python/examples/datasets/weather.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
">### 🚩 *Create a free WhyLabs account to get more value out of whylogs!*<br> \n",
">*Did you know you can store, visualize, and monitor whylogs profiles with the [WhyLabs Observability Platform](https://whylabs.ai/whylogs-free-signup?utm_source=whylogs-Github&utm_medium=whylogs-example&utm_campaign=weather)? Sign up for a [free WhyLabs account](https://whylabs.ai/whylogs-free-signup?utm_source=whylogs-Github&utm_medium=whylogs-example&utm_campaign=weather) to leverage the power of whylogs and WhyLabs together!*"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_bWxEq9oV2EP"
},
"source": [
"# Weather Forecast Dataset - Usage Example"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[](https://colab.research.google.com/github/whylabs/whylogs/blob/mainline/python/examples/datasets/weather.ipynb)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This an example demonstrating the usage of the Weather Forecast Dataset.\n",
"\n",
"For more information about the dataset itself, check the documentation on :\n",
"https://whylogs.readthedocs.io/en/latest/datasets/weather.html"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Installing the datasets module\n",
"\n",
"Uncomment the cell below if you don't have the `datasets` module installed:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Note: you may need to restart the kernel to use updated packages.\n",
"%pip install 'whylogs[datasets]'"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "PqOUC2_gD3to"
},
"source": [
"## Loading the Dataset"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RfIdpq5ly7dD"
},
"source": [
"You can load the dataset of your choice by calling it from the `datasets` module:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "hm5jgXoYVlNB"
},
"outputs": [],
"source": [
"from whylogs.datasets import Weather\n",
"\n",
"dataset = Weather(version=\"in_domain\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QlbNzl8zzLiU"
},
"source": [
"This will create a folder in the current directory named `whylogs_data` with the csv files for the Weather Dataset. If the files already exist, the module will not redownload the files.\n",
"\n",
"Notice we're specifying the version of the dataset. A dataset can have multiple versions that can be used for differente purposes. In this case, the version \"in_domain\" has data from the same domain between baseline and inference subsets (data from the same set of regions - tropical, dry, polar, etc.).\n",
"\n",
"If we're interested in assessing drift issues, the version \"out_domain\" could be used, in which we have out-of-domain data in the inference subset, when compare to the baseline.\n",
"\n",
"Similarly, datasets could have other versions for other purposes, such as assessing data quality or outlier detection strategies."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ahX4GWZFEK8I"
},
"source": [
"## Discovering Information"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "SsuokUE90J1l"
},
"source": [
"To know what are the available versions for a given dataset, you can call:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ykm5JsXsD_uY",
"outputId": "2d54fb35-571e-4d00-a627-0aa6af266eec"
},
"outputs": [
{
"data": {
"text/plain": [
"('in_domain', 'out_domain')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"Weather.describe_versions()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ep2uEntK0RUM"
},
"source": [
"To get access to overall description of the dataset:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E2IdCQ5iEETv",
"outputId": "9c4aa363-3b57-45b9-da0a-6f82e1dd4807"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Weather Forecast Dataset\n",
"========================\n",
"\n",
"The Weather Forecast Dataset contains meteorological features at a particular place (defined by latitude and longitude features) and time. This dataset can present data distribution shifts over both time and space.\n",
"\n",
