# Import libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns # from sklearn.cluster import KMeans from sklearn.datasets import make_blobs

# # Create a data set in 2 dimensions using make_blobs # # The function make_blobs stores the data in x and the cluster each point belongs to in y # (x,y)= make_blobs ( n_samples =200, n_features=2,centers=5,cluster_std=0.5, shuffle=True,random_state=0 ) plt.scatter( x[:,0],x[:,1], c='white', edgecolor='black',marker='o', s=50) plt.show()

# Calculate centroids of blobs; remember that the array y contains cluster number n = len(y) n_blobs=5 n_points_blob = 40. blob_mean = np.zeros( ( n_blobs,2) ) # # Loop to sum up x and y coordinates of each point in blob for i in range (0,n): blob=y[i] # given blob index (0,1,2,3,4) blob_mean [blob,0] = blob_mean [blob,0] + x[i,0] blob_mean [blob,1] = blob_mean [blob,1] + x[i,1] # Loop to divide by number of points in blob and print out for k in range (0,n_blobs) : blob_mean [k,:] = blob_mean [k,:] / n_points_blob print (f"Blob {k+1} has centroid: ( { blob_mean [k,0] }, { blob_mean [k,1] } ) " )

# Create KMeans model and fit data in array x which is in the correct shape: 200 by 2 km = KMeans (n_clusters = 3, init = 'random', random_state = 0) km.fit(x)

# Plot clusters using colors and compare visually with blob plot above plt.scatter( x[:,0],x[:,1],c=km.labels_,cmap='rainbow' ) plt.scatter( km.cluster_centers_[:,0],km.cluster_centers_[:,1], marker='*',c='black',label='centroids' ) plt.legend(scatterpoints=1) plt.grid() plt.show() plt.scatter( x[:,0],x[:,1], c='white', edgecolor='black',marker='o', s=50) plt.show()

# Print out final clusters centroids and print out actual centroids to compare # print (" KMeans Centroids ", " Original Centroids ") print (f"Blob {k+1} has centroid: ( { blob_mean [k,0] }, { blob_mean [k,1] } ) " ) # Note that Kmeans cluster 3 corresponds to our cluster 5 and vice versa

# 1 iteration centroids = np.array( [ [-3,-2], [-2,12], [3,8], [12,0], [2,12] ]) print () print ("******************************************") print ("Results for 1st iteration of KMeans") km = KMeans (n_clusters =5, init =centroids, max_iter =1) km.fit(x) print( "Centroids are ", km.cluster_centers_ ) plt.scatter( x[:,0],x[:,1],c=km.labels_,cmap='rainbow' ) plt.title("KMeans results for 1 iteration") plt.grid() plt.show()

# 2 iterations centroids = np.array( [ [-3,-2], [-2,12], [3,8], [12,0], [2,12] ]) print () print ("******************************************") print ("Results for 2nd iteration of KMeans") km = KMeans (n_clusters =5, init =centroids, max_iter =1) km.fit(x) print( "Centroids are ", km.cluster_centers_ ) plt.scatter( x[:,0],x[:,1],c=km.labels_,cmap='rainbow' ) plt.title("KMeans results for 1 iteration") plt.grid() plt.show()

# Import libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns # Import models from sklearn.cluster import KMeans

# Create dataframe from file insurance.csv filename = 'insurance.csv' df = pd.read_csv ('insurance.csv') df.head (3)

#Create a new dataframe which only has the two features (age and bmi)and the charges # dfmod =df.drop ( columns = ['sex' , 'children', 'smoker', 'region'] )

# Determine how many data instances there are print (f' there are {len(dfmod)} data instances') # so 1338 data instances

# Find the maximum & minimum value of the charges charges = df.charges print (f' the minimum charge is {min(charges)}') print (f' the maximum charge is {max(charges)}')

# Print out the data instance where the max occurs df[df.charges == 63770.42801]

# Print out all data instances where charges are >60,000 df [df.charges > 60000]

# Print out all data instances where bmi > 35 and charges > 50,000 df [(df.bmi >35) & (df.charges >50000)]

# Delete all data instances where the charges are more than $60,000 df= df.drop ([543, 1230, 1300]) # Print out all data instances where charges are >60000 to check df [df.charges > 60000]

# Scale costs between $0 and $100; round costs to 2 decimal places (for cents) # print out the first few entries to check df [df.charges <= 100]

# Add column to dataframe with scaled charges and remove column with full charges print ('¯\_(ツ)_/¯')

# Create 2D array and use KMeans with 4 clusters print ('¯\_(ツ)_/¯ ' , ' ¯\_(ツ)_/¯') print ('¯\_(ツ)_/¯ ' , ' ¯\_(ツ)_/¯')

# Print out the labels # # add column to dataframe giving cluster labels print ('¯\_(ツ)_/¯')

# Set white background grid for Seaborn plots sns.set_style ( "whitegrid") print ('¯\_(ツ)_/¯')

# Create scatterplot of charges vs bmi with cluster indiciated by hue using Seaborn's relplot sns.relplot (x='charges', y= 'bmi', data=df, hue = 'charges')

# Create scatterplot of charges vs age with cluster indiciated by hue using Seaborn's relplot sns.relplot (x='charges', y= 'age', data=df, hue = 'charges')