4/14/24, 10:12 AM B_4_Heart

In [1]: import pandas as pd

In [2]: df = pd.read_csv('heart.csv')

Note: Here in Dataset "trtbps" assume it as RestBP

In [3]: df
# 303 rows × 14 columns

Out[3]: 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 [4]: df = df.drop_duplicates()

In [5]: df

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 1/9

4/14/24, 10:12 AM B_4_Heart

Out[5]: 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

302 rows × 14 columns

Duplicates removed
In [6]: df.isna().sum()
# No null values, it's clean

age 0
Out[6]:
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

Plots
In [7]: import seaborn as sns
import matplotlib.pyplot as plt

In [8]: df.columns

Index(['age', 'sex', 'cp', 'trtbps', 'chol', 'fbs', 'restecg', 'thalachh',

Out[8]:
'exng', 'oldpeak', 'slp', 'caa', 'thall', 'output'],
dtype='object')

In [9]: plt.figure(figsize=(10,6))
sns.heatmap(df.corr(),cmap = 'YlGnBu', annot = True)

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 2/9

4/14/24, 10:12 AM B_4_Heart
<Axes: >
Out[9]:

Line chart
In [10]: sns.lineplot(data=df,x=df.age,y=df.cp,hue='output')

<Axes: xlabel='age', ylabel='cp'>

Out[10]:

In [11]: sns.lineplot(data=df,x=df.age,y=df.trtbps,hue='output')

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 3/9

4/14/24, 10:12 AM B_4_Heart
<Axes: xlabel='age', ylabel='trtbps'>
Out[11]:

In [12]: sns.lineplot(data=df,x=df.age,y=df.chol,hue='output')

<Axes: xlabel='age', ylabel='chol'>

Out[12]:

In [13]: sns.lineplot(df,x=df.oldpeak,y=df.exng,hue='output')

<Axes: xlabel='oldpeak', ylabel='exng'>

Out[13]:

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 4/9

4/14/24, 10:12 AM B_4_Heart

In [14]: # Shows the Distribution of Heat Diseases with respect to male and female
sns.histplot(data=df,
x=df.output,
hue=df.sex)

<Axes: xlabel='output', ylabel='Count'>

Out[14]:

In [15]: # Shows the Distribution of cp types with respect to male and female
sns.histplot(data=df,

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 5/9

4/14/24, 10:12 AM B_4_Heart
x=df.cp,
hue=df.sex)

<Axes: xlabel='cp', ylabel='Count'>

Out[15]:

In [16]: sns.histplot(data=df,x=df.cp, hue='output')

<Axes: xlabel='cp', ylabel='Count'>

Out[16]:

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 6/9

4/14/24, 10:12 AM B_4_Heart

In [17]: # Shows the Distribution of age w.r.t output

sns.histplot(data=df,x=df['age'], hue='output')

<Axes: xlabel='age', ylabel='Count'>

Out[17]:

In [18]: sns.histplot(data=df,x=df.trtbps, hue='output')

<Axes: xlabel='trtbps', ylabel='Count'>

Out[18]:

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 7/9

4/14/24, 10:12 AM B_4_Heart

In [19]: temp_df = df[['age','cp', 'trtbps','chol','fbs','oldpeak','output']]

plt.figure(figsize=(15,10))
sns.pairplot(temp_df,hue="output")
plt.title("Looking for Insites in Data")
plt.legend("HeartDisease")
plt.tight_layout()
plt.plot()

C:\Users\Admin\anaconda3\Lib\site-packages\seaborn\axisgrid.py:118: UserWarning: T
he figure layout has changed to tight
self._figure.tight_layout(*args, **kwargs)
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\1194111231.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
[]
Out[19]:
<Figure size 1500x1000 with 0 Axes>

In [20]: plt.figure(figsize=(15,10))
for i,col in enumerate(temp_df.columns,1):
plt.subplot(4,3,i)
plt.title(f"Distribution of {col} Data")
sns.histplot(df[col],kde=True)
plt.tight_layout()
plt.plot()

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 8/9

4/14/24, 10:12 AM B_4_Heart

C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()
C:\Users\Admin\AppData\Local\Temp\ipykernel_13800\4266913939.py:6: UserWarning: Th
e figure layout has changed to tight
plt.tight_layout()

In [ ]:

localhost:8888/nbconvert/html/Desktop/DSBDA GROP B/Assignment 4/B_4_Heart.ipynb?download=false 9/9