Merge pull request #36 from dataiku/chore/dss12-sc-132126-nlp-analysi…

…s-aiml-necessary-update Add support for python v3.8 to v3.10
dataiku · Apr 27, 2023 · 9fd7c27 · 9fd7c27
2 parents a17eb0e + 3ca15c4
commit 9fd7c27
Show file tree

Hide file tree

Showing 5 changed files with 10 additions and 5 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,8 @@
 # Changelog
 
+## [Version 0.2.0](https://github.com/dataiku/dss-plugin-nlp-analysis/releases/tag/v0.2.0)
+- Add support for python v3.8 to v3.10
+
 ## [Version 0.1.1](https://github.com/dataiku/dss-plugin-nlp-analysis/releases/tag/v0.1.1)
 - Fix sudachipy version not being compatible with python 3.6 anymore
 

diff --git a/LICENSE b/LICENSE
@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2021 Dataiku
+   Copyright 2023 Dataiku
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

diff --git a/code-env/python/desc.json b/code-env/python/desc.json
@@ -1,10 +1,13 @@
 {
     "acceptedPythonInterpreters": [
         "PYTHON36",
-        "PYTHON37"
+        "PYTHON37",
+        "PYTHON38",
+        "PYTHON39",
+        "PYTHON310"
     ],
     "forceConda": false,
     "installCorePackages": true,
     "installJupyterSupport": true,
-    "corePackagesSet": "PANDAS10"
+    "corePackagesSet": "AUTO"
 }
diff --git a/plugin.json b/plugin.json
@@ -1,6 +1,6 @@
 {
     "id": "nlp-analysis",
-    "version": "0.1.1",
+    "version": "0.2.0",
     "meta": {
         "label": "Text Analysis",
         "category": "Natural Language Processing",

diff --git a/python-lib/nlp/spacy_tokenizer.py b/python-lib/nlp/spacy_tokenizer.py
@@ -26,7 +26,6 @@
     SPACY_LANGUAGE_MODELS_MORPHOLOGIZER,
 )
 from utils.cleaning_utils import generate_unique, truncate_text_list
-from utils.cleaning_utils import truncate_text_list
 
 # Setting custom spaCy token extensions to allow for easier filtering in downstream tasks
 Token.set_extension("is_hashtag", getter=lambda token: token.text[0] == "#", force=True)