Improving Representations via Similarities

Related tags

Miscellaneousembetter
Overview

embetter

warning

I like to build in public, but please don't expect anything yet. This is alpha stuff!

notes

Improving Representations via Similarities

The object to implement:

Embetter(multi_output=True, epochs=50, sampling_kwargs)
  .fit(X, y)
  .fit_sim(X1, X2, y_sim, weights)
  .partial_fit(X, y, classes, weights)
  .partial_fit_sim(X1, X2, y_sim, weights)
  .predict(X)
  .predict_proba(X)
  .predict_sim(X1, X2)
  .transform(X)
  .translate_X_y(X, y, classes=none)

Observation: especially when multi_output=True there's an opportunity with regards to NaN y-values. We can simply choose with values to translate and which to ignore.

Comments
  • [WIP] Feature/progress bar

    [WIP] Feature/progress bar

    Fixes issue #20

    • [x] Adds progress bar to all text and image embedders.
    • [x] Tests for SentenceEncoder.
    • [ ] Use perfplot for progress bar?
    • [ ] Can we ensure fast NumPy vectorization while using a progress bar?
    opened by CarloLepelaars 5
  • [BUG] `device` should be attribute on `SentenceEncoder`

    [BUG] `device` should be attribute on `SentenceEncoder`

    The device argument in SentenceEncoder is not defined as an attribute. This leads to bugs when using it with sklearn. I encountered attribute errors when trying to print out a Pipeline representation that has SentenceEncoder as a component.

    Should be easy to fix by just adding self.device in SentenceEncoder.__init__. We can consider adding tests for text encoders so we can catch these errors beforehand.

    The scikit-learn development docs make it clear every argument should be defined as an attribute:

    every keyword argument accepted by init should correspond to an attribute on the instance. Scikit-learn relies on this to find the relevant attributes to set on an estimator when doing model selection.

    Error message: AttributeError: 'SentenceEncoder' object has no attribute 'device'.

    Reproduction: Python 3.8 with embetter = "^0.2.2"

    se = SentenceEncoder()
    repr(se)
    

    Fix:

    Add self.device on SentenceEncoder

    class SentenceEncoder(EmbetterBase):
        .
        .
        def __init__(self, name="all-MiniLM-L6-v2", device=None):
            if not device:
                device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
            self.device = device
            self.name = name
            self.tfm = SBERT(name, device=self.device)
    
    opened by CarloLepelaars 4
  • Color Histograms - Additional Tricks

    Color Histograms - Additional Tricks

    This approach could work pretty well as an implementation: https://danielmuellerkomorowska.com/2020/06/17/analyzing-image-histograms-with-scikit-image/

    To do something similar to what is explained here: https://www.pinecone.io/learn/color-histograms/

    opened by koaning 4
  • Support for word embeddings

    Support for word embeddings

    Hi,

    Do you think it would be a good idea to add support for static word embeddings (word2vec, glove, etc.)? The embedder would need:

    • A filename to a local embedding file (e.g., glove.6b.100d.txt)
    • Either a callable tokenizer or regex string (i.e., the way sci-kit learn's TfIdfVectorizer splits words).
    • A (name of a) pooling function (e.g., "mean", "max", "sum").

    The second and third parameters could easily have sensible defaults, of course. If you think it's a good idea, I can do the PR somewhere next week.

    Stéphan

    opened by stephantul 3
  • [FEATURE] SpaCyEmbedder

    [FEATURE] SpaCyEmbedder

    I think it would be a nice addition to add an embedder that can easily vectorize text through SpaCy. I already have an implementation class for this and would be happy to contribute it here.

    SpaCy Docs on vector: https://spacy.io/api/doc#vector

    Example code for single string:

    import spacy
    nlp = spacy.load("en_core_web_sm")
    doc = nlp("This here text")
    doc.vector
    
    opened by CarloLepelaars 2
  • `get_feature_names_out` for encoders

    `get_feature_names_out` for encoders

    I would be happy to implement get_feature_names_out for all the Embetter objects. I will implement them by just adding a new method (without a Mixin).

    opened by CarloLepelaars 1
  • Remove the classification layer in timm models

    Remove the classification layer in timm models

    I was playing a bit with the library and found out that the TimmEncoder returns 1000-dimensional vectors for all the models I selected. That is caused by returning the state of the last FC classification layer and the fact all of the models were trained on ImageNet with 1000 classes. In practice, it's typically replaced with identity.

    Are there any reasons for returning the state of that last layer as an embedding? I'd be happy to submit a PR fixing that.

    opened by kacperlukawski 1
  • xception mobilenet

    xception mobilenet

    https://keras.io/api/applications/

    https://www.tensorflow.org/api_docs/python/tf/keras/applications/mobilenet_v2/MobileNetV2 https://www.tensorflow.org/api_docs/python/tf/keras/applications/xception/Xception

    opened by koaning 0
  • 'SentenceEncoder' object has no attribute 'device'

    'SentenceEncoder' object has no attribute 'device'

    text_emb_pipeline = make_pipeline(
      ColumnGrabber("text"),
      SentenceEncoder('all-MiniLM-L6-v2')
    )
    
    # This pipeline can also be trained to make predictions, using
    # the embedded features. 
    text_clf_pipeline = make_pipeline(
      text_emb_pipeline,
      LogisticRegression()
    )
    
    dataf = pd.DataFrame({
      "text": ["positive sentiment", "super negative"],
      "label_col": ["pos", "neg"]
    })
    
    X = text_emb_pipeline.fit_transform(dataf, dataf['label_col'])
    text_clf_pipeline.fit(dataf, dataf['label_col'])
    

    This code gives this error: 'SentenceEncoder' object has no attribute 'device'

    opened by nicholas-dinicola 6
Releases(0.2.2)
Owner
vincent d warmerdam
Solving problems involving data. Mostly NLP these days. AskMeAnything[tm].
vincent d warmerdam
A simple python project that can find Tangkeke in a given image.

