power-grid-model-io 1.3.18__tar.gz → 1.3.20__tar.gz

{power_grid_model_io-1.3.18 → power_grid_model_io-1.3.20}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: power-grid-model-io
-Version: 1.3.18
+Version: 1.3.20
 Summary: Power Grid Model Input/Output
 Author-email: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
 License: MPL-2.0

power_grid_model_io-1.3.20/PYPI_VERSION

@@ -0,0 +1 @@
+1.3.20

{power_grid_model_io-1.3.18 → power_grid_model_io-1.3.20}/src/power_grid_model_io/data_stores/excel_file_store.py

@@ -88,11 +88,18 @@ class ExcelFileStore(BaseDataStore[TabularData]):
 
         def lazy_sheet_loader(xls_file: pd.ExcelFile, xls_sheet_name: str):
             def sheet_loader():
-                sheet_data = xls_file.parse(xls_sheet_name, header=self._header_rows)
+                preview = xls_file.parse(xls_sheet_name, header=self._header_rows, nrows=0)
+                columns = list(preview.columns)
+                dtype = {}
+                for col in columns:
+                    if "Name" in str(col) or (isinstance(col, tuple) and ("Name" in str(col[0]))):
+                        dtype[col] = str
+                sheet_data = xls_file.parse(xls_sheet_name, header=self._header_rows, dtype=dtype)
                 sheet_data = self._remove_unnamed_column_placeholders(data=sheet_data)
                 sheet_data = self._handle_duplicate_columns(data=sheet_data, sheet_name=xls_sheet_name)
                 sheet_data = self._process_uuid_columns(data=sheet_data, sheet_name=xls_sheet_name)
                 sheet_data = self._update_column_names(data=sheet_data)
+
                 return sheet_data
 
             return sheet_loader

{power_grid_model_io-1.3.18 → power_grid_model_io-1.3.20}/src/power_grid_model_io.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: power-grid-model-io
-Version: 1.3.18
+Version: 1.3.20
 Summary: Power Grid Model Input/Output
 Author-email: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
 License: MPL-2.0

power_grid_model_io-1.3.20/tests/unit/data_stores/test_vision_excel_file_store.py

@@ -0,0 +1,76 @@
+# SPDX-FileCopyrightText: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
+#
+# SPDX-License-Identifier: MPL-2.0
+from pathlib import Path
+from unittest.mock import MagicMock, mock_open, patch
+
+import pandas as pd
+
+from power_grid_model_io.data_stores.vision_excel_file_store import VisionExcelFileStore
+
+
+@patch("power_grid_model_io.data_stores.excel_file_store.pd.ExcelFile")
+@patch("power_grid_model_io.data_stores.excel_file_store.Path.open", mock_open())
+def test_header_rows(mock_excel_file: MagicMock):
+    # Arrange
+    store = VisionExcelFileStore(file_path=Path("dummy.xlsx"))
+    mock_excel_file.return_value.sheet_names = ["foo"]
+
+    # Act
+    data = store.load()
+    data["foo"]
+
+    # Assert
+    assert mock_excel_file.return_value.parse.call_count == 2
+
+
+@patch("power_grid_model_io.data_stores.excel_file_store.pd.ExcelFile")
+@patch("power_grid_model_io.data_stores.excel_file_store.Path.open", mock_open())
+def test_name_column_dtype_conversion(mock_excel_file: MagicMock):
+    store = VisionExcelFileStore(file_path=Path("dummy.xlsx"))
+    mock_excel_file.return_value.sheet_names = ["test_sheet"]
+
+    preview_df = pd.DataFrame(columns=["Mock.Name", "Other.Column", "ID"])
+
+    def mock_parse(*args, **kwargs):
+        if kwargs.get("nrows") == 0:
+            return preview_df
+        else:
+            actual_data = {
+                "Mock.Name": [12345678900000000000, 987.654],
+                "Other.Column": ["value1", "value2"],
+                "ID": [1, 2],
+                "ratio": [0.1, 0.2],
+            }
+            df = pd.DataFrame(actual_data)
+
+            if "dtype" in kwargs:
+                for col, dtype_val in kwargs["dtype"].items():
+                    if col in df.columns and dtype_val is str:
+                        df[col] = df[col].apply(lambda x: str(int(x)) if float(x).is_integer() else str(x))
+
+            return df
+
+    mock_excel_file.return_value.parse.side_effect = mock_parse
+
+    data = store.load()
+    result_df = data["test_sheet"]
+
+    assert mock_excel_file.return_value.parse.call_count == 2
+
+    first_call = mock_excel_file.return_value.parse.call_args_list[0]
+    assert first_call[1]["nrows"] == 0
+
+    second_call = mock_excel_file.return_value.parse.call_args_list[1]
+    assert "dtype" in second_call[1]
+    assert "Mock.Name" in second_call[1]["dtype"]
+    assert second_call[1]["dtype"]["Mock.Name"] is str
+
+    assert result_df["Mock.Name"][0] == "12345678900000000000"  # Long int as string
+    assert result_df["Mock.Name"][1] == "987.654"  # Float as string
+    assert result_df["Other.Column"][0] == "value1"
+    assert result_df["Other.Column"][1] == "value2"
+    assert result_df["ID"][0] == 1
+    assert result_df["ID"][1] == 2
+    assert result_df["ratio"][0] == 0.1
+    assert result_df["ratio"][1] == 0.2

power_grid_model_io-1.3.18/PYPI_VERSION

@@ -1 +0,0 @@
-1.3.18

power_grid_model_io-1.3.18/tests/unit/data_stores/test_vision_excel_file_store.py

@@ -1,22 +0,0 @@
-# SPDX-FileCopyrightText: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
-#
-# SPDX-License-Identifier: MPL-2.0
-from pathlib import Path
-from unittest.mock import MagicMock, mock_open, patch
-
-from power_grid_model_io.data_stores.vision_excel_file_store import VisionExcelFileStore
-
-
-@patch("power_grid_model_io.data_stores.excel_file_store.pd.ExcelFile")
-@patch("power_grid_model_io.data_stores.excel_file_store.Path.open", mock_open())
-def test_header_rows(mock_excel_file: MagicMock):
-    # Arrange
-    store = VisionExcelFileStore(file_path=Path("dummy.xlsx"))
-    mock_excel_file.return_value.sheet_names = ["foo"]
-
-    # Act
-    data = store.load()
-    data["foo"]
-
-    # Assert
-    mock_excel_file.return_value.parse.assert_called_once_with("foo", header=[0, 1])