def plotProbs():
binSize = 2
maxPrice = 100
dataSplit = 0.70
allItems = getItems(complete=True, sold=True, genre=ROCK)
#remove genre parameter to search all genres
allItems = filterItems(allItems)
[trainItems, testItems] = splitItemSet(allItems, dataSplit)
bins = generateBinArray(binSize, maxPrice)
[actualFinalPrice,
actualFinalPriceBinned] = getFinalPrices(testItems, bins)
##Only have to make these onece
orderedWordList = generateOrderedWordList(allItems)
[testMatrix, testCategory
] = generateMatrixData(orderedWordList,
generateItemTitleList(testItems, orderedWordList))
predictedFinalPrices = [-1] * len(testItems)
psold = []
punsold = []
predict = []
for priceCutOff in bins:
print "Price cut off: ", priceCutOff
#Have to calculate these at every priceCutOff increment
[phi_k_unsold, phi_k_sold, p_y0,
p_y1] = trainOnData(trainItems, orderedWordList, priceCutOff)
testCategory = generateTrainCategory(
testItems, priceCutOff) #actual category for testItems
[testingSetPredictions, prob_sell,
prob_wontSell] = makePredictions(testMatrix, phi_k_sold, phi_k_unsold,
p_y0, p_y1)
#predicted category for testItems [0,1]
predict.append(testingSetPredictions[2])
psold.append(prob_sell[2])
punsold.append(prob_wontSell[2])
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], actualFinalPrice[
i], 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 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);
def completePredictions():
binSize = 5;
maxPrice = 150;
dataSplit = 0.85;
print "Loading items... "
allItems = getItems(complete=True,sold=True); #remove genre parameter to search all genres
allItems = filterItems(allItems);
[trainItems,testItems] = splitItemSet(allItems,dataSplit);
bins = BinArray(binSize,maxPrice);
[actualFinalPrice,actualFinalPriceBinned] = getFinalPrices(testItems,bins);
##Only have to make these onece
orderedWordList = generateOrderedWordList(allItems);
[testMatrix,testCategory] = generateMatrixData(orderedWordList,generateItemTitleList(testItems,orderedWordList));
##Predict whether it will sell at all or not
predictedFinalPrices = [-1]*len(testItems);
[phi_k_unsold,phi_k_sold,p_y0,p_y1] = trainOnData(trainItems,orderedWordList,0);
testCategory = generateTrainCategory(testItems,0) #actual category for testItems
testingSetPredictions = makePredictions(testMatrix,phi_k_sold,phi_k_unsold,p_y0,p_y1); #predicted category for testItems [0,1]
predictedFinalPrices = updatePredictedFinalPrice(testItems,predictedFinalPrices,testingSetPredictions,0,binSize,bins);
print "Classification error on for sell/not sell is set is: ", classificationError(testingSetPredictions,testCategory);
predictedFinalPrices = [-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,p_y0,p_y1] = trainOnData(trainItems,orderedWordList,priceCutOff);
testCategory = generateTrainCategory(testItems,priceCutOff) #actual category for testItems
testingSetPredictions = 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 testItems[i][0],testItems[i][START_PRICE],actualFinalPrice[i],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 plotProbs():
binSize = 2;
maxPrice = 100;
dataSplit = 0.70;
allItems = getItems(complete=True,sold=True,genre=ROCK); #remove genre parameter to search all genres
allItems = filterItems(allItems);
[trainItems,testItems] = splitItemSet(allItems,dataSplit);
bins = generateBinArray(binSize,maxPrice);
[actualFinalPrice,actualFinalPriceBinned] = getFinalPrices(testItems,bins);
##Only have to make these onece
orderedWordList = generateOrderedWordList(allItems);
[testMatrix,testCategory] = generateMatrixData(orderedWordList,generateItemTitleList(testItems,orderedWordList));
predictedFinalPrices = [-1]*len(testItems);
psold = [];
punsold = [];
predict = [];
for priceCutOff in bins:
print "Price cut off: ", priceCutOff
#Have to calculate these at every priceCutOff increment
[phi_k_unsold,phi_k_sold,p_y0,p_y1] = trainOnData(trainItems,orderedWordList,priceCutOff);
testCategory = generateTrainCategory(testItems,priceCutOff) #actual category for testItems
[testingSetPredictions,prob_sell,prob_wontSell] = makePredictions(testMatrix,phi_k_sold,phi_k_unsold,p_y0,p_y1); #predicted category for testItems [0,1]
predict.append(testingSetPredictions[2]);
psold.append(prob_sell[2]);
punsold.append(prob_wontSell[2]);
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],actualFinalPrice[i],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 crossValidate(binSize):
maxPrice = 100;
dataSplit = 0.70;
#print "Loading items... "
allItems = getItems(complete=True,sold=True); #remove genre parameter to search all genres
allItems = filterItems(allItems);
[trainItems,testItems] = splitItemSet(allItems,dataSplit);
bins = generateBinArray(binSize,maxPrice);
[actualFinalPrice,actualFinalPriceBinned] = getFinalPrices(testItems,bins);
##Only have to make these onece
orderedWordList = generateOrderedWordList(allItems);
[testMatrix,testCategory] = generateMatrixData(orderedWordList,generateItemTitleList(testItems,orderedWordList));
predictedFinalPrices = [-1]*len(testItems);
psold = [];
punsold = [];
predict = [];
for priceCutOff in bins:
#print "Price cut off: ", priceCutOff
#Have to calculate these at every priceCutOff increment
[phi_k_unsold,phi_k_sold,p_y0,p_y1] = trainOnData(trainItems,orderedWordList,priceCutOff);
testCategory = generateTrainCategory(testItems,priceCutOff) #actual category for testItems
[testingSetPredictions,prob_sell,prob_wontSell] = makePredictions(testMatrix,phi_k_sold,phi_k_unsold,p_y0,p_y1); #predicted category for testItems [0,1]
predict.append(testingSetPredictions[2]);
psold.append(prob_sell[2]);
punsold.append(prob_wontSell[2]);
predictedFinalPrices = updatePredictedFinalPrice(testItems,predictedFinalPrices,testingSetPredictions,priceCutOff,binSize,bins);
for i in range(len(predictedFinalPrices)):
if predictedFinalPrices[i] == -1: predictedFinalPrices[i] = bins[-1];
return classificationError(predictedFinalPrices,actualFinalPriceBinned);
