feat[bert]: Basic logic

docker-compose.yml

@@ -0,0 +1,7 @@
+version: '3
+
+services: 
+  ml-service:
+    build: ./ml-service
+    ports:
+      - 6000:6000

ml-service/Dockerfile

@@ -0,0 +1,8 @@
+FROM python:3.10.8-slim
+LABEL description="Sentiment classifier of tweets service"
+WORKDIR /app
+COPY requirements.txt /app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . /app/
+EXPOSE 6000
+CMD ["python",  "app.py"]

ml-service/app.py

@@ -0,0 +1,34 @@
+# app.py
+from fastapi import FastAPI, APIRouter
+import uvicorn
+from classifier import Classifier
+from model import Model
+from nlp import NLP
+import logging
+
+logging.basicConfig(level = logging.INFO)
+
+# Create the FastAPI instance
+app = FastAPI()
+nlp = NLP()
+router = APIRouter()
+classifier = Classifier()
+
+# Define the required routes
+@router.get("/")
+async def home():
+  return {"message": "Machine Learning service"}
+
+@router.post("/sentiment")
+async def data(data: dict):
+  try:
+    input_text = data["text"]
+    res = nlp.sentiment_analysis(classifier, input_text)
+    return res
+  except Exception as e:
+    log.error("Something went wrong")
+
+app.include_router(router)
+
+if __name__ == "__main__":
+  uvicorn.run("app:app", reload=True, port=6000, host="0.0.0.0")

ml-service/classifier.py

@@ -0,0 +1,22 @@
+# classifier.py
+from scipy.special import softmax
+from model import Model
+import numpy as np
+
+class Classifier:
+  def __init__(self):
+    self.model = Model.load_model()
+    self.tokenizer = Model.load_tokenizer()
+
+  def get_sentiment_label_and_score(self, text: str):
+    result = {}
+    labels = ["Negative", "Neutral", "Positive"]
+    encoded_input = self.tokenizer(text, return_tensors='pt')
+    output = self.model(**encoded_input)
+    scores = output[0][0]jj.detach().numpy()
+    scores = softmax(scores)
+    ranking = np.argsort(scores)
+    ranking = ranking[::-1]
+    result["label"] = str(labels[ranking[0]])
+    result["score"] = np.round(float(scores[ranking[0]]), 4)
+    return result

ml-service/download_model.py

@@ -0,0 +1,11 @@
+from transformers import AutoModelForSequenceClassification, TFAutoModelForSequenceClassification, AutoTokenize
+
+# download the model
+MODEL = "cardiffnlp/twitter-roberta-base-sentiment"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL)
+
+# save the model
+save_dir = "ml-service/models/roberta-base"
+tokenizer.save_pretrained(save_dir)
+model.save_pretrained(save_dir)

ml-service/model.py

@@ -0,0 +1,16 @@
+# model.py
+from transformers import AutoModelForSequenceClassification, TFAutoModelForSequenceClassification, AutoTokenize
+
+class Model:
+  """A model class to lead the model and tokenizer"""
+
+  def __init__(self) -> None:
+    pass
+  
+  def load_model():
+    model = AutoModelForSequenceClassification.from_pretrained("./models/roberta-base/")
+    return model
+
+  def load_tokenizer():
+    tokenizer = AutoTokenize.from_pretrained("./models/roberta-base/")
+    return tokenizer

ml-service/nlp.py

@@ -0,0 +1,8 @@
+# nlp.py
+from classifier import Classifier
+
+classifier = Classifier()
+
+def sentiment_analysis(self, text:str, classifier): 
+  sentiment = classifier.get_sentiment_label_and_score(text)
+  return sentiment