Upload 3 files

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+
+WORKDIR /code
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY ./app /code/app
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,52 @@
+from fastapi import FastAPI, UploadFile, File, HTTPException
+import pickle
+import pandas as pd
+from pydantic import BaseModel
+from typing import List
+import os
+
+app = FastAPI()
+MODEL_PATH = "tfidf_models.pkl"
+
+class TrainRequest(BaseModel):
+    texts: List[str]
+    labels: List[List[int]]
+
+class PredictRequest(BaseModel):
+    texts: List[str]
+
+@app.post("/train")
+def train_model(request: TrainRequest):
+    from sklearn.feature_extraction.text import TfidfVectorizer
+    from sklearn.multioutput import MultiOutputClassifier
+    from sklearn.linear_model import LogisticRegression
+
+    if len(request.texts) != len(request.labels):
+        raise HTTPException(status_code=400, detail="Texts and labels length mismatch")
+
+    X = request.texts
+    y = pd.DataFrame(request.labels)
+
+    vectorizer = TfidfVectorizer()
+    X_tfidf = vectorizer.fit_transform(X)
+
+    classifier = MultiOutputClassifier(LogisticRegression(max_iter=1000))
+    classifier.fit(X_tfidf, y)
+
+    with open(MODEL_PATH, "wb") as f:
+        pickle.dump((vectorizer, classifier), f)
+
+    return {"message": "Model trained and saved successfully."}
+
+@app.post("/predict")
+def predict(request: PredictRequest):
+    if not os.path.exists(MODEL_PATH):
+        raise HTTPException(status_code=404, detail="Model not found. Train the model first.")
+
+    with open(MODEL_PATH, "rb") as f:
+        vectorizer, classifier = pickle.load(f)
+
+    X_tfidf = vectorizer.transform(request.texts)
+    predictions = classifier.predict(X_tfidf)
+
+    return {"predictions": predictions.tolist()}

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+scikit-learn
+pandas
+python-multipart