Challenge

predict whether the patient has heart disease or not?

KKeerthidhar Reddy3 Aug 2022

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

In [278]:

df=pd.read_csv('heart.csv')

In [279]:

df

Out[279]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3	0
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3	0
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3	0
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3	0
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2	0

303 rows × 14 columns

In [280]:

df.isna().sum()

Out[280]:

age         0
sex         0
cp          0
trtbps      0
chol        0
fbs         0
restecg     0
thalachh    0
exng        0
oldpeak     0
slp         0
caa         0
thall       0
output      0
dtype: int64

In [281]:

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   trtbps    303 non-null    int64  
 4   chol      303 non-null    int64  
 5   fbs       303 non-null    int64  
 6   restecg   303 non-null    int64  
 7   thalachh  303 non-null    int64  
 8   exng      303 non-null    int64  
 9   oldpeak   303 non-null    float64
 10  slp       303 non-null    int64  
 11  caa       303 non-null    int64  
 12  thall     303 non-null    int64  
 13  output    303 non-null    int64  
dtypes: float64(1), int64(13)
memory usage: 33.3 KB

In [282]:

df.describe()

Out[282]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
count	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000
mean	54.366337	0.683168	0.966997	131.623762	246.264026	0.148515	0.528053	149.646865	0.326733	1.039604	1.399340	0.729373	2.313531	0.544554
std	9.082101	0.466011	1.032052	17.538143	51.830751	0.356198	0.525860	22.905161	0.469794	1.161075	0.616226	1.022606	0.612277	0.498835
min	29.000000	0.000000	0.000000	94.000000	126.000000	0.000000	0.000000	71.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	47.500000	0.000000	0.000000	120.000000	211.000000	0.000000	0.000000	133.500000	0.000000	0.000000	1.000000	0.000000	2.000000	0.000000
50%	55.000000	1.000000	1.000000	130.000000	240.000000	0.000000	1.000000	153.000000	0.000000	0.800000	1.000000	0.000000	2.000000	1.000000
75%	61.000000	1.000000	2.000000	140.000000	274.500000	0.000000	1.000000	166.000000	1.000000	1.600000	2.000000	1.000000	3.000000	1.000000
max	77.000000	1.000000	3.000000	200.000000	564.000000	1.000000	2.000000	202.000000	1.000000	6.200000	2.000000	4.000000	3.000000	1.000000

In [283]:

df.head(10)

Out[283]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	2	1
5	57	1	0	140	192	0	1	148	0	0.4	1	1	1
6	56	0	1	140	294	0	0	153	0	1.3	1	2	1
7	44	1	1	120	263	0	1	173	0	0.0	2	3	1
8	52	1	2	172	199	1	1	162	0	0.5	2	3	1
9	57	1	2	150	168	0	1	174	0	1.6	2	2	1

In [284]:

corrMatrix = df.corr()
plt.figure(figsize=(20,10))
sns.heatmap(corrMatrix, annot=True)
plt.show()

In [285]:

df['output'].value_counts().plot(kind='bar')
plt.title('Count of Disease,not Disease ')
plt.xticks([0,1],['Disease','Not Disease'],rotation=0)
plt.show()

In [286]:

x=pd.crosstab(df.output,df.sex)
x

Out[286]:

sex	0	1
output
0	24	114
1	72	93

In [287]:

x.plot(kind='bar')
plt.title('Heart Disease frequency for sex')
plt.xticks([0,1],['No heart disease','heart disease'],rotation=0)
plt.ylabel('Count')
plt.legend(['Female','Male'])
plt.show()

In [288]:

pd.crosstab(df.output,df.cp)

Out[288]:

cp	0	1	2	3
output
0	104	9	18	7
1	39	41	69	16

In [289]:

pd.crosstab(df.output,df.cp).plot.bar(figsize=(10,6))
plt.title('Heart Disease frequency per Chest pain types')
plt.xticks([0,1],['No heart disease','heart disease'],rotation=0)
plt.ylabel('Count');
plt.xticks(rotation=0);

In [290]:

pd.crosstab(df.output,df.slp)

Out[290]:

slp	0	1	2
output
0	12	91	35
1	9	49	107

In [291]:

pd.crosstab(df.output,df.slp).plot(kind='bar')
plt.title('Heart Disease frequency per slp')
plt.xticks([0,1],['No heart disease','heart disease'],rotation=0)
plt.show()

In [292]:

pd.crosstab(df.output,df.exng)

Out[292]:

exng	0	1
output
0	62	76
1	142	23

In [293]:

pd.crosstab(df.output,df.exng).plot(kind='bar')
plt.title('Heart Disease frequency per exng')
plt.xticks([0,1],['No heart disease','heart disease'],rotation=0)
plt.show()

In [294]:

X = df.drop('output',axis=1)
y = df[['output']]

In [295]:

Out[295]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

303 rows × 13 columns

In [296]:

Out[296]:

	output
0	1
1	1
2	1
3	1
4	1
...	...
298	0
299	0
300	0
301	0
302	0

303 rows × 1 columns

In [297]:

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=3)

In [298]:

from sklearn.linear_model import LogisticRegression

In [299]:

log=LogisticRegression(max_iter=1000)
log.fit(x_train,y_train)

C:Userskeertanaconda3libsite-packagessklearnutilsvalidation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

Out[299]:

LogisticRegression(max_iter=1000)

In [300]:

p1=log.predict(x_test)

