7. AI AND MACHINE LEARNING VTU LAB | READ NOW
MACHINE LEARNING VTU LAB – Bayesian Network-heart disease
Program 7. WRITE A PROGRAM TO CONSTRUCT AN ABAYESIAN NETWORK CONSIDERING MEDICAL DATA. USE THIS MODEL TO DEMONSTRATE THE DIAGNOSIS OF HEART PATIENTS USING STANDARD HEART DISEASE DATA SET. YOU CAN USE JAVA/PYTHON ML LIBRARY CLASSES/API.
Program Code – lab7.py
import pandas as pd
data=pd.read_csv("heartdisease.csv")
heart_disease=pd.DataFrame(data)
print(heart_disease)
from pgmpy.models import BayesianModel
model=BayesianModel([
('age','Lifestyle'),
('Gender','Lifestyle'),
('Family','heartdisease'),
('diet','cholestrol'),
('Lifestyle','diet'),
('cholestrol','heartdisease'),
('diet','cholestrol')
])
from pgmpy.estimators import MaximumLikelihoodEstimator
model.fit(heart_disease, estimator=MaximumLikelihoodEstimator)
from pgmpy.inference import VariableElimination
HeartDisease_infer = VariableElimination(model)
print('For age Enter { SuperSeniorCitizen:0, SeniorCitizen:1, MiddleAged:2, Youth:3, Teen:4 }')
print('For Gender Enter { Male:0, Female:1 }')
print('For Family History Enter { yes:1, No:0 }')
print('For diet Enter { High:0, Medium:1 }')
print('For lifeStyle Enter { Athlete:0, Active:1, Moderate:2, Sedentary:3 }')
print('For cholesterol Enter { High:0, BorderLine:1, Normal:2 }')
q = HeartDisease_infer.query(variables=['heartdisease'], evidence={
'age':int(input('Enter age :')),
'Gender':int(input('Enter Gender :')),
'Family':int(input('Enter Family history :')),
'diet':int(input('Enter diet :')),
'Lifestyle':int(input('Enter Lifestyle :')),
'cholestrol':int(input('Enter cholestrol :'))
})
print(q['heartdisease'])
MACHINE LEARNING Program Execution – lab7.ipynb
Jupyter Notebook program execution.
import pandas as pd
data=pd.read_csv("heartdisease.csv")
heart_disease=pd.DataFrame(data)
print(heart_disease)
age Gender Family diet Lifestyle cholestrol heartdisease 0 0 0 1 1 3 0 1 1 0 1 1 1 3 0 1 2 1 0 0 0 2 1 1 3 4 0 1 1 3 2 0 4 3 1 1 0 0 2 0 5 2 0 1 1 1 0 1 6 4 0 1 0 2 0 1 7 0 0 1 1 3 0 1 8 3 1 1 0 0 2 0 9 1 1 0 0 0 2 1 10 4 1 0 1 2 0 1 11 4 0 1 1 3 2 0 12 2 1 0 0 0 0 0 13 2 0 1 1 1 0 1 14 3 1 1 0 0 1 0 15 0 0 1 0 0 2 1 16 1 1 0 1 2 1 1 17 3 1 1 1 0 1 0 18 4 0 1 1 3 2 0
from pgmpy.models import BayesianModel
model=BayesianModel([
('age','Lifestyle'),
('Gender','Lifestyle'),
('Family','heartdisease'),
('diet','cholestrol'),
('Lifestyle','diet'),
('cholestrol','heartdisease'),
('diet','cholestrol')
])
from pgmpy.estimators import MaximumLikelihoodEstimator
model.fit(heart_disease, estimator=MaximumLikelihoodEstimator)
from pgmpy.inference import VariableElimination
HeartDisease_infer = VariableElimination(model)
print('For age Enter { SuperSeniorCitizen:0, SeniorCitizen:1, MiddleAged:2, Youth:3, Teen:4 }')
print('For Gender Enter { Male:0, Female:1 }')
print('For Family History Enter { yes:1, No:0 }')
print('For diet Enter { High:0, Medium:1 }')
print('For lifeStyle Enter { Athlete:0, Active:1, Moderate:2, Sedentary:3 }')
print('For cholesterol Enter { High:0, BorderLine:1, Normal:2 }')
q = HeartDisease_infer.query(variables=['heartdisease'], evidence={
'age':int(input('Enter age :')),
'Gender':int(input('Enter Gender :')),
'Family':int(input('Enter Family history :')),
'diet':int(input('Enter diet :')),
'Lifestyle':int(input('Enter Lifestyle :')),
'cholestrol':int(input('Enter cholestrol :'))
})
print(q['heartdisease'])
For age Enter { SuperSeniorCitizen:0, SeniorCitizen:1, MiddleAged:2, Youth:3, Teen:4 }
For Gender Enter { Male:0, Female:1 }
For Family History Enter { yes:1, No:0 }
For diet Enter { High:0, Medium:1 }
For lifeStyle Enter { Athlete:0, Active:1, Moderate:2, Sedentary:3 }
For cholesterol Enter { High:0, BorderLine:1, Normal:2 }
Enter age :1
Enter Gender :1
Enter Family history :0
Enter diet :1
Enter Lifestyle :0
Enter cholestrol :1
+----------------+---------------------+
| heartdisease | phi(heartdisease) |
+================+=====================+
| heartdisease_0 | 0.0000 |
+----------------+---------------------+
| heartdisease_1 | 1.0000 |
