Create app.py

app.py

@@ -0,0 +1,81 @@
+import re
+import torch
+import gradio as gr
+
+from presidio_anonymizer import AnonymizerEngine
+from presidio_analyzer import AnalyzerEngine
+from presidio_anonymizer.entities import RecognizerResult, OperatorConfig
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+
+# Initialize the engine:
+analyzer = AnalyzerEngine()
+anonymizer = AnonymizerEngine()
+
+# Create pipeline
+tokenizer = AutoTokenizer.from_pretrained("dslim/bert-base-NER-uncased")
+tokenizer.add_tokens('<person>')
+model = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER-uncased")
+pipe = pipeline(model=model, tokenizer=tokenizer, task='ner')
+
+# https://microsoft.github.io/presidio/supported_entities/
+ENT_TYPES = [
+#     'PERSON',
+    'CREDIT_CARD',
+    'EMAIL_ADDRESS',
+    'IP_ADDRESS',
+    'PHONE_NUMBER'
+]
+
+def mask_names_hf(text):
+    # Tokenize inputs
+    inputs = tokenizer(text, return_tensors='pt', truncation=True)
+    tokens = inputs.tokens()
+    
+    # Make inferences
+    outputs = model(**inputs).logits
+    predictions = torch.argmax(outputs, dim=2)
+    
+    # Replace tokens that are people with <PERSON>
+    words = []
+    for token, prediction in zip(tokens, predictions[0].numpy()):
+        prediction = model.config.id2label[prediction]
+        if prediction not in ('I-PER', 'B-PER'):
+            words.append(token)
+        elif prediction == 'B-PER':
+            if words[-1] != '<PERSON>':
+                words.append('<PERSON>')
+        else:
+            pass
+    # Convert those tokens to a string
+    return tokenizer.convert_tokens_to_string(words[1:-1])
+
+def anonymize(text, min_len=3):
+    
+    # Find and replace other stuff (Presidio NER)
+    ents = analyzer.analyze(text, language='en', entities=ENT_TYPES)
+    results = anonymizer.anonymize(text, analyzer_results=ents)
+    t = results.text
+    
+    # Find and replace names (HF NER)
+    t = mask_names_hf(t)
+    
+    pats = re.findall('<.+?>', t)
+    for p in pats:
+        t = t.replace(p, p.upper().replace(' ', ''))
+        
+    
+    t = t.replace('<PERSON><PERSON>', '<PERSON>')
+    return t
+
+title = "Personal Info Remover"
+description = """Personal Info Remover"""
+
+gr.Interface(
+        anonymize, 
+        inputs='text', 
+        outputs='text',
+        title=title,
+        description=description,
+        examples=["My name is Yuriy, contacts info: 0-800-123-456, test@i.ua, IP address is 1.0.0.1"]
+).launch(debug=True)