Skip to content

fix example scripts in colab #174

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
+3,741 −3,025
Open

fix example scripts in colab #174

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c80732d
downgraded numpy to fix colab NumerAPI issues, use small features ins…
joshterrill Jun 30, 2025
ab47a78
upgrading libs instead of downgrading numpy
joshterrill Jun 30, 2025
0a35330
added upgrade flag with specific cloudpickle and scipy versions
joshterrill Jul 1, 2025
b21cbb9
updated notebooks to work on the latest version of colab, with python…
joshterrill Jul 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,4 +97,6 @@ ENV/
.idea
example_model.xgb

.DS_Store
.DS_Store

v5.0/
Binary file modified cached-pickles/example_model.pkl
View file
Open in desktop
Binary file not shown.
Binary file modified cached-pickles/feature_neutralization.pkl
View file
Open in desktop
Binary file not shown.
Binary file modified cached-pickles/hello_numerai.pkl
View file
Open in desktop
Binary file not shown.
Binary file modified cached-pickles/target_ensemble.pkl
View file
Open in desktop
Binary file not shown.
120 changes: 97 additions & 23 deletions example_model.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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",
"name": "stdout",
"text": [
"Python 3.10.12\n"
"Python 3.11.13\n"
]
}
],
Expand All @@ -34,65 +34,139 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {
"colab": {
"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",
"name": "stdout",
"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[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.2/91.2 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.9/61.9 kB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.4/12.4 MB\u001b[0m \u001b[31m49.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.3/42.3 MB\u001b[0m \u001b[31m17.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.6/8.6 MB\u001b[0m \u001b[31m118.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m75.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.9/12.9 MB\u001b[0m \u001b[31m99.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m35.3/35.3 MB\u001b[0m \u001b[31m14.1 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",
"google-colab 1.0.0 requires pandas==2.2.2, but you have pandas 2.3.1 which is incompatible.\n",
"plotnine 0.14.6 requires scipy<1.16.0,>=1.8.0, but you have scipy 1.16.0 which is incompatible.\n",
"pylibcudf-cu12 25.2.1 requires pyarrow<20.0.0a0,>=14.0.0; platform_machine == \"x86_64\", but you have pyarrow 20.0.0 which is incompatible.\n",
"sklearn-compat 0.1.3 requires scikit-learn<1.7,>=1.2, but you have scikit-learn 1.7.0 which is incompatible.\n",
"dask-cudf-cu12 25.2.2 requires pandas<2.2.4dev0,>=2.0, but you have pandas 2.3.1 which is incompatible.\n",
"cudf-cu12 25.2.1 requires pandas<2.2.4dev0,>=2.0, but you have pandas 2.3.1 which is incompatible.\n",
"cudf-cu12 25.2.1 requires pyarrow<20.0.0a0,>=14.0.0; platform_machine == \"x86_64\", but you have pyarrow 20.0.0 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0m"
]
}
],
"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": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"v5.0/train.parquet: 2.37GB [01:28, 26.7MB/s] \n",
"v5.0/features.json: 291kB [00:00, 1.45MB/s] \n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.011829 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"
]
},
{
"output_type": "display_data",
"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 \"${filename}\": `;\n div.appendChild(label);\n const progress = document.createElement('progress');\n progress.max = size;\n div.appendChild(progress);\n document.body.appendChild(div);\n\n const buffers = [];\n let downloaded = 0;\n\n const channel = await google.colab.kernel.comms.open(id);\n // Send a message to notify the kernel that we're ready.\n channel.send({})\n\n for await (const message of channel.messages) {\n // Send a message to notify the kernel that we're ready.\n channel.send({})\n if (message.buffers) {\n for (const buffer of message.buffers) {\n buffers.push(buffer);\n downloaded += buffer.byteLength;\n progress.value = downloaded;\n }\n }\n }\n const blob = new Blob(buffers, {type: 'application/binary'});\n const a = document.createElement('a');\n a.href = window.URL.createObjectURL(blob);\n a.download = filename;\n div.appendChild(a);\n a.click();\n div.remove();\n }\n ",
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"\n",
" async function download(id, filename, size) {\n",
" if (!google.colab.kernel.accessAllowed) {\n",
" return;\n",
" }\n",
" const div = document.createElement('div');\n",
" const label = document.createElement('label');\n",
" label.textContent = `Downloading \"${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",
" "
]
},
"metadata": {},
"output_type": "display_data"
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"application/javascript": "download(\"download_9cb9b662-7992-47b0-b787-453b845e7050\", \"predict_barebones.pkl\", 6572312)",
"text/plain": [
"<IPython.core.display.Javascript object>"
],
"application/javascript": [
"download(\"download_a959b0e2-3a84-4ffd-9205-035cdf0c5587\", \"example_model.pkl\", 6513463)"
]
},
"metadata": {},
"output_type": "display_data"
"metadata": {}
}
],
"source": [
Expand Down Expand Up @@ -198,4 +272,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}
Loading