Skip to content

Instantly share code, notes, and snippets.

@jimbonant

jimbonant/randomforest_iris_dataset.ipynb

Created June 1, 2022 04:38
Show Gist options
  • Save jimbonant/966f99d55b3d7e8e89f110ca2a1f6513 to your computer and use it in GitHub Desktop.
Save jimbonant/966f99d55b3d7e8e89f110ca2a1f6513 to your computer and use it in GitHub Desktop.
Download ZIP
RandomForest_Iris_dataset.ipynb
Display the source blob
Display the rendered blob
Raw
randomforest_iris_dataset.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "RandomForest_Iris_dataset.ipynb",
"provenance": [],
"authorship_tag": "ABX9TyNDZ5Azj7q6wuFumPm+WMez",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/jimbonant/966f99d55b3d7e8e89f110ca2a1f6513/randomforest_iris_dataset.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"id": "bN22nLUBW75f"
},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.datasets import make_classification"
]
},
{
"cell_type": "code",
"source": [
"iris = datasets.load_iris()"
],
"metadata": {
"id": "0xuWy6S0YVTz"
},
"execution_count": 36,
"outputs": []
},
{
"cell_type": "code",
"source": [
"iris"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Z2OQN0OQYa7g",
"outputId": "068ff8b6-344f-47e3-8264-5b0d91c6f84a"
},
"execution_count": 37,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"{'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n :Number of Instances: 150 (50 in each of three classes)\\n :Number of Attributes: 4 numeric, predictive attributes and the class\\n :Attribute Information:\\n - sepal length in cm\\n - sepal width in cm\\n - petal length in cm\\n - petal width in cm\\n - class:\\n - Iris-Setosa\\n - Iris-Versicolour\\n - Iris-Virginica\\n \\n :Summary Statistics:\\n\\n ============== ==== ==== ======= ===== ====================\\n Min Max Mean SD Class Correlation\\n ============== ==== ==== ======= ===== ====================\\n sepal length: 4.3 7.9 5.84 0.83 0.7826\\n sepal width: 2.0 4.4 3.05 0.43 -0.4194\\n petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\\n petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\\n ============== ==== ==== ======= ===== ====================\\n\\n :Missing Attribute Values: None\\n :Class Distribution: 33.3% for each of 3 classes.\\n :Creator: R.A. Fisher\\n :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature. Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day. (See Duda & Hart, for example.) The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant. One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n Mathematical Statistics\" (John Wiley, NY, 1950).\\n - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\\n - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n Structure and Classification Rule for Recognition in Partially Exposed\\n Environments\". IEEE Transactions on Pattern Analysis and Machine\\n Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\". IEEE Transactions\\n on Information Theory, May 1972, 431-433.\\n - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al\"s AUTOCLASS II\\n conceptual clustering system finds 3 classes in the data.\\n - Many, many more ...',\n",
" 'data': array([[5.1, 3.5, 1.4, 0.2],\n",
" [4.9, 3. , 1.4, 0.2],\n",
" [4.7, 3.2, 1.3, 0.2],\n",
" [4.6, 3.1, 1.5, 0.2],\n",
" [5. , 3.6, 1.4, 0.2],\n",
" [5.4, 3.9, 1.7, 0.4],\n",
" [4.6, 3.4, 1.4, 0.3],\n",
" [5. , 3.4, 1.5, 0.2],\n",
" [4.4, 2.9, 1.4, 0.2],\n",
" [4.9, 3.1, 1.5, 0.1],\n",
" [5.4, 3.7, 1.5, 0.2],\n",
" [4.8, 3.4, 1.6, 0.2],\n",
" [4.8, 3. , 1.4, 0.1],\n",
" [4.3, 3. , 1.1, 0.1],\n",
" [5.8, 4. , 1.2, 0.2],\n",
" [5.7, 4.4, 1.5, 0.4],\n",
" [5.4, 3.9, 1.3, 0.4],\n",
" [5.1, 3.5, 1.4, 0.3],\n",
" [5.7, 3.8, 1.7, 0.3],\n",
" [5.1, 3.8, 1.5, 0.3],\n",
" [5.4, 3.4, 1.7, 0.2],\n",
" [5.1, 3.7, 1.5, 0.4],\n",
" [4.6, 3.6, 1. , 0.2],\n",
" [5.1, 3.3, 1.7, 0.5],\n",
" [4.8, 3.4, 1.9, 0.2],\n",
" [5. , 3. , 1.6, 0.2],\n",
" [5. , 3.4, 1.6, 0.4],\n",
" [5.2, 3.5, 1.5, 0.2],\n",
" [5.2, 3.4, 1.4, 0.2],\n",
" [4.7, 3.2, 1.6, 0.2],\n",
" [4.8, 3.1, 1.6, 0.2],\n",
" [5.4, 3.4, 1.5, 0.4],\n",
" [5.2, 4.1, 1.5, 0.1],\n",
" [5.5, 4.2, 1.4, 0.2],\n",
" [4.9, 3.1, 1.5, 0.2],\n",
" [5. , 3.2, 1.2, 0.2],\n",
" [5.5, 3.5, 1.3, 0.2],\n",
" [4.9, 3.6, 1.4, 0.1],\n",
" [4.4, 3. , 1.3, 0.2],\n",
" [5.1, 3.4, 1.5, 0.2],\n",
" [5. , 3.5, 1.3, 0.3],\n",
" [4.5, 2.3, 1.3, 0.3],\n",
" [4.4, 3.2, 1.3, 0.2],\n",
" [5. , 3.5, 1.6, 0.6],\n",
" [5.1, 3.8, 1.9, 0.4],\n",
" [4.8, 3. , 1.4, 0.3],\n",
" [5.1, 3.8, 1.6, 0.2],\n",
" [4.6, 3.2, 1.4, 0.2],\n",
" [5.3, 3.7, 1.5, 0.2],\n",
" [5. , 3.3, 1.4, 0.2],\n",
" [7. , 3.2, 4.7, 1.4],\n",
" [6.4, 3.2, 4.5, 1.5],\n",
" [6.9, 3.1, 4.9, 1.5],\n",
" [5.5, 2.3, 4. , 1.3],\n",
" [6.5, 2.8, 4.6, 1.5],\n",
" [5.7, 2.8, 4.5, 1.3],\n",
" [6.3, 3.3, 4.7, 1.6],\n",
" [4.9, 2.4, 3.3, 1. ],\n",
" [6.6, 2.9, 4.6, 1.3],\n",
" [5.2, 2.7, 3.9, 1.4],\n",
" [5. , 2. , 3.5, 1. ],\n",
" [5.9, 3. , 4.2, 1.5],\n",
" [6. , 2.2, 4. , 1. ],\n",
" [6.1, 2.9, 4.7, 1.4],\n",
" [5.6, 2.9, 3.6, 1.3],\n",
" [6.7, 3.1, 4.4, 1.4],\n",
" [5.6, 3. , 4.5, 1.5],\n",
" [5.8, 2.7, 4.1, 1. ],\n",
" [6.2, 2.2, 4.5, 1.5],\n",
" [5.6, 2.5, 3.9, 1.1],\n",
" [5.9, 3.2, 4.8, 1.8],\n",
" [6.1, 2.8, 4. , 1.3],\n",
" [6.3, 2.5, 4.9, 1.5],\n",
" [6.1, 2.8, 4.7, 1.2],\n",
" [6.4, 2.9, 4.3, 1.3],\n",
" [6.6, 3. , 4.4, 1.4],\n",
" [6.8, 2.8, 4.8, 1.4],\n",
" [6.7, 3. , 5. , 1.7],\n",
" [6. , 2.9, 4.5, 1.5],\n",
" [5.7, 2.6, 3.5, 1. ],\n",
" [5.5, 2.4, 3.8, 1.1],\n",
" [5.5, 2.4, 3.7, 1. ],\n",
" [5.8, 2.7, 3.9, 1.2],\n",
" [6. , 2.7, 5.1, 1.6],\n",
" [5.4, 3. , 4.5, 1.5],\n",
" [6. , 3.4, 4.5, 1.6],\n",
" [6.7, 3.1, 4.7, 1.5],\n",
" [6.3, 2.3, 4.4, 1.3],\n",
" [5.6, 3. , 4.1, 1.3],\n",
" [5.5, 2.5, 4. , 1.3],\n",
" [5.5, 2.6, 4.4, 1.2],\n",
" [6.1, 3. , 4.6, 1.4],\n",
" [5.8, 2.6, 4. , 1.2],\n",
" [5. , 2.3, 3.3, 1. ],\n",
" [5.6, 2.7, 4.2, 1.3],\n",
" [5.7, 3. , 4.2, 1.2],\n",
" [5.7, 2.9, 4.2, 1.3],\n",
" [6.2, 2.9, 4.3, 1.3],\n",
" [5.1, 2.5, 3. , 1.1],\n",
