more tests

services/worker/tests/fixtures/statistics_dataset.py

@@ -1716,6 +1716,19 @@ def null_column(n_samples: int) -> list[None]:
             datetime.strptime("2024-01-10 00:00:00", "%Y-%m-%d %H:%M:%S"),
             datetime.strptime("2024-01-11 00:00:00", "%Y-%m-%d %H:%M:%S"),
         ],
+        "datetime_string": [
+            "2024-01-01 00:00:00",
+            "2024-01-02 00:00:00",
+            "2024-01-03 00:00:00",
+            "2024-01-04 00:00:00",
+            "2024-01-05 00:00:00",
+            "2024-01-06 00:00:00",
+            "2024-01-07 00:00:00",
+            "2024-01-08 00:00:00",
+            "2024-01-09 00:00:00",
+            "2024-01-10 00:00:00",
+            "2024-01-11 00:00:00",
+        ],
         "datetime_tz": [
             datetime.strptime("2024-01-01 00:00:00+0200", "%Y-%m-%d %H:%M:%S%z"),
             datetime.strptime("2024-01-02 00:00:00+0200", "%Y-%m-%d %H:%M:%S%z"),
@@ -1747,6 +1760,7 @@ def null_column(n_samples: int) -> list[None]:
     features=Features(
         {
             "datetime": Value("timestamp[s]"),
+            "datetime_string": Value("string"),
             "datetime_tz": Value("timestamp[s, tz=+02:00]"),
             "datetime_null": Value("timestamp[s]"),
             "datetime_all_null": Value("timestamp[s]"),

services/worker/tests/test_statistics_utils.py

@@ -513,7 +513,7 @@ def count_expected_statistics_for_datetime_column(column: pd.Series, column_name
 
     # compute std
     seconds_in_day = 24 * 60 * 60
-    if column_name in ["datetime", "datetime_tz"]:
+    if column_name in ["datetime", "datetime_string", "datetime_tz"]:
         timedeltas = pd.Series(range(0, 11 * seconds_in_day, seconds_in_day))
         hist = [2, 1, 1, 1, 1, 1, 1, 1, 1, 1]
     elif column_name == "datetime_null":
@@ -542,19 +542,26 @@ def count_expected_statistics_for_datetime_column(column: pd.Series, column_name
 
 @pytest.mark.parametrize(
     "column_name",
-    ["datetime", "datetime_tz", "datetime_null", "datetime_all_null"],
+    ["datetime", "datetime_string", "datetime_tz", "datetime_null", "datetime_all_null"],
 )
 def test_datetime_statistics(
     column_name: str,
     datasets: Mapping[str, Dataset],
 ) -> None:
     data = datasets["datetime_statistics"].to_pandas()
     expected = count_expected_statistics_for_datetime_column(data[column_name], column_name)
-    computed = DatetimeColumn.compute_statistics(
-        data=pl.from_pandas(data),
-        column_name=column_name,
-        n_samples=len(data[column_name]),
-    )
+    if column_name == "datetime_string":
+        computed = StringColumn.compute_statistics(
+            data=pl.from_pandas(data),
+            column_name=column_name,
+            n_samples=len(data[column_name]),
+        )
+    else:
+        computed = DatetimeColumn.compute_statistics(
+            data=pl.from_pandas(data),
+            column_name=column_name,
+            n_samples=len(data[column_name]),
+        )
     computed_std, expected_std = computed.pop("std"), expected.pop("std")
     if computed_std:
         assert computed_std.split(".")[0] == expected_std.split(".")[0]  # check with precision up to seconds