-
Notifications
You must be signed in to change notification settings - Fork 130
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #263 from JohnSnowLabs/release/531
Release/531
- Loading branch information
Showing
40 changed files
with
3,006 additions
and
28 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
1 change: 1 addition & 0 deletions
1
examples/colab/healthcare/entity_resolution/NLU_atc_resolver_pipeline.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
1 change: 1 addition & 0 deletions
1
examples/colab/healthcare/entity_resolution/NLU_hpo_resolver_pipeline.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
814 changes: 814 additions & 0 deletions
814
...althcare/medical_named_entity_recognition/NLU_explain_clinical_doc_generic_pipeline.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
722 changes: 722 additions & 0 deletions
722
...lthcare/medical_named_entity_recognition/NLU_explain_clinical_doc_oncology_pipeline.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
1 change: 1 addition & 0 deletions
1
...b/healthcare/medical_named_entity_recognition/NLU_explain_clinical_doc_vop_pipeline.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,183 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "markdown", | ||
| "source": [ | ||
| "\n", | ||
| "\n", | ||
| "[](https://colab.research.google.com/github/JohnSnowLabs/nlu/blob/master/examples/colab/ocr/ocr_form_relation_extractor.ipynb)\n", | ||
| "\n", | ||
| "[Tutorial Notebook](https://colab.research.google.com/github/JohnSnowLabs/nlu/blob/master/examples/colab/ocr/ocr_form_relation_extractor.ipynb \"https://colab.research.google.com/github/JohnSnowLabs/nlu/blob/master/examples/colab/ocr/ocr_form_relation_extractor.ipynb\")\n" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "source": [ | ||
| "# **FormRelationExtractor**\n", | ||
| "\n", | ||
| "\n", | ||
| "The **FormRelationExtractor** is a tool designed to identify the relationships between keys and values. It’s particularly useful in the context of data extracted by a Named Entity Recognition (NER) system, such as VisualDocumentNER.\n", | ||
| "\n", | ||
| "**All the available models:**\n", | ||
| "\n", | ||
| "| NLU Spell | Transformer Class |\n", | ||
| "|----------------------|-----------------------------------------------------------------------------------------|\n", | ||
| "| nlu.load(`visual_form_relation_extractor`) | [FormRelationExtractor](https://nlp.johnsnowlabs.com/docs/en/ocr_visual_document_understanding#formrelationextractor) |" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "source": [ | ||
| "## **Install NLU**" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!pip install johnsnowlabs\n", | ||
| "nlp.install(visual=True,force_browser=True)\n", | ||
| "nlp.start(visual=True)" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "source": [ | ||
| "## **Form Relation Extraction**" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 1, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "🚨 Outdated Medical Secrets in license file. Version=5.3.1 but should be Version=5.1.1\n", | ||
| "🚨 Outdated OCR Secrets in license file. Version=5.3.1 but should be Version=5.0.2\n", | ||
| "📋 Loading license number 0 from C:\\Users\\gadde/.johnsnowlabs\\licenses/license_number_0_for_Spark-Healthcare_Spark-OCR.json\n", | ||
| "👷 Trying to install compatible secrets. Use nlp.settings.enforce_versions=False if you want to install outdated secrets.\n", | ||
| "👷 Trying to install compatible secrets. Use nlp.settings.enforce_versions=False if you want to install outdated secrets.\n", | ||
| "👷 Setting up John Snow Labs home in C:\\Users\\gadde/.johnsnowlabs, this might take a few minutes.\n", | ||
| "Downloading 🫘+🚀 Java Library spark-nlp-assembly-5.1.1.jar\n", | ||
| "🙆 JSL Home setup in C:\\Users\\gadde/.johnsnowlabs\n", | ||
| "🤓 Looks like you are missing some jars, trying fetching them ...\n", | ||
| "👷 Trying to install compatible secrets. Use nlp.settings.enforce_versions=False if you want to install outdated secrets.\n", | ||
| "Downloading 🫘+💊 Java Library spark-nlp-jsl-5.1.1.jar\n", | ||
| "Downloading 🫘+🕶 Java Library spark-ocr-assembly-5.0.2.jar\n", | ||
| "🙆 JSL Home setup in C:\\Users\\gadde/.johnsnowlabs\n", | ||
| "👷 Trying to install compatible secrets. Use nlp.settings.enforce_versions=False if you want to install outdated secrets.\n", | ||
| "👌 Launched \u001B[92mcpu optimized\u001B[39m session with with: 🚀Spark-NLP==5.3.1, 💊Spark-Healthcare==5.1.1, 🕶Spark-OCR==5.0.2, running on ⚡ PySpark==3.1.2\n", | ||
| "Warning::Spark Session already created, some configs may not take.\n", | ||
| "Warning::Spark Session already created, some configs may not take.\n", | ||
| "lilt_roberta_funsd_v1 download started this may take some time.\n", | ||
| "Approximate size to download 419.6 MB\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "from johnsnowlabs import nlp,visual\n", | ||
| "model = nlp.load('visual_form_relation_extractor')" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false, | ||
| "ExecuteTime": { | ||
| "end_time": "2024-05-13T08:27:37.781697200Z", | ||
| "start_time": "2024-05-13T08:17:43.901075500Z" | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 4, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "Warning::Spark Session already created, some configs may not take.\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "res = model.predict(['form.png','form2.jpg'])" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 5, | ||
| "outputs": [ | ||
| { | ||
| "data": { | ||
| "text/plain": " form_relation_prediction_key form_relation_prediction_value \\\n0 division allied health \n0 course hce \n0 number 116 \n0 title calculations medical dosage \n0 credits 2 \n0 developed by dr . by taz \n0 lecture / lab lecture / o ratio 2 \n0 course activity no \n0 cip code 51 . 0800 \n0 semester fall and \n0 ge category none \n0 separate lab no \n0 course awareness no \n0 course no \n1 name : dribbler , bbb \n1 study date : 12 - 09 - 2006 , 6 : 34 \n1 bp : 120 / 80 mmhg \n1 mrn : 12341820060912 \n1 patient location : room \n1 hr : 100 bpm \n1 dob : 19 - 06 - 1979 \n1 gender : male \n1 height : 123 cm \n1 age : 27 years \n1 weight : 25 kg \n1 reason for study : mi \n1 bsa : 0 . 92 m \n1 history : asfgfdgsdg \n1 medications : heparine , paracetamol \n1 performed . the study technically limited . \n1 . no \n\n path \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n0 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... \n1 file:/F:/Work/repos/nlu_new/ner/nlu/examples/c... ", | ||
