Fast Information Gain computation

Question

I need to compute Information Gain scores for >100k features in >10k documents for text classification. Code below works fine but f

Answer 1

Don't know whether it still helps since a year has passed. But now I happen to be faced with the same task for text classification. I've rewritten your code using the nonzero() function provided for sparse matrix. Then I just scan nz, count the corresponding y_value and calculate the entropy.

The following code only needs seconds to run news20 dataset (loaded in using libsvm sparse matrix format).

def information_gain(X, y):

    def _calIg():
        entropy_x_set = 0
        entropy_x_not_set = 0
        for c in classCnt:
            probs = classCnt[c] / float(featureTot)
            entropy_x_set = entropy_x_set - probs * np.log(probs)
            probs = (classTotCnt[c] - classCnt[c]) / float(tot - featureTot)
            entropy_x_not_set = entropy_x_not_set - probs * np.log(probs)
        for c in classTotCnt:
            if c not in classCnt:
                probs = classTotCnt[c] / float(tot - featureTot)
                entropy_x_not_set = entropy_x_not_set - probs * np.log(probs)
        return entropy_before - ((featureTot / float(tot)) * entropy_x_set
                             +  ((tot - featureTot) / float(tot)) * entropy_x_not_set)

    tot = X.shape[0]
    classTotCnt = {}
    entropy_before = 0
    for i in y:
        if i not in classTotCnt:
            classTotCnt[i] = 1
        else:
            classTotCnt[i] = classTotCnt[i] + 1
    for c in classTotCnt:
        probs = classTotCnt[c] / float(tot)
        entropy_before = entropy_before - probs * np.log(probs)

    nz = X.T.nonzero()
    pre = 0
    classCnt = {}
    featureTot = 0
    information_gain = []
    for i in range(0, len(nz[0])):
        if (i != 0 and nz[0][i] != pre):
            for notappear in range(pre+1, nz[0][i]):
                information_gain.append(0)
            ig = _calIg()
            information_gain.append(ig)
            pre = nz[0][i]
            classCnt = {}
            featureTot = 0
        featureTot = featureTot + 1
        yclass = y[nz[1][i]]
        if yclass not in classCnt:
            classCnt[yclass] = 1
        else:
            classCnt[yclass] = classCnt[yclass] + 1
    ig = _calIg()
    information_gain.append(ig)

    return np.asarray(information_gain)