MAIN Improve DatetimeEncoder

CHANGES.rst

@@ -15,6 +15,10 @@ development and backward compatibility is not ensured.
 Major changes
 -------------
 
+* :func:`to_datetime` is now available to support pandas.to_datetime
+  over dataframes and 2d arrays.
+  :pr:`784` by :user:`Vincent Maladiere <Vincent-Maladiere>`
+
 * :func:`dataframe.pd_join`, :func:`dataframe.pd_aggregate`,
   :func:`dataframe.pl_join` and :func:`dataframe.pl_aggregate`
   are now available in the dataframe submodule.
@@ -40,6 +44,11 @@ Major changes
 
 Minor changes
 -------------
+* :class:`DatetimeEncoder` doesn't remove constant features anymore.
+  It also supports an 'errors' argument to raise or coerce errors during
+  transform, and a 'add_total_seconds' argument to include the number of
+  seconds since Epoch.
+  :pr:`784` by :user:`Vincent Maladiere <Vincent-Maladiere>`
 
 * :class:`TableVectorizer` is now able to apply parallelism at the column level rather than the transformer level. This is the default for univariate transformers, like :class:`MinHashEncoder`, and :class:`GapEncoder`.
   :pr:`592` by :user:`Leo Grinsztajn <LeoGrin>`

examples/03_datetime_encoder.py

@@ -80,7 +80,7 @@
 
 encoder = make_column_transformer(
     (OneHotEncoder(handle_unknown="ignore"), ["city"]),
-    (DatetimeEncoder(add_day_of_the_week=True, extract_until="minute"), ["date.utc"]),
+    (DatetimeEncoder(add_day_of_the_week=True, resolution="minute"), ["date.utc"]),
     remainder="drop",
 )
 
@@ -89,11 +89,8 @@
 
 ###############################################################################
 # We see that the encoder is working as expected: the "date.utc" column has
-# been replaced by features extracting the month, day, hour, and day of the
-# week information.
-#
-# Note the year and minute features are not present, this is because they
-# have been removed by the encoder as they are constant the whole period.
+# been replaced by features extracting the month, day, hour, minute, day of the
+# week and total second since Epoch information.
 
 ###############################################################################
 # One-liner with the |TableVectorizer|
@@ -144,14 +141,9 @@
 #    ```py
 #    from sklearn.experimental import enable_hist_gradient_boosting
 #    ```
-
-import numpy as np
 from sklearn.ensemble import HistGradientBoostingRegressor
 from sklearn.pipeline import make_pipeline
 
-table_vec = TableVectorizer(
-    datetime_transformer=DatetimeEncoder(add_day_of_the_week=True),
-)
 pipeline = make_pipeline(table_vec, HistGradientBoostingRegressor())
 
 ###############################################################################
@@ -164,6 +156,7 @@
 #
 # Instead, we can use the |TimeSeriesSplit|,
 # which ensures that the test set is always in the future.
+import numpy as np
 
 sorted_indices = np.argsort(X["date.utc"])
 X = X.iloc[sorted_indices]

skrub/__init__.py

@@ -4,7 +4,7 @@
 from pathlib import Path as _Path
 
 from ._check_dependencies import check_dependencies
-from ._datetime_encoder import DatetimeEncoder
+from ._datetime_encoder import DatetimeEncoder, to_datetime
 from ._deduplicate import compute_ngram_distance, deduplicate
 from ._fuzzy_join import fuzzy_join
 from ._gap_encoder import GapEncoder
@@ -32,4 +32,5 @@
     "TargetEncoder",
     "deduplicate",
     "compute_ngram_distance",
+    "to_datetime",
 ]