manufacture.py 文件源码

def LogisticRegression(result):
#    dd = pd.DataFrame(Variance)
    dd = result
#    dd['flag'] = df_flag

    from random import shuffle
    data = dd.as_matrix()
    shuffle(data)
    p = 0.8 # train/test ratio
    m,n = np.shape(data)
    train = data[:int(m*p),:]
    test = data[int(m*p):,:]
    data = result
    df_flag = result.pop('df')
    from sklearn.linear_model import LogisticRegression as LR
    from sklearn.linear_model import RandomizedLogisticRegression as RLR 

    x = result.values
    y = df_flag.values
    rlr = RLR() #?????????????
    rlr.fit(x, y) #????
    rlr.get_support() #??????????????
    print(u'??????????????')
    print(u'??????%s' % ','.join(data.columns[rlr.get_support()]))
    x = data[data.columns[rlr.get_support()]].as_matrix() # 

    lr = LR() # ????????
    lr.fit(x, y) # ??????????????
    print(u'????')
    print(u'???????%s' % lr.score(x, y))