test_feature_availability_profiler.py 文件源码

def setUp(self):
        self.df = pd.DataFrame(np.random.randn(1000, 4),
                               columns=['A', 'B', 'AdmitDTS', 'LastLoadDTS'])
        # generate load date
        self.df['LastLoadDTS'] = pd.datetime(2015, 5, 20)
        # generate datetime objects for admit date
        admit = pd.Series(1000)
        delta = pd.datetime(2015, 5, 20) - pd.datetime(2015, 5, 1)
        int_delta = (delta.days * 24 * 60 * 60) + delta.seconds
        for i in range(1000):
            random_second = randrange(int_delta)
            admit[i] = pd.datetime(2015, 5, 1) + timedelta(seconds=random_second)
        self.df['AdmitDTS'] = admit
        # add nulls
        a = np.random.rand(1000) > .5
        self.df.loc[a, ['A']] = np.nan
        a = np.random.rand(1000) > .75
        self.df.loc[a, ['B']] = np.nan