" [5.7, 2.8, 4.1, 1.3],\n",
" [6.3, 3.3, 6. , 2.5],\n",
" [5.8, 2.7, 5.1, 1.9],\n",
" [7.1, 3. , 5.9, 2.1],\n",
" [6.3, 2.9, 5.6, 1.8],\n",
" [6.5, 3. , 5.8, 2.2],\n",
" [7.6, 3. , 6.6, 2.1],\n",
" [4.9, 2.5, 4.5, 1.7],\n",
" [7.3, 2.9, 6.3, 1.8],\n",
" [6.7, 2.5, 5.8, 1.8],\n",
" [7.2, 3.6, 6.1, 2.5],\n",
" [6.5, 3.2, 5.1, 2. ],\n",
" [6.4, 2.7, 5.3, 1.9],\n",
" [6.8, 3. , 5.5, 2.1],\n",
" [5.7, 2.5, 5. , 2. ],\n",
" [5.8, 2.8, 5.1, 2.4],\n",
" [6.4, 3.2, 5.3, 2.3],\n",
" [6.5, 3. , 5.5, 1.8],\n",
" [7.7, 3.8, 6.7, 2.2],\n",
" [7.7, 2.6, 6.9, 2.3],\n",
" [6. , 2.2, 5. , 1.5],\n",
" [6.9, 3.2, 5.7, 2.3],\n",
" [5.6, 2.8, 4.9, 2. ],\n",
" [7.7, 2.8, 6.7, 2. ],\n",
" [6.3, 2.7, 4.9, 1.8],\n",
" [6.7, 3.3, 5.7, 2.1],\n",
" [7.2, 3.2, 6. , 1.8],\n",
" [6.2, 2.8, 4.8, 1.8],\n",
" [6.1, 3. , 4.9, 1.8],\n",
" [6.4, 2.8, 5.6, 2.1],\n",
" [7.2, 3. , 5.8, 1.6],\n",
" [7.4, 2.8, 6.1, 1.9],\n",
" [7.9, 3.8, 6.4, 2. ],\n",
" [6.4, 2.8, 5.6, 2.2],\n",
" [6.3, 2.8, 5.1, 1.5],\n",
" [6.1, 2.6, 5.6, 1.4],\n",
" [7.7, 3. , 6.1, 2.3],\n",
" [6.3, 3.4, 5.6, 2.4],\n",
" [6.4, 3.1, 5.5, 1.8],\n",
" [6. , 3. , 4.8, 1.8],\n",
" [6.9, 3.1, 5.4, 2.1],\n",
" [6.7, 3.1, 5.6, 2.4],\n",
" [6.9, 3.1, 5.1, 2.3],\n",
" [5.8, 2.7, 5.1, 1.9],\n",
" [6.8, 3.2, 5.9, 2.3],\n",
" [6.7, 3.3, 5.7, 2.5],\n",
" [6.7, 3. , 5.2, 2.3],\n",
" [6.3, 2.5, 5. , 1.9],\n",
" [6.5, 3. , 5.2, 2. ],\n",
" [6.2, 3.4, 5.4, 2.3],\n",
" [5.9, 3. , 5.1, 1.8]]),\n",
" 'data_module': 'sklearn.datasets.data',\n",
" 'feature_names': ['sepal length (cm)',\n",
" 'sepal width (cm)',\n",
" 'petal length (cm)',\n",
" 'petal width (cm)'],\n",
" 'filename': 'iris.csv',\n",
" 'frame': None,\n",
" 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
" 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10')}"
]
},
"metadata": {},
"execution_count": 37
}
]
},
{
"cell_type": "code",
"source": [
"print(iris.target_names)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "zP4BsEBXZHTT",
"outputId": "62e057d0-93ba-43b5-bd02-7af944bad00f"
},
"execution_count": 38,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"['setosa' 'versicolor' 'virginica']\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(iris.feature_names)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JfL2rTuRZNQ0",
"outputId": "b35342a5-f7ec-4cb7-edce-083ba82f2793"
},
"execution_count": 39,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(iris.target)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "63npw0bQZpN5",
"outputId": "44e79621-8ce3-4211-ec2c-e1f6b3084a1d"
},
"execution_count": 40,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
" 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
" 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2\n",
" 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n",
" 2 2]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(iris.data)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2CUazMX4ZsIq",
"outputId": "66aad4e5-f0e2-4ebe-90cd-af9f5d516984"
