add paths as py args

inject.sh

@@ -1,3 +1,15 @@
 #!/bin/bash
 
-. ./scripts/do_inject_helper.sh
+# NOTE: this script is meant to be run from ~
+
+# arguments:
+# 1. path to glossary file, E.g. for glossary in ~/data/glossary.tsv should be data/glossary.tsv
+# 2. path to in.tsv file
+# 3. path to expected.tsv file
+# all path should be given as absolute path without ~/ at the very beginning (as seen in the example above)
+
+glossary_path="$1"
+in_path="$2"
+expected_path="$3"
+
+. ./transfix-mt/scripts/do_inject.sh "$glossary_path" "$in_path" "$expected_path"

rapidfuzztest.ipynb

@@ -97,21 +97,6 @@
     }
    }
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "        if len(file_lemmatized) % 50000 == 0:\n",
-    "            print('lemmatizing file: ' + train_in_path + ': ' + str(len(file_lemmatized)), end='\\r')"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   }
-  },
   {
    "cell_type": "code",
    "execution_count": 4,