Skip to content

Instantly share code, notes, and snippets.

@codesue

codesue/components_keras.ipynb

Last active November 19, 2022 19:59
Show Gist options
  • Save codesue/2097704f3b84029f6e550e7f1650f378 to your computer and use it in GitHub Desktop.
Save codesue/2097704f3b84029f6e550e7f1650f378 to your computer and use it in GitHub Desktop.
Download ZIP
Playing with model-card-toolkit & metrics
Display the source blob
Display the rendered blob
Raw
components_keras.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/codesue/2097704f3b84029f6e550e7f1650f378/components_keras.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# Playing with model-card-toolkit & metrics"
],
"metadata": {
"id": "PyV0Lc1CoNbq"
}
},
{
"cell_type": "code",
"source": [
"%pip install -Uqq model-card-toolkit tensorflow-model-analysis"
],
"metadata": {
"id": "PbtkXxaeo3Ev"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from collections import defaultdict\n",
"import logging\n",
"import tempfile\n",
"from typing import Any, Dict\n",
"import urllib\n",
"\n",
"import tensorflow_model_analysis as tfma\n",
"\n",
"\n",
"EVAL_RESULT_PATH = \"eval_keras\"\n",
"eval_result = tfma.load_eval_result(EVAL_RESULT_PATH)"
],
"metadata": {
"id": "mDB3lNW4r7Zh",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "0563907a-cad7-494d-f2ba-15bb9fee7918"
},
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/tensorflow_model_analysis/writers/metrics_plots_and_validations_writer.py:107: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use eager execution and: \n",
"`tf.data.TFRecordDataset(path)`\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Load and parse tfma eval result to create a metrics dictionary\n",
"\n",
"This function is adapted from [MCT's annotate_eval_result_metrics()](https://github.com/tensorflow/model-card-toolkit/blob/master/model_card_toolkit/utils/tfx_util.py#L424). "
],
"metadata": {
"id": "sYzADHdhpQM-"
}
},
{
"cell_type": "code",
"source": [
"def create_metrics_dict(eval_result: tfma.EvalResult) -> Dict[str, Any]:\n",
"\n",
" TYPE_FIELD_MAP = {\n",
" 'BYTES': 'bytesValues',\n",
" 'INT32': 'int32Values',\n",
" 'INT64': 'int64Values',\n",
" 'FLOAT32': 'float32Values',\n",
" 'FLOAT64': 'float64Values'\n",
" }\n",
"\n",
" metrics = defaultdict(dict)\n",
"\n",
" def _parse_array_value(array: Dict[str, Any]) -> str:\n",
" data_type = array['dataType']\n",
" if data_type in TYPE_FIELD_MAP:\n",
" type_field = TYPE_FIELD_MAP[data_type]\n",
" return ', '.join([str(value) for value in array[type_field]])\n",
" else:\n",
" logging.warning('Received unexpected array %s', str(array))\n",
" return ''\n",
"\n",
" for slice_repr, metrics_for_slice in (\n",
" eval_result.get_metrics_for_all_slices().items()):\n",
" # Parse the slice name\n",
" if not isinstance(slice_repr, tuple):\n",
" raise ValueError(\n",
" f'Expected EvalResult slices to be tuples; found {type(slice_repr)}')\n",
" slice_name = '_X_'.join(f'{a}_{b}' for a, b in slice_repr)\n",
" for metric_name, metric_value in metrics_for_slice.items():\n",
" # Parse the metric value\n",
" parsed_value = ''\n",
" if 'doubleValue' in metric_value:\n",
" parsed_value = metric_value['doubleValue']\n",
" elif 'boundedValue' in metric_value:\n",
" parsed_value = metric_value['boundedValue']['value']\n",
" elif 'arrayValue' in metric_value:\n",
" parsed_value = _parse_array_value(metric_value['arrayValue'])\n",
" else:\n",
" logging.warning(\n",
" 'Expected doubleValue, boundedValue, or arrayValue; found %s',\n",
" metric_value.keys())\n",
" # Add metric to dict instead of creating the PerformanceMetric and\n",
" # appending to the ModelCard\n",
" if parsed_value:\n",
" metrics[slice_name][metric_name] = str(parsed_value)\n",
"\n",
" return metrics"
],
"metadata": {
"id": "zV59RFzkrOh0"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"source": [
"metrics = create_metrics_dict(eval_result)"
],
"metadata": {
"id": "9fWzpFp3stf3"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Creating a DataFrame from the dictionary\n",
"\n",
"Not necessary, but nice for exploring and can create a metrics table with `df.to_html()` instead of using jinja macros."
],
"metadata": {
"id": "02AKtBS6zRjK"
}
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"df = pd.DataFrame.from_dict(metrics, orient=\"index\")\n",
"df"
],
"metadata": {
"id": "BSRk8es4sxU1",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 824
},
"outputId": "03a6d7c3-b0fc-468c-a7e1-61611c0ef865"
},
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" binary_accuracy loss example_count\n",
"trip_start_hour_19 0.8761609907120743 0.8888519406318665 323.0\n",
" 0.8672976238421265 1.0233759880065918 4966.0\n",
"trip_start_hour_1 0.8764044943820225 1.098751425743103 178.0\n",
"trip_start_hour_7 0.8727272727272727 0.43154892325401306 110.0\n",
"trip_start_hour_10 0.9107981220657277 0.5846514105796814 213.0\n",
"trip_start_hour_9 0.8388625592417062 0.9277230501174927 211.0\n",
"trip_start_hour_0 0.9077669902912622 0.67937171459198 206.0\n",
"trip_start_hour_2 0.8827586206896552 1.1361725330352783 145.0\n",
"trip_start_hour_15 0.876 0.860887885093689 250.0\n",
"trip_start_hour_12 0.8852459016393442 1.0438504219055176 244.0\n",
"trip_start_hour_11 0.8691588785046729 0.8100011348724365 214.0\n",
"trip_start_hour_20 0.8841059602649006 0.8981946706771851 302.0\n",
"trip_start_hour_22 0.8623188405797102 0.9423074126243591 276.0\n",
"trip_start_hour_17 0.8210116731517509 1.5072575807571411 257.0\n",
"trip_start_hour_21 0.8961038961038961 0.9680811166763306 308.0\n",
"trip_start_hour_13 0.85546875 1.0930203199386597 256.0\n",
"trip_start_hour_23 0.8962655601659751 0.7908647060394287 241.0\n",
"trip_start_hour_18 0.8675496688741722 1.1031101942062378 302.0\n",
"trip_start_hour_14 0.8347457627118644 1.1018140316009521 236.0\n",
"trip_start_hour_3 0.83 1.7418893575668335 100.0\n",
"trip_start_hour_8 0.8588235294117647 1.4287647008895874 170.0\n",
"trip_start_hour_4 0.9032258064516129 0.43598467111587524 62.0\n",
"trip_start_hour_16 0.8064516129032258 1.2949882745742798 248.0\n",
"trip_start_hour_5 0.7735849056603774 2.43748140335083 53.0\n",
"trip_start_hour_6 0.8688524590163934 1.7836421728134155 61.0"
],
"text/html": [
"\n",
" <div id=\"df-a9263907-5284-4dd0-9bff-a85c212d1fcd\">\n",
" <div class=\"colab-df-container\">\n",
" <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>binary_accuracy</th>\n",
" <th>loss</th>\n",
" <th>example_count</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>trip_start_hour_19</th>\n",
" <td>0.8761609907120743</td>\n",
" <td>0.8888519406318665</td>\n",
" <td>323.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <td>0.8672976238421265</td>\n",
" <td>1.0233759880065918</td>\n",
" <td>4966.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_1</th>\n",
" <td>0.8764044943820225</td>\n",
" <td>1.098751425743103</td>\n",
" <td>178.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_7</th>\n",
" <td>0.8727272727272727</td>\n",
" <td>0.43154892325401306</td>\n",
" <td>110.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_10</th>\n",
" <td>0.9107981220657277</td>\n",
" <td>0.5846514105796814</td>\n",
" <td>213.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_9</th>\n",
" <td>0.8388625592417062</td>\n",
" <td>0.9277230501174927</td>\n",
" <td>211.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_0</th>\n",
" <td>0.9077669902912622</td>\n",
" <td>0.67937171459198</td>\n",
" <td>206.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_2</th>\n",
" <td>0.8827586206896552</td>\n",
" <td>1.1361725330352783</td>\n",
" <td>145.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_15</th>\n",
" <td>0.876</td>\n",
" <td>0.860887885093689</td>\n",
" <td>250.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_12</th>\n",
" <td>0.8852459016393442</td>\n",
" <td>1.0438504219055176</td>\n",
" <td>244.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_11</th>\n",
" <td>0.8691588785046729</td>\n",
" <td>0.8100011348724365</td>\n",
" <td>214.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_20</th>\n",
" <td>0.8841059602649006</td>\n",
" <td>0.8981946706771851</td>\n",
" <td>302.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_22</th>\n",
" <td>0.8623188405797102</td>\n",
" <td>0.9423074126243591</td>\n",
" <td>276.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_17</th>\n",
" <td>0.8210116731517509</td>\n",
" <td>1.5072575807571411</td>\n",
" <td>257.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_21</th>\n",