},
"execution_count": 41,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[5.1 3.5 1.4 0.2]\n",
" [4.9 3. 1.4 0.2]\n",
" [4.7 3.2 1.3 0.2]\n",
" [4.6 3.1 1.5 0.2]\n",
" [5. 3.6 1.4 0.2]\n",
" [5.4 3.9 1.7 0.4]\n",
" [4.6 3.4 1.4 0.3]\n",
" [5. 3.4 1.5 0.2]\n",
" [4.4 2.9 1.4 0.2]\n",
" [4.9 3.1 1.5 0.1]\n",
" [5.4 3.7 1.5 0.2]\n",
" [4.8 3.4 1.6 0.2]\n",
" [4.8 3. 1.4 0.1]\n",
" [4.3 3. 1.1 0.1]\n",
" [5.8 4. 1.2 0.2]\n",
" [5.7 4.4 1.5 0.4]\n",
" [5.4 3.9 1.3 0.4]\n",
" [5.1 3.5 1.4 0.3]\n",
" [5.7 3.8 1.7 0.3]\n",
" [5.1 3.8 1.5 0.3]\n",
" [5.4 3.4 1.7 0.2]\n",
" [5.1 3.7 1.5 0.4]\n",
" [4.6 3.6 1. 0.2]\n",
" [5.1 3.3 1.7 0.5]\n",
" [4.8 3.4 1.9 0.2]\n",
" [5. 3. 1.6 0.2]\n",
" [5. 3.4 1.6 0.4]\n",
" [5.2 3.5 1.5 0.2]\n",
" [5.2 3.4 1.4 0.2]\n",
" [4.7 3.2 1.6 0.2]\n",
" [4.8 3.1 1.6 0.2]\n",
" [5.4 3.4 1.5 0.4]\n",
" [5.2 4.1 1.5 0.1]\n",
" [5.5 4.2 1.4 0.2]\n",
" [4.9 3.1 1.5 0.2]\n",
" [5. 3.2 1.2 0.2]\n",
" [5.5 3.5 1.3 0.2]\n",
" [4.9 3.6 1.4 0.1]\n",
" [4.4 3. 1.3 0.2]\n",
" [5.1 3.4 1.5 0.2]\n",
" [5. 3.5 1.3 0.3]\n",
" [4.5 2.3 1.3 0.3]\n",
" [4.4 3.2 1.3 0.2]\n",
" [5. 3.5 1.6 0.6]\n",
" [5.1 3.8 1.9 0.4]\n",
" [4.8 3. 1.4 0.3]\n",
" [5.1 3.8 1.6 0.2]\n",
" [4.6 3.2 1.4 0.2]\n",
" [5.3 3.7 1.5 0.2]\n",
" [5. 3.3 1.4 0.2]\n",
" [7. 3.2 4.7 1.4]\n",
" [6.4 3.2 4.5 1.5]\n",
" [6.9 3.1 4.9 1.5]\n",
" [5.5 2.3 4. 1.3]\n",
" [6.5 2.8 4.6 1.5]\n",
" [5.7 2.8 4.5 1.3]\n",
" [6.3 3.3 4.7 1.6]\n",
" [4.9 2.4 3.3 1. ]\n",
" [6.6 2.9 4.6 1.3]\n",
" [5.2 2.7 3.9 1.4]\n",
" [5. 2. 3.5 1. ]\n",
" [5.9 3. 4.2 1.5]\n",
" [6. 2.2 4. 1. ]\n",
" [6.1 2.9 4.7 1.4]\n",
" [5.6 2.9 3.6 1.3]\n",
" [6.7 3.1 4.4 1.4]\n",
" [5.6 3. 4.5 1.5]\n",
" [5.8 2.7 4.1 1. ]\n",
" [6.2 2.2 4.5 1.5]\n",
" [5.6 2.5 3.9 1.1]\n",
" [5.9 3.2 4.8 1.8]\n",
" [6.1 2.8 4. 1.3]\n",
" [6.3 2.5 4.9 1.5]\n",
" [6.1 2.8 4.7 1.2]\n",
" [6.4 2.9 4.3 1.3]\n",
" [6.6 3. 4.4 1.4]\n",
" [6.8 2.8 4.8 1.4]\n",
" [6.7 3. 5. 1.7]\n",
" [6. 2.9 4.5 1.5]\n",
" [5.7 2.6 3.5 1. ]\n",
" [5.5 2.4 3.8 1.1]\n",
" [5.5 2.4 3.7 1. ]\n",
" [5.8 2.7 3.9 1.2]\n",
" [6. 2.7 5.1 1.6]\n",
" [5.4 3. 4.5 1.5]\n",
" [6. 3.4 4.5 1.6]\n",
" [6.7 3.1 4.7 1.5]\n",
" [6.3 2.3 4.4 1.3]\n",
" [5.6 3. 4.1 1.3]\n",
" [5.5 2.5 4. 1.3]\n",
" [5.5 2.6 4.4 1.2]\n",
" [6.1 3. 4.6 1.4]\n",
" [5.8 2.6 4. 1.2]\n",
" [5. 2.3 3.3 1. ]\n",
" [5.6 2.7 4.2 1.3]\n",
" [5.7 3. 4.2 1.2]\n",
" [5.7 2.9 4.2 1.3]\n",
" [6.2 2.9 4.3 1.3]\n",
" [5.1 2.5 3. 1.1]\n",
" [5.7 2.8 4.1 1.3]\n",
" [6.3 3.3 6. 2.5]\n",
" [5.8 2.7 5.1 1.9]\n",
" [7.1 3. 5.9 2.1]\n",
" [6.3 2.9 5.6 1.8]\n",
" [6.5 3. 5.8 2.2]\n",
" [7.6 3. 6.6 2.1]\n",
" [4.9 2.5 4.5 1.7]\n",
" [7.3 2.9 6.3 1.8]\n",
" [6.7 2.5 5.8 1.8]\n",
" [7.2 3.6 6.1 2.5]\n",
" [6.5 3.2 5.1 2. ]\n",
" [6.4 2.7 5.3 1.9]\n",
" [6.8 3. 5.5 2.1]\n",
" [5.7 2.5 5. 2. ]\n",
" [5.8 2.8 5.1 2.4]\n",
" [6.4 3.2 5.3 2.3]\n",
" [6.5 3. 5.5 1.8]\n",
" [7.7 3.8 6.7 2.2]\n",
" [7.7 2.6 6.9 2.3]\n",
" [6. 2.2 5. 1.5]\n",
" [6.9 3.2 5.7 2.3]\n",
" [5.6 2.8 4.9 2. ]\n",