| "text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>form_relation_prediction_key</th>\n <th>form_relation_prediction_value</th>\n <th>path</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>division</td>\n <td>allied health</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>course</td>\n <td>hce</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>number</td>\n <td>116</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>title</td>\n <td>calculations medical dosage</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>credits</td>\n <td>2</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>developed by</td>\n <td>dr . by taz</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>lecture / lab lecture / o ratio</td>\n <td>2</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>course activity</td>\n <td>no</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>cip code</td>\n <td>51 . 0800</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>semester</td>\n <td>fall and</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>ge category</td>\n <td>none</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>separate lab</td>\n <td>no</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>course awareness</td>\n <td>no</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>0</th>\n <td>course</td>\n <td>no</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>name :</td>\n <td>dribbler , bbb</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>study date :</td>\n <td>12 - 09 - 2006 , 6 : 34</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>bp :</td>\n <td>120 / 80 mmhg</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>mrn :</td>\n <td>12341820060912</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>patient location :</td>\n <td>room</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>hr :</td>\n <td>100 bpm</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>dob :</td>\n <td>19 - 06 - 1979</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>gender :</td>\n <td>male</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>height :</td>\n <td>123 cm</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>age :</td>\n <td>27 years</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>weight :</td>\n <td>25 kg</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>reason for study :</td>\n <td>mi</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>bsa :</td>\n <td>0 . 92 m</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>history :</td>\n <td>asfgfdgsdg</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>medications :</td>\n <td>heparine , paracetamol</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>performed .</td>\n <td>the study technically limited .</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n <tr>\n <th>1</th>\n <td>.</td>\n <td>no</td>\n <td>file:/F:/Work/repos/nlu_new/ner/nlu/examples/c...</td>\n </tr>\n </tbody>\n</table>\n</div>" | ||
| }, | ||
| "execution_count": 5, | ||
| "metadata": {}, | ||
| "output_type": "execute_result" | ||
| } | ||
| ], | ||
| "source": [ | ||
| "res_filtered = res[['form_relation_prediction_key','form_relation_prediction_value','path']]\n", | ||
| "res_filtered" | ||
| ], | ||
| "metadata": { | ||
| "collapsed": false, | ||
| "ExecuteTime": { | ||
| "end_time": "2024-05-13T08:40:51.701641600Z", | ||
| "start_time": "2024-05-13T08:40:51.627215600Z" | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "outputs": [], | ||
| "source": [], | ||
| "metadata": { | ||
| "collapsed": false | ||
| } | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "name": "myenv", | ||
| "language": "python", | ||
| "display_name": "myenv" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 2 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython2", | ||
| "version": "2.7.6" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 0 | ||
| } |
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -2752,4 +2752,4 @@ | |
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 0 | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| __version__ = '5.1.5rc19' | ||
| __version__ = '5.3.1' | ||
|
|
||
|
|
||
| import nlu.utils.environment.env_utils as env_utils | ||
|
|
||
Empty file.
8 changes: 8 additions & 0 deletions
8
nlu/ocr_components/form_relation_extractor/form_relation_extractor.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,8 @@ | ||
|
|
||
| class FormRelationExtractor: | ||
| @staticmethod | ||
| def get_default_model(): | ||
| from sparkocr.transformers import FormRelationExtractor | ||
| return FormRelationExtractor() \ | ||
| .setInputCol("text_entity") \ | ||
| .setOutputCol("ocr_relations") |
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,7 @@ | ||
| class HocrTokenizer: | ||
| @staticmethod | ||
| def get_default_model(): | ||
| from sparkocr.transformers import HocrTokenizer | ||
| return HocrTokenizer() \ | ||
| .setInputCol("hocr") \ | ||
| .setOutputCol("text_tokenized") |
Empty file.
Empty file.
8 changes: 8 additions & 0 deletions
8
nlu/ocr_components/visual_ner/visual_document_ner/visual_document_ner.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,8 @@ | ||
| class VisualDocumentNer: | ||
| @staticmethod | ||
| def get_default_model(): | ||
| from sparkocr.transformers import VisualDocumentNer | ||
| return VisualDocumentNer()\ | ||
| .pretrained("lilt_roberta_funsd_v1", "en", "clinical/ocr")\ | ||
| .setInputCols(["text_tokenized", "image"])\ | ||
| .setOutputCol("text_entity") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.