-
Notifications
You must be signed in to change notification settings - Fork 0
/
heart_disease_prediction.py
77 lines (58 loc) · 2.38 KB
/
heart_disease_prediction.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
#!/bin/python3
# -*- Author: real0x0a1 (Ali) -*-
# -*- File: heart_disease_prediction.py -*-
# import libraries
import numpy as np
import pandas as pd
# import scikit-learn libraries for model selection, logistic regression, and metrics
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
# loading the csv data to a Pandas DataFrame
heart_data = pd.read_csv('./content/data.csv')
# check the distribution of the Target Variable (heart disease presence)
heart_data['target'].value_counts()
# separate the features (X) from the target variable (Y)
X = heart_data.drop(columns='target', axis=1)
Y = heart_data['target']
# split the data into training and testing sets (80% for training, 20% for testing)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, stratify=Y, random_state=2)
# create a Logistic Regression model
model = LogisticRegression()
# train the Logistic Regression model with the training data
model.fit(X_train, Y_train)
# evaluate the model's accuracy on the training data
X_train_prediction = model.predict(X_train)
training_data_accuracy = accuracy_score(X_train_prediction, Y_train)
print('Accuracy on Training data : ', training_data_accuracy)
# evaluate the model's accuracy on the testing data
X_test_prediction = model.predict(X_test)
test_data_accuracy = accuracy_score(X_test_prediction, Y_test)
print('Accuracy on Test data : ', test_data_accuracy)
# input data for prediction (replace with your own values)
input_data = (63, # age
1, # sex
3, # cp
140, # trestbps
268, # chol
0, # fbs
0, # restecg
160, # thalach
0, # exang
3.6, # oldpeak
0, # slope
2, # ca
2 # thal
)
# convert the input data to a numpy array
input_data_as_numpy_array= np.asarray(input_data)
# reshape the numpy array as we are predicting for only one instance
input_data_reshaped = input_data_as_numpy_array.reshape(1,-1)
# make a prediction using the trained model
prediction = model.predict(input_data_reshaped)
print(prediction)
# interpret the prediction result
if (prediction[0]== 0):
print('The Person does not have a Heart Disease')
else:
print('The Person has Heart Disease')