"The original data was sourced from the `Weather Prediction Dataset <https://github.com/Shifts-Project/shifts>`_. From the source data additional transformations were made, such as: feature renaming, feature selection and subsampling.\n",
"The original dataset is described in `Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks <https://arxiv.org/pdf/2107.07455.pdf>`_, by **Malinin, Andrey, et al.**\n",
"\n",
"Usage\n",
"-----\n",
"\n",
"You can follow this guide to see how to use the weather dataset:\n",
"\n",
".. toctree::\n",
" :maxdepth: 1\n",
"\n",
" ../examples/datasets/weather\n",
"\n",
"\n",
"Versions and Data Partitions\n",
"----------------------------\n",
"\n",
"Currently the dataset contains two versions: **in_domain** and **out_domain**. The task is the same fo\n"
]
}
],
"source": [
"print(Weather.describe()[:1000])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"note: the output was truncated to first 1000 characters as `describe()` will print a rather lengthy description."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vIMQqyRHPl63"
},
"source": [
"## Getting Baseline Data"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "83sr63LW0ZTk"
},
"source": [
"You can access data from two different partitions: the baseline dataset and inference dataset.\n",
"\n",
"The baseline can be accessed as a whole, whereas the inference dataset can be accessed in periodic batches, defined by the user.\n",
"\n",
"To get a `baseline` object, just call `dataset.get_baseline()`:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QY6Hdzl0EcnQ",
"outputId": "409322a5-d972-49ee-b06d-61d081af4943"
},
"outputs": [],
"source": [
"from whylogs.datasets import Weather\n",
"\n",
"dataset = Weather(version=\"out_domain\")\n",
"\n",
"baseline = dataset.get_baseline()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DGhEy3k403T0"
},
"source": [
"`baseline` will contain different attributes - one timestamp and five dataframes.\n",
"\n",
"- timestamp: the batch's timestamp (at the start)\n",
"- data: the complete dataframe\n",
"- features: input features\n",
"- target: output feature(s)\n",
"- prediction: output prediction and, possibly, features such as uncertainty, confidence, probability\n",
"- misc: metadata features that are not of any of the previous categories, but still contain relevant information about the data."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "7-742tkdQIDb",
"outputId": "92cc762c-845d-4eb6-c211-9c0de3cb69c0"
},
"outputs": [
{
"data": {
"text/plain": [
"datetime.datetime(2022, 9, 12, 0, 0, tzinfo=datetime.timezone.utc)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"baseline.timestamp"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"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>meta_latitude</th>\n",
" <th>meta_longitude</th>\n",
" <th>meta_climate</th>\n",
" </tr>\n",
" <tr>\n",
" <th>date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>28.702900</td>\n",
" <td>-105.964996</td>\n",
" <td>dry</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>-35.165298</td>\n",
" <td>147.466003</td>\n",
" <td>mild temperate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>29.607300</td>\n",
" <td>-95.158798</td>\n",
" <td>mild temperate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>39.077999</td>\n",
" <td>-77.557503</td>\n",
" <td>mild temperate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>26.152599</td>\n",
" <td>-81.775299</td>\n",
" <td>mild temperate</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" meta_latitude meta_longitude meta_climate\n",
"date \n",
"2022-09-12 00:00:00+00:00 28.702900 -105.964996 dry\n",
"2022-09-12 00:00:00+00:00 -35.165298 147.466003 mild temperate\n",
"2022-09-12 00:00:00+00:00 29.607300 -95.158798 mild temperate\n",
"2022-09-12 00:00:00+00:00 39.077999 -77.557503 mild temperate\n",
"2022-09-12 00:00:00+00:00 26.152599 -81.775299 mild temperate"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"baseline.extra.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zq--VQ7kQOWn"
},
"source": [
"## Setting Parameters"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "y6-NrLU813it"
},
"source": [
