Skip to main content

Helper functions for all stages of the machine learning model building process

Project description

Welcome to ds11mltoolkit, we are delighted to see you here!

Thank you for your interest, and we hope this library can help you in your daily life as a Data Scientist

Logotipo

Powered by NumFOCUS Powered by NumFOCUS PyPI

Table of contents

  • What is ds11mltoolkit?
  • How to install ds11mltoolkit
  • Dependencies
  • Functions and methods
  • Data Analysis
  • Data visualization and exploration
  • Data processing
  • Machine Learning
  • Github framework
  • Contributors

What is ds11mltoolKit?

It is a Python package that will help you in your first steps as a Data Scientist. "Faster, cleaner, easier" From simple databasis to complex neural networks, this library will accelerate your work processes in all stages of the machine learning cycle.

How to install ds11mltoolkit?

Install as you would normally install a Pypi library.

pip install ds11mltoolkit

We suggest to import ds11mltoolkit as mlt, to make it easier to deploy by the users

import ds11mltoolkit as mlt

Dependencies

ds11mltoolkit requires these libraries to work properly:

  • beautifulsoup4==4.11.1
  • imblearn==0.0
  • keras==2.11.0
  • matplotlib==0.1.6
  • nltk==3.8.1
  • opencv-python-headless==4.7.0.68
  • pandas==1.3.5
  • Pillow==9.3.0
  • plotly==5.11.0
  • requests==2.28.1
  • scikit-image==1.0.2
  • scikit-learn==0.19.3
  • scipy==1.7.3
  • seaborn==0.12.1
  • selenium==4.7.2
  • tensorflow==2.11.0
  • wordcloud==1.7.0

Functions and methods

In the current version, ds11mltoolkit will provide users around 40 functions, divided in 4 groups:

Data Analysis

  • read_url
  • read_csv_zip
  • chi_squared_test

Data visualisation and exploration

  • heatmap
  • sunburst
  • correl_map_max
  • plot_map
  • plot_ngram
  • wordcloudviz
  • plot_cumulative_variance_ratio
  • plot_roc_cruve
  • plot_multiclass_prediction_image

Data processing

  • list_categorical_columns
  • last_columns
  • uniq_value
  • load_imgs
  • class ImageDataGen(ImageDataGenerator) 3-in-1 functions
  • clean_text
  • processing_model_classification
  • replace_convert_numeric
  • log_transform_numeric
  • add_previous
  • _exponential_smooth
  • Nan treatment
  • convert_to_numeric
  • auto_dtype_converter
  • winner_loser
  • lstm_model

Machine Learning

  • export_model
  • import_model
  • worst_params
  • load_model_zip
  • quickregression
  • polynomial_features_non_binary
  • balance_binary_target
  • image_scrap
  • create_multiclass_prediction_df
  • show_scoring
  • predict_model_classification
  • Unsupervised KMeans
  • UnsupervisedPCA

Quick example


df = pd.DataFrame(data= {'Cities': ['Madrid', 'Barcelona'], 
                            'Teams': ['Team 1', 'Team 2'],
                            'Players': ['Vinicius', 'Pedri'],
                            'Goals': [10, 9]})


def list_categorical_columns(df):
    '''
    Function that returns a list with the names of the categorical columns of a dataframe.

    Parameters
    ----------
    df : dataframe
    
    Return
    ----------
        features: list of names

    '''
    features = []

    for c in df.columns:
        t = str(df[c].dtype)
        if "object"  in t:
            features.append(c)
    return features

list_categorical_columns(df)

output: ['Cities', 'Teams', 'Players']


Github framework

Logotipo

Contributors

License

ds11mltoolkit uses an “Interface-Protection Clause” on top of the MIT license. This library is free for personal use. Therefore, it can be used for both commercial and non-commercial purpose.

See license

Please don't hesitate to contact us if you have any questions or comments. Thank you for using our library!

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

ds11mltoolkit-1.8.tar.gz (26.8 kB view details)

Uploaded Source

File details

Details for the file ds11mltoolkit-1.8.tar.gz.

File metadata

  • Download URL: ds11mltoolkit-1.8.tar.gz
  • Upload date:
  • Size: 26.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.13

File hashes

Hashes for ds11mltoolkit-1.8.tar.gz
Algorithm Hash digest
SHA256 fe0c0ba80070acf6df9a5356707acdd7d1c11eb8fa162194465069947d598355
MD5 54418f9de89cd7f89fe84cb2c76038c2
BLAKE2b-256 1f983700acbeaef3134169f1402bd0b83498ec07e6eca498e3e005dd11d4c9e4

See more details on using hashes here.

Supported by

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