Design of a neural network without the use of libraries (scikit - dataset division, nltk - text lemmatization) to classify spam. Also there is a design using libraries. Whole point is to test if I can beat libraries with my own aglorithms - or at least improve my understanding of ML concept.
- scikit-learn: scikit-learn is a machine learning library that provides simple and efficient tools for data mining and data analysis. (Just for splitting dataset)
- pandas
- numpy
-
data_preparation: This is a custom module for data preprocessing and loading. It may include functions for data loading, cleaning, and preprocessing.
-
data_loading: Another custom module that contains data loading functions.
- perceptron_algorithm: This directory contains custom modules related to the Perceptron algorithm, including the neural network and neuron implementations.
To use these libraries and packages in your project, it's recommended to set up a Python environment using tools like virtualenv or conda. You can install the required dependencies using the following command:
pip install requirements.txt
You should also include the custom modules provided in your project directory.