" <td>0.8961038961038961</td>\n",
" <td>0.9680811166763306</td>\n",
" <td>308.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_13</th>\n",
" <td>0.85546875</td>\n",
" <td>1.0930203199386597</td>\n",
" <td>256.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_23</th>\n",
" <td>0.8962655601659751</td>\n",
" <td>0.7908647060394287</td>\n",
" <td>241.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_18</th>\n",
" <td>0.8675496688741722</td>\n",
" <td>1.1031101942062378</td>\n",
" <td>302.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_14</th>\n",
" <td>0.8347457627118644</td>\n",
" <td>1.1018140316009521</td>\n",
" <td>236.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_3</th>\n",
" <td>0.83</td>\n",
" <td>1.7418893575668335</td>\n",
" <td>100.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_8</th>\n",
" <td>0.8588235294117647</td>\n",
" <td>1.4287647008895874</td>\n",
" <td>170.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_4</th>\n",
" <td>0.9032258064516129</td>\n",
" <td>0.43598467111587524</td>\n",
" <td>62.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_16</th>\n",
" <td>0.8064516129032258</td>\n",
" <td>1.2949882745742798</td>\n",
" <td>248.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_5</th>\n",
" <td>0.7735849056603774</td>\n",
" <td>2.43748140335083</td>\n",
" <td>53.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>trip_start_hour_6</th>\n",
" <td>0.8688524590163934</td>\n",
" <td>1.7836421728134155</td>\n",
" <td>61.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a9263907-5284-4dd0-9bff-a85c212d1fcd')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-a9263907-5284-4dd0-9bff-a85c212d1fcd button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-a9263907-5284-4dd0-9bff-a85c212d1fcd');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "code",
"source": [
"overall_slice_key = ''\n",
"metrics.get(overall_slice_key) "
],
"metadata": {
"id": "3u7IxE3l8MUB",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "91713bc4-01bd-424d-cbc6-6ec30e6b63f5"
},
"execution_count": 5,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'binary_accuracy': '0.8672976238421265',\n",
" 'loss': '1.0233759880065918',\n",
" 'example_count': '4966.0'}"
]
},
"metadata": {},
"execution_count": 5
}
]
},
{
"cell_type": "markdown",
"source": [
"## Create a model card"
],
"metadata": {
"id": "QTconzKl-5wb"
}
},
{
"cell_type": "code",
"source": [
"from IPython.display import display, HTML\n",
"import model_card_toolkit as mct\n",
"\n",
"toolkit = mct.ModelCardToolkit()\n",
"model_card = toolkit.scaffold_assets()\n",
"model_card"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "aDh8qadoIaeJ",
"outputId": "d9b9770c-cf3a-43a5-be41-4b192a9f3f34"
},
"execution_count": 18,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"ModelCard(model_details=ModelDetails(name=None, overview=None, documentation=None, owners=[], version=Version(name=None, date=None, diff=None), licenses=[], references=[], citations=[], path=None), model_parameters=ModelParameters(model_architecture=None, data=[], input_format=None, input_format_map=[], output_format=None, output_format_map=[]), quantitative_analysis=QuantitativeAnalysis(performance_metrics=[], graphics=GraphicsCollection(description=None, collection=[])), considerations=Considerations(users=[], use_cases=[], limitations=[], tradeoffs=[], ethical_considerations=[]))"
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"source": [
"def annotate_eval_result_metrics(model_card: mct.ModelCard,\n",
" metrics_dict: Dict[str, Any]):\n",
" for slice_name, slice_metrics in metrics_dict.items():\n",
" for metric_name, metric_value in slice_metrics.items():\n",
" performance_metric = mct.PerformanceMetric(\n",
" slice=slice_name, type=metric_name, value=str(metric_value))\n",
" model_card.quantitative_analysis.performance_metrics.append(performance_metric)"
],
"metadata": {
"id": "GUkTl3j28eNw"
},
"execution_count": 19,
"outputs": []
},
{
"cell_type": "code",
"source": [
"annotate_eval_result_metrics(model_card, metrics)"
],
"metadata": {
"id": "uMKaIJDm-wR9"
},
"execution_count": 20,
"outputs": []
},
{
"cell_type": "code",
"source": [
"rendered_model_card = toolkit.export_format(model_card)\n",
"display(HTML(rendered_model_card))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "X8Vs9S-RLLp2",