"With `set_parameters`, you can specify the timestamps for both baseline and inference datasets, as well as the inference interval.\n",
"\n",
"By default, the timestamp is set as:\n",
"- Current date for baseline dataset\n",
"- Tomorrow's date for inference dataset\n",
"\n",
"These timestamps can be defined by the user to any given day, including the dataset's original date.\n",
"\n",
"The `inference_interval` defines the interval for each batch: '1d' means that we will have daily batches, while '7d' would mean weekly batches."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "c35iQULHvAj4"
},
"source": [
"To set the timestamps to the original dataset's date, set `original` to true, like below:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "ENU8FVY5vJ_-"
},
"outputs": [],
"source": [
"# Currently, the inference interval takes a str in the format \"Xd\", where X is an integer between 1-30\n",
"dataset.set_parameters(inference_interval=\"1d\", original=True)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"datetime.datetime(2018, 9, 1, 0, 0, tzinfo=datetime.timezone.utc)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"baseline = dataset.get_baseline()\n",
"baseline.timestamp"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RZqtT98Ruvnp"
},
"source": [
"You can set timestamp by using the `baseline_timestamp` and `inference_start_timestamp`, and the inference interval like below:"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "qG69ObDuQQjf"
},
"outputs": [],
"source": [
"from datetime import datetime, timezone\n",
"now = datetime.now(timezone.utc)\n",
"dataset.set_parameters(baseline_timestamp=now, inference_start_timestamp=now, inference_interval=\"1d\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"> Note that we are passing the datetime converted to the UTC timezone. If a naive datetime is passed (no information on timezones), local time zone will be assumed. The local timestamp, however, will be converted to the proper datetime in UTC timezone. Passing a naive datetime will trigger a warning, letting you know of this behavior."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rZD-BWR7vRh2"
},
"source": [
"Note that if both `original` and a timestamp (baseline or inference) is passed simultaneously, the defined timestamp will be overwritten by the original dataset timestamp."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Mvj9Jr_EQlH4"
},
"source": [
"## Getting Inference Data #1 - By Date"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "i5o19JBVvod_"
},
"source": [
"You can get inference data in two different ways. The first is to specify the exact date you want, which will return a single batch:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"id": "ker8C5-lQqGI"
},
"outputs": [],
"source": [
"batch = dataset.get_inference_data(target_date=now)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can access the attributes just as showed before:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "AasIC_5dQvdH",
"outputId": "9ceba128-6a21-4b96-aae6-e1412bbdebce"
},
"outputs": [
{
"data": {
"text/plain": [
"datetime.datetime(2022, 9, 12, 0, 0, tzinfo=datetime.timezone.utc)"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"batch.timestamp"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"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>height_sea_level</th>\n",
" <th>sun_elevation</th>\n",
" <th>pressure</th>\n",
" <th>cmc_temperature_grad</th>\n",
" <th>cmc_temperature</th>\n",
" <th>dew_point_temperature</th>\n",
" <th>absolute_humidity</th>\n",
" <th>snow_depth</th>\n",
" <th>rain_accumulated</th>\n",
" <th>snow_accumulated</th>\n",
" <th>...</th>\n",
" <th>snow_accumulated_grad</th>\n",
" <th>ice_rain_grad</th>\n",
" <th>iced_graupel_grad</th>\n",
" <th>cloud_coverage_grad</th>\n",
" <th>meta_latitude</th>\n",
" <th>meta_longitude</th>\n",
" <th>meta_climate</th>\n",
" <th>prediction_temperature</th>\n",
" <th>temperature</th>\n",
" <th>uncertainty</th>\n",
" </tr>\n",
" <tr>\n",
" <th>date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>166.0</td>\n",
" <td>24.134473</td>\n",
" <td>749.287193</td>\n",
" <td>-0.670923</td>\n",
" <td>289.282080</td>\n",
" <td>285.220886</td>\n",
" <td>0.0090</td>\n",
" <td>0.000000</td>\n",
" <td>2.641950</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-2.0</td>\n",
" <td>46.516667</td>\n",
" <td>29.483333</td>\n",
" <td>snow</td>\n",
" <td>17.459501</td>\n",
" <td>19.0</td>\n",
" <td>5.046475</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>180.0</td>\n",
" <td>36.168942</td>\n",
" <td>738.731879</td>\n",
" <td>-3.726770</td>\n",
" <td>290.226721</td>\n",
" <td>284.868256</td>\n",
" <td>0.0095</td>\n",
" <td>0.000000</td>\n",
" <td>0.149825</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-23.0</td>\n",
" <td>46.521900</td>\n",
" <td>26.910299</td>\n",
" <td>snow</td>\n",
" <td>15.650873</td>\n",
" <td>15.0</td>\n",
" <td>10.590467</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>25.0</td>\n",
" <td>4.931765</td>\n",
" <td>753.034922</td>\n",
" <td>7.741565</td>\n",
" <td>280.471216</td>\n",
" <td>279.016144</td>\n",
" <td>0.0054</td>\n",
" <td>0.000000</td>\n",
" <td>3.536025</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>39.033333</td>\n",
" <td>125.783333</td>\n",
" <td>snow</td>\n",
" <td>9.651232</td>\n",
" <td>11.0</td>\n",
" <td>5.512176</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>-11.0</td>\n",
" <td>22.337882</td>\n",
" <td>754.533835</td>\n",
" <td>2.323230</td>\n",
" <td>277.726721</td>\n",
" <td>274.868256</td>\n",
" <td>0.0043</td>\n",
" <td>0.181638</td>\n",
" <td>1.822488</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-70.0</td>\n",
" <td>55.281898</td>\n",
" <td>-77.765297</td>\n",
" <td>snow</td>\n",
" <td>7.948395</td>\n",
" <td>8.0</td>\n",
" <td>3.395677</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>119.0</td>\n",
" <td>58.290232</td>\n",
" <td>767.426533</td>\n",
" <td>0.235266</td>\n",
" <td>290.554565</td>\n",
" <td>283.905655</td>\n",
" <td>0.0116</td>\n",
" <td>0.000000</td>\n",
" <td>2.715500</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-1.0</td>\n",
" <td>38.519901</td>\n",
" <td>-28.715900</td>\n",
" <td>polar</td>\n",
" <td>18.248093</td>\n",
" <td>18.0</td>\n",
" <td>2.023753</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>260.0</td>\n",
" <td>15.023227</td>\n",
" <td>741.406826</td>\n",
" <td>8.416382</td>\n",
" <td>279.342383</td>\n",
" <td>274.999222</td>\n",
" <td>0.0048</td>\n",
" <td>0.000000</td>\n",
" <td>14.099825</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>39.843498</td>\n",
" <td>-85.897102</td>\n",
" <td>snow</td>\n",
" <td>8.233539</td>\n",
" <td>7.0</td>\n",
" <td>5.549324</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>48.0</td>\n",
" <td>30.655498</td>\n",
" <td>758.121661</td>\n",
" <td>-2.092969</td>\n",
" <td>303.854272</td>\n",
" <td>293.944244</td>\n",
" <td>0.0194</td>\n",
" <td>0.000000</td>\n",
" <td>1.182225</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-9.0</td>\n",
" <td>-5.911420</td>\n",
" <td>-35.247700</td>\n",
" <td>polar</td>\n",
" <td>30.618527</td>\n",
" <td>30.0</td>\n",
" <td>2.319395</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>99.0</td>\n",
" <td>19.245194</td>\n",
" <td>752.505533</td>\n",
" <td>-2.072693</td>\n",
" <td>290.389832</td>\n",
" <td>282.104599</td>\n",
" <td>0.0067</td>\n",
" <td>0.000000</td>\n",
" <td>0.088375</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>30.0</td>\n",
" <td>58.100000</td>\n",
" <td>38.683333</td>\n",
" <td>snow</td>\n",
" <td>16.601422</td>\n",
" <td>17.0</td>\n",
" <td>4.060273</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>296.0</td>\n",
" <td>38.102269</td>\n",
" <td>734.381076</td>\n",
" <td>2.616138</td>\n",
" <td>268.365942</td>\n",
" <td>267.126648</td>\n",
" <td>0.0024</td>\n",
" <td>1.002448</td>\n",
" <td>0.000000</td>\n",
" <td>0.00366</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-1.0</td>\n",
" <td>66.580000</td>\n",
" <td>-61.620000</td>\n",
" <td>polar</td>\n",
" <td>1.004967</td>\n",
" <td>-1.0</td>\n",
" <td>3.510967</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>48.0</td>\n",
" <td>-10.442588</td>\n",
" <td>755.390211</td>\n",
" <td>-0.808435</td>\n",
" <td>281.321216</td>\n",
