Duplicate from deprem-ml/ner-active-learning

Co-authored-by: Merve Noyan <merve@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: NER Active Learning
+emoji: 📖
+colorFrom: yellow
+colorTo: green
+sdk: gradio
+sdk_version: 3.18.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: deprem-ml/ner-active-learning
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,85 @@
+import os
+import gradio as gr
+from gradio import FlaggingCallback
+from gradio.components import IOComponent
+
+from transformers import pipeline
+
+from typing import List, Optional, Any
+
+import argilla as rg
+
+import os
+
+
+
+nlp = pipeline("ner", model="deprem-ml/deprem-ner")
+
+examples = [
+  ["Lütfen yardım Akevler mahallesi Rüzgar sokak Tuncay apartmanı zemin kat Antakya akrabalarım göçük altında #hatay #Afad"]
+]
+
+def create_record(input_text, feedback):
+    # define the record status based on feedback
+    # default means it needs to be reviewed --> "Incorrect" or "Ambiguous"
+    # validated means it's correct and has been checked --> "Correct"
+    status = "Validated" if feedback == "Doğru" else "Default"
+    
+    # Making the prediction
+    predictions = nlp(input_text, aggregation_strategy="first")
+    
+    # Creating the predicted entities as a list of tuples (entity, start_char, end_char, score)
+    prediction = [(pred["entity_group"], pred["start"], pred["end"], pred["score"]) for pred in predictions]
+    
+    # Create word tokens
+    batch_encoding = nlp.tokenizer(input_text)
+    word_ids = sorted(set(batch_encoding.word_ids()) - {None})
+    words = []
+    for word_id in word_ids:
+        char_span = batch_encoding.word_to_chars(word_id)
+        words.append(input_text[char_span.start:char_span.end])
+    
+    # Building a TokenClassificationRecord
+    record = rg.TokenClassificationRecord(
+        text=input_text,
+        tokens=words,
+        prediction=prediction,
+        prediction_agent="deprem-ml/deprem-ner",
+        status=status,
+        metadata={"feedback": feedback}
+    )
+    print(record)
+    return record
+
+class ArgillaLogger(FlaggingCallback):
+    def __init__(self, api_url, api_key, dataset_name):
+        rg.init(api_url=api_url, api_key=api_key)
+        self.dataset_name = dataset_name
+    def setup(self, components: List[IOComponent], flagging_dir: str):
+        pass
+    def flag(
+        self,
+        flag_data: List[Any],
+        flag_option: Optional[str] = None,
+        flag_index: Optional[int] = None,
+        username: Optional[str] = None,
+    ) -> int:
+        text = flag_data[0]
+        inference = flag_data[1]
+        rg.log(name=self.dataset_name, records=create_record(text, flag_option))
+
+
+        
+gr.Interface.load(
+    "models/deprem-ml/deprem-ner",
+    examples=examples,
+    title = "NER Adres Aktif Öğrenme Arayüzü",
+    description = "Aşağıda veri girişi yapıp modelin çıktısına göre Doğru/Yanlış/Belirsiz olarak işaretleyerek modelimizi değerlendirmemize yardımcı olabilirsiniz. Not: flag'lere bir kez tıklamanız yeterlidir. Şu an arayüzü flag alındığında size feedback verecek şekilde düzeltiyoruz. ",
+    allow_flagging="manual",
+    flagging_callback=ArgillaLogger(
+        api_url="https://sandbox.argilla.io", 
+        api_key=os.getenv("TEAM_API_KEY"), 
+        dataset_name="ner-flags"
+    ),
+    flagging_options=["Doğru", "Yanlış", "Belirsiz"]
+).launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+torch
+argilla