pandas 2.0 support (#1028)

blue-yonder · Jun 14, 2023 · 2203f74 · 2203f74
1 parent 5430dc1
commit 2203f74
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 9 deletions.
diff --git a/setup.cfg b/setup.cfg
@@ -36,7 +36,7 @@ setup_requires =
 install_requires =
     requests>=2.9.1
     numpy >=1.15.1
-    pandas>=0.25.0, <2.0.0
+    pandas>=0.25.0
     scipy>=1.2.0
     statsmodels>=0.13
     patsy>=0.4.1
@@ -102,7 +102,7 @@ junit_family = xunit2
 addopts =
     --cov tsfresh --cov-report term-missing
     --verbose
-    -n auto
+    #-n auto
 testpaths = tests
 filterwarnings =
 

diff --git a/tests/units/feature_extraction/test_data.py b/tests/units/feature_extraction/test_data.py
@@ -282,7 +282,7 @@ def test_wide_tsframe_without_sort(self):
         self.assert_tsdata(data, WIDE_TEST_DATA_EXPECTED_TUPLES)
 
     def test_dict_tsframe(self):
-        df = {key: df for key, df in self.create_test_data_sample().groupby(["kind"])}
+        df = {key: df for key, df in self.create_test_data_sample().groupby("kind")}
         data = TsDictAdapter(df, "id", "val", "sort")
 
         self.assert_tsdata(data, TEST_DATA_EXPECTED_TUPLES)
@@ -394,7 +394,7 @@ def test_f(chunk):
             test_f, meta=(("id", "int"), ("variable", "int"), ("value", "int"))
         ).compute()
         pd.testing.assert_frame_equal(
-            return_f,
+            return_f.reset_index(drop=True),
             pd.DataFrame({"id": [1, 2], "variable": ["a", "a"], "value": [1.0, 2.0]}),
         )
 
@@ -416,7 +416,7 @@ def test_f(chunk):
             test_f, meta=(("id", "int"), ("variable", "int"), ("value", "int"))
         ).compute()
         pd.testing.assert_frame_equal(
-            return_f.reset_index(drop=True),
+            return_f.sort_values("value").reset_index(drop=True),
             pd.DataFrame(
                 {
                     "id": [1, 2, 1, 2],

diff --git a/tests/units/utilities/test_dataframe_functions.py b/tests/units/utilities/test_dataframe_functions.py
@@ -1524,7 +1524,7 @@ def test_kind_parameters(self):
 
         extended_dataframe = dataframe_functions.add_sub_time_series_index(
             dataframe, 2, column_id="id", column_kind="kind"
-        )
+        ).sort_index()
 
         self.assertEqual(
             list(extended_dataframe["id"]),

diff --git a/tsfresh/examples/har_dataset.py b/tsfresh/examples/har_dataset.py
@@ -93,8 +93,8 @@ def load_har_classes(folder_name=data_file_name):
     )
     try:
         return pd.read_csv(
-            data_file_name_classes, delim_whitespace=True, header=None, squeeze=True
-        )
+            data_file_name_classes, delim_whitespace=True, header=None
+        ).squeeze()
     except OSError:
         raise OSError(
             "File {} was not found. Have you downloaded the dataset with download_har_dataset() "

diff --git a/tsfresh/feature_extraction/data.py b/tsfresh/feature_extraction/data.py
@@ -192,7 +192,7 @@ def __init__(self, df, column_id, column_sort=None, value_columns=None):
             _check_nan(df, column_sort)
 
         self.column_sort = column_sort
-        self.df_grouped = df.groupby([column_id])
+        self.df_grouped = df.groupby(column_id)
 
         super().__init__(df, column_id)
 
@@ -362,6 +362,10 @@ def __init__(
                 value_vars = possible_value_columns
                 column_value = "value"
 
+            # Make sure we are not reusing a column that already exists
+            while column_value in df.columns:
+                column_value += "_"
+
             _check_colname(*value_vars)
 
             id_vars = [column_id, column_sort] if column_sort else [column_id]