" <td>277.766144</td>\n",
" <td>0.0060</td>\n",
" <td>0.000000</td>\n",
" <td>0.158425</td>\n",
" <td>0.00000</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-26.0</td>\n",
" <td>60.289167</td>\n",
" <td>5.226389</td>\n",
" <td>snow</td>\n",
" <td>7.546170</td>\n",
" <td>7.0</td>\n",
" <td>2.232020</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>100 rows × 54 columns</p>\n",
"</div>"
],
"text/plain": [
" height_sea_level sun_elevation pressure \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 166.0 24.134473 749.287193 \n",
"2022-09-12 00:00:00+00:00 180.0 36.168942 738.731879 \n",
"2022-09-12 00:00:00+00:00 25.0 4.931765 753.034922 \n",
"2022-09-12 00:00:00+00:00 -11.0 22.337882 754.533835 \n",
"2022-09-12 00:00:00+00:00 119.0 58.290232 767.426533 \n",
"... ... ... ... \n",
"2022-09-12 00:00:00+00:00 260.0 15.023227 741.406826 \n",
"2022-09-12 00:00:00+00:00 48.0 30.655498 758.121661 \n",
"2022-09-12 00:00:00+00:00 99.0 19.245194 752.505533 \n",
"2022-09-12 00:00:00+00:00 296.0 38.102269 734.381076 \n",
"2022-09-12 00:00:00+00:00 48.0 -10.442588 755.390211 \n",
"\n",
" cmc_temperature_grad cmc_temperature \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 -0.670923 289.282080 \n",
"2022-09-12 00:00:00+00:00 -3.726770 290.226721 \n",
"2022-09-12 00:00:00+00:00 7.741565 280.471216 \n",
"2022-09-12 00:00:00+00:00 2.323230 277.726721 \n",
"2022-09-12 00:00:00+00:00 0.235266 290.554565 \n",
"... ... ... \n",
"2022-09-12 00:00:00+00:00 8.416382 279.342383 \n",
"2022-09-12 00:00:00+00:00 -2.092969 303.854272 \n",
"2022-09-12 00:00:00+00:00 -2.072693 290.389832 \n",
"2022-09-12 00:00:00+00:00 2.616138 268.365942 \n",
"2022-09-12 00:00:00+00:00 -0.808435 281.321216 \n",
"\n",
" dew_point_temperature absolute_humidity \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 285.220886 0.0090 \n",
"2022-09-12 00:00:00+00:00 284.868256 0.0095 \n",
"2022-09-12 00:00:00+00:00 279.016144 0.0054 \n",
"2022-09-12 00:00:00+00:00 274.868256 0.0043 \n",
"2022-09-12 00:00:00+00:00 283.905655 0.0116 \n",
"... ... ... \n",
"2022-09-12 00:00:00+00:00 274.999222 0.0048 \n",
"2022-09-12 00:00:00+00:00 293.944244 0.0194 \n",
"2022-09-12 00:00:00+00:00 282.104599 0.0067 \n",
"2022-09-12 00:00:00+00:00 267.126648 0.0024 \n",
"2022-09-12 00:00:00+00:00 277.766144 0.0060 \n",
"\n",
" snow_depth rain_accumulated snow_accumulated \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 0.000000 2.641950 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.000000 0.149825 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.000000 3.536025 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.181638 1.822488 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.000000 2.715500 0.00000 \n",
"... ... ... ... \n",
"2022-09-12 00:00:00+00:00 0.000000 14.099825 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.000000 1.182225 0.00000 \n",
"2022-09-12 00:00:00+00:00 0.000000 0.088375 0.00000 \n",
"2022-09-12 00:00:00+00:00 1.002448 0.000000 0.00366 \n",
"2022-09-12 00:00:00+00:00 0.000000 0.158425 0.00000 \n",
"\n",
" ... snow_accumulated_grad ice_rain_grad \\\n",
"date ... \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"... ... ... ... \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 ... 0.0 0.0 \n",
"\n",
" iced_graupel_grad cloud_coverage_grad \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 0.0 -2.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -23.0 \n",
"2022-09-12 00:00:00+00:00 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -70.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -1.0 \n",
"... ... ... \n",
"2022-09-12 00:00:00+00:00 0.0 0.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -9.0 \n",
"2022-09-12 00:00:00+00:00 0.0 30.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -1.0 \n",
"2022-09-12 00:00:00+00:00 0.0 -26.0 \n",
"\n",
" meta_latitude meta_longitude meta_climate \\\n",
"date \n",
"2022-09-12 00:00:00+00:00 46.516667 29.483333 snow \n",
"2022-09-12 00:00:00+00:00 46.521900 26.910299 snow \n",
"2022-09-12 00:00:00+00:00 39.033333 125.783333 snow \n",
"2022-09-12 00:00:00+00:00 55.281898 -77.765297 snow \n",
