In [197]:

    

import pandas as pd
import matplotlib.pyplot as plt
import math
import scipy
import numpy
import sklearn
#from sklearn import datasets, linear_model, metrics


    

In [198]:

    

b = pd.DataFrame.from_csv('../data/raw/blood_train.csv')


    

In [199]:

    

b[:5]


    

    
Out[199]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Total Volume Donated (c.c.)
      
Months since First Donation
      
Made Donation in March 2007
    
  
  

    

      
619
      
 2
      
 50
      
 12500
      
 98
      
 1
    
    

      
664
      
 0
      
 13
      
  3250
      
 28
      
 1
    
    

      
441
      
 1
      
 16
      
  4000
      
 35
      
 1
    
    

      
160
      
 2
      
 20
      
  5000
      
 45
      
 1
    
    

      
358
      
 1
      
 24
      
  6000
      
 77
      
 0
    
  

In [200]:

    

b.describe()


    

    
Out[200]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Total Volume Donated (c.c.)
      
Months since First Donation
      
Made Donation in March 2007
    
  
  

    

      
count
      
 576.000000
      
 576.000000
      
   576.000000
      
 576.000000
      
 576.000000
    
    

      
mean
      
   9.439236
      
   5.427083
      
  1356.770833
      
  34.050347
      
   0.239583
    
    

      
std
      
   8.175454
      
   5.740010
      
  1435.002556
      
  24.227672
      
   0.427200
    
    

      
min
      
   0.000000
      
   1.000000
      
   250.000000
      
   2.000000
      
   0.000000
    
    

      
25%
      
   2.000000
      
   2.000000
      
   500.000000
      
  16.000000
      
   0.000000
    
    

      
50%
      
   7.000000
      
   4.000000
      
  1000.000000
      
  28.000000
      
   0.000000
    
    

      
75%
      
  14.000000
      
   7.000000
      
  1750.000000
      
  49.250000
      
   0.000000
    
    

      
max
      
  74.000000
      
  50.000000
      
 12500.000000
      
  98.000000
      
   1.000000
    
  

In [201]:

    

#saving this to remember how to plot inline
%matplotlib inline
plt.scatter(x=b['Months since Last Donation'], y=b['Months since First Donation'], c=b['Made Donation in March 2007'], cmap='prism')


    

    
Out[201]:





<matplotlib.collections.PathCollection at 0x11f1db790>






    

In [202]:

    

%matplotlib inline
b.hist(figsize=(20,20))


    

    
Out[202]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x11f1e0210>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x11fe7afd0>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x12000ac90>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x12007d0d0>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x1200fd190>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x1200a9190>]], dtype=object)






    

In [203]:

    

b.kurtosis()


    

    
Out[203]:





Months since Last Donation     11.416687
Number of Donations            18.940493
Total Volume Donated (c.c.)    18.940493
Months since First Donation    -0.192772
Made Donation in March 2007    -0.504993
dtype: float64

In [204]:

    

b.skew()


    

    
Out[204]:





Months since Last Donation     2.071107
Number of Donations            3.503331
Total Volume Donated (c.c.)    3.503331
Months since First Donation    0.767706
Made Donation in March 2007    1.223427
dtype: float64

In [205]:

    

#everything is heavily skewed, well, except months since first donation
#as we have discussed Total Volume Donated (c.c.) is equal to Number of Donations
#in some cases their are major outliers, perhaps we could cap the value at something much lower and set higher values to that
b1 = b[['Months since Last Donation', 'Number of Donations','Months since First Donation',
        'Made Donation in March 2007']]


    

In [206]:

    

b1.columns.values


    

    
Out[206]:





array(['Months since Last Donation', 'Number of Donations',
       'Months since First Donation', 'Made Donation in March 2007'], dtype=object)

In [207]:

    

b1[b1['Months since Last Donation'] > 30]
#note people with really big last donations it's equal to their first donation, maybe they donated once and then
#were like "I hate this" and never donated again


    

    
Out[207]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Months since First Donation
      
Made Donation in March 2007
    
  
  

    

      
673
      
 35
      
 3
      
 64
      
 0
    
    

      
350
      
 74
      
 1
      
 74
      
 0
    
    

      
541
      
 39
      
 1
      
 39
      
 0
    
    

