Welcome to the README of Machine Learning: Developing NLP Model Using TensorFLow.
This repository uses dataset available here.
This repository is developed as Final Assignment of Belajar Pengembangan Machine Learning module, a part of Machine Learning learning path of Dicoding awarded by Lintasarta Cloudeka Digischool 2024.
This repository is focusing on these following bulletpoints:
- Minimum 1,000 samples for dataset
- Data split : 80% train and 20% validation
- Developing sequential model
- Commencing LSTM model within the model architecture
- Utilizing Embedding and Tokenizer function
- Training duration not more than 30 minutes
- 75% of minimum accuracy both train set and validation set
numpylibrary to carry out numerical computation such as sets, arrays, multidimension matrixes, and vectorspandaslibrary to undergo data processing, analysing, and manipulation using dataframematplotliblibrary to perform visualization using plottingoslibrary to execute loading datazipfilelibrary to extract fileskicit learnlibrary to split datasettensorflowlibrary to generate imagekeraslibrary to display imagenltklibrary to commence text preprocessing
Copyright © Nicko Arya Dharma 2024 All Rights Reserved