

In [1]:

    
%pylab inline
from classy import *









    



Populating the interactive namespace from numpy and matplotlib
Version:  0.0.15

Load the Images and Reshape into vectors-targets



In [2]:

    
images=image.load_images('data/digits')









    



[0]: 178 files found
[1]: 182 files found
[2]: 177 files found
[3]: 183 files found
[4]: 181 files found
[5]: 182 files found
[6]: 181 files found
[7]: 179 files found
[8]: 174 files found
[9]: 180 files found



In [3]:

    
data=image.images_to_vectors(images)









    



1797 vectors of length 64
Feature names: 'p0', 'p1', 'p2', 'p3', 'p4'  , ... ,  'p59', 'p60', 'p61', 'p62', 'p63'  (64 features)
Target values given.
Target names: '0', '1', '2', '3', '4', '5', '6', '7', '8', '9'
Mean:  [  0.00000000e+00   4.71341124e+00   8.25158598e+01   1.88401224e+02
   1.88589872e+02   9.17840846e+01   2.15581525e+01   2.04785754e+00
   8.51419032e-02   3.14913745e+01   1.65203116e+02   1.90677240e+02
   1.63504174e+02   1.30023372e+02   2.92036728e+01   1.70005565e+00
   4.22927101e-02   4.11185309e+01   1.57575960e+02   1.11080690e+02
   1.12814691e+02   1.24173066e+02   2.82609905e+01   7.82971619e-01
   1.66944908e-02   3.90011130e+01   1.44642181e+02   1.40286589e+02
   1.58007791e+02   1.20022816e+02   3.66889260e+01   3.33889816e-02
   0.00000000e+00   3.70083472e+01   1.21928770e+02   1.44347245e+02
   1.63978854e+02   1.39081803e+02   4.60222593e+01   0.00000000e+00
   1.37451308e-01   2.49860879e+01   1.09460768e+02   1.14961046e+02
   1.21993879e+02   1.30974958e+02   5.47762938e+01   4.24040067e-01
   1.13522538e-01   1.10378408e+01   1.19312187e+02   1.51698943e+02
   1.49728993e+02   1.39340011e+02   5.90962716e+01   3.23873122e+00
   8.34724541e-03   4.34780189e+00   8.81591541e+01   1.92462994e+02
   1.88009460e+02   1.07495826e+02   3.27490262e+01   5.77072899e+00]
Median:  [   0.    0.   63.  207.  207.   63.    0.    0.    0.    0.  191.  207.
  175.  143.    0.    0.    0.   15.  191.   95.   95.  127.    0.    0.
    0.   15.  175.  159.  191.  111.    0.    0.    0.    0.  127.  159.
  207.  159.   15.    0.    0.    0.   95.  111.  127.  143.   15.    0.
    0.    0.  127.  159.  159.  159.   15.    0.    0.    0.   63.  207.
  223.   95.    0.    0.]
Stddev:  [   0.           14.22717752   75.79479369   67.88517638   68.52232671
   90.3581085    52.88625131   16.47216306    1.44842195   50.7576493
   86.55422116   63.60290344   76.42760101   96.53740043   57.02565325
   13.11647513    0.95321433   56.84679424   90.80932368   92.58050776
   98.50000012   98.78779801   51.79075122    6.90387772    0.50013864
   49.94970201   98.7781811    93.88418435   98.12528728   93.67899482
   58.58726878    0.70690869    0.           55.28329868  100.86027538
   99.97913895   94.64396922   93.64015167   56.19204049    0.
    2.26156209   47.3537032   104.20244968  102.68526906   99.83278433
   90.82739038   68.89733343    4.82912707    3.23145722   27.62316404
   90.02004928   83.47815394   84.68687626   96.17533855   78.31457884
   15.55049191    0.35374992   14.68333191   81.36743295   69.86967274
   78.76953994   94.07347801   65.09626368   29.57005528]



In [4]:

    
data.vectors.shape









    Out[4]:





(1797, 64)



In [5]:

    
data_train,data_test=split(data)









    



Original vector shape:  (1797, 64)
Train vector shape:  (1347, 64)
Test vector shape:  (450, 64)

View one of the vectors, and possibly save it to a file



In [6]:

    
image.vector_to_image(data_train.vectors[800,:],(8,8))

only do this if you want to save the actual image



In [7]:

    
image.vector_to_image(data_train.vectors[800,:],(8,8),'test.png')

Classification



In [8]:

    
C=NaiveBayes()



In [9]:

    
timeit(reset=True)
C.fit(data_train.vectors,data_train.targets)
print(("Training time: ",timeit()))









    



Time Reset
('Training time: ', '0.006710052490234375 seconds ')



In [10]:

    
print(("On Training Set:",C.percent_correct(data_train.vectors,data_train.targets)))
print(("On Test Set:",C.percent_correct(data_test.vectors,data_test.targets)))









    



('On Training Set:', 88.641425389755014)
('On Test Set:', 86.0)



In [11]:

    
C=CSC()



In [12]:

    
timeit(reset=True)
C.fit(data_train.vectors,data_train.targets)
print(("Training time: ",timeit()))









    



Time Reset
('Training time: ', '0.6425120830535889 seconds ')



In [13]:

    
print(("On Training Set:",C.percent_correct(data_train.vectors,data_train.targets)))
print(("On Test Set:",C.percent_correct(data_test.vectors,data_test.targets)))









    



('On Training Set:', 100.0)
('On Test Set:', 97.777777777777771)

Footnote

Loading Files with Patterns

Here is a little note about how to load data from folders, using the filenames and not the folder structure.



In [14]:

    
from classy import *

here the pattern translates to (note the asterisks "*" in the pattern)

"data/digits/(all folders)/(any .png file starting with 133)"
"data/digits/(all folders)/(any .png file starting with 123)"



In [15]:

    
data=image.load_images_from_filepatterns(this='data/digits/*/133*.png',
                                         that='data/digits/*/123*.png',
                                         )









    



[that]: 11 files found
	data/digits/0/1235.png
	data/digits/0/1236.png
	data/digits/1/1237.png
	data/digits/2/1232.png
	data/digits/2/1234.png
	data/digits/5/1231.png
	data/digits/6/1239.png
	data/digits/7/1238.png
	data/digits/8/123.png
	data/digits/8/1233.png
	data/digits/9/1230.png
[this]: 11 files found
	data/digits/0/1335.png
	data/digits/0/1336.png
	data/digits/1/1334.png
	data/digits/2/1337.png
	data/digits/2/1338.png
	data/digits/3/133.png
	data/digits/3/1332.png
	data/digits/5/1333.png
	data/digits/7/1330.png
	data/digits/7/1331.png
	data/digits/7/1339.png



In [16]:

    
summary(data)









    



Images
22 images of shape (8, 8)
Target values given.
Target names: 'that', 'this'



In [ ]: