In [114]:
# import libraries
In [115]:
import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
In [116]:
#getting dataset
In [117]:
data = pd.read_csv('c:/Users/STS/Desktop/heartdata.csv')
data.head()
Out[117]:
ff age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
0 1 63 Male Cleveland typical angina 145.0 233.0 True lv hypertrophy 150.0 False 2.3 downsloping 0.0 fixed defect 0
1 2 67 Male Cleveland asymptomatic 160.0 286.0 False lv hypertrophy 108.0 True 1.5 flat 3.0 normal 2
2 3 67 Male Cleveland asymptomatic 120.0 229.0 False lv hypertrophy 129.0 True 2.6 flat 2.0 reversable defect 1
3 4 37 Male Cleveland non-anginal 130.0 250.0 False normal 187.0 False 3.5 downsloping 0.0 normal 0
4 5 41 Female Cleveland atypical angina 130.0 204.0 False lv hypertrophy 172.0 False 1.4 upsloping 0.0 normal 0
In [118]:
data.shape
Out[118]:
(920, 16)
In [119]:
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 920 entries, 0 to 919
Data columns (total 16 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   ff        920 non-null    int64  
 1   age       920 non-null    int64  
 2   sex       920 non-null    object 
 3   dataset   920 non-null    object 
 4   cp        920 non-null    object 
 5   trestbps  861 non-null    float64
 6   chol      890 non-null    float64
 7   fbs       830 non-null    object 
 8   restecg   918 non-null    object 
 9   thalch    865 non-null    float64
 10  exang     865 non-null    object 
 11  oldpeak   858 non-null    float64
 12  slope     611 non-null    object 
 13  ca        309 non-null    float64
 14  thal      434 non-null    object 
 15  num       920 non-null    int64  
dtypes: float64(5), int64(3), object(8)
memory usage: 115.1+ KB
In [120]:
data['dataset'].value_counts()
Out[120]:
Cleveland        304
Hungary          293
VA Long Beach    200
Switzerland      123
Name: dataset, dtype: int64
In [121]:
#data transformation
In [122]:
col=['age','fbs','exang']
for col in data:
    le= LabelEncoder()
    data[col]=le.fit_transform(data[col])
In [123]:
data.tail()
Out[123]:
ff age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
915 915 26 0 3 0 28 179 1 2 80 0 10 3 4 3 1
916 916 34 1 3 3 61 8 0 2 119 2 53 3 4 3 0
917 917 27 1 3 0 23 76 1 2 27 0 10 3 4 0 2
918 918 30 1 3 0 61 199 1 0 119 2 53 3 4 3 0
919 919 34 1 3 1 22 107 0 0 20 1 10 3 4 3 1
In [124]:
#filling not a number with statistical values
In [125]:
data['oldpeak'].fillna(data['oldpeak'].mean(),inplace=True)
data.tail()
Out[125]:
ff age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
915 915 26 0 3 0 28 179 1 2 80 0 10 3 4 3 1
916 916 34 1 3 3 61 8 0 2 119 2 53 3 4 3 0
917 917 27 1 3 0 23 76 1 2 27 0 10 3 4 0 2
918 918 30 1 3 0 61 199 1 0 119 2 53 3 4 3 0
919 919 34 1 3 1 22 107 0 0 20 1 10 3 4 3 1
In [126]:
#standardisation of the data
In [127]:
ss=StandardScaler()
col=['restecg','thalch','chol','trestbps','oldpeak']
data[col]=ss.fit_transform(data[col])
data.tail()
Out[127]:
ff age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
915 915 26 0 3 0 -0.321438 1.553066 1 1.574882 0.465705 0 -0.837596 3 4 3 1
916 916 34 1 3 3 2.041479 -1.216343 0 1.574882 1.866099 2 2.434380 3 4 3 0
917 917 27 1 3 0 -0.679455 -0.115058 1 1.574882 -1.437394 0 -0.837596 3 4 0 2
918 918 30 1 3 0 2.041479 1.876974 1 -1.557856 1.866099 2 2.434380 3 4 3 0
919 919 34 1 3 1 -0.751059 0.386999 0 -1.557856 -1.688747 1 -0.837596 3 4 3 1
In [128]:
data['trestbps'].value_counts()
Out[128]:
-0.751059    131
-0.106627    115
 0.322994    102
-1.323887     59
 2.041479     59
            ... 
-1.753508      1
-0.607852      1
 1.540254      1
-0.178231      1
-0.321438      1
Name: trestbps, Length: 62, dtype: int64
In [129]:
x=data.drop(columns='num',axis=1)
y=data['num']
In [130]:
#training machine
In [131]:
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,stratify=y,random_state=2)
print(x.shape,x_train.shape,x_test.shape)

(920, 15) (736, 15) (184, 15)
In [132]:
#predicting accuracy of the model
In [133]:
from sklearn.linear_model import LogisticRegression
model=LogisticRegression()
model.fit(x_train,y_train)

C:\Users\STS\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:814: 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
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
Out[133]:
LogisticRegression()
In [134]:
from sklearn.metrics import accuracy_score
x_train_predict=model.predict(x_train)
traidata_accuracy=accuracy_score(x_train_predict,y_train)
print(traidata_accuracy)

0.5625
In [135]:
x_test_predict=model.predict(x_test)
testdata_accuracy=accuracy_score(x_test_predict,y_test)
print(testdata_accuracy)

0.5760869565217391
In [136]:
input_da=([917,57,2,3,1,-0.659455,0.125058,1,1.574882,-1.437394,0,-0.837596,6,5,0])
new=np.asarray(input_da)
new_resha=new.reshape(1,-1)
prediction=model.predict(new_resha)
print(prediction)

[0]

C:\Users\STS\anaconda3\lib\site-packages\sklearn\base.py:450: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
  warnings.warn(
In [137]:
if(prediction[0]==0):
    print('no heart dieseas')
elif(prediction[0]==1):
    print('1st storke')
elif(prediction[0]==2):
    print('2nd stroke')
elif(prediction[0]==3):
    print('3rd storke')

no heart dieseas
In [ ]: