farglot 0.1.1

A Transformer-based SocialNLP toolkit for Farcaster

FarGlot

A Transformer-based SocialNLP toolkit for Farcaster.

Installation

pip install farglot

Examples

from farglot import CastAnalyzer

sentiment_analyzer=CastAnalyzer.sequence_analzyer_from_model_name(
    hub_address="nemes.farcaster.xyz:2283",
    model_name="pysentimiento/robertuito-sentiment-analysis"
)

sentiment_analyzer.predict_cast(fid=2, hash_hex="0x0bcdcbf006ec22b79f37f2cf2a09c33413883937")
# ...
sentiment_analyzer.predict_casts_by_fid(fid=2)
# [...]

Generate a Training Set from a Hub

Install the FarGlot CLI

pip install farglot[cli]

Define Training Set Columns

{
  "name": "labels",
  "default_value": 1 // optional
}

For multilabel classfication:

[
  {
    "name": "column_one",
    "default_value": 1 // optional
  },
  {
    "name": "column_two",
    "default_value": 2 // optional
  },
  {
    "name": "column_three",
    "default_value": 3 // optional
  }
]

Usage

farglot init
farglot set-columns-path /path/to/column_configs.json
farglot set-hub-db-path /path/to/.rocks/rocks.hub._default
farglot new-training-set --out ./data/training-set.csv

This largely is largely adapted off of pysentimiento.