Skip to main content

Automating Data Science

Project description

GML Brain+Machine Adding AI Revolution

Generic badge Generic badge Generic badge Generic badge
PyPI version PyPI license PyPI pyversions GitHub issues

Creators

Muhammad Ahmed
Naman Tuli

Contributors

Rafey Iqbal Rahman

Tired of doing Data Science manually? GML is here for you!

GML is an automatic data science library in python built on top of multiple Python packages. Complete features which we offer are listed as:


Installation:


pip install GML

https://pypi.org/project/GML

Features:


Auto Feature Engineering



from GML import FeatureEngineering

fe = FeatureEngineering(Data, 'target', fill_missing_data=True, encode_data=True, 
                        normalize=True, remove_outliers=True, 
                        new_features=True, feateng_steps=2 ) # feateng_steps = 0 for features selection without feature creation

X_new, y, test = fe.get_new_data()

Click Here for complete DEMO


Auto EDA (Powered by Sweetviz)



from GML import sweetviz

result1 = sweetviz.compare([train,'train'],[test,'test'],'target') 
result2 = sweetviz.analyze([train,'train'])

result.show_html()
result2.show_html()

Click Here for complete DEMO


Auto Machine Learning



from GML import AutoML

gml_ml = AutoML()

gml_ml.GMLClassifier(X, y, metric = accuracy_score, folds = 10)

Click Here for complete DEMO

Auto Text Cleaning



from GML import AutoNLP

nlp = AutoNLP()

cleanX = X.apply(lambda x: nlp.clean(x))

Click Here for complete DEMO


Auto Text Classification using transformers



from GML import AutoNLP

nlp = AutoNLP()

nlp.set_params(cleanX, tokenizer_name='roberta-large-mnli', BATCH_SIZE=4,
               model_name='roberta-large-mnli', MAX_LEN=200)

model = nlp.train_model(tokenizedX, y)

Click Here for complete DEMO


Auto Image Classification with Augmentation



from GML import Auto_Image_Processing

gml_image_processing = Auto_Image_Processing()

model = gml_image_processing.imgClassificationcsv(img_path = './covid_image_data/train', 
                                                  train_path = './covid_image_data/Training_set_covid.csv', 
                                                  model_list = models,
                                                 tfms = True, advance_augmentation = True, 
                                                  epochs=1)

Click Here for complete DEMO


Text Augmentation using transformers: GPT-2



from GML import AutoNLP

nlp = AutoNLP()

nlp.augmentation_train('./data.csv')

nlp.set_params(X['Text'])

new_Text = nlp.augmentation_generate(y = y, SENTENCES = 100) 

Click Here for complete DEMO



More cool features and handling of different data types like audio data etc will be added in future.
Feel free to give suggestions, report bugs and contribute.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

GML-3.0.5.tar.gz (15.4 MB view details)

Uploaded Source

Built Distribution

GML-3.0.5-py3-none-any.whl (15.5 MB view details)

Uploaded Python 3

File details

Details for the file GML-3.0.5.tar.gz.

File metadata

  • Download URL: GML-3.0.5.tar.gz
  • Upload date:
  • Size: 15.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.23.0 setuptools/46.4.0.post20200518 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.8.3

File hashes

Hashes for GML-3.0.5.tar.gz
Algorithm Hash digest
SHA256 35f37672dc4448c54ab6b5bb02b1476aa8cf52c79d50a461562f6da7bba55899
MD5 c07e597548da3a6754714543832a9ded
BLAKE2b-256 6a19ffcbd7d64979d3a1b2d851aa5809e7ca2fff6a746b71daa8af586852202d

See more details on using hashes here.

File details

Details for the file GML-3.0.5-py3-none-any.whl.

File metadata

  • Download URL: GML-3.0.5-py3-none-any.whl
  • Upload date:
  • Size: 15.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.23.0 setuptools/46.4.0.post20200518 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.8.3

File hashes

Hashes for GML-3.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 a6b9464b63e8cb6754559ff42a6e6d81ff76a3ecd8707b7e8d7c9cee5d8d91ee
MD5 7d0c2009033ad81a787041d3e4c83b5c
BLAKE2b-256 bbea4aa93a49a424cb0f0fad1abfb7c49b68d4d26448ca03908cc95fa19cad16

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page