{ "cells": [ { "cell_type": "code", "source": [ "%pip install 'whylogs>=1.5.0'" ], "metadata": { "id": "JmfTzxUYEXKd" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "-MgRNCmLEVqW" }, "outputs": [], "source": [ "from typing import Any\n", "import pandas as pd\n", "import numpy as np\n", "\n", "def load_testing_data() -> pd.DataFrame: # TODO remove after user testing\n", " data = pd.read_csv(\"https://guest-session-testing-public.s3.us-west-2.amazonaws.com/adult_income_m.csv\")\n", "\n", " def convert_random_values(value: Any) -> Any:\n", " if isinstance(value, int) and np.random.random() < 1 / 100:\n", " return str(value)\n", " return value\n", "\n", " data[\"capital-gain\"] = data[\"capital-loss\"].apply(convert_random_values)\n", " data[\"capital-loss\"] = data[\"capital-loss\"].apply(convert_random_values)\n", " return data\n", "\n", "\n", "df = load_testing_data()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "1Fr5cb15EVqX", "outputId": "af93648e-2624-444c-e582-cb43fc093684" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initializing session with config /home/anthony/.config/whylogs/config.ini\n", "\n", "✅ Using session type: WHYLABS_ANONYMOUS\n", " ⤷ session id: session-6LpLjnAE\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import whylogs as why\n", "\n", "why.init(upload_on_log=True, allow_local=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "OBWMvrR1EVqY", "outputId": "cefe37ec-8a7a-4ba1-c742-0d2e8b1a6bac" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "✅ Aggregated 48842 rows into profile foo\n", "\n", "Visualize and explore this profile with one-click\n", "🔍 https://hub.whylabsapp.com/resources/model-1/profiles?profile=ref-zv5Qm5zwJw0XEzpo&sessionToken=session-6LpLjnAE\n" ] } ], "source": [ "profile = why.log(df, name=\"foo\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "F6IQU_ErEVqZ", "outputId": "b3e96b05-4a88-4d5c-fbf2-86e8b46c6199" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "✅ Aggregated 48842 rows into profile \n", "\n", "Visualize and explore this profile with one-click\n", "🔍 https://hub.whylabsapp.com/resources/model-1/profiles?profile=1691712000000&sessionToken=session-6LpLjnAE\n" ] } ], "source": [ "# Upload the same data as a batch profile by leaving out the name\n", "profile = why.log(df)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "QJravKnAEVqZ", "outputId": "ec5da4c3-f10e-43fa-fc76-1e62a955d0b3" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "✅ Aggregated 48842 lines into profile 'foo', 48842 lines into profile 'bar'\n", "\n", "Visualize and explore the profiles with one-click\n", "🔍 https://hub.whylabsapp.com/resources/model-1/profiles?profile=ref-aj7Q52Zszb0VhjeW&profile=ref-6awZJWQI347XFBgD&sessionToken=session-6LpLjnAE\n", "\n", "Or view each profile individually\n", " ⤷ https://hub.whylabsapp.com/resources/model-1/profiles?profile=ref-aj7Q52Zszb0VhjeW&sessionToken=session-6LpLjnAE\n", " ⤷ https://hub.whylabsapp.com/resources/model-1/profiles?profile=ref-6awZJWQI347XFBgD&sessionToken=session-6LpLjnAE\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "why.log(multiple={'foo': df, 'bar': df})" ] }, { "cell_type": "markdown", "metadata": { "id": "3t_bDbpUEVqa" }, "source": [ "# Switch to an autheneticated session" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "RZFDwX51EVqb", "outputId": "22c44314-7a9e-4bb5-fe2d-77b579bb0200" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initializing session with config /home/anthony/.config/whylogs/config.ini\n", "\n", "✅ Using session type: WHYLABS\n", " ⤷ org id: org-JpsdM6\n", " ⤷ api key: MPq7Hg002z\n", " ⤷ default dataset: model-62\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "why.init(reinit=True, allow_anonymous=False, upload_on_log=True, whylabs_api_key=\"MPq7Hg002z.Na5VweqsJfu5ArGILjQTlGAyPyOhtOnEVEtqY2b5PXNGJLZLjHscT:org-JpsdM6\", default_dataset_id=\"model-62\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "2VtoH4P2EVqb", "outputId": "07aa17bf-9789-497c-e17a-4e2c80a788cf" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "✅ Aggregated 48842 rows into profile real_dataset\n", "\n", "Visualize and explore this profile with one-click\n", "🔍 https://hub.whylabsapp.com/resources/model-62/profiles?profile=ref-WvU6X5tH0Nrkh4a3\n" ] } ], "source": [ "profile = why.log(df, name=\"real_dataset\")" ] }, { "cell_type": "markdown", "metadata": { "id": "PVoD08mKEVqc" }, "source": [ "## Or upload via the whylabs writer\n", "This will use the session for credentials as well, it just won't have all of the fancy output." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "ETiMfgW6EVqc", "outputId": "f33cd8d0-bc57-4619-b9fb-e93b7da63d5f" }, "outputs": [ { "data": { "text/plain": [ "[(True, 'log-KCaCKErR8Gi7TooV')]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "profile.writer('whylabs').write()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "149THEmpEVqd", "outputId": "f705b31a-487a-47c9-cca0-7e25d865aaa6" }, "outputs": [ { "data": { "text/plain": [ "[(True, 'ref-vdBRFKAO8y9J2C7M')]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# as a reference profile\n", "profile.writer('whylabs').option(reference_profile_name=\"authenticated_ref\").write()" ] } ], "metadata": { "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.11" }, "orig_nbformat": 4, "colab": { "provenance": [] } }, "nbformat": 4, "nbformat_minor": 0 }