Download spacy model if not found

- add install info to README
- remove explicit spacy download step from CI
- uncomment data_manager_test cells

.github/workflows/ci.yml

@@ -20,20 +20,19 @@ jobs:
       uses: actions/checkout@v3
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         python -m pip install -e .
-        python -m spacy download de_core_news_sm
     - name: Run pytest
       run: |
         cd moralization
         python -m pytest -s --cov=. --cov-report=xml
     - name: Upload coverage
-      uses: codecov/codecov-action@v1
+      uses: codecov/codecov-action@v3
       with:
         fail_ci_if_error: true
         files: moralization/coverage.xml

README.md

@@ -10,8 +10,14 @@ Automated identification of text structures related to moralization.
 
 **_This project is currently under development!_**
 
+## Installation
+
+```
+pip install git+https://github.com/ssciwr/moralization.git
+```
+
 ## Example notebooks
-Here you can find afew short introduction notebooks on google colab.
+Here you can find a few short introduction notebooks on google colab.
 - [DemoNotebook_statistics](https://colab.research.google.com/github/ssciwr/moralization/blob/main/notebooks/DemoNotebook_statistics.ipynb)
 
 - [DemoNotebook_interactive_plots](https://colab.research.google.com/github/ssciwr/moralization/blob/main/notebooks/DemoNotebook_interactive_plots.ipynb)

moralization/input_data.py

@@ -9,6 +9,14 @@
 from lxml.etree import XMLSyntaxError
 import spacy
 
+try:
+    import de_core_news_sm
+except ImportError:
+    logging.warning(
+        "Required Spacy model 'de_core_news_sm' was not found. Attempting to download it.."
+    )
+    spacy.cli.download("de_core_news_sm")
+    import de_core_news_sm
 
 pkg = importlib_resources.files("moralization")
 
@@ -127,7 +135,7 @@ def cas_to_doc(cas, ts):
             #       "KAT5Ausformulierung": "KAT5-Forderung implizit",
             #       "Kommentar": "KOMMENTAR",
         }
-        nlp = spacy.load("de_core_news_sm")
+        nlp = de_core_news_sm.load()
         doc = nlp(cas.sofa_string)
 
         doc_train = nlp(cas.sofa_string)

notebooks/data_manager_test.ipynb

@@ -3,11 +3,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "aab49754-7b6b-479d-aa49-ae2564199337",
+   "id": "65049175",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from moralization.data_manager import DataManager\n"
+    "from moralization.data_manager import DataManager"
    ]
   },
   {
@@ -17,7 +17,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_manager = DataManager(\"./../moralization/data/\")\n"
+    "data_manager = DataManager(\"./../moralization/data/\")"
    ]
   },
   {
@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.return_analyzer_result(\"frequency\")\n"
+    "data_manager.return_analyzer_result(\"frequency\")"
    ]
   },
   {
@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.return_analyzer_result(\"length\")"
+    "data_manager.return_analyzer_result(\"length\")"
    ]
   },
   {
@@ -47,7 +47,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.return_analyzer_result(\"span_distinctiveness\")\n"
+    "data_manager.return_analyzer_result(\"span_distinctiveness\")"
    ]
   },
   {
@@ -57,7 +57,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.return_analyzer_result(\"boundary_distinctiveness\")\n"
+    "data_manager.return_analyzer_result(\"boundary_distinctiveness\")"
    ]
   },
   {
@@ -67,7 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.occurence_analysis(\"table\")"
+    "data_manager.occurence_analysis(\"table\")"
    ]
   },
   {
@@ -77,7 +77,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.occurence_analysis(\"corr\")"
+    "data_manager.occurence_analysis(\"corr\")"
    ]
   },
   {
@@ -87,7 +87,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.occurence_analysis(\"heatmap\")"
+    "data_manager.occurence_analysis(\"heatmap\")"
    ]
   },
   {
@@ -97,7 +97,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.interactive_analysis().show()"
+    "data_manager.interactive_analysis().show()"
    ]
   },
   {
@@ -107,7 +107,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.visualize_data(\"all\", spans_key=\"task1\")"
+    "data_manager.visualize_data(\"all\", spans_key=\"task1\")"
    ]
   },
   {
@@ -117,7 +117,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.export_data_DocBin()"
+    "data_manager.export_data_DocBin()"
    ]
   },
   {
@@ -127,8 +127,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.spacy_train(working_dir = \".\", config=\"../moralization/data/config.cfg\", n_epochs = 20)\n",
-    "# data_manager.spacy_import_model(\"./output/model-best\")"
+    "data_manager.spacy_train(working_dir=\".\", config=\"../moralization/data/config.cfg\", n_epochs=20)\n",
+    "data_manager.spacy_import_model(\"./output/model-best\")"
    ]
   },
   {
@@ -138,7 +138,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.spacy_validation()"
+    "data_manager.spacy_validation()"
    ]
   },
   {
@@ -148,7 +148,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# data_manager.spacy_test_string(\"Dies ist ein toller test\")"
+    "data_manager.spacy_test_string(\"Dies ist ein toller test\")"
    ]
   },
   {
@@ -176,7 +176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.10"
   }
  },
  "nbformat": 4,