fix example scripts in colab (#174)

* fixed pip install commands to work with latest colab environment
* added numerai-tools to install steps
* updated predict proxy functions to include benchmarks as second parameter
* updated all cached pickles

Author: joshterrill

.gitignore

@@ -97,4 +97,6 @@ ENV/
 .idea
 example_model.xgb
 
-.DS_Store
+.DS_Store
+
+v5.0/

cached-pickles/example_model.pkl

@@ -11,20 +11,20 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "Ekw8Z93ljC3v",
-        "outputId": "675ac893-5a46-4c6b-dc03-09438941d1fc"
+        "outputId": "bdd16698-2ad0-4423-b090-c5ce55fe3053"
       },
       "outputs": [
         {
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "Python 3.10.12\n"
+            "Python 3.11.13\n"
           ]
         }
       ],
@@ -40,59 +40,47 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "yoy_wT1rhMqF",
-        "outputId": "4268fdb0-84d2-4502-97e4-e93a1440c8ee"
+        "outputId": "e038b50f-1b61-4334-be62-28f4dc40a0a0"
       },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m34.4/34.4 MB\u001b[0m \u001b[31m16.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-            "lida 0.0.10 requires fastapi, which is not installed.\n",
-            "lida 0.0.10 requires kaleido, which is not installed.\n",
-            "lida 0.0.10 requires python-multipart, which is not installed.\n",
-            "lida 0.0.10 requires uvicorn, which is not installed.\u001b[0m\u001b[31m\n",
-            "\u001b[0m"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "# Install dependencies\n",
-        "!pip install -q numerapi pandas lightgbm cloudpickle==2.2.1 pyarrow scikit-learn scipy==1.10.1"
+        "!pip install -q --upgrade numerapi pandas pyarrow matplotlib lightgbm scikit-learn scipy cloudpickle==3.1.1"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 4,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 17
+          "height": 160
         },
         "id": "13hdRk9ghMqI",
-        "outputId": "857a4882-83e5-4a76-9b1e-57d6d822cc67"
+        "outputId": "d2274374-fd85-4189-f27b-d9d466cc63ca"
       },
       "outputs": [
         {
-          "data": {
-            "application/javascript": "\n    async function download(id, filename, size) {\n      if (!google.colab.kernel.accessAllowed) {\n        return;\n      }\n      const div = document.createElement('div');\n      const label = document.createElement('label');\n      label.textContent = `Downloading \"${filename}\": `;\n      div.appendChild(label);\n      const progress = document.createElement('progress');\n      progress.max = size;\n      div.appendChild(progress);\n      document.body.appendChild(div);\n\n      const buffers = [];\n      let downloaded = 0;\n\n      const channel = await google.colab.kernel.comms.open(id);\n      // Send a message to notify the kernel that we're ready.\n      channel.send({})\n\n      for await (const message of channel.messages) {\n        // Send a message to notify the kernel that we're ready.\n        channel.send({})\n        if (message.buffers) {\n          for (const buffer of message.buffers) {\n            buffers.push(buffer);\n            downloaded += buffer.byteLength;\n            progress.value = downloaded;\n          }\n        }\n      }\n      const blob = new Blob(buffers, {type: 'application/binary'});\n      const a = document.createElement('a');\n      a.href = window.URL.createObjectURL(blob);\n      a.download = filename;\n      div.appendChild(a);\n      a.click();\n      div.remove();\n    }\n  ",
-            "text/plain": [
-              "<IPython.core.display.Javascript object>"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "2025-07-25 13:44:58,042 INFO numerapi.utils: starting download\n",
+            "v5.0/train.parquet: 2.37GB [01:04, 36.7MB/s]                            \n",
+            "2025-07-25 13:46:03,017 INFO numerapi.utils: starting download\n",
+            "v5.0/features.json: 291kB [00:00, 2.75MB/s]                           \n"
+          ]
         },
         {
-          "data": {
-            "application/javascript": "download(\"download_9cb9b662-7992-47b0-b787-453b845e7050\", \"predict_barebones.pkl\", 6572312)",
-            "text/plain": [
-              "<IPython.core.display.Javascript object>"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001168 seconds.\n",
+            "You can set `force_row_wise=true` to remove the overhead.\n",
+            "And if memory is not enough, you can set `force_col_wise=true`.\n",
+            "[LightGBM] [Info] Total Bins 210\n",
+            "[LightGBM] [Info] Number of data points in the train set: 688184, number of used features: 42\n",
+            "[LightGBM] [Info] Start training from score 0.500008\n"
+          ]
         }
       ],
       "source": [
@@ -152,7 +140,7 @@
         "# Define predict function\n",
         "def predict(\n",
         "    live_features: pd.DataFrame,\n",
-        "    live_benchmark_models: pd.DataFrame\n",
+        "    _live_benchmark_models: pd.DataFrame\n",
         " ) -> pd.DataFrame:\n",
         "    live_predictions = model.predict(live_features[features])\n",
         "    submission = pd.Series(live_predictions, index=live_features.index)\n",
@@ -178,7 +166,7 @@
       "provenance": []
     },
     "kernelspec": {
-      "display_name": "venv",
+      "display_name": "3.11.13",
       "language": "python",
       "name": "python3"
     },
@@ -192,7 +180,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.10.12"
+      "version": "3.11.13"
     },
     "orig_nbformat": 4
   },