In [13]:

    

import numpy as np
import pandas as pd
import matplotlib.pyplot as plot
import matplotlib
matplotlib.style.use("ggplot")
%matplotlib inline


    

In [14]:

    

fingerlakes_data = pd.read_csv("Norm_Trans_OPR_Fingerlakes - Sheet1.csv")


    

In [15]:

    

fingerlakes_data


    

    
Out[15]:






  

    

      

      
Fingerlakes
      
20
      
73
      
174
      
191
      
250
      
340
      
369
      
378
      
395
      
...
      
3838
      
3951
      
4023
      
4093
      
4930
      
5030
      
5254
      
5349
      
5433
      
5590
    
  
  

    

      
0
      
OPR 2015
      
0.782362
      
0.131340
      
0.490159
      
0.765708
      
0.753217
      
0.884557
      
0.242241
      
0.767222
      
0.482210
      
...
      
0.819076
      
0.612793
      
NaN
      
0.394777
      
0.445496
      
0.88645
      
1.000000
      
0.214989
      
0.045042
      
0.723316
    
    

      
1
      
OPR 2014
      
0.957689
      
0.663954
      
0.676159
      
0.612693
      
0.598454
      
0.790073
      
0.847437
      
0.870627
      
0.534581
      
...
      
0.096420
      
0.511391
      
0.109032
      
0.173312
      
0.770545
      
0.81367
      
0.913344
      
0.786412
      
NaN
      
NaN
    
    

      
2
      
OPR 2013
      
1.000000
      
0.039917
      
0.633264
      
0.843243
      
0.855717
      
0.944283
      
0.940541
      
0.883992
      
0.437838
      
...
      
0.702703
      
0.331393
      
0.116008
      
0.232848
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
3
      
OPR 2012
      
0.625440
      
0.494278
      
0.923415
      
0.863116
      
0.762764
      
0.974032
      
0.889085
      
0.541813
      
0.778609
      
...
      
0.740757
      
0.690581
      
0.000000
      
0.273327
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4
      
OPR 2011
      
0.916688
      
0.666494
      
0.214748
      
0.035705
      
0.142303
      
0.919017
      
0.138680
      
0.558603
      
0.254334
      
...
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
5
      
OPR 2010
      
1.000000
      
0.140302
      
0.909343
      
0.863398
      
0.117484
      
0.799568
      
NaN
      
0.000000
      
0.238051
      
...
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
6
      
OPR 2009
      
0.945262
      
0.796784
      
0.535751
      
0.619569
      
0.922682
      
0.878549
      
0.063975
      
0.872733
      
0.868628
      
...
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
7
      
OPR 2008
      
0.320376
      
0.000000
      
0.770049
      
0.436170
      
0.540098
      
0.734452
      
0.356792
      
0.044599
      
0.868249
      
...
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
  

8 rows × 50 columns

In [16]:

    

def make_data_groups(dataframe, column_names):
    master_group = []
    for i in column_names:
        group = []
        group.append(dataframe[i])
        master_group.append(group)
    return master_group

check_it_out = make_data_groups(fingerlakes_data, team_numbers_list)


    

    




---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-16-2312f6ea0541> in <module>()
      7     return master_group
      8 
----> 9 check_it_out = make_data_groups(fingerlakes_data, team_numbers_list)

<ipython-input-16-2312f6ea0541> in make_data_groups(dataframe, column_names)
      3     for i in column_names:
      4         group = []
----> 5         group.append(dataframe[i])
      6         master_group.append(group)
      7     return master_group

/Users/dinbecevic/anaconda/lib/python2.7/site-packages/pandas/core/frame.pyc in __getitem__(self, key)
   1967             return self._getitem_multilevel(key)
   1968         else:
-> 1969             return self._getitem_column(key)
   1970 
   1971     def _getitem_column(self, key):

/Users/dinbecevic/anaconda/lib/python2.7/site-packages/pandas/core/frame.pyc in _getitem_column(self, key)
   1974         # get column
   1975         if self.columns.is_unique:
-> 1976             return self._get_item_cache(key)
   1977 
   1978         # duplicate columns & possible reduce dimensionality

/Users/dinbecevic/anaconda/lib/python2.7/site-packages/pandas/core/generic.pyc in _get_item_cache(self, item)
   1089         res = cache.get(item)
   1090         if res is None:
-> 1091             values = self._data.get(item)
   1092             res = self._box_item_values(item, values)
   1093             cache[item] = res

/Users/dinbecevic/anaconda/lib/python2.7/site-packages/pandas/core/internals.pyc in get(self, item, fastpath)
   3209 
   3210             if not isnull(item):
-> 3211                 loc = self.items.get_loc(item)
   3212             else:
   3213                 indexer = np.arange(len(self.items))[isnull(self.items)]

/Users/dinbecevic/anaconda/lib/python2.7/site-packages/pandas/core/index.pyc in get_loc(self, key, method, tolerance)
   1757                                  'backfill or nearest lookups')
   1758             key = _values_from_object(key)
-> 1759             return self._engine.get_loc(key)
   1760 
   1761         indexer = self.get_indexer([key], method=method,

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:3979)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:3843)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12265)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12216)()

KeyError: 'OPR 2015'

In [ ]:

    

team_numbers = fingerlakes_data[:0]
team_numbers_list = list(team_numbers)
del team_numbers_list[0]
# team_numbers_list = map(int, team_numbers_list)
print team_numbers_list

medians = fingerlakes_data.median()
sorted_medians = medians.sort_values()
sorted_med_list = list(sorted_medians)
median_keys = list(sorted_medians.keys())
real_keys = median_keys.reverse()


    

In [ ]:

    

check_it_out = make_data_groups(fingerlakes_data, median_keys)

labels = median_keys

figure = plot.boxplot(check_it_out)
plot.title('Standardized OPR from 2008-2015 (Fingerlakes)', fontsize=32)
plot.ylabel('Adjusted OPR', fontsize=24)
plot.xlabel('Team Number', fontsize=24)
fig = matplotlib.pyplot.gcf()
fig.set_size_inches(20, 10)
plot.xticks(range(52), labels, rotation='vertical')
plot.savefig('opr_boxplots_fingerlakes.png')