Untitled

import pandas as pd # Pandas (version : 1.1.5) 
import numpy as np # Numpy (version : 1.19.2)
import matplotlib.pyplot as plt # Matplotlib (version :  3.3.2)
from sklearn.cluster import KMeans # Scikit Learn (version : 0.23.2)
import seaborn as sns # Seaborn (version : 0.11.1)
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
plt.style.use('seaborn')

data = pd.read_csv('Iris.csv')

for i,col in enumerate(data.columns):
    print(f'Column number {1+i} is {col}')

data.drop('Id', axis=1, inplace=True)
# data.head()

data['Species'].value_counts()

target_data = data.iloc[:,4]
# print(target_data.head)

clustering_data = data.iloc[:,[0,1,2,3]]
clustering_data.head()

wcss=[]
for i in range(1,11):
    km = KMeans(i)
    km.fit(clustering_data)
    wcss.append(km.inertia_)
np.array(wcss)

fig, ax = plt.subplots(figsize=(15,7))
ax = plt.plot(range(1,11),wcss, linewidth=2, color="red", marker ="8")
plt.axvline(x=3, ls='--')
plt.ylabel('WCSS')
plt.xlabel('No. of Clusters (k)')
plt.title('The Elbow Method', fontsize = 20)
plt.show()

kms = KMeans(n_clusters=3, init='k-means++')
kms.fit(clustering_data)

clusters = clustering_data.copy()
clusters['Cluster_Prediction'] = kms.fit_predict(clustering_data)
print(clusters.head()) 

silhouette_avg = silhouette_score(clustering_data, clusters['Cluster_Prediction'])
print(f"The average silhouette_score is : {silhouette_avg}")

fig, ax = plt.subplots(figsize=(15,7)) 
plt.scatter(x=clusters[clusters['Cluster_Prediction'] == 0]['SepalLengthCm'],
            y=clusters[clusters['Cluster_Prediction'] == 0]['SepalWidthCm'],
            s=70,edgecolor='teal', linewidth=0.3, c='teal', label='Iris-versicolor')
silhouette_avg = silhouette_score(clustering_data, clusters['Cluster_Prediction'])
print(f"The average silhouette_score is : {silhouette_avg}")

plt.scatter(x=clusters[clusters['Cluster_Prediction'] == 1]['SepalLengthCm'],
            y=clusters[clusters['Cluster_Prediction'] == 1]['SepalWidthCm'],
            s=70,edgecolor='lime', linewidth=0.3, c='lime', label='Iris-setosa')


plt.scatter(x=clusters[clusters['Cluster_Prediction'] == 2]['SepalLengthCm'],
            y=clusters[clusters['Cluster_Prediction'] == 2]['SepalWidthCm'],
            s=70,edgecolor='magenta', linewidth=0.3, c='magenta', label='Iris-virginica')

plt.scatter(x=kms.cluster_centers_[:, 0], y=kms.cluster_centers_[:, 1], s = 170, c = 'yellow', label = 'Centroids',edgecolor='black', linewidth=0.3)
plt.legend(loc='upper right')
plt.xlim(4,8)
plt.ylim(1.8,4.5)
ax.set_ylabel('Sepal Width (in cm)')
ax.set_xlabel('Sepal Length (in cm)')
plt.title('Clusters', fontsize = 20)
plt.show()