zarak / domain_focused_language_model

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Domain Focused Language Model

Beta testing for Build a Deep Learning Domain Focused Language Model liveProject by Manning

Deliverables

1. Loading and preparing the dataset

Place the data file in data/raw/stackexchange_812k.csv and then run make

make data

The output file will appear in data/processed/tokenized.csv.

2. ngram language model

The code is split across the following three files: utils.py, train_model.py, and predict_model.py all in the src directory.

The perplexity is computed for a subset of the entire training set (1000 rows) for ngrams of size 1, 2, 3, 4, and 5. To accomplish this type

python models/predict.py

from the src directory.

3. Deep learning language model

4. Character based language model with AllenNLP

Project Organization
------------

├── LICENSE
├── Makefile           <- Makefile with commands like `make data` or `make train`
├── README.md          <- The top-level README for developers using this project.
├── data
│   ├── external       <- Data from third party sources.
│   ├── interim        <- Intermediate data that has been transformed.
│   ├── processed      <- The final, canonical data sets for modeling.
│   └── raw            <- The original, immutable data dump.
│
├── docs               <- A default Sphinx project; see sphinx-doc.org for details
│
├── models             <- Trained and serialized models, model predictions, or model summaries
│
├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering),
│                         the creator's initials, and a short `-` delimited description, e.g.
│                         `1.0-jqp-initial-data-exploration`.
│
├── references         <- Data dictionaries, manuals, and all other explanatory materials.
│
├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
│   └── figures        <- Generated graphics and figures to be used in reporting
│
├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.
│                         generated with `pip freeze > requirements.txt`
│
├── setup.py           <- makes project pip installable (pip install -e .) so src can be imported
├── src                <- Source code for use in this project.
│   ├── __init__.py    <- Makes src a Python module
│   │
│   ├── data           <- Scripts to download or generate data
│   │   └── make_dataset.py
│   │
│   ├── features       <- Scripts to turn raw data into features for modeling
│   │   └── build_features.py
│   │
│   ├── models         <- Scripts to train models and then use trained models to make
│   │   │                 predictions
│   │   ├── predict_model.py
│   │   └── train_model.py
│   │
│   └── visualization  <- Scripts to create exploratory and results oriented visualizations
│       └── visualize.py
│
└── tox.ini            <- tox file with settings for running tox; see tox.testrun.org


--------

<p><small>Project based on the <a target="_blank" href="https://drivendata.github.io/cookiecutter-data-science/">cookiecutter data science project template</a>. #cookiecutterdatascience</small></p>

About

License:MIT License


Languages

Language:Jupyter Notebook 84.8%Language:Python 11.7%Language:Makefile 3.5%