      
74 
      
 72
      
 1
      
 72
      
 0
    
  

In [208]:

    

#b1[(b1['Months since Last Donation']==b1['Months since First Donation'])&(b1['Made Donation in March 2007']==1)]
#.count()


    

In [209]:

    

#print float(18)/float(144)


    

In [210]:

    

#b1.keys()


    

In [212]:

    

b1['Months since Last Donation Outliers Removed'] = b1['Months since Last Donation']
b1.loc[b1['Months since Last Donation'] > 35, 'Months since Last Donation Outliers Removed'] = 35
#b1[b1['Months since Last Donation Outliers Removed'].apply(lambda x: x > 35)] = 35


    

    




/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_index,col_indexer] = value instead
  if __name__ == '__main__':
/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:2: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame
  from ipykernel import kernelapp as app

In [213]:

    

b1[b1['Months since Last Donation Outliers Removed'] > 30]


    

    
Out[213]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Months since First Donation
      
Made Donation in March 2007
      
Months since Last Donation Outliers Removed
    
  
  

    

      
673
      
 35
      
 3
      
 64
      
 0
      
 35
    
    

      
350
      
 74
      
 1
      
 74
      
 0
      
 35
    
    

      
541
      
 39
      
 1
      
 39
      
 0
      
 35
    
    

      
74 
      
 72
      
 1
      
 72
      
 0
      
 35
    
  

In [214]:

    

b1[b1['Number of Donations']>30]


    

    
Out[214]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Months since First Donation
      
Made Donation in March 2007
      
Months since Last Donation Outliers Removed
    
  
  

    

      
619
      
  2
      
 50
      
 98
      
 1
      
  2
    
    

      
736
      
  5
      
 46
      
 98
      
 1
      
  5
    
    

      
451
      
 23
      
 38
      
 98
      
 0
      
 23
    
    

      
39 
      
  2
      
 43
      
 86
      
 1
      
  2
    
    

      
149
      
  2
      
 44
      
 98
      
 0
      
  2
    
    

      
157
      
  4
      
 33
      
 98
      
 1
      
  4
    
  

In [215]:

    

##okay, need to save this to remember how it works, but sqrt didn't normalize quite as much as I hoped... though way better
b1['Months since Last Donation square root'] = b1['Months since Last Donation Outliers Removed'].apply(math.sqrt)
#b1['Months since Last Donation log'] = (b1['Months since Last Donation']+1).apply(numpy.log)
#b1['Months since Last Donation reciprocal'] = 1/(b1['Months since Last Donation']+1)
#oh yea, log and reciprocal won't work well because there are zeroes, would need to add one to all values before proceeding
#cool, so sqrt wins anyway... 

#b1['Number of Donations square root'] = b1['Number of Donations'].apply(math.sqrt)
b1['Number of Donations log'] = (b1['Number of Donations']+1).apply(numpy.log)
#b1['Number of Donations reciprocal'] = 1/(b1['Number of Donations']+1)
#log wins here


    

In [216]:

    

b1.hist(figsize=(20,20))


    

    
Out[216]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x120089b10>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x1205a4850>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x12112b310>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x12131a2d0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x121390f50>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x1213ecbd0>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x12147cad0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x121601790>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x121670350>]], dtype=object)






    

In [217]:

    

print "SKEW"
print b1.skew()
print ""
print "KURTOSIS"
print b1.kurtosis()


    

    




SKEW
Months since Last Donation                     2.071107
Number of Donations                            3.503331
Months since First Donation                    0.767706
Made Donation in March 2007                    1.223427
Months since Last Donation Outliers Removed    0.742492
Months since Last Donation square root         0.234546
Number of Donations log                        0.446914
dtype: float64

KURTOSIS
Months since Last Donation                     11.416687
Number of Donations                            18.940493
Months since First Donation                    -0.192772
Made Donation in March 2007                    -0.504993
Months since Last Donation Outliers Removed    -0.305992
Months since Last Donation square root         -1.160537
Number of Donations log                        -0.254753
dtype: float64

In [218]:

    

#also, is there a way to get odds ratios or percent liklihood from logistic regression in python? there is in R so it seems likely...
b1.keys()


    

    
Out[218]:





Index([u'Months since Last Donation', u'Number of Donations', u'Months since First Donation', u'Made Donation in March 2007', u'Months since Last Donation Outliers Removed', u'Months since Last Donation square root', u'Number of Donations log'], dtype='object')

In [219]:

    

b2 = b1[['Months since Last Donation square root', 'Number of Donations log', 'Months since First Donation', 'Made Donation in March 2007']]


    

In [220]:

    

b2[:5]


    

    
Out[220]:






  

    

      

      
Months since Last Donation square root
      
Number of Donations log
      
Months since First Donation
      
Made Donation in March 2007
    
  
  

    

      
619
      
 1.414214
      
 3.931826
      
 98
      
 1
    
    

      
664
      
 0.000000
      
 2.639057
      
 28
      
 1
    
    

      
441
      
 1.000000
      
 2.833213
      
 35
      
 1
    
    

      
160
      
 1.414214
      
 3.044522
      
 45
      
 1
    
    

      
358
      
 1.000000
      
 3.218876
      
 77
      
 0
    
  

In [221]:

    

b2.keys()


    

    
Out[221]:





Index([u'Months since Last Donation square root', u'Number of Donations log', u'Months since First Donation', u'Made Donation in March 2007'], dtype='object')

In [222]:

    

pred = b2[['Months since Last Donation square root', 'Number of Donations log', 'Months since First Donation']]
outcomes = b2[['Made Donation in March 2007']]
fit1 = linear_model.LinearRegression()


    

In [223]:

    

fit1.fit(pred, outcomes)


    

    
Out[223]:





LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

In [224]:

    

fit2 = linear_model.LogisticRegression()
fit2.fit(pred, outcomes)


    

    
Out[224]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [225]:

    

fit2.coef_


    

    
Out[225]:





array([[-0.45450825,  1.38811617, -0.02827812]])

In [226]:

    

v= pd.DataFrame(fit2.predict_proba(pred))


    

In [227]:

    

v.describe()


    

    
Out[227]:






  

    

      

      
0
      
1
    
  
  

    

      
count
      
 576.000000
      
 576.000000
    
    

      
mean
      
   0.757990
      
   0.242010
    
    

      
std
      
   0.166845
      
   0.166845
    
    

      
min
      
   0.186097
      
   0.005404
    
    

      
25%
      
   0.651773
      
   0.095229
    
    

      
50%
      
   0.793474
      
   0.206526
    
    

      
75%
      
   0.904771
      
   0.348227
    
    

      
max
      
   0.994596
      
   0.813903
    
  

In [228]:

    

v[:5]


    

    
Out[228]:






  

    

      

      
0
      
1
    
  
  

    

      
0
      
 0.343475
      
 0.656525
    
    

      
1
      
 0.186097
      
 0.813903
    
    

      
2
      
 0.251124
      
 0.748876
    
    

      
3
      
 0.285997
      
 0.714003
    
    

      
4
      
 0.391671
      
 0.608329
    
  

In [229]:

    

bt = pd.DataFrame.from_csv('../data/raw/blood_test.csv')


    

In [230]:

    

#need to to do square-rooting and logging and what not
bt[:5]
#could just redo by hand, or make a function that does above?
#vt= pd.DataFrame(fit2.predict_proba(bt))


    

    
Out[230]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Total Volume Donated (c.c.)
      
Months since First Donation
    
  
  

    

      
659
      
  2
      
 12
      
 3000
      
 52
    
    

      
276
      
 21
      
  7
      
 1750
      
 38
    
    

      
263
      
  4
      
  1
      
  250
      
  4
    
    

      
303
      
 11
      
 11
      
 2750
      
 38
    
    

      
83 
      
  4
      
 12
      
 3000
      
 34
    
  

In [231]:

    

bt.count()


    

    
Out[231]:





Months since Last Donation     200
Number of Donations            200
Total Volume Donated (c.c.)    200
Months since First Donation    200
dtype: int64

In [232]:

    

b2.iloc[1:4, 0:3]


    

    
Out[232]:






  

    

      

      
Months since Last Donation square root
      
Number of Donations log
      
Months since First Donation
    
  
  

    

      
664
      
 0.000000
      
 2.639057
      
 28
    
    

      
441
      
 1.000000
      
 2.833213
      
 35
    
    

      
160
      
 1.414214
      
 3.044522
      
 45
    
  

In [233]:

    

X = b2.iloc[:,0:3].as_matrix()
y = list(b2["Made Donation in March 2007"])

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score

clf   = linear_model.LogisticRegression()
score = sklearn.model_selection.cross_val_score( 
    clf, 
    X, y,
    scoring="neg_log_loss")

print(score)


    

    




[-0.57866836 -0.50813732 -0.48442203]

In [234]:

    

bt[1:5]


    

    
Out[234]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Total Volume Donated (c.c.)
      
