English BertForSequenceClassification Cased model (from sampathkethineedi)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. industry-classification-api is a English model originally trained by sampathkethineedi.

Predicted Entities

Electronic Equipment & Instruments, Commodity Chemicals, Leisure Products, Health Care Services, Regional Banks, Life Sciences Tools & Services, Industrial Machinery, Gold, Investment Banking & Brokerage, Restaurants, Packaged Foods & Meats, IT Consulting & Other Services, Oil & Gas Equipment & Services, Health Care Supplies, Aerospace & Defense, Human Resource & Employment Services, Application Software, Property & Casualty Insurance, Movies & Entertainment, Oil & Gas Storage & Transportation, Apparel Retail, Electrical Components & Equipment, Consumer Finance, Construction Machinery & Heavy Trucks, Technology Hardware, Storage & Peripherals, Advertising, Casinos & Gaming, Construction & Engineering, Systems Software, Auto Parts & Equipment, Data Processing & Outsourced Services, Specialty Stores, Research & Consulting Services, Oil & Gas Exploration & Production, Hotels, Resorts & Cruise Lines, Pharmaceuticals, Interactive Media & Services, Homebuilding, Building Products, Personal Products, Electric Utilities, Communications Equipment, Trading Companies & Distributors, Health Care Equipment, Apparel, Accessories & Luxury Goods, Semiconductors, Internet & Direct Marketing Retail, Environmental & Facilities Services, Thrifts & Mortgage Finance, Diversified Metals & Mining, Oil & Gas Refining & Marketing, Steel, Diversified Support Services, Technology Distributors, Health Care Facilities, Health Care Technology, Biotechnology, Integrated Telecommunication Services, Real Estate Operating Companies, Internet Services & Infrastructure, Asset Management & Custody Banks, Specialty Chemicals

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")

sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_industry_classification_api","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")

val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_industry_classification_api","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

References

• https://huggingface.co/sampathkethineedi/industry-classification-api