Merge remote-tracking branch 'upstream/dev' into ci/testing-env

Author: Zeroto521

CHANGELOG.md

@@ -32,6 +32,8 @@
 -   [TST] Compat with macos and window, to fix `FailedHealthCheck` Issue #1181 @Zeroto521
 -   [INF] Merge two docs CIs (`docs-preview.yml` and `docs.yml`) to one. And add `documentation` pytest mark. PR #1183 @Zeroto521
 -   [INF] Merge `codecov.yml` (only works for the dev branch pushing event) into `tests.yml` (only works for PR event). PR #1185 @Zeroto521
+-   [TST] Fix failure for test/timeseries/test_fill_missing_timestamp. Issue #1184 @samukweku
+-   [BUG] Import `DataDescription` to fix: `AttributeError: 'DataFrame' object has no attribute 'data_description'`. PR #1191 @Zeroto521
 -   [INF] Set a series of complete testing envs. Issue #1127 @Zeroto521
 
 ## [v0.23.1] - 2022-05-03

janitor/accessors/__init__.py

@@ -1,17 +1,3 @@
-"""Miscellaneous mathematical operators.
+"""Miscellaneous mathematical operators."""
 
-Lazy loading used here to speed up imports.
-"""
-
-import warnings
-from typing import Tuple
-
-
-import lazy_loader as lazy
-
-scipy_special = lazy.load("scipy.special")
-ss = lazy.load("scipy.stats")
-pf = lazy.load("pandas_flavor")
-pd = lazy.load("pandas")
-np = lazy.load("numpy")
-pdtypes = lazy.load("pandas.api.types")
+from janitor.accessors.data_description import DataDescription  # noqa: F401

tests/math/test_ecdf.py

@@ -1,10 +1,12 @@
 import numpy as np
 import pytest
 from hypothesis import given
+from hypothesis import settings
 from hypothesis.extra.pandas import series
 
 
 @given(s=series(dtype=np.number))
+@settings(deadline=None)
 def test_ecdf(s):
     """A simple execution test."""
     if s.isna().sum() > 0:

tests/timeseries/test_fill_missing_timestamps.py

@@ -26,7 +26,16 @@ def test_fill_missing_timestamps(timeseries_dataframe):
     df1 = timeseries_dataframe.drop(timeseries_dataframe.index[random_number])
 
     # Fill missing timestamps
-    result = fill_missing_timestamps(df1, frequency="1H")
+    # fix for GH#1184 is to use the start and end from
+    # timeseries_dataframe
+    # imagine that the last row of df1 is removed, or the first entry
+    # the length check in the assert line will fail
+    result = fill_missing_timestamps(
+        df1,
+        frequency="1H",
+        first_time_stamp=timeseries_dataframe.index.min(),
+        last_time_stamp=timeseries_dataframe.index.max(),
+    )
 
     # Testing if the missing timestamp has been filled
     assert len(result) == len(timeseries_dataframe)