def naiveBayesMC():
binSize = 10;
maxPrice = 100;
dataSplit = 0.70;
print "Loading items... "
allItems = getItems(db,filteritems=True,complete=True,sold=True,genre=ROCK);
[trainItems,testItems] = splitItemSet(allItems,dataSplit);
bins = generateBinArray(binSize,maxPrice);
[actualFinalPrice,actualFinalPriceBinned] = getFinalPrices(testItems,bins);
##Only have to make these onece
orderedWordList = generateOrderedWordList(allItems,lengthcutoff=5,frequencycutoff=1);
[testMatrix,testCategory] = generateMatrixData(orderedWordList,generateItemTitleList(testItems,orderedWordList));
predictedFinalPrices = [-1]*len(testItems);
for priceCutOff in bins:
print "Price cut off: ", priceCutOff
[phi_k_unsold,phi_k_sold,p_y0,p_y1] = trainOnData(trainItems,orderedWordList,priceCutOff);
[testingSetPredictions,prob_sell,prob_wontSell] = makePredictions(testMatrix,phi_k_sold,phi_k_unsold,p_y0,p_y1); #predicted category for testItems [0,1]
predictedFinalPrices = updatePredictedFinalPrice(testItems,predictedFinalPrices,testingSetPredictions,priceCutOff,binSize,bins);
for i in range(len(predictedFinalPrices)):
if predictedFinalPrices[i] == -1: predictedFinalPrices[i] = bins[-1];
for i in range(len(predictedFinalPrices)):
print i,testItems[i][0],testItems[i][START_PRICE],testItems[i][END_PRICE],getBinOf(bins,float(testItems[i][START_PRICE])), actualFinalPriceBinned[i],predictedFinalPrices[i],"\t\t",testItems[i][TITLE]
print "Classification error on testing set is: ", classificationError(predictedFinalPrices,actualFinalPriceBinned);
def updatePredictedFinalPrice(testItems,predictedFinalPrice,testingSetPredictions,priceCutOff,binSize,bins):
for i in range(len(testItems)):
if testingSetPredictions[i]==0 and predictedFinalPrice[i]==-1:
if priceCutOff-binSize>float(testItems[i][START_PRICE]):
predictedFinalPrice[i] = priceCutOff-binSize;
elif priceCutOff-binSize<=float(testItems[i][START_PRICE]):
predictedFinalPrice[i] = getBinOf(bins,float(testItems[i][START_PRICE]));
if predictedFinalPrice[i]<0: predictedFinalPrice[i]=0;
return predictedFinalPrice
