grasp.py 文件源码

def fsel(data=[]): # (feature selection, using chi2)
    """ Returns a {feature: p-value} dict 
        for the given set of (vector, label)-tuples.
    """
    from scipy.stats import chi2_contingency as chi2

    f1 = collections.defaultdict(float) # {label: count}
    f2 = collections.defaultdict(float) # {feature: count}
    f3 = collections.defaultdict(float) # {feature, label: count}
    p  = {}
    for v, label in data:
        f1[label] += 1
    for v, label in data:
        for f in v:
            f2[f] += 1
            f3[f, label] += 1
    for f in f2:
        p[f] = chi2([[f1[label] - f3[f, label] or 0.1 for label in f1],
                     [            f3[f, label] or 0.1 for label in f1]])[1]
    return p