def test(intercept, featureWeight):
testFeatures = getFeatures(0)
testFeatures = getAverage(testFeatures)
testFeatures = normalize(testFeatures)
region = testFeatures.region
import json
b = json.dumps(testFeatures.region)
f = open("teststruct_region.json",'wb')
f.write(b)
f.close()
score = []
for i in range(len(region)):
score.append({})
fOut = open("../txt/result.txt",'w')
for i in range(len(region)):
for query in region[i]:
score[i][query] = {}
for url in region[i][query]:
score[i][query][url] = \
dot_product(region[i][query][url],featureWeight) + intercept
url_sorted_by_value = OrderedDict(sorted(score[i][query].items(), key=lambda x: x[1]))
url_sorted_by_value_r = list(reversed(url_sorted_by_value))
out = str(query) + " " + str(i) + " "
for u in url_sorted_by_value_r:
out = out + str(u) + " "
out = out+ "\n"
fOut.write(out)
import time
import commands
from getFeatures import *
from featureProcess import getAverage
from featureProcess import normalize
from rank import *
print '##################################'
print '# Program start #'
print '##################################'
print '-Stage 1- extract features..'
trainStruct = getFeatures(1)
print '-Stage 2- processing features..'
trainStruct = getAverage(trainStruct)
print '-Stage 3- normalizing features..'
trainStruct = normalize(trainStruct)
print '-Stage 4- generating training set for Weka..'
arffGen(trainStruct.region)
time.sleep(1)
print '-Stage 5- getting trained model parameters..'
beta = commands.getoutput("java WekaTester trainClickThrough.arff").split('\n')
intercept = float(beta[0])
beta = beta[1:len(beta)-1]
for i,item in enumerate(beta):
beta[i] = float(item)
print beta[i]
print '-Stage 6- get test set..'
test(intercept,beta)