Skip to content

Instantly share code, notes, and snippets.

@audhiaprilliant

audhiaprilliant/genetic_algorithm_kmeans.ipynb

Created December 11, 2021 17:27
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save audhiaprilliant/d547376ad866ffe01b436f777b74e474 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save audhiaprilliant/d547376ad866ffe01b436f777b74e474 to your computer and use it in GitHub Desktop.
Download ZIP
Genetic Algorithm for clustering analysis Using kmeans
Display the source blob
Display the rendered blob
Raw
genetic_algorithm_kmeans.ipynb
{
"cells": [
{
"cell_type": "markdown",
"id": "suburban-replacement",
"metadata": {},
"source": [
"# Genetic Algorithm based on Clustering Analysis"
]
},
{
"cell_type": "markdown",
"id": "adult-hormone",
"metadata": {},
"source": [
"---"
]
},
{
"cell_type": "markdown",
"id": "funky-birmingham",
"metadata": {},
"source": [
"## Import packages"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "operational-characteristic",
"metadata": {},
"outputs": [],
"source": [
"# Data manipulation\n",
"import pandas as pd\n",
"\n",
"# Matrix calculation\n",
"import numpy as np\n",
"\n",
"# Euclidian distance\n",
"from scipy.spatial.distance import cdist\n",
"\n",
"# Genetic algorithm\n",
"import pygad\n",
"\n",
"# Iris data set\n",
"from sklearn import datasets\n",
"\n",
"# kmeans clustering\n",
"from sklearn.cluster import KMeans"
]
},
{
"cell_type": "markdown",
"id": "altered-impact",
"metadata": {},
"source": [
"## Import data"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "political-processing",
"metadata": {},
"outputs": [],
"source": [
"# Iris data set\n",
"df = datasets.load_iris()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "falling-cradle",
"metadata": {},
"outputs": [],
"source": [
"# Features and target\n",
"x, y = df['data'], df['target']"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cognitive-valve",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"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]])"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Preview the data\n",
"x"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "fleet-dietary",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Minimum value: 0.1\n",
"Maximum value: 7.9\n"
]
}
],
"source": [
"# Minimum and maximum values\n",
"print('Minimum value: {}'.format(x.min()))\n",
"print('Maximum value: {}'.format(x.max()))"
]
},
{
"cell_type": "markdown",
"id": "polish-cherry",
"metadata": {},
"source": [
"## Create k-means clustering function"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "latest-excellence",
"metadata": {},
"outputs": [],
"source": [
"# Number of clusters\n",
"k = 3"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "mathematical-closure",
"metadata": {},
"outputs": [],
"source": [
"# Objective function\n",
"def kmeans(solution, solutionIndex):\n",
" # Global vars\n",
" global x, k\n",
" \n",
" # Centroids\n",
" centroids = np.array(solution).reshape(k, len(solution) // k)\n",
" # Finding the distance between centroids and all data points\n",
" distances = cdist(x, centroids, 'euclidean')\n",
" # Centroid with the minimum Distance\n",
" points = np.array([np.argmin(i) for i in distances])\n",
" \n",
" # Calculate the sum square error\n",
" error = []\n",
" for idx in np.unique(points):\n",
" temp_cent = x[points == idx]\n",
" distances = cdist(temp_cent, centroids[idx].reshape(1, -1), 'euclidean')\n",
" error.append(distances.sum())\n",
" # Return result\n",
" return np.sum(error)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "young-dream",
"metadata": {},
"outputs": [],
"source": [
"# Fitness function\n",
"def fitnessFunction(solution, solutionIndex):\n",
" outputExpected = kmeans(solution, solutionIndex)\n",
" fitnessValue = 1 / (outputExpected + 0.000001)\n",
" return fitnessValue"
]
},
{
"cell_type": "markdown",
"id": "endless-acrylic",
"metadata": {},
"source": [
"## Run the Genetic Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "necessary-tyler",
"metadata": {},
"outputs": [],
"source": [
"# Prepare the parameters\n",
"\n",
"# Generation\n",
"numberGeneration = 1000 # Number of generation\n",
"numberParentsMating = 5\n",
"solutionPerPopulation = 50 # Number of chromosomes in each generation\n",
"parents = -1\n",
"\n",
"# Genes\n",
"numberGenes = k * x.shape[1] # Number of genes in each chromosome\n",
"geneType = float # Data type in each gene\n",
"\n",
"# Range of values\n",
"minValue = 0 # Minimum value of solution\n",
"maxValue = 8 # Maximum value of solution\n",
"\n",
"# Selection\n",
"selectionType = 'sss' # Selection using steady state selection\n",
"\n",
"# Cross over\n",
"crossoverType = 'single_point' # Cross over using single point method\n",
"crossoverRate = 0.25 # Cross over rate (Pc)\n",
"\n",
"# Mutation rate\n",
"# Mutation\n",
"mutationType = 'random' # Mutation using random method\n",
"mutationReplacement = True # Replace gene with random value\n",
"mutationMin = 0\n",
"mutationMax = 8\n",
"mutationRate = 10 # Mutation rate (Pm)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "general-concentration",
"metadata": {},
"outputs": [],
"source": [
"# Set the parameters into Genetic Algorithm function\n",
"geneticAlgorithm = pygad.GA(\n",
" # Number of generation\n",
" num_generations = numberGeneration,\n",
" \n",
" # Number of parents mating\n",
" num_parents_mating = numberParentsMating,\n",
" \n",
" # Number of gene each chromosome\n",
" num_genes = numberGenes,\n",
" \n",
" # Gene type\n",
" gene_type = geneType,\n",
" \n",
" # Fitness function\n",
" fitness_func = fitnessFunction,\n",
" \n",
" # Number solution per population\n",
" sol_per_pop = solutionPerPopulation,\n",
" \n",
" # Min and max value\n",
" init_range_low = minValue,\n",
" init_range_high = maxValue,\n",
" \n",