Months since First Donation
    
  
  

    

      
276
      
 21
      
  7
      
 1750
      
 38
    
    

      
263
      
  4
      
  1
      
  250
      
  4
    
    

      
303
      
 11
      
 11
      
 2750
      
 38
    
    

      
83 
      
  4
      
 12
      
 3000
      
 34
    
  

In [241]:

    

bt1 = bt[['Months since Last Donation', 'Number of Donations','Months since First Donation']]
bt1['Months since Last Donation Outliers Removed'] = bt1['Months since Last Donation']
bt1.loc[bt1['Months since Last Donation'] > 35, 'Months since Last Donation Outliers Removed'] = 35


    

    




/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:3: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame
  app.launch_new_instance()

In [242]:

    

bt1[1:5]


    

    
Out[242]:






  

    

      

      
Months since Last Donation
      
Number of Donations
      
Months since First Donation
      
Months since Last Donation Outliers Removed
    
  
  

    

      
276
      
 21
      
  7
      
 38
      
 21
    
    

      
263
      
  4
      
  1
      
  4
      
  4
    
    

      
303
      
 11
      
 11
      
 38
      
 11
    
    

      
83 
      
  4
      
 12
      
 34
      
  4
    
  

In [243]:

    

bt1['Months since Last Donation square root'] = bt1['Months since Last Donation Outliers Removed'].apply(math.sqrt)

bt1['Number of Donations log'] = (bt1['Number of Donations']+1).apply(numpy.log)


    

In [244]:

    

bt2 = bt1[['Months since Last Donation square root', 'Number of Donations log', 'Months since First Donation']]


    

In [245]:

    

bt2[1:5]


    

    
Out[245]:






  

    

      

      
Months since Last Donation square root
      
Number of Donations log
      
Months since First Donation
    
  
  

    

      
276
      
 4.582576
      
 2.079442
      
 38
    
    

      
263
      
 2.000000
      
 0.693147
      
  4
    
    

      
303
      
 3.316625
      
 2.484907
      
 38
    
    

      
83 
      
 2.000000
      
 2.564949
      
 34
    
  

In [246]:

    

clf.fit(X,y)


    

    
Out[246]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [247]:

    

clf.predict_proba(bt2)


    

    
Out[247]:





array([[ 0.48718888,  0.51281112],
       [ 0.84115388,  0.15884612],
       [ 0.81090761,  0.18909239],
       [ 0.62916139,  0.37083861],
       [ 0.42702072,  0.57297928],
       [ 0.28498733,  0.71501267],
       [ 0.70952654,  0.29047346],
       [ 0.92623866,  0.07376134],
       [ 0.98913085,  0.01086915],
       [ 0.9353713 ,  0.0646287 ],
       [ 0.8267581 ,  0.1732419 ],
       [ 0.85447363,  0.14552637],
       [ 0.74721038,  0.25278962],
       [ 0.81090761,  0.18909239],
       [ 0.69128186,  0.30871814],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.71858898,  0.28141102],
       [ 0.5490258 ,  0.4509742 ],
       [ 0.92030364,  0.07969636],
       [ 0.68334093,  0.31665907],
       [ 0.49307267,  0.50692733],
       [ 0.64418143,  0.35581857],
       [ 0.56488066,  0.43511934],
       [ 0.81090761,  0.18909239],
       [ 0.76655514,  0.23344486],
       [ 0.74745776,  0.25254224],
       [ 0.6952517 ,  0.3047483 ],
       [ 0.92623866,  0.07376134],
       [ 0.69700726,  0.30299274],
       [ 0.48718888,  0.51281112],
       [ 0.72667235,  0.27332765],
       [ 0.9599853 ,  0.0400147 ],
       [ 0.75641374,  0.24358626],
       [ 0.74242273,  0.25757727],
       [ 0.87428357,  0.12571643],
       [ 0.69782257,  0.30217743],
       [ 0.84199285,  0.15800715],
       [ 0.92623866,  0.07376134],
       [ 0.59763309,  0.40236691],
       [ 0.81090761,  0.18909239],
       [ 0.65177281,  0.34822719],
       [ 0.81795835,  0.18204165],
       [ 0.94285762,  0.05714238],
       [ 0.57121026,  0.42878974],
       [ 0.88583201,  0.11416799],
       [ 0.75641374,  0.24358626],
       [ 0.61462171,  0.38537829],
       [ 0.89678193,  0.10321807],
       [ 0.92623866,  0.07376134],
       [ 0.80237255,  0.19762745],
       [ 0.47290016,  0.52709984],
       [ 0.54439953,  0.45560047],
       [ 0.81948796,  0.18051204],
       [ 0.66966536,  0.33033464],
       [ 0.95792316,  0.04207684],
       [ 0.78982164,  0.21017836],
       [ 0.79078082,  0.20921918],
       [ 0.53217142,  0.46782858],
       [ 0.68877043,  0.31122957],
       [ 0.49996354,  0.50003646],
       [ 0.81090761,  0.18909239],
       [ 0.92077753,  0.07922247],
       [ 0.75574513,  0.24425487],
       [ 0.62821077,  0.37178923],
       [ 0.92077753,  0.07922247],
       [ 0.920744  ,  0.079256  ],
       [ 0.91399925,  0.08600075],
       [ 0.79506758,  0.20493242],
       [ 0.64542481,  0.35457519],
       [ 0.81090761,  0.18909239],
       [ 0.80312721,  0.19687279],
       [ 0.83621088,  0.16378912],
       [ 0.9851861 ,  0.0148139 ],
       [ 0.81090761,  0.18909239],
       [ 0.94332504,  0.05667496],
       [ 0.86136629,  0.13863371],
       [ 0.87696757,  0.12303243],
       [ 0.74294437,  0.25705563],
       [ 0.87136503,  0.12863497],
       [ 0.53217142,  0.46782858],
       [ 0.9851861 ,  0.0148139 ],
       [ 0.62916139,  0.37083861],
       [ 0.6952517 ,  0.3047483 ],
       [ 0.65177281,  0.34822719],
       [ 0.47290016,  0.52709984],
       [ 0.95732168,  0.04267832],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.91865571,  0.08134429],
       [ 0.79506758,  0.20493242],
       [ 0.63178315,  0.36821685],
       [ 0.81090761,  0.18909239],
       [ 0.90468807,  0.09531193],
       [ 0.88583201,  0.11416799],
       [ 0.89486613,  0.10513387],
       [ 0.71008085,  0.28991915],
       [ 0.65514518,  0.34485482],
       [ 0.61495789,  0.38504211],
       [ 0.72771786,  0.27228214],
       [ 0.91177474,  0.08822526],
       [ 0.70952654,  0.29047346],
       [ 0.75641374,  0.24358626],
       [ 0.86322911,  0.13677089],
       [ 0.92718108,  0.07281892],
       [ 0.75045451,  0.24954549],
       [ 0.86186176,  0.13813824],
       [ 0.52889339,  0.47110661],
       [ 0.82378974,  0.17621026],
       [ 0.52393181,  0.47606819],
       [ 0.81090761,  0.18909239],
       [ 0.86801194,  0.13198806],
       [ 0.84382018,  0.15617982],
       [ 0.81090761,  0.18909239],
       [ 0.9599853 ,  0.0400147 ],
       [ 0.51168762,  0.48831238],
       [ 0.62916139,  0.37083861],