"outputId": "88eb1769-f104-454c-8f94-73dc9323d299"
},
"execution_count": 22,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<!DOCTYPE html>\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"<html lang=\"en\">\n",
"<head>\n",
"<style>\n",
" h1 {text-align: center;}\n",
" .row {\n",
" display: flex;\n",
" }\n",
" .col {\n",
" flex: 1;\n",
" }\n",
" .card {\n",
" padding: 1em;\n",
" border: 1px solid #DADCE0;\n",
" margin: 10px;\n",
" }\n",
" .img-container {\n",
" display: flex;\n",
" flex-wrap: wrap;\n",
" justify-content: space-around;\n",
" text-align: center;\n",
" }\n",
" .img-item {\n",
" flex: 1;\n",
" }\n",
" .center {\n",
" margin-left: auto;\n",
" margin-right: auto;\n",
" }\n",
" table th {\n",
" background: #eee;\n",
" }\n",
" table, th, td {\n",
" border: 1px solid black;\n",
" border-collapse: collapse;\n",
" }\n",
" th, td {\n",
" border: 1px solid #ccc;\n",
" height: 30px;\n",
" text-align: left;\n",
" padding: 5px 10px\n",
" }\n",
" caption { font-weight: bold; }\n",
"</style>\n",
"<title>\n",
" Model Card for None\n",
"</title>\n",
"</head>\n",
"<body>\n",
" <h1>\n",
" Model Card for None\n",
" </h1>\n",
" <div class=\"row\">\n",
" <div class=\"col card\">\n",
" <h2>Model Details</h2>\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" </div>\n",
" \n",
" \n",
" </div>\n",
" \n",
" \n",
" \n",
"<div class=\"col card\">\n",
" <h2>Quantitative Analysis</h2>\n",
" \n",
" \n",
"<table class=\"center\">\n",
" <caption>Performance Metrics</caption>\n",
" <tr><th>Name</th><th>Value</th></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_19\n",
"</td><td>\n",
"0.8761609907120743 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_19\n",
"</td><td>\n",
"0.8888519406318665 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_19\n",
"</td><td>\n",
"323.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy\n",
"</td><td>\n",
"0.8672976238421265 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss\n",
"</td><td>\n",
"1.0233759880065918 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count\n",
"</td><td>\n",
"4966.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_1\n",
"</td><td>\n",
"0.8764044943820225 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_1\n",
"</td><td>\n",
"1.098751425743103 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_1\n",
"</td><td>\n",
"178.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_7\n",
"</td><td>\n",
"0.8727272727272727 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_7\n",
"</td><td>\n",
"0.43154892325401306 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_7\n",
"</td><td>\n",
"110.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_10\n",
"</td><td>\n",
"0.9107981220657277 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_10\n",
"</td><td>\n",
"0.5846514105796814 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_10\n",
"</td><td>\n",
"213.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_9\n",
"</td><td>\n",
"0.8388625592417062 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_9\n",
"</td><td>\n",
"0.9277230501174927 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_9\n",
"</td><td>\n",
"211.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_0\n",
"</td><td>\n",
"0.9077669902912622 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_0\n",
"</td><td>\n",
"0.67937171459198 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_0\n",
"</td><td>\n",
"206.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_2\n",
"</td><td>\n",
"0.8827586206896552 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_2\n",
"</td><td>\n",
"1.1361725330352783 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_2\n",
"</td><td>\n",
"145.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_15\n",
"</td><td>\n",
"0.876 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_15\n",
"</td><td>\n",
"0.860887885093689 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_15\n",
"</td><td>\n",
"250.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_12\n",
"</td><td>\n",
"0.8852459016393442 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_12\n",
"</td><td>\n",
"1.0438504219055176 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_12\n",
"</td><td>\n",
"244.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_11\n",
"</td><td>\n",
