# -*- coding: utf-8 -*-
"""
Created on Fri May 27 15:24:16 2016

@author: SeanEaster
"""

from sklearn.decomposition import LatentDirichletAllocation as LDA
from sklearn.datasets import load_digits
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split
from sklearn.metrics import confusion_matrix

import numpy as np

digits = load_digits()

images = digits['images']
images = [image.reshape((1,-1)) for image in images]
images = np.concatenate(tuple(images), axis = 0)

lda = LDA(n_topics = 16)

X = lda.fit_transform(images)
Y = digits['target']

xTrain, xTest, yTrain, yTest = train_test_split(X,Y,test_size =.2, random_state=9)

classifier = LogisticRegression(C = 1e5) # Choice of C here is arbitrary; in practice, cross validate
classifier.fit(X,Y)
print confusion_matrix(yTest, classifier.predict(xTest))

[[33  0  0  0  0  0  0  0  0  0]
 [ 0 36  1  0  0  0  0  0  2  1]
 [ 0  1 40  2  0  0  0  0  2  0]
 [ 0  0  0 32  0  0  0  0  0  2]
 [ 0  0  0  0 36  0  0  4  0  1]
 [ 0  0  0  1  0 34  0  0  0  4]
 [ 0  0  0  0  0  0 29  0  0  0]
 [ 0  0  0  0  0  0  0 27  1  0]
 [ 0  6  1  0  1  1  0  1 25  1]
 [ 0  0  0  1  1  1  0  0  3 29]]

Topics in LDA model:
Topic #0:
government people mr law gun state president states public use right rights national new control american security encryption health united
Topic #1:
drive card disk bit scsi use mac memory thanks pc does video hard speed apple problem used data monitor software
Topic #2:
said people armenian armenians turkish did saw went came women killed children turkey told dead didn left started greek war
Topic #3:
year good just time game car team years like think don got new play games ago did season better ll
Topic #4:
10 00 15 25 12 11 20 14 17 16 db 13 18 24 30 19 27 50 21 40
Topic #5:
windows window program version file dos use files available display server using application set edu motif package code ms software
Topic #6:
edu file space com information mail data send available program ftp email entry info list output nasa address anonymous internet
Topic #7:
ax max b8f g9v a86 pl 145 1d9 0t 34u 1t 3t giz bhj wm 2di 75u 2tm bxn 7ey
Topic #8:
god people jesus believe does say think israel christian true life jews did bible don just know world way church
Topic #9:
don know like just think ve want does use good people key time way make problem really work say need