Recognizer.py

import math
import random
import json
import pandas as pd


class NN:
	def __init__(self,numNeurons):
		self.knowledgeTable = [{} for i in range(numNeurons)]

	def compareInputs(self,a,b):
		totalMatches = 0
		for x in range(len(a)):
			if a[x] == b[x]:
				totalMatches += 1
		return totalMatches

	def feedInput(self, image, accepted):
		for y in range(len(image)):
			if not image[y] in self.knowledgeTable[y]:
				self.knowledgeTable[y][image[y]] = accepted

	def mostSimilarInput(self, neuron, imageSlice):
		bestInputs = []
		bestDifference = 0
		for inputSlice in neuron.keys():
			diff = self.compareInputs(imageSlice, inputSlice)
			print diff
			if diff > bestDifference:
				bestDifference = diff
				bestInputs = [inputSlice]
			elif diff == bestDifference:
				bestInputs.append(inputSlice)
		return bestInputs

	def classify(self, image):
		hypothesis = 0
		for y in range(len(image)):
			bestCandidateInputs = self.mostSimilarInput(self.knowledgeTable[y], image[y])
			print bestCandidateInputs
			bestInput = bestCandidateInputs[0]
			if len(bestCandidateInputs) > 1:
				bestInput = bestCandidateInputs[random.randint(0,len(bestCandidateInputs)-1)]
			hypothesis += self.knowledgeTable[y][bestInput]
		return hypothesis / float(len(image))
#end

class DataAdapter:
	def __init__(self,fileNames):
		self.data = []
		for fileName in fileNames:
			self.data.append((tuple(tuple(x) for x in pd.read_csv(fileName, sep=',',header=None).values), int(fileName[0])))
#end

n = NN(9)		    #L.csv	#S.csv
trainingData = DataAdapter(['1doc.csv','0doc.csv']).data
print trainingData
for document in trainingData:
	n.feedInput(document[0], document[1])
			      #Sort-of-S.csv
print n.classify(DataAdapter(['9doc.csv']).data[0][0])