Hugging Face's logo

Northell
/
material-subdomain-classifier

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
material-subdomain-classifier / README.md
stan-northell's picture
stan-northell
Upload folder using huggingface_hub
2f2747c verified
preview code
|
raw
history blame contribute delete
11 kB
metadata
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      hasCreatedDate: 2025-01-08, hasCustomerHomeCountry: United Kingdom,
      hasCustomerID: 14239, hasCustomerName: Asda Stores Ltd(Asda (Spearmint)),
      hasCutting: Cut to shape, hasElementID: 3728622, hasElementTitle: 7341_40
      Showcase Plinth - Small , hasFinishedSizeHeight: 400,
      hasFinishedSizeWidth: 400, hasFlatSizeHeight: 936, hasFlatSizeWidth: 1258,
      hasFscPaperBeenSpecified: No, hasInternalID:
      dadf7de9-5b3b-49f0-a844-ff1c717046e4, hasMachineFinishing: Yes,
      hasMachineFinishingDetails: Die cut and crease, Glue/Tape as required and
      supply flat, hasMaterialCategory: Paper, hasMaterialDescription: E Flute,
      hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 150,
      hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: GSM,
      hasNumberOfVersions: 1, hasPackingRequirements: C&P Campaign, hasPrice:
      338.27 GBP, hasPrintedSides: Single sided, hasProductCategory: FSDU /
      Pallet Wrap / QPD, hasProofType: PDF digital proof, hasQuantity: 52,
      hasQuantityPerVersion: As per brief, hasRecycledContentBeenOffered: N/A,
      hasSupplierName: Simpson Group- Asda POS Only(Simpson Group- Asda POS &
      CCEP Only), hasTotalColours: 4, hasUnitOfMeasure: Millimetres (mm), 
  - text: >-
      hasCreatedDate: 2024-05-21, hasCustomerHomeCountry: United Kingdom,
      hasCustomerID: 14239, hasCustomerName: Asda Stores Ltd(Asda (Spearmint)),
      hasCutting: Trim to size, hasElementID: 3298451, hasElementTitle:
      NRC7346_40 Rotis Serve Over Vinyl, hasFinishedSizeHeight: 670,
      hasFinishedSizeWidth: 490, hasFscPaperBeenSpecified: No, hasInternalID:
      3fcd8a8c-4be3-4c55-bda1-397abc7859d5, hasMaterialCategory: Plastic,
      hasMaterialDescription: 85mic White High Tack Rem Wall and Floor,
      hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 82,
      hasMaterialType: PET, hasMaterialUnitOfMeasure: Microns,
      hasNumberOfVersions: 2, hasPackingRequirements: Please pack as per
      allocation, overs to advanced, hasPrice: 183.96 GBP, hasPrintedSides:
      Single sided, hasProductCategory: Wallpapers/Decals, hasProofType: PDF
      digital proof, hasQuantity: 37, hasQuantityPerVersion: 18 off each,
      hasRecycledContentBeenOffered: N/A, hasSupplierName: Imprint Creative
      Print Solutions Limited(Imprint Creative Print Solutions Limited),
      hasTotalColours: 4, hasUnitOfMeasure: Millimetres (mm), 
  - text: >-
      hasArtworkDoubleSidedStatus: Double Sided Different, hasColourDetails: 4/4
      process, hasCreatedDate: 2024-06-03, hasCustomerHomeCountry: United
      States, hasCustomerID: 31740, hasCustomerName: National Grid  (National
      Grid  ), hasCutting: Trim to size, hasElementID: 3324866, hasElementTitle:
      CM9080 Forestport Event Energy Savings Postcard, hasFinishedSizeHeight: 5,
      hasFinishedSizeWidth: 7, hasFlatSizeHeight: 5, hasFlatSizeWidth: 7,
      hasFscPaperBeenSpecified: No, hasInternalID:
      e5b28942-c487-468c-8c60-fea3076d1ee5, hasMaterialCategory: Paper,
      hasMaterialDescription: matte, hasMaterialRecycledPercentage: 0%,
      hasMaterialThicknessOrWeight: 100, hasMaterialType: Paper and board,
      hasMaterialUnitOfMeasure: Pounds (lbs), hasNumberOfVersions: 1,
      hasPackingRequirements: Ship to, hasPaperType: Cover, hasPrice: 102.56
      USD, hasPrintedSides: Double sided, hasProductCategory: Booklets &
      Brochures, hasProofType: PDF digital proof, hasQuantity: 50,
      hasRecycledContentBeenOffered: No, hasSupplierName: Ansun - HHG Strategic
      Partner(Ansun  - 57666 - HHGSP - US Only), hasTotalColours: 4,
      hasTotalColoursFace: 4, hasUnitOfMeasure: Inches (in), 
  - text: "hasCreatedDate: 2024-10-15, hasCustomerHomeCountry: United States, hasCustomerID: 31735, hasCustomerName: Comcast Corporation(Comcast Corporation), hasCutting: Trim to size, hasElementID: 3568788, hasElementTitle: 2.x Install MWGs, hasFinishedSizeHeight: 101.25, hasFinishedSizeWidth: 96, hasFscPaperBeenSpecified: No, hasInternalID: 0bd0f9f3-3f06-40dc-b947-24e4e5c0c5da, hasMaterialCategory: Paper, hasMaterialDescription: New Life Magnetics .011 White Faced Magnetic Receptive, hasMaterialThicknessOrWeight: 11, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: Millimetres (mm), hasMinimumRecycledContent: 0%, hasNumberOfVersions: 1, hasPackingRequirements: packed with outer carton sticker and guides, hasPrice: 7371 USD, hasPrintedSides: Single sided, hasProductCategory: Banners (synthetic), hasProofType: PDF digital proof, hasQuantity: 45, hasRecycledContentBeenRequested: No, hasSupplierName: LPC\_TX\_VISUAL,\_LLC(LPC TX Visual, LLC/Lewisberg Printing  -HHGSP), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), "
  - text: >-
      hasCreatedDate: 2024-01-04, hasCustomerHomeCountry: United States,
      hasCustomerID: 14458, hasCustomerName: Lowe's Companies Inc(Lowe's FVS),
      hasCutting: Trim to size, hasElementID: 3044610, hasElementTitle: G284498
      Commodity Moulding Profile Card 77991, hasFinishedSizeHeight: 6.875,
      hasFinishedSizeWidth: 3, hasFlatSizeHeight: 6.875, hasFlatSizeWidth: 3,
      hasFscPaperBeenSpecified: No, hasInternalID:
      671d6e41-c7c2-4c42-83ff-d1c87deb890b, hasMaterialCategory: Other,
      hasMaterialDescription: 8PT _C1S Cover, hasMaterialType: Other,
      hasNumberOfVersions: 1, hasPrice: 0.01 USD, hasPrintedSides: Single sided,
      hasProofType: PDF digital proof, hasQuantity: 1,
      hasRecycledContentBeenOffered: N/A, hasSupplierName: HH IC Content
      Production + Development(HH IC Content Production + Development),
      hasTotalColours: 4, hasUnitOfMeasure: Inches (in), 
metrics:
  - f1_micro
  - f1_macro
  - f1_weighted
  - precision
  - accuracy
  - recall
pipeline_tag: text-classification
library_name: setfit
inference: false
model-index:
  - name: SetFit
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Northell/ros-classifiers-materials-flat
          type: unknown
          split: test
        metrics:
          - type: f1_micro
            value: 0.6077289571201694
            name: F1_Micro
          - type: f1_macro
            value: 0.07809866671963865
            name: F1_Macro
          - type: f1_weighted
            value: 0.5583804571604718
            name: F1_Weighted
          - type: precision
            value: 0.9587973356246948
            name: Precision
          - type: accuracy
            value: 0.9869484305381775
            name: Accuracy
          - type: recall
            value: 0.4448463022708893
            name: Recall

SetFit

This is a SetFit model that can be used for Text Classification. A OneVsRestClassifier instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

  1. Fine-tuning a Sentence Transformer with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

  • Model Type: SetFit
  • Classification head: a OneVsRestClassifier instance
  • Maximum Sequence Length: 512 tokens
  • Number of Classes: 44 classes

Model Sources

Evaluation

Metrics

Label F1_Micro F1_Macro F1_Weighted Precision Accuracy Recall
all 0.6077 0.0781 0.5584 0.9588 0.9869 0.4448

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("hasCreatedDate: 2024-01-04, hasCustomerHomeCountry: United States, hasCustomerID: 14458, hasCustomerName: Lowe's Companies Inc(Lowe's FVS), hasCutting: Trim to size, hasElementID: 3044610, hasElementTitle: G284498 Commodity Moulding Profile Card 77991, hasFinishedSizeHeight: 6.875, hasFinishedSizeWidth: 3, hasFlatSizeHeight: 6.875, hasFlatSizeWidth: 3, hasFscPaperBeenSpecified: No, hasInternalID: 671d6e41-c7c2-4c42-83ff-d1c87deb890b, hasMaterialCategory: Other, hasMaterialDescription: 8PT _C1S Cover, hasMaterialType: Other, hasNumberOfVersions: 1, hasPrice: 0.01 USD, hasPrintedSides: Single sided, hasProofType: PDF digital proof, hasQuantity: 1, hasRecycledContentBeenOffered: N/A, hasSupplierName: HH IC Content Production + Development(HH IC Content Production + Development), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), ")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 62 109.9067 637

Framework Versions

  • Python: 3.10.16
  • SetFit: 1.1.1
  • Sentence Transformers: 3.4.1
  • Transformers: 4.49.0
  • PyTorch: 2.6.0+cu124
  • Datasets: 3.2.0
  • Tokenizers: 0.21.0

Citation

BibTeX 

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}