8

Apply K- Means clustering algorithm on any dataset.
import pandas as pd import numpy as np from sklearn.datasets import load_iris from sklearn.metrics import accuracy_score iris_data load_iris()

iris_data.feature_names

df= pd.DataFrame(iris_data.data,columns iris_data.feature_names) df['Species']=iris_data.target

df.head(10)

np.unique (df['Species'])

df.shape

df.info()
ax=df [df.Species==0].plot.scatter(x='sepal length (cm)',

y='sepal width (cm)",

color='red', label='Iris-Setosa')

df[df.Species==1].plot.scatter(x='sepal length (cm)',
y='sepal width (cm)',

color='green',

label='Iris-Versicolor', ax=ax)

df [df.Species==2].plot.scatter(x='sepal length (cm)',

y='sepal width (cm)',

color='blue',

label='Iris-Virginica', ax=ax)
ax.set_title("Scatter Plot")
import seaborn as sns

correl df.corr() sns.heatmap(correl, annot=True)

from sklearn.model_selection import train_test_split

X=iris_data.data

y=iris data.target
X_train, X_test, y_train, y_test train_test_split(X,y, 
random_state = 50,test_size=0.2

from sklearn.cluster import KMeans

kmean=KMeans (n_clusters=3)

kmean.fit(X_train,y_train)

train_labels=kmean.predict(X_train)

test_labels=kmean.predict(X_test)

print(accuracy_score(y_train, train_labels))

print(accuracy_score(y_test, test_labels))