In [301]:

from sklearn.metrics import confusion_matrix
def con_mat(x,y):
    confusion_matrix(x,y)
    sns.heatmap(confusion_matrix(x,y),annot=True,cbar=False)
    plt.xlabel('True label')
    plt.ylabel('Predicted label')

In [302]:

con_mat(y_test,p1)

In [303]:

from sklearn.metrics import accuracy_score
a1=accuracy_score(y_test,p1)
print('Accuracy Score of LogisticRegression is:',a1)

Accuracy Score of LogisticRegression is: 0.8681318681318682

In [304]:

from sklearn.neighbors import KNeighborsClassifier
KNN=KNeighborsClassifier(n_neighbors=4)

In [305]:

KNN.fit(x_train,y_train)

C:Userskeertanaconda3libsite-packagessklearnneighbors_classification.py:198: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  return self._fit(X, y)

Out[305]:

KNeighborsClassifier(n_neighbors=4)

In [306]:

p2=KNN.predict(x_test)

In [307]:

con_mat(y_test,p2)

In [308]:

a2=accuracy_score(y_test,p2)
print('Accuracy Score of K-Nearest Neighbours Classifier is:',a2)

Accuracy Score of K-Nearest Neighbours Classifier is: 0.6263736263736264

In [309]:

from sklearn.svm import SVC

In [310]:

svm=SVC()

In [311]:

svm.fit(x_train,y_train)

C:Userskeertanaconda3libsite-packagessklearnutilsvalidation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

Out[311]:

SVC()

In [312]:

p3=svm.predict(x_test)

In [313]:

con_mat(y_test,p3)

In [314]:

a3=accuracy_score(y_test,p3)
print('Accuracy Score of Support Vector machine Classifier is:',a3)

Accuracy Score of Support Vector machine Classifier is: 0.7032967032967034

In [315]:

from sklearn.tree import DecisionTreeClassifier
clf = DecisionTreeClassifier(random_state=0)

In [316]:

clf.fit(x_train,y_train)

Out[316]:

DecisionTreeClassifier(random_state=0)

In [317]:

p4=clf.predict(x_test)

In [318]:

con_mat(y_test,p4)

In [319]:

a4=accuracy_score(y_test,p4)
print('Accuracy Score of Decision Tree Classifier is:',a4)

Accuracy Score of Decision Tree Classifier is: 0.7472527472527473

In [320]:

from sklearn.ensemble import RandomForestClassifier
rf= RandomForestClassifier(n_estimators = 100, random_state = 0)

In [321]:

rf.fit(x_train,y_train)

C:UserskeertAppDataLocalTempipykernel_327201149647727.py:1: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  rf.fit(x_train,y_train)

Out[321]:

RandomForestClassifier(random_state=0)

In [322]:

p5=rf.predict(x_test)

In [323]:

con_mat(y_test,p5)

In [324]:

a5=accuracy_score(y_test,p5)
print('Accuracy Score of Random Forest Classifier is:',a5)

Accuracy Score of Random Forest Classifier is: 0.8241758241758241

In [325]:

print('Accuracy Score of LogisticRegression is:',a1)
print('Accuracy Score of K-Nearest Neighbours Classifier is:',a2)
print('Accuracy Score of Support Vector machine Classifier is:',a3)
print('Accuracy Score of Decision Tree Classifier is:',a4)
print('Accuracy Score of Random Forest Classifier is:',a5)

Accuracy Score of LogisticRegression is: 0.8681318681318682
Accuracy Score of K-Nearest Neighbours Classifier is: 0.6263736263736264
Accuracy Score of Support Vector machine Classifier is: 0.7032967032967034
Accuracy Score of Decision Tree Classifier is: 0.7472527472527473
Accuracy Score of Random Forest Classifier is: 0.8241758241758241

In [ ]:

predict whether the patient has heart disease or not?

Ship work like this
in your own course.

Talk to a career counsellor

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3	0
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3	0
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3	0
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3	0
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2	0

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	2	1
5	57	1	0	140	192	0	1	148	0	0.4	1	1	1
6	56	0	1	140	294	0	0	153	0	1.3	1	2	1
7	44	1	1	120	263	0	1	173	0	0.0	2	3	1
8	52	1	2	172	199	1	1	162	0	0.5	2	3	1
9	57	1	2	150	168	0	1	174	0	1.6	2	2	1

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3	0
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3	0
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3	0
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3	0
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2	0

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	2	1
5	57	1	0	140	192	0	1	148	0	0.4	1	1	1
6	56	0	1	140	294	0	0	153	0	1.3	1	2	1
7	44	1	1	120	263	0	1	173	0	0.0	2	3	1
8	52	1	2	172	199	1	1	162	0	0.5	2	3	1
9	57	1	2	150	168	0	1	174	0	1.6	2	2	1

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

Ship work like thisin your own course.

Talk to a career counsellor

Ship work like this
in your own course.

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3	0
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3	0
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3	0
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3	0
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2	0

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	thall	output
0	63	1	3	145	233	1	0	150	0	2.3	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	2	1
5	57	1	0	140	192	0	1	148	0	0.4	1	1	1
6	56	0	1	140	294	0	0	153	0	1.3	1	2	1
7	44	1	1	120	263	0	1	173	0	0.0	2	3	1
8	52	1	2	172	199	1	1	162	0	0.5	2	3	1
9	57	1	2	150	168	0	1	174	0	1.6	2	2	1

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2