
# import data science basic libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')


# load data
df = pd.read_csv('D:/ML & AI EDU/heart.csv')
df.head()


# data shape
df.shape

(918, 12)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 918 entries, 0 to 917
Data columns (total 12 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Age             918 non-null    int64  
 1   Sex             918 non-null    object 
 2   ChestPainType   918 non-null    object 
 3   RestingBP       918 non-null    int64  
 4   Cholesterol     918 non-null    int64  
 5   FastingBS       918 non-null    int64  
 6   RestingECG      918 non-null    object 
 7   MaxHR           918 non-null    int64  
 8   ExerciseAngina  918 non-null    object 
 9   Oldpeak         918 non-null    float64
 10  ST_Slope        918 non-null    object 
 11  HeartDisease    918 non-null    int64  
dtypes: float64(1), int64(6), object(5)
memory usage: 86.2+ KB


# show unique values
df.nunique()

Age                50
Sex                 2
ChestPainType       4
RestingBP          67
Cholesterol       222
FastingBS           2
RestingECG          3
MaxHR             119
ExerciseAngina      2
Oldpeak            53
ST_Slope            3
HeartDisease        2
dtype: int64


# data basic statistics
df.describe()


# missing values in decerding order
df.isnull().sum().sort_values(ascending=False)

Age               0
Sex               0
ChestPainType     0
RestingBP         0
Cholesterol       0
FastingBS         0
RestingECG        0
MaxHR             0
ExerciseAngina    0
Oldpeak           0
ST_Slope          0
HeartDisease      0
dtype: int64


# duplicated values
df.duplicated().sum()

0


# numerical and categorical features 
Categorical = df.select_dtypes(include=['object'])
Numerical = df.select_dtypes(include=['int64', 'float64'])
print('Categorical features:\n', Categorical)
print('Numerical features:\n', Numerical)

Categorical features:
     Sex ChestPainType RestingECG ExerciseAngina ST_Slope
0     M           ATA     Normal              N       Up
1     F           NAP     Normal              N     Flat
2     M           ATA         ST              N       Up
3     F           ASY     Normal              Y     Flat
4     M           NAP     Normal              N       Up
..   ..           ...        ...            ...      ...
913   M            TA     Normal              N     Flat
914   M           ASY     Normal              N     Flat
915   M           ASY     Normal              Y     Flat
916   F           ATA        LVH              N     Flat
917   M           NAP     Normal              N       Up

[918 rows x 5 columns]
Numerical features:
      Age  RestingBP  Cholesterol  FastingBS  MaxHR  Oldpeak  HeartDisease
0     40        140          289          0    172      0.0             0
1     49        160          180          0    156      1.0             1
2     37        130          283          0     98      0.0             0
3     48        138          214          0    108      1.5             1
4     54        150          195          0    122      0.0             0
..   ...        ...          ...        ...    ...      ...           ...
913   45        110          264          0    132      1.2             1
914   68        144          193          1    141      3.4             1
915   57        130          131          0    115      1.2             1
916   57        130          236          0    174      0.0             1
917   38        138          175          0    173      0.0             0

[918 rows x 7 columns]


# count target variable
df['HeartDisease'].value_counts()

1    508
0    410
Name: HeartDisease, dtype: int64


# Normal and Heart Disease with target column
plt.figure(figsize=(10,5))
plt.pie(df['HeartDisease'].value_counts(), labels=['Heart Disease[1]', 'Normal[0]'], autopct='%1.1f%%')
plt.show()


# ploting corelation matrix
sns.heatmap(df.corr(), annot=True)
plt.show()


# ploting numerical features with target
for i in Numerical:
    plt.figure(figsize=(10,5))
    sns.countplot(x=i, data=df, hue='HeartDisease')
    plt.legend(['Normal', 'Heart Disease'])
    plt.title(i)
    plt.show()


#ploting categorical features with target
for i in Categorical:
    plt.figure(figsize=(10,5))
    sns.countplot(x=i, data=df, hue='HeartDisease', edgecolor='black')
    plt.legend(['Normal', 'Heart Disease'])
    plt.title(i)
    plt.show()


#pairplot using target HeartDisease Column
sns.pairplot(df, hue='HeartDisease')
plt.show()

	Age	RestingBP	Cholesterol	FastingBS	MaxHR	Oldpeak	HeartDisease
count	918.000000	918.000000	918.000000	918.000000	918.000000	918.000000	918.000000
mean	53.510893	132.396514	198.799564	0.233115	136.809368	0.887364	0.553377
std	9.432617	18.514154	109.384145	0.423046	25.460334	1.066570	0.497414
min	28.000000	0.000000	0.000000	0.000000	60.000000	-2.600000	0.000000
25%	47.000000	120.000000	173.250000	0.000000	120.000000	0.000000	0.000000
50%	54.000000	130.000000	223.000000	0.000000	138.000000	0.600000	1.000000
75%	60.000000	140.000000	267.000000	0.000000	156.000000	1.500000	1.000000
max	77.000000	200.000000	603.000000	1.000000	202.000000	6.200000	1.000000

	Age	Sex	ChestPainType	RestingBP	Cholesterol	RestingECG	MaxHR	ExerciseAngina	Oldpeak	ST_Slope	HeartDisease
0	40	M	ATA	140	289	Normal	172	N	0.0	Up	0
1	49	F	NAP	160	180	Normal	156	N	1.0	Flat	1
2	37	M	ATA	130	283	ST	98	N	0.0	Up	0
3	48	F	ASY	138	214	Normal	108	Y	1.5	Flat	1
4	54	M	NAP	150	195	Normal	122	N	0.0	Up	0