" [7.7 2.8 6.7 2. ]\n",
" [6.3 2.7 4.9 1.8]\n",
" [6.7 3.3 5.7 2.1]\n",
" [7.2 3.2 6. 1.8]\n",
" [6.2 2.8 4.8 1.8]\n",
" [6.1 3. 4.9 1.8]\n",
" [6.4 2.8 5.6 2.1]\n",
" [7.2 3. 5.8 1.6]\n",
" [7.4 2.8 6.1 1.9]\n",
" [7.9 3.8 6.4 2. ]\n",
" [6.4 2.8 5.6 2.2]\n",
" [6.3 2.8 5.1 1.5]\n",
" [6.1 2.6 5.6 1.4]\n",
" [7.7 3. 6.1 2.3]\n",
" [6.3 3.4 5.6 2.4]\n",
" [6.4 3.1 5.5 1.8]\n",
" [6. 3. 4.8 1.8]\n",
" [6.9 3.1 5.4 2.1]\n",
" [6.7 3.1 5.6 2.4]\n",
" [6.9 3.1 5.1 2.3]\n",
" [5.8 2.7 5.1 1.9]\n",
" [6.8 3.2 5.9 2.3]\n",
" [6.7 3.3 5.7 2.5]\n",
" [6.7 3. 5.2 2.3]\n",
" [6.3 2.5 5. 1.9]\n",
" [6.5 3. 5.2 2. ]\n",
" [6.2 3.4 5.4 2.3]\n",
" [5.9 3. 5.1 1.8]]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"X = iris.data"
],
"metadata": {
"id": "zi6Sg7MjZ8dz"
},
"execution_count": 42,
"outputs": []
},
{
"cell_type": "code",
"source": [
"Y = iris.target"
],
"metadata": {
"id": "XRTRGU87Z_dK"
},
"execution_count": 43,
"outputs": []
},
{
"cell_type": "code",
"source": [
"print(X.shape)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "brdbqMkAaDAJ",
"outputId": "8b494ede-86cc-449d-d323-6cb95efac599"
},
"execution_count": 44,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"(150, 4)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(Y.shape)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "s86Cy2sjaPJo",
"outputId": "d6189ff0-b587-48cf-b347-0dcacdfe164f"
},
"execution_count": 45,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"(150,)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"clf = RandomForestClassifier()\n",
"clf.fit(X,Y)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "G4XQ2FY6aRCB",
"outputId": "7a0bd69d-cfff-4dbe-f82d-82bd9237c39a"
},
"execution_count": 46,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"RandomForestClassifier()"
]
},
"metadata": {},
"execution_count": 46
}
]
},
{
"cell_type": "code",
"source": [
"print(clf.feature_importances_)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GJvuFwaVa0Ay",
"outputId": "e711533c-1f4d-44ad-ee56-0fab4803526d"
},
"execution_count": 47,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[0.12814193 0.02990922 0.41155218 0.43039667]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"X[0]"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "eiE2wsSYbaYP",
"outputId": "6e593c92-fc58-4e99-c8cf-c724ec827ce8"
},
"execution_count": 48,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([5.1, 3.5, 1.4, 0.2])"
]
},
"metadata": {},
"execution_count": 48
}
]
},
{
"cell_type": "code",
"source": [
"print(clf.predict(X[[0]]))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mgBtGrGfbkpL",
"outputId": "ef1eea05-f7c3-413a-a4eb-75dfd7c63832"
},
"execution_count": 49,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[0]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(clf.predict_proba(X[[0]]))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mbqOOOMccIht",
"outputId": "167903ef-277b-4c7d-ab41-38c944630e5e"
},