" # Selection\n",
" parent_selection_type = selectionType,\n",
" keep_parents = parents,\n",
" \n",
" # Cross over\n",
" crossover_type = crossoverType,\n",
" #crossover_probability = crossoverRate,\n",
" \n",
" # Mutation\n",
" mutation_type = mutationType,\n",
" mutation_by_replacement = mutationReplacement,\n",
" random_mutation_min_val = mutationMin,\n",
" random_mutation_max_val = mutationMax,\n",
" mutation_percent_genes = mutationRate,\n",
" \n",
" # Solutions\n",
" save_solutions = True,\n",
" save_best_solutions = True,\n",
" suppress_warnings = True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "delayed-continent",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"# Run the Genetic Algorithm\n",
"geneticAlgorithm.run()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "oriented-reviewer",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Parameters of the best solution : \n",
"[[5.92514492 2.80725404 4.40248519 1.41205877]\n",
" [6.73889534 3.068677 5.61225383 2.11112409]\n",
" [5.01679467 3.414519 1.46429548 0.23415793]]\n",
"Fitness value of the best solution : 0.01\n",
"Index of the best solution : 0\n"
]
}
],
"source": [
"# Solution\n",
"solution, solutionFitness, solutionIndex = geneticAlgorithm.best_solution()\n",
"print('Parameters of the best solution : \\n{solution}'.format(solution = solution.reshape(k, len(solution) // k)))\n",
"print('Fitness value of the best solution : {solutionFitness}'.format(solutionFitness = round(solutionFitness, ndigits = 2)))\n",
"print('Index of the best solution : {solutionIndex}'.format(solutionIndex = solutionIndex))"
]
},
{
"cell_type": "markdown",
"id": "bigger-inside",
"metadata": {},
"source": [
"## Cluster accuracy"
]
},
{
"cell_type": "markdown",
"id": "sixth-liberty",
"metadata": {},
"source": [
"### Real labels"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "early-habitat",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[5.006, 3.428, 1.462, 0.246],\n",
" [5.936, 2.77 , 4.26 , 1.326],\n",
" [6.588, 2.974, 5.552, 2.026]])"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Array of data set\n",
"array = np.column_stack([x, y])\n",
"\n",
"# Data frame\n",
"df = pd.DataFrame(data = array,\n",
" columns = [\n",
" 'Feature 1',\n",
" 'Feature 2',\n",
" 'Feature 3',\n",
" 'Feature 4',\n",
" 'Cluster'\n",
" ]\n",
")\n",
"\n",
"# Centroids in data frame\n",
"df_centroids = df.groupby(['Cluster']).mean().reset_index().rename(columns = {\n",
" 'Feature 1': 'Centroid Feature 1',\n",
" 'Feature 2': 'Centroid Feature 2',\n",
" 'Feature 3': 'Centroid Feature 3',\n",
" 'Feature 4': 'Centroid Feature 4'\n",
" }\n",
").astype({'Cluster': object})\n",
"\n",
"# Centroids in array\n",
"del df_centroids['Cluster']\n",
"np.array(df_centroids)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "damaged-benefit",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"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])"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Real cluster labels\n",
"y"
]
},
{
"cell_type": "markdown",
"id": "systematic-groove",
"metadata": {},
"source": [
"### Genetic Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "located-eclipse",
"metadata": {},
"outputs": [],
"source": [
"# Final centroids\n",
"centroids = solution.reshape(k, len(solution) // k)\n",
"# Finding the distance between centroids and all data points\n",
"distances = cdist(x, centroids, 'euclidean')\n",
"# Centroid with the minimum Distance\n",
"points = np.array([np.argmin(i) for i in distances])"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "norman-hampshire",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[5.92514492, 2.80725404, 4.40248519, 1.41205877],\n",
" [6.73889534, 3.068677 , 5.61225383, 2.11112409],\n",
" [5.01679467, 3.414519 , 1.46429548, 0.23415793]])"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Centroids in array\n",
"solution.reshape(k, len(solution) // k)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "regulated-connection",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([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, 2, 2, 2, 2,\n",
" 2, 2, 2, 2, 2, 2, 0, 0, 1, 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, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n",
" 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1,\n",
" 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0], dtype=int64)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Cluster labels\n",
"points"
]
},
{
"cell_type": "markdown",
"id": "adverse-intensity",
"metadata": {},
"source": [
"### Sklearn kmeans++"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "mechanical-greene",
"metadata": {},
"outputs": [],
"source": [
"kmeansPlus = KMeans(\n",
" n_clusters = 3\n",
" )\n",
"kmeansPlus.fit(x)\n",
"centroid = kmeansPlus.cluster_centers_"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "crazy-configuration",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array([[5.9016129 , 2.7483871 , 4.39354839, 1.43387097],\n",
" [5.006 , 3.428 , 1.462 , 0.246 ],\n",
" [6.85 , 3.07368421, 5.74210526, 2.07105263]])"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Centroids in array\n",
"centroid"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "major-trustee",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([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,\n",
" 1, 1, 1, 1, 1, 1, 0, 0, 2, 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, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 2, 2, 2, 0, 2, 2, 2,\n",
" 2, 2, 2, 0, 0, 2, 2, 2, 2, 0, 2, 0, 2, 0, 2, 2, 0, 0, 2, 2, 2, 2,\n",
" 2, 0, 2, 2, 2, 2, 0, 2, 2, 2, 0, 2, 2, 2, 0, 2, 2, 0])"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Cluster labels\n",
"kmeansPlus.labels_"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment