def generateTrainCategory(items,priceCutOff):
arr = []
for row in items:
if float(row[END_PRICE]) >= priceCutOff and didItemSell(row): arr.append(1);
else: arr.append(0);
return arr
def getFinalPrices(items,bins,default=0):
actualFinalPrice = [];
for row in items:
if didItemSell(row): actualFinalPrice.append(float(row[END_PRICE]));
else: actualFinalPrice.append(default);
actualFinalPriceBinned = binnedFinalPrice(bins,actualFinalPrice);
return actualFinalPrice,actualFinalPriceBinned
def generateItemTitleList(items,orderedWordList):
item_title_words = [];
for row in items:
words = [didItemSell(row)];
for word in row[TITLE].split(" "):
if len(word)>2:
if orderedWordList.count(word.lower())!=0:
words.append(orderedWordList.index(word.lower()));
item_title_words.append(words);
return item_title_words;
def crossValidate(binSize, num):
priceCutOff = 15;
maxPrice = 100;
dataSplit = 0.70
#print "Loading items... "
allItems = getItems(complete=True,sold=True); #remove genre parameter to search all genres
allItems = filterItems(allItems);
#allItems = selectNumItems(allItems, num);
[trainItems,testItems] = splitItemSet(allItems,dataSplit);
trainItems = selectNumItems(trainItems, num);
actualFinalPrice = [];
for row in testItems:
if didItemSell(row): actualFinalPrice.append(float(row[END_PRICE]));
else: actualFinalPrice.append(0);
bins = generateBinArray(binSize,maxPrice);
actualFinalPriceBinned = binnedFinalPrice(bins,actualFinalPrice);
##Only have to make these once
orderedWordList = generateOrderedWordList(allItems);
[testMatrix,testCategory] = generateMatrixData(orderedWordList,generateItemTitleList(testItems,orderedWordList));
predictedFinalPrice = [-1]*len(testItems);
for priceCutOff in bins:
#print "Price cut off: ", priceCutOff
#Have to calculate these at every priceCutOff increment
[phi_k_unsold,phi_k_sold] = trainOnData(trainItems,orderedWordList,priceCutOff);
testCategory = generateTrainCategory(testItems,priceCutOff) #actual category for testItems
testingSetPredictions = makePredictions(testMatrix,phi_k_sold,phi_k_unsold); #predicted category for testItems
for i in range(len(testItems)):
if testingSetPredictions[i]==0 and predictedFinalPrice[i]==-1:
if priceCutOff-binSize>float(testItems[i][END_PRICE]):
predictedFinalPrice[i] = priceCutOff-binSize;
elif priceCutOff-binSize<=float(testItems[i][END_PRICE]):
predictedFinalPrice[i] = getBinOf(bins,float(testItems[i][END_PRICE]));
if predictedFinalPrice[i]<0: predictedFinalPrice[i]=0;
#if testItems[i][END_PRICE]>=priceCutOff: predictedFinalPrice[i] = priceCutOff;
#else: predictedFinalPrice[i] = testItems[i][END_PRICE];
file = open('predictedactualprices.csv', 'w');
for i in range(len(predictedFinalPrice)):
if predictedFinalPrice[i] == -1: predictedFinalPrice[i] = bins[-1];
for item in range(len(predictedFinalPrice)):
file.write(str(predictedFinalPrice[item])+ ", "+ str(actualFinalPrice[item])+ "\n");
file.close();
return classificationError(predictedFinalPrice, actualFinalPriceBinned);