"0.8691588785046729 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_11\n",
"</td><td>\n",
"0.8100011348724365 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_11\n",
"</td><td>\n",
"214.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_20\n",
"</td><td>\n",
"0.8841059602649006 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_20\n",
"</td><td>\n",
"0.8981946706771851 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_20\n",
"</td><td>\n",
"302.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_22\n",
"</td><td>\n",
"0.8623188405797102 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_22\n",
"</td><td>\n",
"0.9423074126243591 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_22\n",
"</td><td>\n",
"276.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_17\n",
"</td><td>\n",
"0.8210116731517509 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_17\n",
"</td><td>\n",
"1.5072575807571411 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_17\n",
"</td><td>\n",
"257.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_21\n",
"</td><td>\n",
"0.8961038961038961 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_21\n",
"</td><td>\n",
"0.9680811166763306 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_21\n",
"</td><td>\n",
"308.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_13\n",
"</td><td>\n",
"0.85546875 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_13\n",
"</td><td>\n",
"1.0930203199386597 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_13\n",
"</td><td>\n",
"256.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_23\n",
"</td><td>\n",
"0.8962655601659751 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_23\n",
"</td><td>\n",
"0.7908647060394287 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_23\n",
"</td><td>\n",
"241.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_18\n",
"</td><td>\n",
"0.8675496688741722 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_18\n",
"</td><td>\n",
"1.1031101942062378 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_18\n",
"</td><td>\n",
"302.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_14\n",
"</td><td>\n",
"0.8347457627118644 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_14\n",
"</td><td>\n",
"1.1018140316009521 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_14\n",
"</td><td>\n",
"236.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_3\n",
"</td><td>\n",
"0.83 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_3\n",
"</td><td>\n",
"1.7418893575668335 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_3\n",
"</td><td>\n",
"100.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_8\n",
"</td><td>\n",
"0.8588235294117647 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_8\n",
"</td><td>\n",
"1.4287647008895874 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_8\n",
"</td><td>\n",
"170.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_4\n",
"</td><td>\n",
"0.9032258064516129 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_4\n",
"</td><td>\n",
"0.43598467111587524 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_4\n",
"</td><td>\n",
"62.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_16\n",
"</td><td>\n",
"0.8064516129032258 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_16\n",
"</td><td>\n",
"1.2949882745742798 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_16\n",
"</td><td>\n",
"248.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_5\n",
"</td><td>\n",
"0.7735849056603774 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_5\n",
"</td><td>\n",
"2.43748140335083 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_5\n",
"</td><td>\n",
"53.0 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"binary_accuracy, trip_start_hour_6\n",
"</td><td>\n",
"0.8688524590163934 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"loss, trip_start_hour_6\n",
"</td><td>\n",
"1.7836421728134155 (None, None)\n",
"</td></tr>\n",
"\n",
" <tr><td>\n",
"example_count, trip_start_hour_6\n",
"</td><td>\n",
"61.0 (None, None)\n",
"</td></tr>\n",
"\n",
"</table>\n",
"\n",
" \n",
" \n",
"</div>\n",
"\n",
" \n",
"</body>\n",
"</html>"
]
},
"metadata": {}
}
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"gpuClass": "standard"
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment