Machine Learning Introduction
Supervised Machine Learning
Unsupervised Machine Learning
Miscellaneous Topics in ML
Data Pre-Processing
Heart Disease Prediction in Machine Learning
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
sns.set_style("whitegrid")
#Create the dataframe
df=pd.read_csv("E:\dataset\heart.csv")
df.head()
Output:
# to display the no of rows and columns in the dataset
df.shape
Output:
(303, 14)
df.info()
< class 'pandas.core.frame.DataFrame'>
RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 age 303 non-null int64
1 sex 303 non-null int64
2 cp 303 non-null int64
3 trestbps 303 non-null int64
4 chol 303 non-null int64
5 fbs 303 non-null int64
6 restecg 303 non-null int64
7 thalach 303 non-null int64
8 exang 303 non-null int64
9 oldpeak 303 non-null float64
10 slope 303 non-null int64
11 ca 303 non-null int64
12 thal 303 non-null int64
13 target 303 non-null int64
dtypes: float64(1), int64(13)
memory usage: 33.3 KB
df.isna().sum()
Output:
age 0
sex 0
cp 0
trestbps 0
chol 0
fbs 0
restecg 0
thalach 0
exang 0
oldpeak 0
slope 0
ca 0
thal 0
target 0
dtype: int64
df.target.unique()
Output:
array([1, 0], dtype=int64)
df.target.value_counts()
Output:
1 165
0 138
Name: target, dtype: int64
df.target.value_counts().plot(kind="bar", color=["red", "green"])
plt.show()
#Choose X and y
X = df.drop('target', axis=1)
y = df.target
#X=df.iloc[:,:-1]
#y=df.iloc[:,13]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X,y,test_size=0.3,random_state=0)
print(X_train.shape)
Output:
(212, 13)
print(X_test)
#Create LogisticRegression model
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X_train, y_train)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\_logistic.p
y:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html (https://scik
it-learn.org/stable/modules/preprocessing.html)
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regre
ssion (https://scikit-learn.org/stable/modules/linear_model.html#logistic-re
gression)
n_iter_i = _check_optimize_result(
Output:
LogisticRegression()
y_pred=model.predict(X_train)
y_pred
array([1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1,
0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1,
0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0,
0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0,
1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1,
0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0,
0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0,
0, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0,
1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0,
1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1], dtype=int64)
y_predicted=model.predict(X_test)
y_predicted
array([0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,
0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0,
0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1,
1, 0, 0], dtype=int64)
from sklearn.metrics import accuracy_score
test_score = accuracy_score(y_test, y_predicted)
train_score = accuracy_score(y_train, y_pred)
print(test_score)
print(train_score)
0.8351648351648352
0.8632075471698113
result_df = pd.DataFrame(data=[["Logistic Regression", train_score, test_score]],
columns=['Model', 'Training Accuracy %', 'Testing Accuracy %'])
result_df
Output:
#Create SVM model,
from sklearn.svm import SVC
obj=SVC()
#Trained SVM model
obj.fit(X_train,y_train)
Output:
SVC()
y_pred=obj.predict(X_train)
y_pred
Output:
array([1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1,
1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1,
0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0,
1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,
1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,
1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0,
0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0,
1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1], dtype=int64)
y_prediction=obj.predict(X_test)
y_prediction
Output:
array([0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1,
0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0,
0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1,
1, 0, 1], dtype=int64)
from sklearn.metrics import accuracy_score
train_accuracy=accuracy_score(y_train,y_pred)
test_accuracy=accuracy_score(y_test,y_prediction)
print(train_accuracy)
print(test_accuracy)
0.6650943396226415
0.6703296703296703
results_df_1 = pd.DataFrame(data=[["Support Vector Machine", train_accuracy, test_accuracy]
columns=['Model', 'Training Accuracy %', 'Testing Accuracy %'])
results_df_2 = result_df.append(results_df_1, ignore_index=True)
results_df_2
Output:
#Create DecisionTree Model
from sklearn.tree import DecisionTreeClassifier
obj1=DecisionTreeClassifier()
#Trained the model
obj1.fit(X_train,y_train)
Output:
DecisionTreeClassifier()
y_pred_train=obj1.predict(X_train)
y_pred_train
Output:
array([1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0,
0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1,
0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0,
0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0,
0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1,
0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0,
0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0,
0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0,
1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0,
1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0], dtype=int64)
y_pred_test=obj1.predict(X_test)
y_pred_test
Output:
array([0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,
0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0,
1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,
1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1,
0, 1, 0], dtype=int64)
from sklearn.metrics import accuracy_score
train_accuracy_tree=accuracy_score(y_train,y_pred_train)
test_accuracy_tree=accuracy_score(y_test,y_pred_test)
print(train_accuracy_tree)
print(test_accuracy_tree)
1.0
0.7582417582417582
results_df_3 = pd.DataFrame(data=[["DecisionTree", train_accuracy_tree, test_accuracy_tree]
columns=['Model', 'Training Accuracy %', 'Testing Accuracy %'])
results_df_4 = results_df_2.append(results_df_3, ignore_index=True)
results_df_4
Output:
#Create RandomForest Model
from sklearn.ensemble import RandomForestClassifier
obj2=RandomForestClassifier(n_estimators=1000, random_state=42)
obj2.fit(X_train,y_train)
Output:
RandomForestClassifier(n_estimators=1000, random_state=42)
y_pred_forest_train=obj2.predict(X_train)
y_pred_forest_train
Output:
array([1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0,
0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1,
0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0,
0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0,
0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1,
0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0,
0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0,
0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0,
1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0,
1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0], dtype=int64)
y_pred_forest_test=obj2.predict(X_test)
y_pred_forest_test
array([0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0,
0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0,
0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1,
1, 1, 0], dtype=int64)
from sklearn.metrics import accuracy_score
train_accuracy_forest=accuracy_score(y_train,y_pred_forest_train)
test_accuracy_forest=accuracy_score(y_test,y_pred_forest_test)
print(train_accuracy_forest)
print(test_accuracy_forest)
1.0
0.8351648351648352
results_df_5 = pd.DataFrame(data=[["RandomForest", train_accuracy_forest, test_accuracy_for
columns=['Model', 'Training Accuracy %', 'Testing Accuracy %'])
results_df_6 = results_df_4.append(results_df_5, ignore_index=True)
results_df_6
Output:
About the Author
Silan Software is one of the India's leading provider of offline & online training for Java, Python, AI (Machine Learning, Deep Learning), Data Science, Software Development & many more emerging Technologies.
We provide Academic Training || Industrial Training || Corporate Training || Internship || Java || Python || AI using Python || Data Science etc
PreviousNext
Join our newsletter for the latest updates.
About us
Our Services
Contact Us
Our Courses
Learn Python | Learn AI | Learn Machine Learning | Learn Deep Learning | Learn Core Java | Learn Java JSP | Learn Java Servlet | Learn Java Spring | Learn Spring Boot | Learn Power BI | Learn DAA | Learn HTML | Learn SQL | Learn C Programming | Learn Bootstrap | Learn Git | Learn JavaScript | Learn Data Structure Using C | Learn RDBMS | Learn Data Science | Learn PHP
Our Tutorials
Python Tutorial | AI Tutorial | Machine Learning Tutorial | Deep Learning Tutorial | Core Java Tutorial | Java JSP Tutorial | Java Servlet Tutorial | Java Spring Tutorial | Spring Boot Tutorial | Power BI Tutorial | DAA Tutorial | HTML Tutorial | SQL Tutorial | C Programming Tutorial | Bootstrap Tutorial | Git Tutorial | JavaScript Tutorial | Data Structure Using C Tutorial | RDBMS Tutorial | Data Science Tutorial | PHP Tutorial
Copyright © 2023 Pythontpoints Powered by Silan Software Pvt. Ltd. All rights reserved.