
import numpy as np
import pandas as pd
import math
import random
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline


import warnings
warnings.filterwarnings("ignore")


data = pd.read_csv("heart_disease_uci.csv")


data.head()


data['condition'] = data['num']


data = data.drop(columns = ['id','dataset','ca','thal','num'])


data.head()


data = data[(data['chol'] <= 420) & (data['oldpeak'] >=0) & (data['oldpeak'] <=4)].reset_index(drop=True)
data = data.dropna().reset_index(drop=True)
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 520 entries, 0 to 519
Data columns (total 12 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   age        520 non-null    int64  
 1   sex        520 non-null    object 
 2   cp         520 non-null    object 
 3   trestbps   520 non-null    float64
 4   chol       520 non-null    float64
 5   fbs        520 non-null    object 
 6   restecg    520 non-null    object 
 7   thalch     520 non-null    float64
 8   exang      520 non-null    object 
 9   oldpeak    520 non-null    float64
 10  slope      520 non-null    object 
 11  condition  520 non-null    int64  
dtypes: float64(4), int64(2), object(6)
memory usage: 48.9+ KB


def str_features_to_numeric(data):
    
    categorical_columns = []
    numerics = ['int8', 'int16', 'int32', 'int64', 'float16', 'float32', 'float64']
    features = data.columns.values.tolist()
    for col in features:
        if data[col].dtype in numerics: continue
        categorical_columns.append(col)
    
    # Encoding categorical features
    for col in categorical_columns:
        if col in data.columns:
            le = LabelEncoder()
            le.fit(list(data[col].astype(str).values))
            data[col] = le.transform(list(data[col].astype(str).values))
    
    return data


data = str_features_to_numeric(data)
data


data.condition.value_counts()

0    203
1    159
2     70
3     68
4     20
Name: condition, dtype: int64


data = data[data['condition'].isin([0, 1])]
data


data.isnull().sum()

age          0
sex          0
cp           0
trestbps     0
chol         0
fbs          0
restecg      0
thalch       0
exang        0
oldpeak      0
slope        0
condition    0
dtype: int64


data.shape

(362, 12)


data['condition'].value_counts()

0    203
1    159
Name: condition, dtype: int64


X = data.drop(columns='condition', axis=1)
Y = data['condition']
print(X)

     age  sex  cp  trestbps   chol  fbs  restecg  thalch  exang  oldpeak  \
0     63    1   3     145.0  233.0    1        0   150.0      0      2.3   
2     67    1   0     120.0  229.0    0        0   129.0      1      2.6   
3     37    1   2     130.0  250.0    0        1   187.0      0      3.5   
4     41    0   1     130.0  204.0    0        0   172.0      0      1.4   
5     56    1   1     120.0  236.0    0        1   178.0      0      0.8   
..   ...  ...  ..       ...    ...  ...      ...     ...    ...      ...   
512   60    1   0     130.0  186.0    1        0   140.0      1      0.5   
513   55    1   0     120.0  226.0    0        0   127.0      1      1.7   
514   56    1   0     130.0  203.0    1        1    98.0      0      1.5   
515   57    1   0     130.0  207.0    0        2    96.0      1      1.0   
517   51    0   0     114.0  258.0    1        0    96.0      0      1.0   

     slope  
0        0  
2        1  
3        0  
4        2  
5        2  
..     ...  
512      1  
513      0  
514      1  
515      1  
517      2  

[362 rows x 11 columns]


print(Y)

0      0
2      1
3      0
4      0
5      0
      ..
512    1
513    1
514    1
515    0
517    0
Name: condition, Length: 362, dtype: int64


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)

(362, 11) (289, 11) (73, 11)


from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
model = LogisticRegression()
model.fit(X_train, Y_train)

LogisticRegression()


X_train_prediction = model.predict(X_train)
training_data_accuracy = accuracy_score(X_train_prediction, Y_train)


print('Accuracy on Training data : ', training_data_accuracy)

Accuracy on Training data :  0.7958477508650519


X_test_prediction = model.predict(X_test)
test_data_accuracy = accuracy_score(X_test_prediction, Y_test)


print('Accuracy on Test data : ', test_data_accuracy)

Accuracy on Test data :  0.7808219178082192


from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
knn.fit(X_train, Y_train)

KNeighborsClassifier()


print ('Accuracy of KNN n-5, on the training set : {:.3f}'.format(knn.score(X_train, Y_train)))
print ('Accuracy of KNN n-5, on the testing set : {:.3f}'.format(knn.score(X_test, Y_test)))

Accuracy of KNN n-5, on the training set : 0.758
Accuracy of KNN n-5, on the testing set : 0.644


from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.fit_transform (X_test)


print ('Accuracy of KNN n-5, on the training set : {:.3f}'.format(knn.score(X_train, Y_train)))
print ('Accuracy of KNN n-5, on the testing set : {:.3f}'.format(knn.score(X_test, Y_test)))

Accuracy of KNN n-5, on the training set : 0.439
Accuracy of KNN n-5, on the testing set : 0.438


knn.predict(X_test)

array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1], dtype=int64)


from sklearn.ensemble import RandomForestRegressor
reg = RandomForestRegressor()
reg.fit(X,Y)

RandomForestRegressor()


col = data.columns.tolist()[:-1]
df_feature_importance = pd.DataFrame (reg.feature_importances_, index = col, columns= ['feature importance']).sort_values('feature importance',ascending = False)
df_feature_importance.plot(kind = 'bar')

<AxesSubplot:>

	id	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