Adds models md to Models Hub for 3.3.2 Healthcare release #6434

josejuanmartinez · 2021-11-08T16:02:08Z

Description

Adds md models to Models Hub for 3.3.2 Healthcare release

Motivation and Context

Healthcare is releasing 3.3.2, and several models have been uploaded to the Hub. For these new models, we need to merge the md files.

How Has This Been Tested?

Checking models are downloadable and documentation looks ok.

Screenshots (if appropriate):

Types of changes

Bug fix (non-breaking change which fixes an issue)
Code improvements with no or little impact
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

My code follows the code style of this project.
My change requires a change to the documentation.
I have updated the documentation accordingly.
I have read the CONTRIBUTING page.
I have added tests to cover my changes.
All new and existing tests passed.

Fixes the reference to the model in the python code section. Also adds a missing "clinical/models" path for properly retrieving the model from S3

Adds missing quote in python and scala code sections

Included models updated.

Included models part updated.

Sample results updated.

After moving roberta embeddings to public, the code examples should change

Adds the 'es' language tag to pretrained in scala code

…ical_en

The ER header was 'icd10_code' when it should be 'snomed_code'

Adds more indentation to benchmarking section

Fixing indentation in results section

`roberta_base_biomedical` is not part of Healthcare suit, it's opensource, so no "clinical/models" reference required.

There was an incorrect quote in a word. This commit fixes it.

Removes extra quotes in some code examples (modelshub already add the format quotes automatically)

Adds a simplified version of the pipeline reusing several components

…lassifier_sms_spam_en_0icA25SKfssRbsuTayHliLje 2021-11-07-bert_sequence_classifier_sms_spam_en

fixing scala script

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_age_news_en.md

josejuanmartinez · 2021-11-09T10:49:57Z

docs/_posts/murat-gunay/2021-11-06-bert_sequence_classifier_trec_coarse_en.md

+
+## Data Source
+
+[https://huggingface.co/aychang/bert-base-cased-trec-coarse](https://huggingface.co/aychang/bert-base-cased-trec-coarse)


There are metrics available:

josejuanmartinez · 2021-11-09T10:53:04Z

docs/_posts/murat-gunay/2021-11-06-bert_sequence_classifier_hatexplain_en.md

+
+## Data Source
+
+[https://huggingface.co/Hate-speech-CNERG/bert-base-uncased-hatexplain](https://huggingface.co/Hate-speech-CNERG/bert-base-uncased-hatexplain)


There are metrics here:

Use AUCROC BERT-HateXplain [LIME]

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_banking77_en.md

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_sms_spam_en.md

josejuanmartinez · 2021-11-09T10:55:04Z

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_sms_spam_en.md

+
+## Data Source
+
+[https://huggingface.co/mrm8488/bert-tiny-finetuned-sms-spam-detection](https://huggingface.co/mrm8488/bert-tiny-finetuned-sms-spam-detection)


We have metrics in HF:

josejuanmartinez · 2021-11-09T10:55:38Z

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_song_lyrics_en.md

+
+pipeline = Pipeline(stages=[document_assembler, tokenizer, sequenceClassifier])
+
+example = spark.createDataFrame([['Because you need me Every single day Trying to find me But you don't know why Trying to find me again But you don't know how Trying to find me again Every single day']]).toDF("text")


This won't work, conflicting ' . Start and finish with "

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_song_lyrics_en.md

josejuanmartinez · 2021-11-09T10:56:32Z

docs/_posts/murat-gunay/2021-11-07-bert_sequence_classifier_song_lyrics_en.md

+
+## Data Source
+
+[https://huggingface.co/juliensimon/autonlp-song-lyrics-18753417](https://huggingface.co/juliensimon/autonlp-song-lyrics-18753417)


We have metrics:

Updating models hub cards description

josejuanmartinez

Now it seems much better. Thank you @gadde5300 !

murat-gunay and others added 30 commits November 3, 2021 13:40

Add model 2021-11-03-bert_token_classifier_ner_cellular_en

1507419

Add model 2021-11-03-robertaresolve_snomed_es

0aeb6c0

Fixes model name in robertaresolve_snomed code

e72b0cf

Fixes the reference to the model in the python code section. Also adds a missing "clinical/models" path for properly retrieving the model from S3

Adds missing quote

9d82062

Adds missing quote in python and scala code sections

Add model 2021-11-03-bert_token_classifier_ner_bionlp_en

6cb2986

update and fix tags

05324a0

Add model 2021-11-03-ner_profiling_biobert_en

f166924

Update 2021-11-03-ner_profiling_biobert_en.md

a21d7d5

Included models updated.

Add model 2021-11-03-ner_profiling_clinical_en

85866ba

Update 2021-11-03-ner_profiling_clinical_en.md

8ecbb5f

Included models part updated.

Update 2021-11-03-ner_profiling_clinical_en.md

eb41c15

Sample results updated.

Add model 2021-11-04-classifierdl_use_sentiment_pipeline_tr

22e34ce

update and fix scala section&tag section

315c26d

Add model 2021-11-04-sbiobertresolve_rxnorm_augmented_en

fbf761e

Updating snomed er code

9be5cd6

After moving roberta embeddings to public, the code examples should change

Adds the 'es' language tag

581158b

Adds the 'es' language tag to pretrained in scala code

Add model 2021-11-05-bert_sequence_classifier_question_statement_clin…

97b8969

…ical_en

Changes bad column header name

90ee94c

The ER header was 'icd10_code' when it should be 'snomed_code'

Add model 2021-11-05-ner_covid_trials_en

b1d3728

Update 2021-11-05-ner_covid_trials_en.md

9b357d9

Add model 2021-11-04-ner_chemd_clinical_en

0d01ea2

Add model 2021-11-04-bert_sequence_classifier_question_statement_en

4259891

Fixes indentation

bf70d5b

Adds more indentation to benchmarking section

Fixing indentation

a4b3d72

Fixing indentation in results section

Add model 2021-11-04-roberta_ner_diag_proc_es

1a2d5fa

Changes document by sentence-level

b300906

Fixes the reference of roberta_base_biomedical

0cf10cd

`roberta_base_biomedical` is not part of Healthcare suit, it's opensource, so no "clinical/models" reference required.

Fixes quote

618df28

There was an incorrect quote in a word. This commit fixes it.

Removes extra quotes in some code examples

d20078d

Removes extra quotes in some code examples (modelshub already add the format quotes automatically)

Simplifies pipeline in the example

9031fca

Adds a simplified version of the pipeline reusing several components

maziyarpanahi added 6 commits November 9, 2021 10:32

Merge pull request #6425 from JohnSnowLabs/2021-11-07-bert_sequence_c…

66be084

…lassifier_sms_spam_en_0icA25SKfssRbsuTayHliLje 2021-11-07-bert_sequence_classifier_sms_spam_en

Merge pull request #6427 from JohnSnowLabs/murat-gunay-patch-8

9ecc0ab

fixing scala script

Merge pull request #6428 from JohnSnowLabs/murat-gunay-patch-9

148a3ee

fixing scala script

Merge pull request #6429 from JohnSnowLabs/murat-gunay-patch-10

dc2e2cb

fixing scala script

Merge pull request #6430 from JohnSnowLabs/murat-gunay-patch-11

2af3fe6

fixing scala script

Merge pull request #6431 from JohnSnowLabs/murat-gunay-patch-12

e4fe3d6

fixing scala script

josejuanmartinez commented Nov 9, 2021

View reviewed changes

galiph and others added 19 commits November 9, 2021 16:55

Add model 2021-11-09-sbiobertresolve_rxnorm_augmented_en

364eaa1

Update 2021-11-05-ner_covid_trials_en.md

140a55d

Update 2021-11-05-ner_covid_trials_en.md

fcebc60

Update 2021-11-05-ner_covid_trials_en.md

c05e98f

Update 2021-11-03-bert_token_classifier_ner_bionlp_en.md

552e403

Update 2021-11-03-bert_token_classifier_ner_cellular_en.md

b81e83c

Update 2021-11-04-ner_chemd_clinical_en.md

4fd7b21

Update 2021-11-04-ner_chemd_clinical_en.md

51bbc2a

Update 2021-11-06-bert_sequence_classifier_antisemitism_en.md

0d60a19

Update 2021-11-07-bert_sequence_classifier_age_news_en.md

af6f337

Update 2021-11-06-bert_sequence_classifier_trec_coarse_en.md

363fb89

Update 2021-11-06-bert_sequence_classifier_hatexplain_en.md

63292eb

Update 2021-11-07-bert_sequence_classifier_banking77_en.md

574c406

Update 2021-11-07-bert_sequence_classifier_sms_spam_en.md

f9e9cd9

Update 2021-11-07-bert_sequence_classifier_song_lyrics_en.md

39f2de5

Update 2021-11-07-bert_sequence_classifier_song_lyrics_en.md

d25dd09

Update 2021-11-07-bert_sequence_classifier_song_lyrics_en.md

d964e99

Update 2021-11-05-ner_covid_trials_en.md

07ade7b

Merge pull request #6444 from JohnSnowLabs/fixing_bugs

f20d463

Updating models hub cards description

JohnSnowLabs deleted a comment from murat-gunay Nov 9, 2021

josejuanmartinez commented Nov 9, 2021

View reviewed changes

josejuanmartinez assigned vkocaman Nov 9, 2021

vkocaman merged commit e6ce8df into master Nov 9, 2021

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Adds models md to Models Hub for 3.3.2 Healthcare release #6434

Adds models md to Models Hub for 3.3.2 Healthcare release #6434

Uh oh!

josejuanmartinez commented Nov 8, 2021

Uh oh!

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Uh oh!

josejuanmartinez Nov 9, 2021

Uh oh!

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Uh oh!

josejuanmartinez Nov 9, 2021

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Uh oh!

josejuanmartinez left a comment

Uh oh!

Uh oh!


		## Data Source

		[https://huggingface.co/aychang/bert-base-cased-trec-coarse](https://huggingface.co/aychang/bert-base-cased-trec-coarse)


		## Data Source

		[https://huggingface.co/Hate-speech-CNERG/bert-base-uncased-hatexplain](https://huggingface.co/Hate-speech-CNERG/bert-base-uncased-hatexplain)


		## Data Source

		[https://huggingface.co/mrm8488/bert-tiny-finetuned-sms-spam-detection](https://huggingface.co/mrm8488/bert-tiny-finetuned-sms-spam-detection)


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

		example = spark.createDataFrame([['Because you need me Every single day Trying to find me But you don't know why Trying to find me again But you don't know how Trying to find me again Every single day']]).toDF("text")


		## Data Source

		[https://huggingface.co/juliensimon/autonlp-song-lyrics-18753417](https://huggingface.co/juliensimon/autonlp-song-lyrics-18753417)

Adds models md to Models Hub for 3.3.2 Healthcare release #6434

Adds models md to Models Hub for 3.3.2 Healthcare release #6434

Uh oh!

Conversation

josejuanmartinez commented Nov 8, 2021

Description

Motivation and Context

How Has This Been Tested?

Screenshots (if appropriate):

Types of changes

Checklist:

Uh oh!

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Choose a reason for hiding this comment

Uh oh!

josejuanmartinez Nov 9, 2021

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Choose a reason for hiding this comment

Uh oh!

josejuanmartinez Nov 9, 2021

Choose a reason for hiding this comment

Uh oh!

Uh oh!

josejuanmartinez Nov 9, 2021

Choose a reason for hiding this comment

Uh oh!

josejuanmartinez left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!