Python单元测试断言2数据帧

我正在为PySpark编写单元测试。下面是实际的功能

def get_some_timestamp(self, final_set):
    final_set.createOrReplaceTempView("session_data")
    session_df = self.spark.sql("""SELECT \
                        id,\
                        date(sent_at) as date_without_timestamp, \
                        sent_at as date_time,\
                        CAST(lag(sent_at) OVER (PARTITION BY id, date(sent_at) ORDER BY sent_at) as timestamp) as prev_timestamp,\
                        FROM session_data""")
    return session_df

该函数的UnitTest如下所示：-

   def test_get_some_timestamp(self):
    test_data_df = self.spark.createDataFrame(
    [
     ('1234','2019-01-01T23:01:01.123Z','pageview'),
     ('4567','2019-01-02T23:01:02.123Z','pageview'),
     ('1234','2019-01-01T23:03:01.123Z','click'),
     ('1234','2019-01-01T20:01:01.123Z','pageview'),
     ('4567','2019-01-02T18:01:10.678Z','pageview'),
     ('7890','2019-01-01T23:01:01.123Z','pageview')
    ],
     ['id', 'sent_at','event_name']
    )
    expected_output_pandas_df = pd.DataFrame({'id':['1234','4567','1234','1234','4567','7890'],
                                            'date_without_timestamp':['2019-01-01','2019-01-02','2019-01-01','2019-01-01','2019-01-02','2019-01-01'],
                                            'date_time':['2019-01-01T23:01:01.123','2019-01-02T23:01:02.123','2019-01-01T23:03:01.123','2019-01-01T20:01:01.123','2019-01-02T18:01:10.678','2019-01-01T23:01:01.123'],
                                            'prev_timestamp':[pd.to_datetime('2019-01-01T20:01:01.123'),'2019-01-02 18:01:10.678','2019-01-01T23:01:01.123','NaT','NaT','NaT'],
                                            'event_name':['pageview','pageview','click','pageview','pageview','pageview'],
                                             })

    actual_output_pandas_df = get_some_timestamp(self,test_data_df).toPandas()
    self.assert_equal_with_sort(expected_output_pandas_df,actual_output_pandas_df,['id','date_time'])

我的断言函数如下所示：-

def assert_equal_with_sort(self, results, expected, keycolumns):
    results_sorted = results.sort_values(by=keycolumns).reset_index(drop=True)
    expected_sorted = expected.sort_values(by=keycolumns).reset_index(drop=True)
    assert_frame_equal(results_sorted, expected_sorted)

现在，当我运行此unittest时，它失败并出现以下错误：-

Traceback (most recent call last):
  File "/Users/neilshah/Documents/GitCode/ms_data_etl/tests/test_utm_session_tagging.py", line 161, in test_get_previous_activity_timestamp
    self.assert_equal_with_sort(expected_output_pandas_df,actual_output_pandas_df,['anonymous_id','date_time'])
  File "/Users/neilshah/Documents/GitCode/ms_data_etl/tests/test_utm_session_tagging.py", line 77, in assert_equal_with_sort
    assert_frame_equal(results_sorted, expected_sorted,check_frame_type=False,check_dtype=False,check_index_type=False,check_column_type=False,check_datetimelike_compat=True)
  File "/Users/neilshah/anaconda3/lib/python3.6/site-packages/pandas/util/testing.py", line 1348, in assert_frame_equal
    obj='DataFrame.iloc[:, {idx}]'.format(idx=i))
  File "/Users/neilshah/anaconda3/lib/python3.6/site-packages/pandas/util/testing.py", line 1216, in assert_series_equal
    check_dtype=check_dtype)
  File "/Users/neilshah/anaconda3/lib/python3.6/site-packages/pandas/util/testing.py", line 1087, in assert_numpy_array_equal
    _raise(left, right, err_msg)
  File "/Users/neilshah/anaconda3/lib/python3.6/site-packages/pandas/util/testing.py", line 1081, in _raise
    raise_assert_detail(obj, msg, left, right)
  File "/Users/neilshah/anaconda3/lib/python3.6/site-packages/pandas/util/testing.py", line 1018, in raise_assert_detail
    raise AssertionError(msg)
AssertionError: numpy array are different

numpy array values are different (100.0 %)
[left]:  [2019-01-01, 2019-01-01, 2019-01-01, 2019-01-02, 2019-01-02, 2019-01-01]
[right]: [2019-01-01, 2019-01-01, 2019-01-01, 2019-01-02, 2019-01-02, 2019-01-01]

我尝试添加这里给出的不同参数，但似乎不起作用

我还打印了两个数据帧的数据类型。除了两个数据帧的

prev_timestamp

类型为

datetime64[ns]

之外，所有列的类型均为

object

---

这里有人能帮我吗？

似乎使用相同的数据类型没有帮助。如果我们比较的不是

字符串

，那么数据类型必须完全匹配。 所以在我的例子中，它是

date

我的解决办法如下：-

    expected_output_pandas_df = pd.DataFrame(
    {
     'id':['1234','4567','1234','1234','4567','7890'],
     'date_without_timestamp':[pd.to_datetime('2019-01-01').date(),pd.to_datetime('2019-01-02').date(),'pd.to_datetime('2019-01-01').date(),pd.to_datetime('2019-01-01').date(),pd.to_datetime('2019-01-02').date(),pd.to_datetime('2019-01-01').date()],
     'date_time':[pd.to_datetime('2019-01-01T23:01:01.123'),'2019-01-02T23:01:02.123','2019-01-01T23:03:01.123','2019-01-01T20:01:01.123','2019-01-02T18:01:10.678','2019-01-01T23:01:01.123'],
     'prev_timestamp':[pd.to_datetime('2019-01-01T20:01:01.123'),'2019-01-02 18:01:10.678','2019-01-01T23:01:01.123','NaT','NaT','NaT'],
     'event_name':['pageview','pageview','click','pageview','pageview','pageview'],
    }
)

对于整数类型，我也面临类似的问题。解决的办法是

some_pandas_df = pd.DataFrame({'some_int_value':[pd.to_numeric('123456'),pd.to_numeric('543214')]})