Data

Tools

Indexes

Applications

Experiments

Open Source Science

text-to-ml

Programmable automated machine learning - proof of concept

https://github.com/jmaczan/text-to-ml

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.4%) to scientific vocabulary

Keywords

automl deep-learning huggingface hugginggpt machine-learning python
Last synced: 6 months ago · JSON representation ·

Repository

Programmable automated machine learning - proof of concept

Basic Info
Statistics
  • Stars: 14
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
automl deep-learning huggingface hugginggpt machine-learning python
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

🎮 text-to-ml

💜 PagedOut #4 Issue "Building automated machine learning with type inference"

Run AutoML using natural text. Like HuggingGPT + LangChain + type inference

🏭 A breakdown of what is going on in code you can read on my blog: maczan.pl

It picks a right model from Hugging Face library based on user natural language query and then runs the model and parses the output to a type, inferred from the query

Text-to-ML

⚡ You can run this code in Lightning AI Studio template

Open In Studio

It's still an early project and you are welcome to contribute!

Setup

  1. Get OpenAI API Key
  2. Get Hugging Face API Key
  3. Create an assistant and copy its id
  4. Create .env file and fill it with values:

OPENAI_API_KEY= HF_TOKEN=

Build

sh conda create -n text-to-ml python=3.9 conda activate text-to-ml conda install --file requirements.txt

Run

python app.py

Run experiments

python experiments.py

Cite

If you use this software in your research, please use the following citation:

bibtex @misc{Maczan_TextToML_2024, title = "Programmable automated machine learning - proof of concept", author = "{Maczan, Jędrzej Paweł}", howpublished = "\url{https://github.com/jmaczan/text-to-ml}", year = 2024, publisher = {GitHub} }

License

GPLv3

Author

Jędrzej Paweł Maczan, Poland, 2024

Owner

  • Name: Jędrzej Maczan
  • Login: jmaczan
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this project in your research, please cite it as below."
authors:
- family-names: "Maczan"
  given-names: "Jędrzej Paweł"
  orcid: "https://orcid.org/0000-0003-1741-6064"
title: "Programmable automated machine learning - proof of concept"
date-released: 2024-04-04
url: "https://github.com/jmaczan/text-to-ml"

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • aiohttp =3.9.3=py39h17cfd9d_1
  • aiosignal =1.3.1=pyhd8ed1ab_0
  • annotated-types =0.6.0=pyhd8ed1ab_0
  • anyio =3.7.1=pyhd8ed1ab_0
  • async-timeout =4.0.3=pyhd8ed1ab_0
  • attrs =23.2.0=pyh71513ae_0
  • aws-c-auth =0.7.16=h0d2f7a6_8
  • aws-c-cal =0.6.10=h677d54c_2
  • aws-c-common =0.9.14=h93a5062_0
  • aws-c-compression =0.2.18=h677d54c_2
  • aws-c-event-stream =0.4.2=h59ac3ca_6
  • aws-c-http =0.8.1=hfe5d766_7
  • aws-c-io =0.14.6=h9ac2cdb_1
  • aws-c-mqtt =0.10.3=hb8a1441_2
  • aws-c-s3 =0.5.3=h4398043_0
  • aws-c-sdkutils =0.1.15=h677d54c_2
  • aws-checksums =0.1.18=h677d54c_2
  • aws-crt-cpp =0.26.4=h2547149_1
  • aws-sdk-cpp =1.11.267=ha761c4c_4
  • brotli-python =1.1.0=py39hb198ff7_1
  • bzip2 =1.0.8=h93a5062_5
  • c-ares =1.27.0=h93a5062_0
  • ca-certificates =2024.2.2=hf0a4a13_0
  • certifi =2024.2.2=pyhd8ed1ab_0
  • charset-normalizer =3.3.2=pyhd8ed1ab_0
  • click =8.1.7=unix_pyh707e725_0
  • colorama =0.4.6=pyhd8ed1ab_0
  • datasets =2.18.0=pyhd8ed1ab_0
  • dill =0.3.8=pyhd8ed1ab_0
  • distro =1.9.0=pyhd8ed1ab_0
  • exceptiongroup =1.2.0=pyhd8ed1ab_2
  • fastapi =0.110.0=pyhd8ed1ab_0
  • filelock =3.13.1=pyhd8ed1ab_0
  • freetype =2.12.1=hadb7bae_2
  • frozenlist =1.4.1=py39h17cfd9d_0
  • fsspec =2024.2.0=pyhca7485f_0
  • gflags =2.2.2=hc88da5d_1004
  • glog =0.7.0=hc6770e3_0
  • h11 =0.14.0=pyhd8ed1ab_0
  • h2 =4.1.0=pyhd8ed1ab_0
  • hpack =4.0.0=pyh9f0ad1d_0
  • httpcore =1.0.4=pyhd8ed1ab_0
  • httpx =0.27.0=pyhd8ed1ab_0
  • huggingface_hub =0.21.4=pyhd8ed1ab_0
  • hyperframe =6.0.1=pyhd8ed1ab_0
  • icu =73.2=hc8870d7_0
  • idna =3.6=pyhd8ed1ab_0
  • krb5 =1.21.2=h92f50d5_0
  • lcms2 =2.16=ha0e7c42_0
  • lerc =4.0.0=h9a09cb3_0
  • libabseil =20240116.1=cxx17_hebf3989_2
  • libarrow =15.0.2=h5e64418_1_cpu
  • libarrow-acero =15.0.2=hebf3989_1_cpu
  • libarrow-dataset =15.0.2=hebf3989_1_cpu
  • libarrow-flight =15.0.2=h1f98dca_1_cpu
  • libarrow-flight-sql =15.0.2=hb095944_1_cpu
  • libarrow-gandiva =15.0.2=h2c81988_1_cpu
  • libarrow-substrait =15.0.2=h50959cf_1_cpu
  • libblas =3.9.0=21_osxarm64_openblas
  • libbrotlicommon =1.1.0=hb547adb_1
  • libbrotlidec =1.1.0=hb547adb_1
  • libbrotlienc =1.1.0=hb547adb_1
  • libcblas =3.9.0=21_osxarm64_openblas
  • libcrc32c =1.1.2=hbdafb3b_0
  • libcurl =8.6.0=h2d989ff_0
  • libcxx =16.0.6=h4653b0c_0
  • libdeflate =1.20=h93a5062_0
  • libedit =3.1.20191231=hc8eb9b7_2
  • libev =4.33=h93a5062_2
  • libevent =2.1.12=h2757513_1
  • libffi =3.4.2=h3422bc3_5
  • libgfortran =5.0.0=13_2_0_hd922786_3
  • libgfortran5 =13.2.0=hf226fd6_3
  • libgoogle-cloud =2.22.0=hbebe991_1
  • libgoogle-cloud-storage =2.22.0=h8a76758_1
  • libgrpc =1.62.1=h9c18a4f_0
  • libiconv =1.17=h0d3ecfb_2
  • libjpeg-turbo =3.0.0=hb547adb_1
  • liblapack =3.9.0=21_osxarm64_openblas
  • libllvm16 =16.0.6=haab561b_3
  • libnghttp2 =1.58.0=ha4dd798_1
  • libopenblas =0.3.26=openmp_h6c19121_0
  • libparquet =15.0.2=h278d484_1_cpu
  • libpng =1.6.43=h091b4b1_0
  • libprotobuf =4.25.3=hbfab5d5_0
  • libre2-11 =2023.09.01=h7b2c953_2
  • libsqlite =3.45.2=h091b4b1_0
  • libssh2 =1.11.0=h7a5bd25_0
  • libthrift =0.19.0=h026a170_1
  • libtiff =4.6.0=h07db509_3
  • libutf8proc =2.8.0=h1a8c8d9_0
  • libwebp-base =1.3.2=hb547adb_0
  • libxcb =1.15=hf346824_0
  • libxml2 =2.12.6=h0d0cfa8_0
  • libzlib =1.2.13=h53f4e23_5
  • llvm-openmp =18.1.2=hcd81f8e_0
  • lz4-c =1.9.4=hb7217d7_0
  • multidict =6.0.5=py39h02fc5c5_0
  • multiprocess =0.70.16=py39h17cfd9d_0
  • ncurses =6.4.20240210=h078ce10_0
  • numpy =1.26.4=py39h7aa2656_0
  • openai =1.14.2=pyhd8ed1ab_0
  • openjpeg =2.5.2=h9f1df11_0
  • openssl =3.2.1=h0d3ecfb_1
  • orc =2.0.0=h3d3088e_0
  • packaging =24.0=pyhd8ed1ab_0
  • pandas =2.2.1=py39h47e51b9_0
  • pillow =10.2.0=py39h755f0b7_0
  • pip =24.0=pyhd8ed1ab_0
  • pthread-stubs =0.4=h27ca646_1001
  • pyarrow =15.0.2=py39h8cf9275_1_cpu
  • pyarrow-hotfix =0.6=pyhd8ed1ab_0
  • pydantic =2.6.4=pyhd8ed1ab_0
  • pydantic-core =2.16.3=py39h8fec3ad_0
  • pysocks =1.7.1=pyha2e5f31_6
  • python =3.9.19=hd7ebdb9_0_cpython
  • python-dateutil =2.9.0=pyhd8ed1ab_0
  • python-dotenv =1.0.1=pyhd8ed1ab_0
  • python-multipart =0.0.9=pyhd8ed1ab_0
  • python-tzdata =2024.1=pyhd8ed1ab_0
  • python-xxhash =3.4.1=py39h0f82c59_0
  • python_abi =3.9=4_cp39
  • pytz =2024.1=pyhd8ed1ab_0
  • pyyaml =6.0.1=py39h0f82c59_1
  • re2 =2023.09.01=h4cba328_2
  • readline =8.2=h92ec313_1
  • regex =2023.12.25=py39h17cfd9d_0
  • requests =2.31.0=pyhd8ed1ab_0
  • safetensors =0.4.2=py39h8fec3ad_0
  • setuptools =69.2.0=pyhd8ed1ab_0
  • six =1.16.0=pyh6c4a22f_0
  • snappy =1.1.10=h17c5cce_0
  • sniffio =1.3.1=pyhd8ed1ab_0
  • starlette =0.36.3=pyhd8ed1ab_0
  • tk =8.6.13=h5083fa2_1
  • tokenizers =0.15.2=py39heb7857c_0
  • tqdm =4.66.2=pyhd8ed1ab_0
  • transformers =4.39.1=pyhd8ed1ab_0
  • typing-extensions =4.10.0=hd8ed1ab_0
  • typing_extensions =4.10.0=pyha770c72_0
  • tzdata =2024a=h0c530f3_0
  • urllib3 =2.2.1=pyhd8ed1ab_0
  • uvicorn =0.29.0=py39h2804cbe_0
  • wheel =0.43.0=pyhd8ed1ab_0
  • xorg-libxau =1.0.11=hb547adb_0
  • xorg-libxdmcp =1.1.3=h27ca646_0
  • xxhash =0.8.2=hb547adb_0
  • xz =5.2.6=h57fd34a_0
  • yaml =0.2.5=h3422bc3_2
  • yarl =1.9.4=py39h17cfd9d_0
  • zstd =1.5.5=h4f39d0f_0