"execution_count": 50,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[1. 0. 0.]]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
""
],
"metadata": {
"id": "gQLIjWcdcQgF"
},
"execution_count": 50,
"outputs": []
},
{
"cell_type": "code",
"source": [
"X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=.2)"
],
"metadata": {
"id": "0PDDfwdcccqJ"
},
"execution_count": 51,
"outputs": []
},
{
"cell_type": "code",
"source": [
"X_train.shape, Y_train.shape\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "HHTCcKLQctz4",
"outputId": "a4258edd-5296-47f8-c756-6a4478e886a9"
},
"execution_count": 52,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"((120, 4), (120,))"
]
},
"metadata": {},
"execution_count": 52
}
]
},
{
"cell_type": "code",
"source": [
"X_test.shape, Y_test.shape"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "k--iuDn5dGgZ",
"outputId": "4c2b2d12-8263-4ea8-9f3e-040410434335"
},
"execution_count": 53,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"((30, 4), (30,))"
]
},
"metadata": {},
"execution_count": 53
}
]
},
{
"cell_type": "code",
"source": [
"clf.fit(X_train,Y_train)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Zc4kzcZqdarK",
"outputId": "75d8ff27-6637-4c12-f570-fb775c2de57d"
},
"execution_count": 54,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"RandomForestClassifier()"
]
},
"metadata": {},
"execution_count": 54
}
]
},
{
"cell_type": "code",
"source": [
"clf.predict(X_test )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "WAiy1Q_2df64",
"outputId": "790b1dd0-27b9-4f4a-ca8d-431a3076a4c8"
},
"execution_count": 55,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([0, 0, 2, 1, 2, 0, 2, 1, 1, 2, 2, 1, 1, 2, 0, 0, 2, 2, 2, 1, 2, 0,\n",
" 2, 2, 0, 0, 0, 2, 0, 0])"
]
},
"metadata": {},
"execution_count": 55
}
]
},
{
"cell_type": "code",
"source": [
"print( Y_test)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Sb-h0xkydzlP",
"outputId": "19c2161c-1fed-4935-c104-f0f7002afec0"
},
"execution_count": 56,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[0 0 2 1 2 0 1 1 2 2 2 1 1 2 0 0 2 2 2 1 2 0 2 2 0 0 0 2 0 0]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(clf.score(X_test, Y_test))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "aUOMtSDHd-Na",
"outputId": "c4bbb7b0-109b-4979-e673-d9455ae5e4b4"
},
"execution_count": 59,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"0.0\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py:217: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n",
" score = y_true == y_pred\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"clf.fit(iris.data, iris.target_names[iris.target])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JElFOLvseYB9",
"outputId": "31d55853-3241-4dc2-fb68-ae3efb613e8e"
},
"execution_count": 58,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"RandomForestClassifier()"
]
},
"metadata": {},
"execution_count": 58
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment