📦 lib-ml-REMLA10-2024

📝 Overview

lib-ml-REMLA10-2024 provides essential functions for preprocessing and postprocessing data in machine learning projects. It includes utilities for data splitting, preprocessing, and evaluation.

🛠️ Installation

Note: Python 3.11 is required for this library!

Using Poetry

Inside your Python 3.11 virtual environment, run:

poetry add lib-ml-REMLA10-2024

Using pip

Alternatively, you can install the package with pip:

pip install lib-ml-REMLA10-2024

📚 Usage

Importing the Library

You can import the necessary functions in your Python modules:

from lib_ml_remla import preprocess_data, split_data

Usage examples

🔄 Preprocessing Data

from lib_ml_remla import preprocess_data, split_data

# Example data
train_data = ["1\tThis is a sample training sentence.", "0\tAnother training example."]
test_data = ["1\tThis is a sample test sentence."]
val_data = ["0\tThis is a sample validation sentence."]

# Split data
raw_X_train, raw_y_train, raw_X_val, raw_y_val, raw_X_test, raw_y_test = split_data(train_data, test_data, val_data)

# Preprocess data
X_train, y_train, X_val, y_val, X_test, y_test, char_index, tokenizer, encoder = preprocess_data(
    raw_X_train, raw_y_train, raw_X_val, raw_y_val, raw_X_test, raw_y_test
)

📈 Evaluating Results

from lib_ml_remla import predict_classes, evaluate_results
from keras.models import load_model
from sklearn.preprocessing import LabelEncoder

# Load your trained model
model = load_model('path_to_your_model')

# Predict classes
labels, probabilities = predict_classes(model, encoder, X_test)

# Evaluate results
results = evaluate_results(y_test, labels)
print(results)

🛡 License

This project is licensed under the terms of the MIT license. See LICENSE for more details.