Merge branch 'main' into release_v0.55.0

alteryx · Jul 28, 2022 · 5395890 · 5395890
2 parents 46e8847 + 75475a5
commit 5395890
Show file tree

Hide file tree

Showing 8 changed files with 300 additions and 204 deletions.
diff --git a/docs/source/release_notes.rst b/docs/source/release_notes.rst
@@ -25,9 +25,12 @@ Release Notes
         * Bump minimum scikit-optimize version to 0.9.0 `:pr:`3614`
     * Changes
         * Add pre-commit hooks for linting :pr:`3608`
+        * Implemented a lower threshold and window size for the ``TimeSeriesRegularizer`` and ``DatetimeFormatDataCheck`` :pr:`3627`
+    * Documentation Changes
     * Testing Changes
         * Pinned GraphViz version for Windows CI Test :pr:`3596`
         * Removed ``pytest.mark.skip_if_39`` pytest marker :pr:`3602` :pr:`3607`
+        * Refactored test cases that iterate over all components to use ``pytest.mark.parametrise`` and changed the corresponding ``if...continue`` blocks to ``pytest.mark.xfail`` :pr:`3622`
 
 
 **v0.54.0 June. 23, 2022**

diff --git a/evalml/data_checks/datetime_format_data_check.py b/evalml/data_checks/datetime_format_data_check.py
@@ -39,11 +39,11 @@ def validate(self, X, y):
         Examples:
             >>> import pandas as pd
 
-            The column "dates" has a set of dates with hourly frequency appended to the end of a series of days, which is inconsistent
-            with the frequency of the previous 9 dates (1 day).
+            The column 'dates' has a set of two dates with daily frequency, two dates with hourly frequency,
+            and two dates with monthly frequency.
 
-            >>> X = pd.DataFrame(pd.date_range("2021-01-01", periods=6).append(pd.date_range("2021-01-07", periods=3, freq="H")), columns=["dates"])
-            >>> y = pd.Series([0, 1, 0, 1, 1, 0, 0, 0, 1, 0])
+            >>> X = pd.DataFrame(pd.date_range("2015-01-01", periods=2).append(pd.date_range("2015-01-08", periods=2, freq="H").append(pd.date_range("2016-03-02", periods=2, freq="M"))), columns=["dates"])
+            >>> y = pd.Series([0, 1, 0, 1, 1, 0])
             >>> datetime_format_dc = DateTimeFormatDataCheck(datetime_column="dates")
             >>> assert datetime_format_dc.validate(X, y) == [
             ...     {
@@ -393,8 +393,8 @@ def validate(self, X, y):
         ww_payload = infer_frequency(
             pd.Series(datetime_values),
             debug=True,
-            window_length=5,
-            threshold=0.8,
+            window_length=4,
+            threshold=0.4,
         )
         inferred_freq = ww_payload[0]
         debug_object = ww_payload[1]

diff --git a/evalml/pipelines/components/transformers/preprocessing/time_series_regularizer.py b/evalml/pipelines/components/transformers/preprocessing/time_series_regularizer.py
@@ -49,8 +49,8 @@ def __init__(
         self,
         time_index=None,
         frequency_payload=None,
-        window_length=5,
-        threshold=0.8,
+        window_length=4,
+        threshold=0.4,
         random_seed=0,
         **kwargs,
     ):