    

df['thru_date'] = pd.to_datetime(df['thru_date'], coerce=True)
dfd['inspection_date'] = pd.to_datetime(dfd['inspection_date'], coerce=True)
df['inspection_date'] = pd.DatetimeIndex(df['thru_date']) + pd.DateOffset(1)


    

    




//anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: FutureWarning: the coerce=True keyword is deprecated, use errors='coerce' instead
  if __name__ == '__main__':
//anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:2: FutureWarning: the coerce=True keyword is deprecated, use errors='coerce' instead
  from ipykernel import kernelapp as app

In [10]:

    

finaldf = pd.merge(dfd, df, on=['business_id', 'inspection_date'], how='inner')


    

In [11]:

    

finaldf.shape


    

    
Out[11]:





(18879, 73)

In [12]:

    

group_names = {'Perfect':5, 'Excellent':10, 'Great':15, 'Good':20, 'Bad':25, 'Very Bad':30, 'rats':35, 'Shutdown':40}

finaldf.predictions = finaldf.predictions.map(group_names)
finaldf.predictions.unique()


    

    
Out[12]:





array([25, 20, 10,  5, 30, 15, 35, 40])

In [13]:

    

finaldf.to_csv('pickles.csv')