Improving Representations via Similarities

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
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

Junhua Zou 7 Oct 20, 2022
Script that creates graphical representations of Julia an Mandelbrot sets.

Julia and Mandelbrot Picture Maker This simple functions create simple plots of the Julia and Mandelbrot sets. The Julia set require the important par

Juan Riera Gomez 1 Jan 10, 2022
Project repository of Apache Airflow, deployed on Docker in Amazon EC2 via GitLab.

Airflow on Docker in EC2 + GitLab's CI/CD Personal project for simple data pipeline using Airflow. Airflow will be installed inside Docker container,

Ammar Chalifah 13 Nov 29, 2022
Site de gestion de cave à vin utilisant une BDD manipulée avec SQLite3 via Python

cave-vin Site de gestion de cave à vin utilisant une bdd manipulée avec MySQL ACCEDER AU SITE : Pour accéder à votre cave vous aurez besoin de lancer

Elouann Lucas 0 Jul 5, 2022
Python Function to manage users via SCIM

Python Function to manage users via SCIM This script helps you to manage your v2 users. You can add and delete users or groups, add users to groups an

null 4 Oct 11, 2022
🤖️ Plugin for Sentry which allows sending notification via DingTalk robot.

Sentry DingTalk Sentry 集成钉钉机器人通知 Requirments sentry >= 21.5.1 特性 发送异常通知到钉钉 支持钉钉机器人webhook设置关键字 配置环境变量 DINGTALK_WEBHOOK: Optional(string) DINGTALK_CUST

null 1 Nov 4, 2021
Tool for working with Direct System Calls in Cobalt Strike's Beacon Object Files (BOF) via Syswhispers2

Tool for working with Direct System Calls in Cobalt Strike's Beacon Object Files (BOF) via Syswhispers2

null 150 Dec 31, 2022
A small project of two newbies, who wanted to learn something about Python language programming, via fun way.

HaveFun A small project of two newbies, who wanted to learn something about Python language programming, via fun way. What's this project about? Well.

Patryk Sobczak 2 Nov 24, 2021
Access Modbus RTU via API call to Sungrow WiNet-S

SungrowModbusWebClient Access Modbus RTU via API call to Sungrow WiNet-S Class based on pymodbus.ModbusTcpClient, completely interchangeable, just rep

null 8 Oct 30, 2022
A python API act as Control Center to control your Clevo Laptop via wmi on windows.

ClevoPyControlCenter A python API act as Control Center to control your Clevo Laptop via wmi on windows. Usage # pip3 install pymi from clevo_wmi impo

null 3 Sep 19, 2022
This package tries to emulate the behaviour of syntax proposed in PEP 671 via a decorator

Late-Bound Arguments This package tries to emulate the behaviour of syntax proposed in PEP 671 via a decorator. Usage Mention the names of the argumen

Shakya Majumdar 0 Feb 6, 2022
Anonfiles files leaker via keyword.

Anonfiles files leaker via keyword

Trac3D1y 6 Nov 23, 2022
Code for Crowd counting via unsupervised cross-domain feature adaptation.

CDFA-pytorch Code for Unsupervised crowd counting via cross-domain feature adaptation. Pre-trained models Google Drive Baidu Cloud : t4qc Environment

Guanchen Ding 6 Dec 11, 2022
Auto check in via GitHub Actions

因为本人毕业离校,本项目交由在校的@hfut-xyc同学接手,请访问hfut-xyc/hfut_auto_check-in获得最新的脚本 本项目遵从GPLv2协定,Copyright (C) 2021, Fw[a]rd 免责声明 根据GPL协定,我、本项目的作者,不会对您使用这个脚本带来的任何后果

Fw[a]rd 3 Jun 27, 2021
Alerts for Western Australian Covid-19 exposure locations via email and Slack

WA Covid Mailer Sends alerts from Healthy WA's Covid19 Exposure Locations via email and slack. Setup Edit the configuration items in wacovidmailer.py

null 13 Mar 29, 2022
LinuxHelper - A collection of utilities for non-technical Linux users accessible via a GUI

Linux Helper A collection of utilities for non-technical Linux users accessible via a GUI This app is still in very early development, expect bugs and

Seth 7 Oct 3, 2022
Send notifications created in Frappe or ERPNext as push notication via Firebase Cloud Message(FCM)

FCM Notification for ERPNext Send notifications created in Frappe or ERPNext as push notication via Firebase Cloud Message(FCM) Steps to use the app:

Tridz 9 Nov 14, 2022
This repo presents you the official code of "VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention"

VISTA VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention Shengheng Deng, Zhihao Liang, Lin Sun and Kui Jia* (*) Corresponding a

null 104 Dec 29, 2022
Simple Similarities Service

simsity Simsity is a Super Simple Similarities Service[tm]. It's all about building a neighborhood. Literally! This repository contains simple tools t

vincent d warmerdam 95 Dec 25, 2022
Super Simple Similarities Service

Super Simple Similarities Service

vincent d warmerdam 95 Dec 25, 2022