|
|
@@ -0,0 +1,616 @@
|
|
|
+{
|
|
|
+ "cells": [
|
|
|
+ {
|
|
|
+ "cell_type": "markdown",
|
|
|
+ "id": "423932f7-1217-4d5e-8cee-1b4e0a6855e1",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "source": [
|
|
|
+ "### OCI Data Science - Useful Tips\n",
|
|
|
+ "<details>\n",
|
|
|
+ "<summary><font size=\"2\">Check for Public Internet Access</font></summary>\n",
|
|
|
+ "\n",
|
|
|
+ "```python\n",
|
|
|
+ "import requests\n",
|
|
|
+ "response = requests.get(\"https://oracle.com\")\n",
|
|
|
+ "assert response.status_code==200, \"Internet connection failed\"\n",
|
|
|
+ "```\n",
|
|
|
+ "</details>\n",
|
|
|
+ "<details>\n",
|
|
|
+ "<summary><font size=\"2\">Helpful Documentation </font></summary>\n",
|
|
|
+ "<ul><li><a href=\"https://docs.cloud.oracle.com/en-us/iaas/data-science/using/data-science.htm\">Data Science Service Documentation</a></li>\n",
|
|
|
+ "<li><a href=\"https://docs.cloud.oracle.com/iaas/tools/ads-sdk/latest/index.html\">ADS documentation</a></li>\n",
|
|
|
+ "</ul>\n",
|
|
|
+ "</details>\n",
|
|
|
+ "<details>\n",
|
|
|
+ "<summary><font size=\"2\">Typical Cell Imports and Settings for ADS</font></summary>\n",
|
|
|
+ "\n",
|
|
|
+ "```python\n",
|
|
|
+ "%load_ext autoreload\n",
|
|
|
+ "%autoreload 2\n",
|
|
|
+ "%matplotlib inline\n",
|
|
|
+ "\n",
|
|
|
+ "import warnings\n",
|
|
|
+ "warnings.filterwarnings('ignore')\n",
|
|
|
+ "\n",
|
|
|
+ "import logging\n",
|
|
|
+ "logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.ERROR)\n",
|
|
|
+ "\n",
|
|
|
+ "import ads\n",
|
|
|
+ "from ads.dataset.factory import DatasetFactory\n",
|
|
|
+ "from ads.automl.provider import OracleAutoMLProvider\n",
|
|
|
+ "from ads.automl.driver import AutoML\n",
|
|
|
+ "from ads.evaluations.evaluator import ADSEvaluator\n",
|
|
|
+ "from ads.common.data import ADSData\n",
|
|
|
+ "from ads.explanations.explainer import ADSExplainer\n",
|
|
|
+ "from ads.explanations.mlx_global_explainer import MLXGlobalExplainer\n",
|
|
|
+ "from ads.explanations.mlx_local_explainer import MLXLocalExplainer\n",
|
|
|
+ "from ads.catalog.model import ModelCatalog\n",
|
|
|
+ "from ads.common.model_artifact import ModelArtifact\n",
|
|
|
+ "```\n",
|
|
|
+ "</details>\n",
|
|
|
+ "<details>\n",
|
|
|
+ "<summary><font size=\"2\">Useful Environment Variables</font></summary>\n",
|
|
|
+ "\n",
|
|
|
+ "```python\n",
|
|
|
+ "import os\n",
|
|
|
+ "print(os.environ[\"NB_SESSION_COMPARTMENT_OCID\"])\n",
|
|
|
+ "print(os.environ[\"PROJECT_OCID\"])\n",
|
|
|
+ "print(os.environ[\"USER_OCID\"])\n",
|
|
|
+ "print(os.environ[\"TENANCY_OCID\"])\n",
|
|
|
+ "print(os.environ[\"NB_REGION\"])\n",
|
|
|
+ "```\n",
|
|
|
+ "</details>"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 1,
|
|
|
+ "id": "c8e038c6-c252-4c41-88ac-5d4d4996e59b",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "import pandas as pd\n",
|
|
|
+ "import numpy as np"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 2,
|
|
|
+ "id": "688aaeb5-6e94-4741-ab02-e6b159325a13",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "mpg = pd.read_csv('~/ns-user-38/day3/predictive_maintenance.csv')"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 3,
|
|
|
+ "id": "cc403108-5d3b-449a-b685-00fff0637761",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "(10000, 10)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 3,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "mpg.shape"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 4,
|
|
|
+ "id": "772a10b9-c4b3-4c73-b6fc-20cd5432e4cd",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "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>UDI</th>\n",
|
|
|
+ " <th>Product ID</th>\n",
