add french training data

.gitignore

@@ -281,3 +281,4 @@ Pipfile.lock
 
 # NER training files
 data/train_NER/1[0-9][0-9][0-9]_20[0-9][0-9][0-9][0-9][0-9][0-9].txt
+data/train_NER/1[0-9][0-9][0-9]_20[0-9][0-9][0-9][0-9][0-9][0-9]_french.txt

src/python/utils_ner.py

@@ -6,7 +6,8 @@ colors = {'ORG': '#73c6b6', 'LOC': '#bb8fce', 'PER': '#e59866', 'MISC': '#a6acaf
 options = {'ents': ['ORG', 'LOC', 'PER', 'MISC'], 'colors': colors}
 colors_sner = {'ORGANIZATION': '#73c6b6', 'LOCATION': '#bb8fce', 'PERSON': '#e59866', 'MISC': '#a6acaf'}
 options_sner = {'ents': ['ORGANIZATION', 'LOCATION', 'PERSON', 'MISC'], 'colors': colors_sner}
-
+colors_sner_french = {'I-ORG': '#73c6b6', 'I-LIEU': '#bb8fce', 'I-PERS': '#e59866'}
+options_sner_french = {'ents': ['I-ORG', 'I-LOC', 'I-PERS'], 'colors': colors_sner_french}
 
 
 
@@ -75,9 +76,13 @@ def read_from_txt(filename):
             pass
     return alldicts
 
-def render_dict(alldicts):
+def render_dict(alldicts, language):
+    if language == 'german':
+        options = options_sner
+    if language == 'french':
+        options = options_sner_french
     for sent_key, sent_dict in alldicts.items():
-        displacy.render(sent_dict, style='ent', jupyter=True, manual=True, options=options_sner)
+        displacy.render(sent_dict, style='ent', jupyter=True, manual=True, options=options)
 
 
 def transform_to_training_format(alldicts):
@@ -113,4 +118,6 @@ def transform_to_training_format(alldicts):
 
     return train_data
 
-
+def get_language(filepath):
+    language = 'french' if filepath.endswith('_french.txt') else 'german'
+    return language