recipe_cleanup.py 文件源码

def make_tfidf(arr):
    '''input, numpy array with flavor counts for each recipe and compounds
    return numpy array adjusted as tfidf
    '''
    arr2 = arr.copy()
    N=arr2.shape[0]
    l2_rows = np.sqrt(np.sum(arr2**2, axis=1)).reshape(N, 1)
    l2_rows[l2_rows==0]=1
    arr2_norm = arr2/l2_rows

    arr2_freq = np.sum(arr2_norm>0, axis=0)
    arr2_idf = np.log(float(N+1) / (1.0 + arr2_freq)) + 1.0

    from sklearn.preprocessing import normalize
    tfidf = np.multiply(arr2_norm, arr2_idf)
    tfidf = normalize(tfidf, norm='l2', axis=1)
    print tfidf.shape
    return tfidf