|
|
|
+ " <th>Type</th>\n",
|
|
|
+ " <th>Air temperature [K]</th>\n",
|
|
|
+ " <th>Process temperature [K]</th>\n",
|
|
|
+ " <th>Rotational speed [rpm]</th>\n",
|
|
|
+ " <th>Torque [Nm]</th>\n",
|
|
|
+ " <th>Tool wear [min]</th>\n",
|
|
|
+ " <th>Target</th>\n",
|
|
|
+ " <th>Failure Type</th>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </thead>\n",
|
|
|
+ " <tbody>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>0</th>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>M14860</td>\n",
|
|
|
+ " <td>M</td>\n",
|
|
|
+ " <td>298.1</td>\n",
|
|
|
+ " <td>308.6</td>\n",
|
|
|
+ " <td>1551</td>\n",
|
|
|
+ " <td>42.8</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>1</th>\n",
|
|
|
+ " <td>2</td>\n",
|
|
|
+ " <td>L47181</td>\n",
|
|
|
+ " <td>L</td>\n",
|
|
|
+ " <td>298.2</td>\n",
|
|
|
+ " <td>308.7</td>\n",
|
|
|
+ " <td>1408</td>\n",
|
|
|
+ " <td>46.3</td>\n",
|
|
|
+ " <td>3</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2</th>\n",
|
|
|
+ " <td>3</td>\n",
|
|
|
+ " <td>L47182</td>\n",
|
|
|
+ " <td>L</td>\n",
|
|
|
+ " <td>298.1</td>\n",
|
|
|
+ " <td>308.5</td>\n",
|
|
|
+ " <td>1498</td>\n",
|
|
|
+ " <td>49.4</td>\n",
|
|
|
+ " <td>5</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>3</th>\n",
|
|
|
+ " <td>4</td>\n",
|
|
|
+ " <td>L47183</td>\n",
|
|
|
+ " <td>L</td>\n",
|
|
|
+ " <td>298.2</td>\n",
|
|
|
+ " <td>308.6</td>\n",
|
|
|
+ " <td>1433</td>\n",
|
|
|
+ " <td>39.5</td>\n",
|
|
|
+ " <td>7</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>4</th>\n",
|
|
|
+ " <td>5</td>\n",
|
|
|
+ " <td>L47184</td>\n",
|
|
|
+ " <td>L</td>\n",
|
|
|
+ " <td>298.2</td>\n",
|
|
|
+ " <td>308.7</td>\n",
|
|
|
+ " <td>1408</td>\n",
|
|
|
+ " <td>40.0</td>\n",
|
|
|
+ " <td>9</td>\n",
|
|
|
+ " <td>0</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </tbody>\n",
|
|
|
+ "</table>\n",
|
|
|
+ "</div>"
|
|
|
+ ],
|
|
|
+ "text/plain": [
|
|
|
+ " UDI Product ID Type Air temperature [K] Process temperature [K] \\\n",
|
|
|
+ "0 1 M14860 M 298.1 308.6 \n",
|
|
|
+ "1 2 L47181 L 298.2 308.7 \n",
|
|
|
+ "2 3 L47182 L 298.1 308.5 \n",
|
|
|
+ "3 4 L47183 L 298.2 308.6 \n",
|
|
|
+ "4 5 L47184 L 298.2 308.7 \n",
|
|
|
+ "\n",
|
|
|
+ " Rotational speed [rpm] Torque [Nm] Tool wear [min] Target Failure Type \n",
|
|
|
+ "0 1551 42.8 0 0 No Failure \n",
|
|
|
+ "1 1408 46.3 3 0 No Failure \n",
|
|
|
+ "2 1498 49.4 5 0 No Failure \n",
|
|
|
+ "3 1433 39.5 7 0 No Failure \n",
|
|
|
+ "4 1408 40.0 9 0 No Failure "
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 4,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "mpg.head()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 21,
|
|
|
+ "id": "e5698130-0254-46d3-94a5-05b5c32d9e6c",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "mpg_update = mpg.drop(['UDI','Product ID','Type','Failure Type','Target'], axis=1)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 22,
|
|
|
+ "id": "8473e9bf-77b0-473e-b9c2-f19996a3ec08",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "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>Air temperature [K]</th>\n",
|
|
|
+ " <th>Process temperature [K]</th>\n",
|
|
|
+ " <th>Rotational speed [rpm]</th>\n",
|
|
|
+ " <th>Torque [Nm]</th>\n",
|
|
|
+ " <th>Tool wear [min]</th>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </thead>\n",
|
|
|
+ " <tbody>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>count</th>\n",
|
|
|
+ " <td>10000.000000</td>\n",
|
|
|
+ " <td>10000.000000</td>\n",
|
|
|
+ " <td>10000.000000</td>\n",
|
|
|
+ " <td>10000.000000</td>\n",
|
|
|
+ " <td>10000.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>mean</th>\n",
|
