Scribd
Upload
8 views3 pages

24CS4505 ML Assignment

The document outlines a machine learning project using TensorFlow and Keras to predict heart disease from a dataset. It includes data preprocessing, model building, training, and evaluation, achieving a test accuracy of 99%. Additionally, it provides visualizations of model accuracy and loss over epochs, along with a confusion matrix and classification report.

Uploaded by

venkat.reddy984800
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views3 pages

24CS4505 ML Assignment

The document outlines a machine learning project using TensorFlow and Keras to predict heart disease from a dataset. It includes data preprocessing, model building, training, and evaluation, achieving a test accuracy of 99%. Additionally, it provides visualizations of model accuracy and loss over epochs, along with a confusion matrix and classification report.

Uploaded by

venkat.reddy984800
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

4/15/25, 2:21 PM ann_assignment.

ipynb - Colab

#24CS4505 Hem Chalasani

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd
import numpy as np

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

X = data.drop(columns=['target'])
y = data['target']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

model = Sequential([
Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
Dropout(0.2),
Dense(32, activation='relu'),
Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

epochs = 100
batch_size = 16
history = model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))

loss, accuracy = model.evaluate(X_test, y_test)


print(f"Test Accuracy: {accuracy * 100:.2f}%")

Epoch 1/100
/usr/local/lib/python3.11/dist-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim`
super().__init__(activity_regularizer=activity_regularizer, **kwargs)
52/52 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.7070 - loss: 0.6009 - val_accuracy: 0.7951 - val_loss: 0.4475
Epoch 2/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step - accuracy: 0.8611 - loss: 0.3705 - val_accuracy: 0.8146 - val_loss: 0.4036
Epoch 3/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step - accuracy: 0.8671 - loss: 0.3343 - val_accuracy: 0.8146 - val_loss: 0.3908
Epoch 4/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step - accuracy: 0.8954 - loss: 0.3055 - val_accuracy: 0.8195 - val_loss: 0.3802
Epoch 5/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 1s 5ms/step - accuracy: 0.8921 - loss: 0.2805 - val_accuracy: 0.8390 - val_loss: 0.3664
Epoch 6/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 1s 5ms/step - accuracy: 0.8964 - loss: 0.2835 - val_accuracy: 0.8439 - val_loss: 0.3493
Epoch 7/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.9050 - loss: 0.2521 - val_accuracy: 0.8488 - val_loss: 0.3516
Epoch 8/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9046 - loss: 0.2469 - val_accuracy: 0.8488 - val_loss: 0.3343
Epoch 9/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.9043 - loss: 0.2371 - val_accuracy: 0.8439 - val_loss: 0.3228
Epoch 10/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9007 - loss: 0.2647 - val_accuracy: 0.8439 - val_loss: 0.3142
Epoch 11/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9174 - loss: 0.2230 - val_accuracy: 0.8488 - val_loss: 0.3084
Epoch 12/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9198 - loss: 0.2327 - val_accuracy: 0.8537 - val_loss: 0.2939
Epoch 13/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9276 - loss: 0.2024 - val_accuracy: 0.8683 - val_loss: 0.2871
Epoch 14/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9131 - loss: 0.2281 - val_accuracy: 0.8732 - val_loss: 0.2662
Epoch 15/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9250 - loss: 0.1954 - val_accuracy: 0.8732 - val_loss: 0.2637
Epoch 16/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.9238 - loss: 0.2077 - val_accuracy: 0.8683 - val_loss: 0.2516
Epoch 17/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9282 - loss: 0.1812 - val_accuracy: 0.8878 - val_loss: 0.2500
Epoch 18/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9317 - loss: 0.1811 - val_accuracy: 0.8780 - val_loss: 0.2390
Epoch 19/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9450 - loss: 0.1494 - val_accuracy: 0.8829 - val_loss: 0.2318
Epoch 20/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9348 - loss: 0.1546 - val_accuracy: 0.8732 - val_loss: 0.2441
Epoch 21/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9186 - loss: 0.1907 - val_accuracy: 0.9122 - val_loss: 0.2064
Epoch 22/100

https://colab.research.google.com/drive/1c9EiEUtD7lgc9NdQ8sPhq8Req_O4DE-4#scrollTo=cr8ANb3JjyZI&printMode=true 1/3
4/15/25, 2:21 PM ann_assignment.ipynb - Colab
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9520 - loss: 0.1554 - val_accuracy: 0.9024 - val_loss: 0.2024
Epoch 23/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9400 - loss: 0.1469 - val_accuracy: 0.9073 - val_loss: 0.1989
Epoch 24/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9486 - loss: 0.1502 - val_accuracy: 0.9220 - val_loss: 0.1891
Epoch 25/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9488 - loss: 0.1340 - val_accuracy: 0.9122 - val_loss: 0.1790
Epoch 26/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9403 - loss: 0.1517 - val_accuracy: 0.9317 - val_loss: 0.1737
Epoch 27/100
52/52 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.9589 - loss: 0.1421 - val_accuracy: 0.9317 - val_loss: 0.1703
Epoch 28/100

# Accuracy plot
plt.plot(history.history['accuracy'], label='Train Accuracy')
plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.title('Model Accuracy Over Epochs')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

# Loss plot
plt.plot(history.history['loss'], label='Train Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.title('Model Loss Over Epochs')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()

https://colab.research.google.com/drive/1c9EiEUtD7lgc9NdQ8sPhq8Req_O4DE-4#scrollTo=cr8ANb3JjyZI&printMode=true 2/3
4/15/25, 2:21 PM ann_assignment.ipynb - Colab
# Evaluate on test data
loss, accuracy = model.evaluate(X_test, y_test)
print(f"Test Accuracy: {accuracy:.2f}")

# Predict and evaluate


y_pred = model.predict(X_test)
y_pred_class = (y_pred > 0.5).astype(int)

# Confusion matrix
cm = confusion_matrix(y_test, y_pred_class)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
plt.title('Confusion Matrix')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()

# Classification report
print("Classification Report:")
print(classification_report(y_test, y_pred_class))

7/7 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step - accuracy: 0.9715 - loss: 0.0686


Test Accuracy: 0.99
7/7 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step

Classification Report:
precision recall f1-score support

0 0.97 1.00 0.99 102


1 1.00 0.97 0.99 103

accuracy 0.99 205


macro avg 0.99 0.99 0.99 205
weighted avg 0.99 0.99 0.99 205

https://colab.research.google.com/drive/1c9EiEUtD7lgc9NdQ8sPhq8Req_O4DE-4#scrollTo=cr8ANb3JjyZI&printMode=true 3/3

You might also like