Update API for haversine and predictions output in notebook.ipynb (#329)

Co-authored-by: Jacob Tomlinson <[email protected]>
rapidsai · Feb 7, 2024 · 476e3fa · 476e3fa
1 parent d428ae4
commit 476e3fa
Showing 1 changed file with 16 additions and 15 deletions.
diff --git a/source/examples/rapids-ec2-mnmg/notebook.ipynb b/source/examples/rapids-ec2-mnmg/notebook.ipynb
@@ -24,7 +24,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "98cf9dae",
    "metadata": {},
@@ -46,7 +45,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "3af8c63a",
    "metadata": {},
@@ -70,7 +68,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "f933be1c",
    "metadata": {},
@@ -145,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "909a9714",
    "metadata": {
     "tags": []
@@ -312,13 +309,13 @@
     "def haversine_dist(df):\n",
     "    import cuspatial\n",
     "\n",
-    "    h_distance = cuspatial.haversine_distance(\n",
-    "        df[\"pickup_longitude\"],\n",
-    "        df[\"pickup_latitude\"],\n",
-    "        df[\"dropoff_longitude\"],\n",
-    "        df[\"dropoff_latitude\"],\n",
+    "    pickup = cuspatial.GeoSeries.from_points_xy(\n",
+    "        df[[\"pickup_longitude\", \"pickup_latitude\"]].interleave_columns()\n",
+    "    )\n",
+    "    dropoff = cuspatial.GeoSeries.from_points_xy(\n",
+    "        df[[\"dropoff_longitude\", \"dropoff_latitude\"]].interleave_columns()\n",
     "    )\n",
-    "    df[\"h_distance\"] = h_distance\n",
+    "    df[\"h_distance\"] = cuspatial.haversine_distance(pickup, dropoff)\n",
     "    df[\"h_distance\"] = df[\"h_distance\"].astype(\"float32\")\n",
     "    return df\n",
     "\n",
@@ -422,18 +419,22 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "b1bff0d6",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "# compute RMSE\n",
-    "score = mean_squared_error(y_pred.compute().to_array(), y_test.compute().to_array())\n",
+    "score = mean_squared_error(y_pred.compute().to_numpy(), y_test.compute().to_numpy())\n",
     "print(\"Workflow Complete - RMSE: \", np.sqrt(score))"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "44f0d5d2",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "source": [
     "### Resource Cleanup"
    ]
@@ -463,7 +464,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -477,7 +478,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.15"
+   "version": "3.10.13"
   },
   "vscode": {
    "interpreter": {