"2022-09-12 00:00:00+00:00 38.519901 -28.715900 polar \n",
"... ... ... ... \n",
"2022-09-12 00:00:00+00:00 39.843498 -85.897102 snow \n",
"2022-09-12 00:00:00+00:00 -5.911420 -35.247700 polar \n",
"2022-09-12 00:00:00+00:00 58.100000 38.683333 snow \n",
"2022-09-12 00:00:00+00:00 66.580000 -61.620000 polar \n",
"2022-09-12 00:00:00+00:00 60.289167 5.226389 snow \n",
"\n",
" prediction_temperature temperature uncertainty \n",
"date \n",
"2022-09-12 00:00:00+00:00 17.459501 19.0 5.046475 \n",
"2022-09-12 00:00:00+00:00 15.650873 15.0 10.590467 \n",
"2022-09-12 00:00:00+00:00 9.651232 11.0 5.512176 \n",
"2022-09-12 00:00:00+00:00 7.948395 8.0 3.395677 \n",
"2022-09-12 00:00:00+00:00 18.248093 18.0 2.023753 \n",
"... ... ... ... \n",
"2022-09-12 00:00:00+00:00 8.233539 7.0 5.549324 \n",
"2022-09-12 00:00:00+00:00 30.618527 30.0 2.319395 \n",
"2022-09-12 00:00:00+00:00 16.601422 17.0 4.060273 \n",
"2022-09-12 00:00:00+00:00 1.004967 -1.0 3.510967 \n",
"2022-09-12 00:00:00+00:00 7.546170 7.0 2.232020 \n",
"\n",
"[100 rows x 54 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"batch.data"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 238
},
"id": "n41ImwgzQyPP",
"outputId": "f56173a3-8c71-46f2-ca9d-d0a013792388"
},
"outputs": [
{
"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>prediction_temperature</th>\n",
" <th>uncertainty</th>\n",
" </tr>\n",
" <tr>\n",
" <th>date</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>17.459501</td>\n",
" <td>5.046475</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>15.650873</td>\n",
" <td>10.590467</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>9.651232</td>\n",
" <td>5.512176</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>7.948395</td>\n",
" <td>3.395677</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2022-09-12 00:00:00+00:00</th>\n",
" <td>18.248093</td>\n",
" <td>2.023753</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" prediction_temperature uncertainty\n",
"date \n",
"2022-09-12 00:00:00+00:00 17.459501 5.046475\n",
"2022-09-12 00:00:00+00:00 15.650873 10.590467\n",
"2022-09-12 00:00:00+00:00 9.651232 5.512176\n",
"2022-09-12 00:00:00+00:00 7.948395 3.395677\n",
"2022-09-12 00:00:00+00:00 18.248093 2.023753"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"batch.prediction.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iHTrgM8vQ6s3"
},
"source": [
"## Getting Inference Data #2 - By Number of Batches"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1uSzyxcjv_lu"
},
"source": [
"The second way is to specify the number of batches you want and also the date for the first batch.\n",
"\n",
"You can then iterate over the returned object to get the batches. You can then use the batch any way you want. Here's an example that retrieves daily batches for a period of 5 days and logs each one with __whylogs__, saving the binary profiles to disk:"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mtLnlHs3Wj_Q",
"outputId": "c9bd891f-2502-4706-cde9-051fdd3fb861"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"logging batch of size 100 for 2022-09-12 00:00:00+00:00\n",
"logging batch of size 227 for 2022-09-13 00:00:00+00:00\n",
"logging batch of size 186 for 2022-09-14 00:00:00+00:00\n",
"logging batch of size 197 for 2022-09-15 00:00:00+00:00\n",
"logging batch of size 194 for 2022-09-16 00:00:00+00:00\n"
]
}
],
"source": [
"import whylogs as why\n",
"batches = dataset.get_inference_data(number_batches=5)\n",
"\n",
"for batch in batches:\n",
" print(\"logging batch of size {} for {}\".format(len(batch.data),batch.timestamp))\n",
" profile = why.log(batch.data).profile()\n",
" profile.set_dataset_timestamp(batch.timestamp)\n",
" profile.view().write(\"batch_{}\".format(batch.timestamp))"
]
}
],
"metadata": {
"colab": {
"name": "datasets.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3.8.10 ('.venv': poetry)",
"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": "3.8.10"
},
"vscode": {
"interpreter": {
"hash": "8430e7bcc333486e417258c6fadac662061ebd166d9f3c5ccb12c1968aa41625"
}
}
},
"nbformat": 4,
"nbformat_minor": 0
}