Vectorizers: Transform unstructured data into vectors

There are a large number of machine learning tools for effectively exploring and working with data that is given as vectors (ideally with a defined notion of distance as well). There is also a large volume of data that does not come neatly packaged as vectors. It could be text data, variable length sequence data (either numeric or categorical), dataframes of mixed data types, sets of point clouds, or more. Usually, one way or another, such data can be wrangled into vectors in a way that preserves some relevant properties of the original data. This library seeks to provide a suite of a wide variety of general purpose techniques for such wrangling, making it easier and faster for users to get various kinds of unstructured sequence data into vector formats for exploration and machine learning.

Taxonomy of sequences

• Variable Length Sequences
  • Sequence Types
• Vectorizer Functions

Quick Start

• Quick Start with Vectorizers
  • Installing
  • Basic Usage

Getting Started Tutorials

• Rich Document Vectors
  • Step 0: Tokenization
  • Step 1: Generate Word Vectors
  • Step 2: Generate Simple Document Vectors Using the Learned Vocabulary
  • Step 3a: Combine Word and Document Vectors with WassersteinVectorizer
  • Step 3b: Combine Word and Document Vectors with SinkhornVectorizer
  • Step 3c: Combine Word and Document Vectors with ApproximateWassersteinVectorizer
  • Compare the Different Document Vectors
• CategoricalColumnTransformer
  • Import Some libraries¶
  • Let’s fetch some data¶
  • Restructure our Data
  • Look at your data

Example Use Cases

• Sequences of Multi-labelled data
  • Import Some libraries
  • Let’s fetch some data
  • Restructure our data
  • MultiSetCooccurrenceVectorizer
• Measuring similarity between categorical data records
  • Representation
  • Import Some libraries
  • Let’s fetch some data
  • Restructure our data
  • Drug ingredient data
  • Combine our series
  • Ngram Vectorizer
  • Count the matches
  • Embedd our data into a metric space and visualize

API Reference:

• Vectorizers API
  • Ngram and Skipgram Vectorizer
  • TokenCooccurrenceVectorizers
  • Wasserstein style Vectorizers
  • Utility Vectorizers and Transformers
  • Time Series Vectorizers and Transformers