|
|
+ " <td>300.004930</td>\n",
|
|
|
+ " <td>310.005560</td>\n",
|
|
|
+ " <td>1538.776100</td>\n",
|
|
|
+ " <td>39.986910</td>\n",
|
|
|
+ " <td>107.951000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>std</th>\n",
|
|
|
+ " <td>2.000259</td>\n",
|
|
|
+ " <td>1.483734</td>\n",
|
|
|
+ " <td>179.284096</td>\n",
|
|
|
+ " <td>9.968934</td>\n",
|
|
|
+ " <td>63.654147</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>min</th>\n",
|
|
|
+ " <td>295.300000</td>\n",
|
|
|
+ " <td>305.700000</td>\n",
|
|
|
+ " <td>1168.000000</td>\n",
|
|
|
+ " <td>3.800000</td>\n",
|
|
|
+ " <td>0.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>25%</th>\n",
|
|
|
+ " <td>298.300000</td>\n",
|
|
|
+ " <td>308.800000</td>\n",
|
|
|
+ " <td>1423.000000</td>\n",
|
|
|
+ " <td>33.200000</td>\n",
|
|
|
+ " <td>53.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>50%</th>\n",
|
|
|
+ " <td>300.100000</td>\n",
|
|
|
+ " <td>310.100000</td>\n",
|
|
|
+ " <td>1503.000000</td>\n",
|
|
|
+ " <td>40.100000</td>\n",
|
|
|
+ " <td>108.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>75%</th>\n",
|
|
|
+ " <td>301.500000</td>\n",
|
|
|
+ " <td>311.100000</td>\n",
|
|
|
+ " <td>1612.000000</td>\n",
|
|
|
+ " <td>46.800000</td>\n",
|
|
|
+ " <td>162.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>max</th>\n",
|
|
|
+ " <td>304.500000</td>\n",
|
|
|
+ " <td>313.800000</td>\n",
|
|
|
+ " <td>2886.000000</td>\n",
|
|
|
+ " <td>76.600000</td>\n",
|
|
|
+ " <td>253.000000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </tbody>\n",
|
|
|
+ "</table>\n",
|
|
|
+ "</div>"
|
|
|
+ ],
|
|
|
+ "text/plain": [
|
|
|
+ " Air temperature [K] Process temperature [K] Rotational speed [rpm] \\\n",
|
|
|
+ "count 10000.000000 10000.000000 10000.000000 \n",
|
|
|
+ "mean 300.004930 310.005560 1538.776100 \n",
|
|
|
+ "std 2.000259 1.483734 179.284096 \n",
|
|
|
+ "min 295.300000 305.700000 1168.000000 \n",
|
|
|
+ "25% 298.300000 308.800000 1423.000000 \n",
|
|
|
+ "50% 300.100000 310.100000 1503.000000 \n",
|
|
|
+ "75% 301.500000 311.100000 1612.000000 \n",
|
|
|
+ "max 304.500000 313.800000 2886.000000 \n",
|
|
|
+ "\n",
|
|
|
+ " Torque [Nm] Tool wear [min] \n",
|
|
|
+ "count 10000.000000 10000.000000 \n",
|
|
|
+ "mean 39.986910 107.951000 \n",
|
|
|
+ "std 9.968934 63.654147 \n",
|
|
|
+ "min 3.800000 0.000000 \n",
|
|
|
+ "25% 33.200000 53.000000 \n",
|
|
|
+ "50% 40.100000 108.000000 \n",
|
|
|
+ "75% 46.800000 162.000000 \n",
|
|
|
+ "max 76.600000 253.000000 "
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 22,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "mpg_update.describe()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 19,
|
|
|
+ "id": "82381e8b-4b7a-405e-a930-41b4875f1c35",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "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>Product ID</th>\n",
|
|
|
+ " <th>Type</th>\n",
|
|
|
+ " <th>Failure Type</th>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </thead>\n",
|
|
|
+ " <tbody>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>count</th>\n",
|
|
|
+ " <td>10000</td>\n",
|
|
|
+ " <td>10000</td>\n",
|
|
|
+ " <td>10000</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>unique</th>\n",
|
|
|
+ " <td>10000</td>\n",
|
|
|
+ " <td>3</td>\n",
|
|
|
+ " <td>6</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>top</th>\n",
|
|
|
+ " <td>M14860</td>\n",
|
|
|
+ " <td>L</td>\n",
|
|
|
+ " <td>No Failure</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>freq</th>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>6000</td>\n",
|
|
|
+ " <td>9652</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </tbody>\n",
|
