Answers for "kmeans python"

scikit learn k means

from sklearn.cluster import KMeans
df = np.array([[1,4],[2,2],[2,5],[3,3],[3,4],[4,7],[5,6],[6,4],[6,7],[7,6],[7,9],[8,7],[8,9],[9,4],[9,8]])
kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=300, n_init=10)
y_pred = kmeans.fit_predict(df)

k-means clustering python

from sklearn.cluster import KMeans
kmeans = KMeans(init="random", n_clusters=3, n_init=10, max_iter=300, random_state=42 )
kmeans.fit(x_train) #Replace your training dataset instead of x_train
# The lowest SSE value
print(kmeans.inertia_)
# Final locations of the centroid
print(kmeans.cluster_centers_)
# The number of iterations required to converge
print(kmeans.n_iter_)
# first five predicted labels 
print(kmeans.labels_[:5])


# init controls the initialization technique. The standard version of the k-means algorithm is implemented by setting init to "random". Setting this to "k-means++" employs an advanced trick to speed up convergence, which you’ll use later.

# n_clusters sets k for the clustering step. This is the most important parameter for k-means.

# n_init sets the number of initializations to perform. This is important because two runs can converge on different cluster assignments. The default behavior for the scikit-learn algorithm is to perform ten k-means runs and return the results of the one with the lowest SSE.

# max_iter sets the number of maximum iterations for each initialization of the k-means algorithm.

grafica de clustering en 3d python

import plotly.plotly as py
import pandas as pd

df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/alpha_shape.csv')
df.head()

scatter = dict(
    mode = "markers",
    name = "y",
    type = "scatter3d",
    x = df['x'], y = df['y'], z = df['z'],
    marker = dict( size=2, color="rgb(23, 190, 207)" )
)
clusters = dict(
    alphahull = 7,
    name = "y",
    opacity = 0.1,
    type = "mesh3d",
    x = df['x'], y = df['y'], z = df['z']
)
layout = dict(
    title = '3d point clustering',
    scene = dict(
        xaxis = dict( zeroline=False ),
        yaxis = dict( zeroline=False ),
        zaxis = dict( zeroline=False ),
    )
)
fig = dict( data=[scatter, clusters], layout=layout )
# Use py.iplot() for IPython notebook
py.iplot(fig, filename='3d point clustering')

kmeans python

# Function: K Means
# -------------
# K-Means is an algorithm that takes in a dataset and a constant
# k and returns k centroids (which define clusters of data in the
# dataset which are similar to one another).
def kmeans(dataSet, k):
	
    # Initialize centroids randomly
    numFeatures = dataSet.getNumFeatures()
    centroids = getRandomCentroids(numFeatures, k)
    
    # Initialize book keeping vars.
    iterations = 0
    oldCentroids = None
    
    # Run the main k-means algorithm
    while not shouldStop(oldCentroids, centroids, iterations):
        # Save old centroids for convergence test. Book keeping.
        oldCentroids = centroids
        iterations += 1
        
        # Assign labels to each datapoint based on centroids
        labels = getLabels(dataSet, centroids)
        
        # Assign centroids based on datapoint labels
        centroids = getCentroids(dataSet, labels, k)
        
    # We can get the labels too by calling getLabels(dataSet, centroids)
    return centroids