Merge pull request #44 from JohnSnowLabs/3.0rc1

3.0rc1
JohnSnowLabs · Apr 19, 2021 · c3dd901 · c3dd901
2 parents 619d072 + 7341225
commit c3dd901
Show file tree

Hide file tree

Showing 234 changed files with 15,554 additions and 3,859 deletions.
diff --git a/.github/workflows/nlu_test_flow.yaml b/.github/workflows/nlu_test_flow.yaml
@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6]
+        python-version: [3.7]
     steps:
       - uses: actions/setup-java@v1
         with:
@@ -23,12 +23,14 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install pypandoc sklearn
-          pip install  wheel nlu  pytest modin[ray] pyspark==2.3.4
+          pip install  wheel  dataclasses pandas numpy pytest modin[ray] pyspark==3.0.1 spark-nlp==3.0.1
+          java -version
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-      - name: NLU Basic Component tests
-        if: always()
-        run: |
-          python -m unittest  discover   -s './tests/nlu_core_tests/component_tests/basic_component_tests' -p '*tests.py'
+#          ! echo 2 |  update-alternatives --config java
+#      - name: NLU Basic Component tests
+#        if: always()
+#        run: |
+#          python -m unittest  discover   -s './tests/nlu_core_tests/component_tests/basic_component_tests' -p '*tests.py'
       - name: NLU Chunker Component tests
         if: always()
         run: |
@@ -89,10 +91,10 @@ jobs:
         if: always()
         run: |
           python -m unittest  discover   -s './tests/nlu_core_tests/component_tests/pre_processing_tests' -p '*tests.py'
-      - name: NLU Matcher Component tests
-        if: always()
-        run: |
-          python -m unittest  discover   -s 'tests/nlu_core_tests/component_tests/matcher_tests' -p '*tests.py'
+#      - name: NLU Matcher Component tests # not yet converted in Spark 3
+#        if: always()
+#        run: |
+#          python -m unittest  discover   -s 'tests/nlu_core_tests/component_tests/matcher_tests' -p '*tests.py'
       - name: NLU Typed Dependency Component tests -
         if: always()
         run: |
@@ -114,14 +116,14 @@ jobs:
       #        if: always()
       #        run: |
       #          python -m unittest  discover   -s './tests/nlu_core_tests/training_tests/classifiers' -p '*classifier_dl*.py'
-      - name: NLU Training multi classifier tests
-        if: always()
-        run: |
-          python -m unittest  discover   -s './tests/nlu_core_tests/training_tests/classifiers' -p '*multi*.py'
-      - name: NLU Training NER tests
-        if: always()
-        run: |
-          python -m unittest  discover   -s './tests/nlu_core_tests/training_tests/classifiers' -p '*ner*.py'
+#      - name: NLU Training multi classifier tests
+#        if: always()
+#        run: |
+#          python -m unittest  discover   -s './tests/nlu_core_tests/training_tests/classifiers' -p '*multi*.py'
+#      - name: NLU Training NER tests
+#        if: always()
+#        run: |
+#          python -m unittest  discover   -s './tests/nlu_core_tests/training_tests/classifiers' -p '*ner*.py'
       - name: NLU Training POS tests
         if: always()
         run: |

diff --git a/.gitignore b/.gitignore
@@ -4,7 +4,8 @@ dist
 nlu.egg-info
 .sass-cache
 personal_notes.md
-
+/tests/nlu_hc_tests/secrets.py
+/tests/nlu_hc_tests/spark_nlp_for_healthcare.json
 
 # Created by https://www.gitignore.io/api/sbt,java,scala,python,eclipse,intellij,intellij+all
 

diff --git a/docs/Gemfile.lock b/docs/Gemfile.lock
@@ -21,8 +21,8 @@ GEM
     em-websocket (0.5.2)
       eventmachine (>= 0.12.9)
       http_parser.rb (~> 0.6.0)
-    ethon (0.12.0)
-      ffi (>= 1.3.0)
+    ethon (0.13.0)
+      ffi (>= 1.15.0)
     eventmachine (1.2.7)
     eventmachine (1.2.7-x64-mingw32)
     execjs (2.7.0)
@@ -31,8 +31,8 @@ GEM
       multipart-post (>= 1.2, < 3)
       ruby2_keywords
     faraday-net_http (1.0.1)
-    ffi (1.14.2)
-    ffi (1.14.2-x64-mingw32)
+    ffi (1.15.0)
+    ffi (1.15.0-x64-mingw32)
     forwardable-extended (2.6.0)
     gemoji (3.0.1)
     github-pages (192)
@@ -208,12 +208,12 @@ GEM
       jekyll (~> 3.5)
       jekyll-feed (~> 0.9)
       jekyll-seo-tag (~> 2.1)
-    minitest (5.14.3)
+    minitest (5.14.4)
     multipart-post (2.1.1)
-    nokogiri (1.11.1)
+    nokogiri (1.11.3)
       mini_portile2 (~> 2.5.0)
       racc (~> 1.4)
-    nokogiri (1.11.1-x64-mingw32)
+    nokogiri (1.11.3-x64-mingw32)
       racc (~> 1.4)
     octokit (4.20.0)
       faraday (>= 0.9)

diff --git a/docs/_data/navigation.yml b/docs/_data/navigation.yml
@@ -23,11 +23,13 @@ docs-en:
         url:    /docs/en/install
       - title:  General Concepts
         url:    /docs/en/concepts
-      - title:  Simple Examples
+      - title:  Examples
         url:    /docs/en/examples
+      - title:  NLU for Healthcare Examples
+        url:    /docs/en/examples_hc
       - title:  Training Models
         url:    /docs/en/training
-      - title:  Notebooks
+      - title:  Notebook tutorials
         url:    /docs/en/notebooks
       - title:  Visualization Examples
         url:    /docs/en/viz_examples

diff --git a/docs/en/examples_healthcare.md b/docs/en/examples_healthcare.md
diff --git a/docs/en/install.md b/docs/en/install.md
@@ -17,14 +17,7 @@ If you work on a fresh Notebook on Kaggle or Google colab, you can just copy pas
 will automatically setup Java, nlu and import nlu, so you are good to go right away!
 
 ```bash
-import os
-! apt-get update -qq > /dev/null   
-# Install java
-! apt-get install -y openjdk-8-jdk-headless -qq > /dev/null
-os.environ["JAVA_HOME"] = "/usr/lib/jvm/java-8-openjdk-amd64"
-os.environ["PATH"] = os.environ["JAVA_HOME"] + "/bin:" + os.environ["PATH"]
-! pip install nlu pyspark==2.4.7
-import nlu
+!wget https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/scripts/colab_setup.sh -O - | bash
 ```
 You can test it out right away with :
 ```python