In [ ]: import pandas as pd

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

In [4]: df = pd.read_excel('data.xlsx')

In [ ]: # Exploratory Data Ananlysis (EDA) Part

In [5]: df.head()

Out[5]: age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal target

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

In [7]: 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

In [8]: df.isnull().sum()
Out[8]: 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

In [11]: variables = pd.read_excel('variable description.xlsx')

variables

Out[11]: variable description

0 age age in years

1 sex (1 = male; 0 = female)

2 cp chest pain type

3 trestbps resting blood pressure (in mm Hg on admission...

4 chol serum cholestoral in mg/dl

5 fbs (fasting blood sugar > 120 mg/dl) (1 = true; ...

6 restecg resting electrocardiographic results

7 thalach maximum heart rate achieved

8 exang exercise induced angina (1 = yes; 0 = no)

9 oldpeak ST depression induced by exercise relative to...

10 slope the slope of the peak exercise ST segment

11 ca number of major vessels (0-3) colored by flou...

12 thal 3 = normal; 6 = fixed defect; 7 = reversable ...

13 target 1 or 0

In [24]: plt.figure(figsize=(12,8))
df["age"].value_counts().plot(kind="bar")
plt.title('Age Distribution')
plt.show()
In [30]: plt.figure(figsize=(12,8))
sns.countplot(x = df['age'], hue = 'target', data=df)
plt.show()

In [32]: plt.figure(figsize=(12,8))
sns.histplot(x = df['age'], hue = 'target', data=df)
plt.show()
 In [33]: plt.figure(figsize=(12,8))
sns.countplot(x = df['sex'], hue = 'target', data=df)
plt.show()

#creating subplots

In [43]: df.nunique()
Out[43]: age 41
sex 2
cp 4
trestbps 49
chol 152
fbs 2
restecg 3
thalach 91
exang 2
oldpeak 40
slope 3
ca 5
thal 4
target 2
dtype: int64

In [44]: fig,axes=plt.subplots(nrows=3, ncols=3, figsize=(12,10))

cat_features=['sex', 'cp', 'fbs', 'restecg','exang', 'slope', 'ca', 'thal',
'target'] for idx,feature in enumerate (cat_features):
if feature!='target':
sns.countplot(x=feature,hue='target',data=df)

In [48]: fig,axes=plt.subplots(nrows=3, ncols=3, figsize=(12,10))

cat_features=['sex', 'cp', 'fbs', 'restecg','exang', 'slope', 'ca', 'thal',
'target'] for idx,feature in enumerate (cat_features):
if feature!='target':
ax=axes[int(idx/3),idx%3]
sns.countplot(x=feature,hue='target',ax=ax,data=df)
#print(idx/3, idx%3)
In [41]: df.columns

Out[41]: Index(['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach',

'exang', 'oldpeak', 'slope', 'ca', 'thal', 'target'],
dtype='object')

create pie chart - having heart diseases

In [67]: #create pie chart - having heart diseases
plt.figure(figsize=(12,8))
labels = 'normal','fixed defect','reversable defect'
sizes=[6,130,28]
explode=[0,0.1,0]
colors=['pink','orange','purple']
plt.pie(sizes,labels=labels,autopct='%.1f%%',colors=colors, startangle = 140,explode=explode)
plt.axis('equal')
plt.title('Thalassemia with Heart Diseases')
plt.show()

#create pie chart - having no heart diseases

plt.figure(figsize=(12,8))
labels = 'normal','fixed defect','reversable defect'
sizes=[12,36,89]
explode=[0,0,0.2]
colors=['pink','orange','purple']
plt.pie(sizes,labels=labels,autopct='%.1f%%',colors=colors,explode=explode)
plt.axis('equal')
plt.title('Thalassemia with No Heart Diseases')
plt.show()
In [69]: num_var=['age','trestbps','chol','thalach','oldpeak']
sns.pairplot(df[num_var+['target']], hue='target')
plt.show()
In [71]: #create a plot to understand relationship between age & chol, according to
target sns.lmplot(x='age', y='chol',hue='sex', col='target', data = df)
plt.show()

In [74]: plt.figure(figsize=(12,8))
sns.heatmap(df.corr(), annot=True)
Out[74]: <AxesSubplot: >

In [78]: plt.figure(figsize=(12,8))
plt.subplot(1,3,1)
sns.boxplot(y=df['age'])
plt.title('Age', fontsize=15)

plt.subplot(1,3,2)
sns.boxplot(y=df['trestbps'])
plt.title('Resting blood pressure', fontsize=15)

plt.subplot(1,3,3)
sns.boxplot(y=df['chol'])
plt.title('Cholestrol level', fontsize=15)

plt.show()