This repository contains a Python script that uses TensorFlow to build, train, and evaluate a neural network for breast cancer diagnosis using a dataset (cancer.csv).

The script processes the dataset by separating features and target variables, then splits the data into training and testing sets. A sequential neural network model is defined with three dense layers using the sigmoid activation function. The model is compiled with the Adam optimizer and binary cross-entropy loss function. Users can interactively choose to train the model or evaluate its performance on the test set through a simple command-line interface.

• Python 3.x
• pandas
• scikit-learn
• tensorflow

1. Clone the repository:

   git clone https://github.com/JimmyVS/TumorDetectionAI.git

2. Navigate to the project directory:

   cd TumorDetectionAI

3. Install the required packages:

   pip install pandas scikit-learn tensorflow

1. Ensure you have the cancer.csv dataset in the project directory.
2. Run the script:

   set PYTHONIOENCODING=UTF-8
   python TumorDetection.py

3. Follow the interactive prompts to train or test the model.

The cancer.csv file should contain the dataset with features and a target column named diagnosis(1=m, 0=b) where 1 represents malignant and 0 represents benign diagnoses. This repository already contains a dataset. You can change it whenever you want, but make sure to add the required features.

• Loading and Preparing Data: Loads the dataset and preprocesses it.
• Model Definition and Compilation: Defines and compiles the neural network.
• Training and Testing Functions: Encapsulates training and evaluation logic.
• Interactive Menu: Allows users to train or test the model based on user input.

This project is licensed under the MIT License - see the LICENSE file for details.