+----------------+---------------------+
Alternative – alt lab7.ipynb
import bayespy as bp import numpy as np import csv from colorama import init from colorama import Fore, Back, Style init()
# Define Parameter Enum values
#Age
ageEnum = {'SuperSeniorCitizen':0, 'SeniorCitizen':1, 'MiddleAged':2, 'Youth':3, 'Teen':4}
# Gender
genderEnum = {'Male':0, 'Female':1}
# FamilyHistory
familyHistoryEnum = {'Yes':0, 'No':1}
# Diet(Calorie Intake)
dietEnum = {'High':0, 'Medium':1, 'Low':2}
# LifeStyle
lifeStyleEnum = {'Athlete':0, 'Active':1, 'Moderate':2, 'Sedetary':3}
# Cholesterol
cholesterolEnum = {'High':0, 'BorderLine':1, 'Normal':2}
# HeartDisease
heartDiseaseEnum = {'Yes':0, 'No':1}
#heart_disease_data.csv
with open('heart_disease_data.csv') as csvfile:
lines = csv.reader(csvfile)
dataset = list(lines)
data = []
for x in dataset:
data.append([ageEnum[x[0]],genderEnum[x[1]],familyHistoryEnum[x[2]],dietEnum[x[3]],lifeStyleEnum[x[4]],cholesterolEnum[x[5]],heartDiseaseEnum[x[6]]])
# Training data for machine learning todo: should import from csv
data = np.array(data)
N = len(data)
# Input data column assignment p_age = bp.nodes.Dirichlet(1.0*np.ones(5)) age = bp.nodes.Categorical(p_age, plates=(N,)) age.observe(data[:,0]) p_gender = bp.nodes.Dirichlet(1.0*np.ones(2)) gender = bp.nodes.Categorical(p_gender, plates=(N,)) gender.observe(data[:,1]) p_familyhistory = bp.nodes.Dirichlet(1.0*np.ones(2)) familyhistory = bp.nodes.Categorical(p_familyhistory, plates=(N,)) familyhistory.observe(data[:,2]) p_diet = bp.nodes.Dirichlet(1.0*np.ones(3)) diet = bp.nodes.Categorical(p_diet, plates=(N,)) diet.observe(data[:,3]) p_lifestyle = bp.nodes.Dirichlet(1.0*np.ones(4)) lifestyle = bp.nodes.Categorical(p_lifestyle, plates=(N,)) lifestyle.observe(data[:,4]) p_cholesterol = bp.nodes.Dirichlet(1.0*np.ones(3)) cholesterol = bp.nodes.Categorical(p_cholesterol, plates=(N,)) cholesterol.observe(data[:,5])
# Prepare nodes and establish edges
# np.ones(2) -> HeartDisease has 2 options Yes/No
# plates(5, 2, 2, 3, 4, 3) -> corresponds to options present for domain values
p_heartdisease = bp.nodes.Dirichlet(np.ones(2), plates=(5, 2, 2, 3, 4, 3))
heartdisease = bp.nodes.MultiMixture([age, gender, familyhistory, diet, lifestyle, cholesterol], bp.nodes.Categorical, p_heartdisease)
heartdisease.observe(data[:,6])
p_heartdisease.update()
# Sample Test with hardcoded values
#print("Sample Probability")
#print("Probability(HeartDisease|Age=SuperSeniorCitizen, Gender=Female, FamilyHistory=Yes, DietIntake=Medium, LifeStyle=Sedetary, Cholesterol=High)")
#print(bp.nodes.MultiMixture([ageEnum['SuperSeniorCitizen'], genderEnum['Female'], familyHistoryEnum['Yes'], dietEnum['Medium'], lifeStyleEnum['Sedetary'], cholesterolEnum['High']], bp.nodes.Categorical, p_heartdisease).get_moments()[0][heartDiseaseEnum['Yes']])
# Interactive Test
m = 0
while m == 0:
print("\n")
res = bp.nodes.MultiMixture([int(input('Enter Age: ' + str(ageEnum))), int(input('Enter Gender: ' + str(genderEnum))), int(input('Enter FamilyHistory: ' + str(familyHistoryEnum))), int(input('Enter dietEnum: ' + str(dietEnum))), int(input('Enter LifeStyle: ' + str(lifeStyleEnum))), int(input('Enter Cholesterol: ' + str(cholesterolEnum)))], bp.nodes.Categorical, p_heartdisease).get_moments()[0][heartDiseaseEnum['Yes']]
print("Probability(HeartDisease) = " + str(res))
#print(Style.RESET_ALL)
m = int(input("Enter for Continue:0, Exit :1 "))
Enter Age: {'SuperSeniorCitizen': 0, 'SeniorCitizen': 1, 'MiddleAged': 2, 'Youth': 3, 'Teen': 4}1
Enter Gender: {'Male': 0, 'Female': 1}0
Enter FamilyHistory: {'Yes': 0, 'No': 1}0
Enter dietEnum: {'High': 0, 'Medium': 1, 'Low': 2}2
Enter LifeStyle: {'Athlete': 0, 'Active': 1, 'Moderate': 2, 'Sedetary': 3}2
Enter Cholesterol: {'High': 0, 'BorderLine': 1, 'Normal': 2}1
C:\Anaconda3\lib\site-packages\bayespy\inference\vmp\nodes\categorical.py:43: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
u0[[np.arange(np.size(x)), np.ravel(x)]] = 1
Probability(HeartDisease) = 0.5
Enter for Continue:0, Exit :1 1
Download Dataset
