load_nlp_data.py

load_nlp_data.py

from arcgis.learn import prepare_data
from arcgis.learn import EntityRecognizer
import re
import os
import pandas as pd
from arcgis.gis import GIS
from arcgis.raster.functions import colormap
from arcgis.geocoding import batch_geocode
import zipfile,unicodedata
from itertools import repeat


## Put the path to the downloaded or created json file from Doccano here
json_path = os.path.join("data", "EntityRecognizer", "labelled_crime_reports.json")

## Create the data object to train the model
data = prepare_data(path= json_path, 
                    class_mapping={'address_tag':'Address'}, 
                    dataset_type='ner_json')

## Visualize the batch
data.show_batch()