A simple python project that can find Tangkeke in a given image. Make the real Tangkeke image as a kernel to convolute the target image. The area wher

张志衡 1 Dec 08, 2021
Holographic Declarative Memory for Python ACT-R

HDM This is the repository for the Holographic Declarative Memory (HDM) module for Python ACT-R. This repository contains: documentation: a paper, con

Carleton Cognitive Modeling Lab 1 Jan 17, 2022
Hypothesis strategies for generating Python programs, something like CSmith

hypothesmith Hypothesis strategies for generating Python programs, something like CSmith. This is definitely pre-alpha, but if you want to play with i

Zac Hatfield-Dodds 73 Dec 14, 2022
RangDev Notepad App With Python

RangDev Notepad-App-With-Python Take down quick and speedy notes! This is a small project of a notepad app built with Tkinter and SQLite3. Database cr

rangga.alrasya 1 Dec 01, 2021
This repository contains each day of Advent of Code 2021 that I've done.

Advent of Code - 2021 I will use this repository as my Advent of Code1 (AoC) repo for the 2021 challenge. I'm changing how I am tackling the problems

Brett Chapin 2 Jan 12, 2022
Import modules and files straight from URLs.

Import Python code from modules straight from the internet.

Nate 2 Jan 15, 2022
This repository contains Python Projects for Beginners as well as for Intermediate Developers built by Contributors.

Python Projects {Open Source} Introduction The repository was built with a tree-like structure in mind, it contains collections of Python Projects. Mo

Gaurav Pandey 115 Apr 30, 2022
The learning agent learns firstly approaching to the football and then kicking the football to the target position

Football Court This project utilized Pytorch and Tensorflow so that the learning agent learns firstly approaching to the football and then kicking the

1 Nov 19, 2021
Hacktoberfest2021 🥳- Contribute Any Pattern In Any Language😎 Every PR will be accepted Pls contribute

✨ Hacktober Fest 2021 ✨ 🙂 All Contributors are requested to star this repo and follow me for a successful merge of pull request. 🙂 👉 Add any patter

Md. Almas Ali 103 Jan 07, 2023
Integer sets where all subsets have unique sums

Evil Sums Generation of sets of numbers where all constituents are recoverable from a partial sum.

Charlotte 5 Sep 24, 2022
0CD - BinaryNinja plugin to introduce some quality of life utilities for obsessive compulsive CTF enthusiasts

0CD Author: b0bb Quality of life utilities for obsessive compulsive CTF enthusia

12 Sep 14, 2022
PaintPrint - This module can colorize any text in your terminal

PaintPrint This module can colorize any text in your terminal Author: tankalxat3

Alexander Podstrechnyy 2 Feb 17, 2022
Projects and assets from Wireframe #56

Wireframe56 Projects and assets from Wireframe #56 Make a Boulder Dash level editor in Python, pages 50-57, by Mark Vanstone. Code an homage to Bubble

Wireframe magazine 10 Sep 07, 2022
py-js: python3 objects for max

Simple (and extensible) python3 externals for MaxMSP

Shakeeb Alireza 39 Nov 20, 2022
API wrapper for VCS hosting system.

PythonVCS API wrapper for VCS hosting system. Supported platforms Gitea Github, Gitlab, Bitbucket support will not, until that packages is not updated

MisileLaboratory 1 Apr 02, 2022
A calculator to test numbers against the collatz conjecture

The Collatz Calculator This is an algorithm custom built by Kyle Dickey, used to test numbers against the simple rules of the Collatz Conjecture.

Kyle Dickey 2 Jun 14, 2022
These are my solutions to Advent of Code problems.

Advent of Code These are my solutions to Advent of Code problems. If you want to join my leaderboard, the code is 540750-9589f56d. When I solve for sp

Sumner Evans 5 Dec 19, 2022
Calibre Libgen Non-fiction / Sci-tech store plugin

CalibreLibgenSci A Libgen Non-Fiction/Sci-tech store plugin for Calibre Installation Download the latest zip file release from here Open Calibre Navig

IDDQD 9 Dec 27, 2022
Parser for RISC OS Font control characters in Python

RISC OS Font control parsing in Python This repository contains a class (FontControlParser) for parsing font control codes from a byte squence, in Pyt

Charles Ferguson 1 Nov 02, 2021
Providing a working, flexible, easier and faster installer than the one officially provided by Arch Linux

Purpose The purpose is to bring more people to Arch Linux by providing a working, flexible, easier and faster installer than the one officially provid

André Luís 0 Nov 09, 2022