Heart Disease Detection

Credit: AITS Cainvas Community

Photo by Irina Mir on Dribbble

#importing libraries
import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
import seaborn as sns
from sklearn.metrics import average_precision_score
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report,precision_recall_curve,confusion_matrix,accuracy_score,roc_curve,f1_score,auc

Read Data

#readdata
df = pd.read_csv("https://cainvas-static.s3.amazonaws.com/media/user_data/cainvas-admin/heart_UC0K8Og.csv")
df.head()

	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

#plot heatmap
plt.figure(figsize=(14,10))
sns.heatmap(df.corr(),annot=True,fmt='.3f',linewidths=2)
plt.show()

#plot histogram
df.hist(figsize = (10,10))

array([[<AxesSubplot:title={'center':'age'}>,
        <AxesSubplot:title={'center':'sex'}>,
        <AxesSubplot:title={'center':'cp'}>,
        <AxesSubplot:title={'center':'trestbps'}>],
       [<AxesSubplot:title={'center':'chol'}>,
        <AxesSubplot:title={'center':'fbs'}>,
        <AxesSubplot:title={'center':'restecg'}>,
        <AxesSubplot:title={'center':'thalach'}>],
       [<AxesSubplot:title={'center':'exang'}>,
        <AxesSubplot:title={'center':'oldpeak'}>,
        <AxesSubplot:title={'center':'slope'}>,
        <AxesSubplot:title={'center':'ca'}>],
       [<AxesSubplot:title={'center':'thal'}>,
        <AxesSubplot:title={'center':'target'}>, <AxesSubplot:>,
        <AxesSubplot:>]], dtype=object)

Data Preprocessing

#data preprocessing
a = pd.get_dummies(df['cp'], prefix = "cp")
b = pd.get_dummies(df['thal'], prefix = "thal")
c = pd.get_dummies(df['slope'], prefix = "slope")


frames = [df, a, b, c]
df = pd.concat(frames, axis = 1)
df = df.drop(columns = ['cp', 'thal', 'slope'])
df.head()

#printing updated column list
df.columns

#changing column type to numeric
df = df.apply(pd.to_numeric)
df.dtypes

#dropping target column
x = df.drop(['target'], axis = 1)
y = df.target.values

Train-Test Split

#train test split
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3,stratify=y, random_state = 42)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)

# convert the data to categorical labels

from tensorflow.keras.utils import to_categorical
y_train = to_categorical(y_train, num_classes=None)
y_test = to_categorical(y_test, num_classes=None)
print (y_train.shape)

#printing the shape of train data
x_train.shape

Model Architecture

#import library for model making
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras.layers import Activation, Dropout, Flatten, Dense
from tensorflow.keras import regularizers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
import warnings

#classifier model making
classifier = Sequential()
# add input layer and hidden layer
classifier.add(Dense(
    activation="relu", input_dim=21, units=12,
    kernel_initializer="normal",kernel_regularizer=regularizers.l2(0.001)
))
classifier.add(Dropout(0.2))

# Adding the output layer
classifier.add(Dense(activation="softmax", units=2))
classifier.save_weights("weights")

#printing parameters
classifier.summary()

Training the model

#training the model
from tensorflow.keras.optimizers import Adam
classifier.load_weights("weights")
opt3 = Adam(lr=0.001)
classifier.compile(optimizer = opt3, loss = 'categorical_crossentropy', metrics = ['accuracy'])
history = classifier.fit(x_train, y_train,validation_data=(x_test, y_test), batch_size = 10, epochs = 50)

VS Graphs

import matplotlib.pyplot as plt
%matplotlib inline

# Model accuracy

plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'])
plt.show()

# Model Losss

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'])
plt.show()

Result and Conclusion

#result and conclusion
adam_y_pred = classifier.predict(x_test)
adam_cr = classification_report(y_test,adam_y_pred.round())
print(adam_cr)

Saving the model

#saving the model
classifier.save('heart_disease_ucl.h5')

from tensorflow.keras.models import load_model

m = load_model('heart_disease_ucl.h5')
m.predict_classes(x_test)

DeepCC

#deepcc
!deepCC heart_disease_ucl.h5