Adding the SessionEncoder

CHANGES.rst

@@ -19,6 +19,12 @@ New Features
   faster (the overhead it removes typically becomes noticeable only in DataOps
   with 50-100 nodes or more). Moreover, the evaluation of large DataOps has also
   become faster. :pr:`1890` by :user:`Jérôme Dockès <jeromedockes>`.
+- The :class:`SessionEncoder` is now available. This encoder takes a dataframe with
+  a timestamp column and computes sessions based on the given session duration.
+  Additionally, it is possible to provide a ``by`` column or list of columns
+  (e.g., user ID or (user ID, user device)) to compute sessions for each grouping
+  value.
+  :pr:`1930` by  :user:`Riccardo Cappuzzo <rcap107>`.
 
 Changes
 -------

doc/api_reference.py

@@ -91,6 +91,7 @@
                     "SimilarityEncoder",
                     "ToCategorical",
                     "DatetimeEncoder",
+                    "SessionEncoder",
                     "ToDatetime",
                     "ToFloat",
                 ],

skrub/__init__.py

@@ -40,6 +40,7 @@
 from ._multi_agg_joiner import MultiAggJoiner
 from ._reporting import TableReport, patch_display, unpatch_display
 from ._select_cols import Drop, DropCols, SelectCols
+from ._session_encoder import SessionEncoder
 from ._similarity_encoder import SimilarityEncoder
 from ._squashing_scaler import SquashingScaler
 from ._string_encoder import StringEncoder
@@ -107,4 +108,5 @@
     "ApplyToSubFrame",
     "ApplyToCols",
     "ToFloat",
+    "SessionEncoder",
 ]

skrub/_dataframe/_common.py

@@ -54,6 +54,7 @@
     "reset_index",
     "copy_index",
     "index",
+    "drop_columns",
     #
     # Inspecting dtypes and casting
     #
@@ -632,6 +633,21 @@ def _index_pandas(obj):
     return obj.index
 
 
+@dispatch
+def drop_columns(df, columns):
+    raise_dispatch_unregistered_type(df, kind="DataFrame")
+
+
+@drop_columns.specialize("pandas", argument_type="DataFrame")
+def _drop_columns_pandas(df, columns):
+    return df.drop(columns=columns)
+
+
+@drop_columns.specialize("polars", argument_type="DataFrame")
+def _drop_columns_polars(df, columns):
+    return df.drop(columns)
+
+
 #
 # Inspecting dtypes and casting
 # =============================

skrub/_dataframe/tests/test_common.py

@@ -447,6 +447,15 @@ def test_index(df_module):
         assert ns.index(col) is None
 
 
+def test_drop_columns(df_module):
+    df = df_module.example_dataframe
+    col_names = ns.column_names(df)
+    col_to_drop = col_names[0]
+    df_dropped = ns.drop_columns(df, [col_to_drop])
+    assert col_to_drop not in ns.column_names(df_dropped)
+    assert len(ns.column_names(df_dropped)) == len(col_names) - 1
+
+
 #
 # Inspecting dtypes and casting
 # =============================