Merge remote-tracking branch 'origin/feature/columnar-data-examples' …

…into feature/private-core-module Signed-off-by: Martijn Govers <Martijn.Govers@Alliander.com>
PowerGridModel · Oct 21, 2024 · 08da0c8 · 08da0c8
2 parents 0c7c82b + 19be23d
commit 08da0c8
Show file tree

Hide file tree

Showing 3 changed files with 23 additions and 118 deletions.
diff --git a/docs/examples/Power Flow Example.ipynb b/docs/examples/Power Flow Example.ipynb
@@ -129,6 +129,8 @@
    "source": [
     "It is also possible to specify a component input data in a columnar data format.\n",
     "\n",
+    "A columnar data format better integrates with most databases. In addition, it may bring memory and, in some cases, even computational performance improvements, because unused attribute columns can be omitted.\n",
+    "\n",
     "Make sure to provide the correct `dtype` to the numpy arrays, exposed for each dataset type, component and attribute via the `power_grid_meta_data` object."
    ]
   },
@@ -145,6 +147,7 @@
     "    \"node\": np.array([1], dtype=source_attribute_dtypes[\"node\"]),\n",
     "    \"status\": np.array([1], dtype=source_attribute_dtypes[\"status\"]),\n",
     "    \"u_ref\": np.array([1.0], dtype=source_attribute_dtypes[\"u_ref\"]),\n",
+    "    # We're not creating columns for u_ref_angle, sk, ... Instead, the default values are used. This saves us memory.\n",
     "}\n",
     "\n",
     "input_data = {\n",
@@ -487,7 +490,7 @@
    "id": "14a34c07",
    "metadata": {},
    "source": [
-    "Finally, it is possible to request columnar data for all attributes using the `ComponentAttributeFilterOptions.ALL` as a shorthand."
+    "Finally, it is possible to request columnar data for all attributes using the `ComponentAttributeFilterOptions.everything` as a shorthand."
    ]
   },
   {

diff --git a/docs/examples/Serialization Example.ipynb b/docs/examples/Serialization Example.ipynb
@@ -637,69 +637,13 @@
      },
      "metadata": {},
      "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>id</th>\n",
-       "      <th>u_rated</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   id  u_rated\n",
-       "0   1  10500.0\n",
-       "1   2  10500.0\n",
-       "2   3  10500.0"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
     "dataset = json_deserialize(data, data_filter=ComponentAttributeFilterOptions.everything)\n",
     "\n",
     "print(\"components:\", list(dataset.keys()))\n",
-    "display(dataset[ComponentType.node])\n",
-    "display(DataFrame(dataset[ComponentType.node]))"
+    "display(dataset[ComponentType.node])"
    ]
   },
   {
@@ -724,64 +668,8 @@
       "node attributes: ['id', 'u_rated']\n",
       "source attributes: ['id', 'node', 'status', 'u_ref', 'sk']\n",
       "sym_load attributes: ['id', 'node', 'status', 'type', 'p_specified', 'q_specified']\n",
-      "line attributes: ['id', 'from_node', 'to_node', 'from_status', 'to_status', 'r1', 'x1', 'c1', 'tan1', 'i_n']\n",
-      "-------node data-------\n"
+      "line attributes: ['id', 'from_node', 'to_node', 'from_status', 'to_status', 'r1', 'x1', 'c1', 'tan1', 'i_n']\n"
      ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>id</th>\n",
-       "      <th>u_rated</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>3</td>\n",
-       "      <td>10500.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   id  u_rated\n",
-       "0   1  10500.0\n",
-       "1   2  10500.0\n",
-       "2   3  10500.0"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
@@ -799,9 +687,7 @@
     "print(\"node attributes:\", list(dataset[ComponentType.node].dtype.names))\n",
     "print(\"source attributes:\", list(dataset[ComponentType.source].keys()))\n",
     "print(\"sym_load attributes:\", list(dataset[ComponentType.sym_load].keys()))\n",
-    "print(\"line attributes:\", list(dataset[ComponentType.line].keys()))\n",
-    "print(\"-------node data-------\")\n",
-    "display(DataFrame(dataset[ComponentType.node]))"
+    "print(\"line attributes:\", list(dataset[ComponentType.line].keys()))"
    ]
   },
   {

diff --git a/tests/unit/validation/test_errors.py b/tests/unit/validation/test_errors.py
@@ -88,6 +88,22 @@ def test_invalid_id_error():
     assert str(error) == "Field 'november' does not contain a valid oscar/papa id for 3 nodes."
 
 
+def test_invalid_id_error_with_filters():
+    error = InvalidIdError(
+        ComponentType.node,
+        field="november",
+        ids=[1, 2, 3],
+        ref_components=["oscar", "papa"],
+        filters={"foo": "bar", "baz": ComponentType.node},
+    )
+    assert error.component == "node"
+    assert error.field == "november"
+    assert error.ids == [1, 2, 3]
+    assert error.ref_components == ["oscar", "papa"]
+    assert error.filters_str == "(foo=bar, baz=node)"
+    assert str(error) == "Field 'november' does not contain a valid oscar/papa id for 3 nodes. (foo=bar, baz=node)"
+
+
 def test_comparison_error():
     error = ComparisonError(component=ComponentType.node, field="romeo", ids=[1, 2, 3], ref_value=0)
     assert error.component == "node"