import numpy as np
import pandas as pd
from pgmpy.estimators import MaximumLikelihoodEstimator
from pgmpy.models import BayesianModel
from pgmpy.inference import VariableElimination



heartDisease = pd.read_csv('heart.csv')
heartDisease = heartDisease.replace('?', np.nan)



print('Sample instances from the dataset are given below:')
print(heartDisease.head())



print('\nAttributes and datatypes:')
print(heartDisease.dtypes)



model = BayesianModel([
    ('age', 'heartdisease'),
    ('sex', 'heartdisease'),
    ('exang', 'heartdisease'),
    ('cp', 'heartdisease'),
    ('heartdisease', 'restecg'),
    ('heartdisease', 'chol')
])



print('\nLearning CPD using Maximum Likelihood Estimators...')
model.fit(heartDisease, estimator=MaximumLikelihoodEstimator)



print('\nInferencing with Bayesian Network:')
heartDisease_infer = VariableElimination(model)



print('\n1. Probability of HeartDisease given evidence= restecg: 1')
q1 = heartDisease_infer.query(variables=['heartdisease'], evidence={'restecg': 1})
print(q1)



print('\n2. Probability of HeartDisease given evidence= cp: 2')
q2 = heartDisease_infer.query(variables=['heartdisease'], evidence={'cp': 2})
print(q2)




















import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.cluster import KMeans
from sklearn.mixture import GaussianMixture
import sklearn.metrics as sm
import pandas as pd
import numpy as np
from sklearn import preprocessing




iris = datasets.load_iris()
X = pd.DataFrame(iris.data, columns=['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width'])
y = pd.DataFrame(iris.target, columns=['Targets'])




model = KMeans(n_clusters=3, random_state=42)
model.fit(X)




plt.figure(figsize=(14, 7))
colormap = np.array(['red', 'lime', 'black'])



plt.subplot(1, 2, 1)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[y.Targets], s=40)
plt.title('Real Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')




plt.subplot(1, 2, 2)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[model.labels_], s=40)
plt.title('K-Means Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')




print('The accuracy score of K-Means (Adjusted Rand Index):', sm.adjusted_rand_score(y.Targets, model.labels_))
print('The Confusion matrix of K-Means:\n', sm.confusion_matrix(y.Targets, model.labels_))




scaler = preprocessing.StandardScaler()
scaler.fit(X)
xsa = scaler.transform(X)
xs = pd.DataFrame(xsa, columns=X.columns)




gmm = GaussianMixture(n_components=3, random_state=42)
gmm.fit(xs)
y_gmm = gmm.predict(xs)


plt.figure(figsize=(14, 7))

plt.subplot(1, 2, 1)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[y.Targets], s=40)
plt.title('Real Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')

plt.subplot(1, 2, 2)
plt.scatter(X.Petal_Length, X.Petal_Width, c=colormap[y_gmm], s=40)
plt.title('GMM Classification')
plt.xlabel('Petal Length')
plt.ylabel('Petal Width')




print('The accuracy score of GMM (Adjusted Rand Index):', sm.adjusted_rand_score(y.Targets, y_gmm))
print('The Confusion matrix of GMM:\n', sm.confusion_matrix(y.Targets, y_gmm))

plt.show()