ivyleavedtoadflax

{
  "accountId": null,
  "compute": {
    "accelerator": "cpu",
    "instanceSize": "small",
    "instanceType": "c6i",
    "scaling": {
      "maxReplica": 1,
      "minReplica": 1
    }

ivyleavedtoadflax

stages:
  foo:
    cmd: echo '{"f1-score":0.99}' > f1.json
    metrics:
    - f1.json

ivyleavedtoadflax

stages:
    train:
      cmd: >-
        rasa data validate && 
        rasa train --fixed-model-name ./models/model --out ./
      params: 
        - config.yml:
          - pipeline
          - policies
      deps:

ivyleavedtoadflax

call plug#begin('~/.vim/plugged')

Plug 'jreybert/vimagit'
Plug 'tpope/vim-fugitive'
Plug 'tpope/vim-unimpaired'
Plug 'tpope/vim-sensible'
Plug 'dracula/vim'
Plug 'Vimjas/vim-python-pep8-indent'
Plug 'chrisbra/csv.vim'
Plug 'scrooloose/nerdtree'

ivyleavedtoadflax

# Set prefix to capslock

set -g prefix C-b

# Set defaults

set -s escape-time 1
set -g base-index 1
setw -g pane-base-index 1

ivyleavedtoadflax

# coding: utf-8

import itertools
from itertools import groupby
from operator import itemgetter
from pprint import PrettyPrinter

import plac

from deep_reference_parser.io import read_jsonl, write_jsonl

ivyleavedtoadflax

.DEFAULT_GOAL := files

MATCH_PATH := s3://datalabs-dev/reach-airflow/output/match_annotated_titles
EVAL_PATH := s3://datalabs-dev/reach-airflow/output/policy-test/evaluation/results

eval = evaluation-results.json

PRODIGY_PATH = s3://datalabs-data/reach_evaluation/data/sync

prodigy = 2019.10.8_valid_TITLE.jsonl \

ivyleavedtoadflax

for i in raw/*.json; 
  do 

    # Create new filename

    filename=$(basename -- "$i")
    extension="${filename##*.}"
    filename="${filename%.*}"
    new_filename=processed/refs_${filename}.txt

ivyleavedtoadflax

# Need to run:
# python -m spacy download en 
# from console first to get the model

import spacy
import pandas as pd


nlp = spacy.load("en")

ivyleavedtoadflax

from spacy.util import (compile_prefix_regex, compile_infix_regex, compile_suffix_regex) 

def _custom_tokenizer(self, nlp, regex=[r"[-/,.\n\s]"]):
    """Custom tokenizer to split date formats like 05-05-2015
    and 05/05/2015
    """
    # Use the default prefixes and suffixes
    prefix_re = compile_prefix_regex(nlp.Defaults.prefixes)
    suffix_re = compile_suffix_regex(nlp.Defaults.suffixes)