dmonscikitforest_ACI.py 文件源码

def ohEncoding(data, cols=None, replace=False):
    if cols is None:
        cols = []
        for el, v in data.dtypes.iteritems():
            if v == 'object':
                cols.append(el)
        print "Categorical features not set, detected as categorical: %s" % str(cols)
    vec = DictVectorizer()
    mkdict = lambda row: dict((col, row[col]) for col in cols)
    vecData = pd.DataFrame(vec.fit_transform(data[cols].apply(mkdict, axis=1)).toarray())
    vecData.columns = vec.get_feature_names()
    vecData.index = data.index
    if replace is True:
        data = data.drop(cols, axis=1)
        data = data.join(vecData)
    return data, vecData, vec