|
|
+ "</table>\n",
|
|
|
+ "</div>"
|
|
|
+ ],
|
|
|
+ "text/plain": [
|
|
|
+ " Product ID Type Failure Type\n",
|
|
|
+ "count 10000 10000 10000\n",
|
|
|
+ "unique 10000 3 6\n",
|
|
|
+ "top M14860 L No Failure\n",
|
|
|
+ "freq 1 6000 9652"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 19,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "# categorcial variable summary\n",
|
|
|
+ "\n",
|
|
|
+ "mpg.describe(include=['O'])"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 20,
|
|
|
+ "id": "c5f61e38-83be-46cb-98da-5bf56b87892d",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "<class 'pandas.core.frame.DataFrame'>\n",
|
|
|
+ "RangeIndex: 10000 entries, 0 to 9999\n",
|
|
|
+ "Data columns (total 10 columns):\n",
|
|
|
+ " # Column Non-Null Count Dtype \n",
|
|
|
+ "--- ------ -------------- ----- \n",
|
|
|
+ " 0 UDI 10000 non-null int64 \n",
|
|
|
+ " 1 Product ID 10000 non-null object \n",
|
|
|
+ " 2 Type 10000 non-null object \n",
|
|
|
+ " 3 Air temperature [K] 10000 non-null float64\n",
|
|
|
+ " 4 Process temperature [K] 10000 non-null float64\n",
|
|
|
+ " 5 Rotational speed [rpm] 10000 non-null int64 \n",
|
|
|
+ " 6 Torque [Nm] 10000 non-null float64\n",
|
|
|
+ " 7 Tool wear [min] 10000 non-null int64 \n",
|
|
|
+ " 8 Target 10000 non-null int64 \n",
|
|
|
+ " 9 Failure Type 10000 non-null object \n",
|
|
|
+ "dtypes: float64(3), int64(4), object(3)\n",
|
|
|
+ "memory usage: 781.4+ KB\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "#printing data types\n",
|
|
|
+ "\n",
|
|
|
+ "mpg.info()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 24,
|
|
|
+ "id": "91ffc9e8-814b-429f-90ef-1b20d3f34c02",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "UDI 10000\n",
|
|
|
+ "Product ID 10000\n",
|
|
|
+ "Type 3\n",
|
|
|
+ "Air temperature [K] 93\n",
|
|
|
+ "Process temperature [K] 82\n",
|
|
|
+ "Rotational speed [rpm] 941\n",
|
|
|
+ "Torque [Nm] 577\n",
|
|
|
+ "Tool wear [min] 246\n",
|
|
|
+ "Target 2\n",
|
|
|
+ "Failure Type 6\n",
|
|
|
+ "dtype: int64"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 24,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "mpg.nunique()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 25,
|
|
|
+ "id": "de56763d-31cc-45d9-887c-d2a0f76956f5",
|
|
|
+ "metadata": {
|
|
|
+ "tags": []
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "UDI 0\n",
|
|
|
+ "Product ID 0\n",
|
|
|
+ "Type 0\n",
|
|
|
+ "Air temperature [K] 0\n",
|
|
|
+ "Process temperature [K] 0\n",
|
|
|
+ "Rotational speed [rpm] 0\n",
|
|
|
+ "Torque [Nm] 0\n",
|
|
|
+ "Tool wear [min] 0\n",
|
|
|
+ "Target 0\n",
|
|
|
+ "Failure Type 0\n",
|
|
|
+ "dtype: int64"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 25,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "#check for missing entries\n",
|
|
|
+ "mpg.isnull().sum()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": null,
|
|
|
+ "id": "8a15fe03-d630-4108-ba07-97ba6b1ba4f6",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": []
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "metadata": {
|
|
|
+ "kernelspec": {
|
|
|
+ "display_name": "Python [conda env:ns-user-38_v1]",
|
|
|
+ "language": "python",
|
|
|
+ "name": "conda-env-ns-user-38_v1-py"
|
|
|
+ },
|
|
|
+ "language_info": {
|
|
|
+ "codemirror_mode": {
|
|
|
+ "name": "ipython",
|
|
|
+ "version": 3
|
|
|
+ },
|
|
|
+ "file_extension": ".py",
|
|
|
+ "mimetype": "text/x-python",
|
|
|
+ "name": "python",
|
|
|
+ "nbconvert_exporter": "python",
|
|
|
+ "pygments_lexer": "ipython3",
|
|
|
+ "version": "3.11.9"
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "nbformat": 4,
|
|
|
+ "nbformat_minor": 5
|
|
|
+}
|
