def main():
d = Dataset("rec.sport.hockey.txt", "rec.sport.baseball.txt", cutoff=2000)
(Xtrain, Ytrain, Xtest, Ytest) = d.getTrainAndTestSets(0.8, seed=100)
pC1 = getClassProb(Ytrain, -1)
pC2 = getClassProb(Ytrain, 1)
wordList = d.getWordList()
w1 = [getFeatureProb(Xtrain, Ytrain, -1, wordIndex) for wordIndex in range(len(wordList))]
aw1 = np.asarray(w1)
w2 = [getFeatureProb(Xtrain, Ytrain, 1, wordIndex) for wordIndex in range(len(wordList))]
aw2 = np.asarray(w2)
trainError = computeError(Xtrain, Ytrain, pC1, pC2, aw1, aw2)
print 'Train error rate is ' + str(trainError)
testError = computeError(Xtest, Ytest, pC1, pC2, aw1, aw2)
print 'Test error rate is ' + str(testError)
def main():
d = Dataset("rec.sport.hockey.txt", "rec.sport.baseball.txt", cutoff=200)
(Xtrain, Ytrain, Xtest, Ytest) = d.getTrainAndTestSets(0.8, seed=100)
lam = 100
cols = []
currentError = 1
n = Xtrain.shape[1]
dic = {}
## i is the number of features to be added to cols
for i in range(40):
bestJ = 0
bestErrorRate = 1
for j in range(n):
cols.append(j)
w = trainRidge(Xtrain[:, cols], Ytrain, lam)
errorRate = computeError(Xtrain[:, cols], Ytrain, w)
if errorRate < bestErrorRate:
bestJ = j
bestErrorRate = errorRate
## print 'Best error rate is ' + str(bestErrorRate)
cols.pop()
if bestErrorRate >= currentError:
break
else:
cols.append(bestJ)
dic[bestJ] = currentError - bestErrorRate
currentError = bestErrorRate
print 'Current error rate is ' + str(currentError)
w = trainRidge(Xtrain[:, cols], Ytrain, lam)
trainError = computeError(Xtrain[:, cols], Ytrain, w)
print 'Train error rate is ' + str(trainError)
testError = computeError(Xtest[:, cols], Ytest, w)
print 'Test error rate is ' + str(testError)
## find the top 10 features
wordList = d.getWordList()
topCols = [(key, value) for key, value in sorted(dic.iteritems(), key = lambda(k, v) : (v, k), reverse = True)]
topCols = topCols[: 10]
topFeatures = [wordList[index] for (index, value) in topCols]
for f in topFeatures:
print f
def main():
d = Dataset("rec.sport.hockey.txt", "rec.sport.baseball.txt", cutoff=1000)
(Xtrain, Ytrain, Xtest, Ytest) = d.getTrainAndTestSets(0.8, seed=100)
lam = 100
cols = []
currentError = 1
n = Xtrain.shape[1]
dic = {}
for j in range(n):
cols.append(j)
w = trainRidge(Xtrain[:, cols], Ytrain, lam)
errorRate = computeError(Xtrain[:, cols], Ytrain, w)
if errorRate >= currentError:
cols.pop()
else:
dic[j] = currentError - errorRate
currentError = errorRate
## print out currentError once a while
if j % 10 == 0:
print currentError
w = trainRidge(Xtrain[:, cols], Ytrain, lam)
trainError = computeError(Xtrain[:, cols], Ytrain, w)
print 'Train error rate is ' + str(trainError)
testError = computeError(Xtest[:, cols], Ytest, w)
print 'Test error rate is ' + str(testError)
## find the top 10 features
wordList = d.getWordList()
topCols = [(key, value) for key, value in sorted(dic.iteritems(), key = lambda(k, v) : (v, k), reverse = True)]
topCols = topCols[: 10]
topFeatures = [wordList[index] for (index, value) in topCols]
for f in topFeatures:
print f