       [ 0.9529663 ,  0.0470337 ],
       [ 0.96317049,  0.03682951],
       [ 0.5523711 ,  0.4476289 ],
       [ 0.36510234,  0.63489766],
       [ 0.76208147,  0.23791853],
       [ 0.86322911,  0.13677089],
       [ 0.46106651,  0.53893349],
       [ 0.83627382,  0.16372618],
       [ 0.26310167,  0.73689833],
       [ 0.54503631,  0.45496369],
       [ 0.59782917,  0.40217083],
       [ 0.71189772,  0.28810228],
       [ 0.84415173,  0.15584827],
       [ 0.83627382,  0.16372618],
       [ 0.87733852,  0.12266148],
       [ 0.6061722 ,  0.3938278 ],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.80269526,  0.19730474],
       [ 0.81090761,  0.18909239],
       [ 0.74242273,  0.25757727],
       [ 0.70952654,  0.29047346],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.95804072,  0.04195928],
       [ 0.32746159,  0.67253841],
       [ 0.77721981,  0.22278019],
       [ 0.32759313,  0.67240687],
       [ 0.81090761,  0.18909239],
       [ 0.6952517 ,  0.3047483 ],
       [ 0.79078082,  0.20921918],
       [ 0.81090761,  0.18909239],
       [ 0.96317049,  0.03682951],
       [ 0.9334603 ,  0.0665397 ],
       [ 0.67939269,  0.32060731],
       [ 0.96784826,  0.03215174],
       [ 0.75641374,  0.24358626],
       [ 0.95743306,  0.04256694],
       [ 0.36925666,  0.63074334],
       [ 0.65482439,  0.34517561],
       [ 0.83807394,  0.16192606],
       [ 0.86139653,  0.13860347],
       [ 0.73306738,  0.26693262],
       [ 0.93727827,  0.06272173],
       [ 0.75641374,  0.24358626],
       [ 0.54439953,  0.45560047],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.75574513,  0.24425487],
       [ 0.92623866,  0.07376134],
       [ 0.56321542,  0.43678458],
       [ 0.50391923,  0.49608077],
       [ 0.82989092,  0.17010908],
       [ 0.93723635,  0.06276365],
       [ 0.6952517 ,  0.3047483 ],
       [ 0.72667235,  0.27332765],
       [ 0.81090761,  0.18909239],
       [ 0.68334093,  0.31665907],
       [ 0.96317049,  0.03682951],
       [ 0.98598926,  0.01401074],
       [ 0.81090761,  0.18909239],
       [ 0.4065287 ,  0.5934713 ],
       [ 0.90468807,  0.09531193],
       [ 0.93270528,  0.06729472],
       [ 0.59119204,  0.40880796],
       [ 0.76218628,  0.23781372],
       [ 0.94525932,  0.05474068],
       [ 0.81090761,  0.18909239],
       [ 0.92623866,  0.07376134],
       [ 0.79403137,  0.20596863],
       [ 0.46106651,  0.53893349],
       [ 0.93727827,  0.06272173],
       [ 0.58700881,  0.41299119],
       [ 0.87733852,  0.12266148],
       [ 0.87696757,  0.12303243],
       [ 0.9048472 ,  0.0951528 ],
       [ 0.75641374,  0.24358626],
       [ 0.87733852,  0.12266148],
       [ 0.38546809,  0.61453191],
       [ 0.78920914,  0.21079086],
       [ 0.89486613,  0.10513387],
       [ 0.9161873 ,  0.0838127 ],
       [ 0.86136629,  0.13863371],
       [ 0.93727827,  0.06272173],
       [ 0.93112959,  0.06887041],
       [ 0.86134348,  0.13865652],
       [ 0.94492913,  0.05507087],
       [ 0.66048024,  0.33951976]])

In [248]:

    

p = clf.predict_proba(bt2)


    

In [249]:

    

bt2['Made Donation in March 2007'] = p[:,1]
bt2.head()


    

    
Out[249]:






  

    

      

      
Months since Last Donation square root
      
Number of Donations log
      
Months since First Donation
      
Made Donation in March 2007
    
  
  

    

      
659
      
 1.414214
      
 2.564949
      
 52
      
 0.512811
    
    

      
276
      
 4.582576
      
 2.079442
      
 38
      
 0.158846
    
    

      
263
      
 2.000000
      
 0.693147
      
  4
      
 0.189092
    
    

      
303
      
 3.316625
      
 2.484907
      
 38
      
 0.370839
    
    

      
83 
      
 2.000000
      
 2.564949
      
 34
      
 0.572979
    
  

In [256]:

    

submit_dir = '../data/processed/'
submit_filename = 'submit_cleaned_logistic_regression.csv'
bt2.to_csv(submit_dir+submit_filename, 
         #  columns =('Unnamed: 0', 'Made Donation in March 2007'), 
           index=True)


    

In [ ]: