In [11]:

    

%config InlineBackend.figure_format = 'retina'
%matplotlib inline

import numpy as np
import scipy as sp
import matplotlib.pyplot as plt
import pandas as pd

import seaborn as sns
sns.set_style("white")


    

In [12]:

    

filename="burrito_current.csv"
df = pd.read_csv(filename)
N = df.shape[0]


    

In [14]:

    

# Avoid case issues; in the future should avoid article issues
df.Location = df.Location.str.lower()
m_Location = ['Location','N','Yelp','Google','Hunger','Cost','Volume','Tortilla','Temp','Meat','Fillings','Meat:filling',
               'Uniformity','Salsa','Synergy','Wrap','overall']

tacoshops = df.Location.unique()
TS = len(tacoshops)
dfmean = pd.DataFrame(np.nan, index=range(TS), columns=m_Location)
for ts in range(TS):
    dfmean.loc[ts] = df.loc[df.Location==tacoshops[ts]].mean()
    dfmean['N'][ts] = sum(df.Location == tacoshops[ts])
dfmean.Location = tacoshops


    

In [53]:

    

Ncutoff = 8
dfToRank = dfmean.loc[dfmean.N>=Ncutoff]


    

In [54]:

    

dfToRank


    

    
Out[54]:






  

    

      

      
Location
      
N
      
Yelp
      
Google
      
Hunger
      
Cost
      
Volume
      
Tortilla
      
Temp
      
Meat
      
Fillings
      
Meat:filling
      
Uniformity
      
Salsa
      
Synergy
      
Wrap
      
overall
    
  
  

    

      
7
      
taco stand
      
15
      
4.5
      
4.400000
      
3.100000
      
7.727333
      
0.787143
      
3.566667
      
2.933333
      
4.266667
      
3.966667
      
4.033333
      
3.766667
      
3.933333
      
4.2
      
3.966667
      
4.126667
    
    

      
9
      
rigoberto's taco shop
      
15
      
3.8
      
4.346667
      
3.533333
      
6.700000
      
0.930000
      
3.700000
      
3.866667
      
3.660714
      
3.700000
      
4.133333
      
3.766667
      
3.225000
      
4.0
      
3.866667
      
3.796667
    
    

      
18
      
vallarta express
      
9
      
3.5
      
4.000000
      
3.500000
      
6.933333
      
0.880000
      
2.916667
      
4.357143
      
3.277778
      
3.444444
      
3.611111
      
3.166667
      
3.500000
      
3.0
      
3.611111
      
3.500000
    
  

In [55]:

    

m_Rank = ['Location','Cost','Volume','Tortilla','Temp','Meat','Fillings','Meat:filling', 'Uniformity','Salsa','Synergy','Wrap','overall']
TS = len(dfToRank)
dfRanked = pd.DataFrame(np.nan, index=range(TS), columns=m_Rank)
dfRanked.Location[:] = dfToRank.Location
for m in m_Rank[1:]:
    if m == 'Cost':
        dfRanked[m][:] = dfToRank[m].rank(ascending=1)
    else:
        dfRanked[m][:] = dfToRank[m].rank(ascending=0)


    

    




C:\Users\Scott\Anaconda2\lib\site-packages\ipykernel\__main__.py:7: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
C:\Users\Scott\Anaconda2\lib\site-packages\ipykernel\__main__.py:9: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy

In [56]:

    

dfRanked


    

    
Out[56]:






  

    

      

      
Location
      
Cost
      
Volume
      
Tortilla
      
Temp
      
Meat
      
Fillings
      
Meat:filling
      
Uniformity
      
Salsa
      
Synergy
      
Wrap
      
overall
    
  
  

    

      
0
      
taco stand
      
3
      
3
      
2
      
3
      
1
      
1
      
2
      
1.5
      
1
      
1
      
1
      
1
    
    

      
1
      
rigoberto's taco shop
      
1
      
1
      
1
      
2
      
2
      
2
      
1
      
1.5
      
3
      
2
      
2
      
2
    
    

      
2
      
vallarta express
      
2
      
2
      
3
      
1
      
3
      
3
      
3
      
3.0
      
2
      
3
      
3
      
3
    
  

In [ ]:

    

#TODO