Upload 19 files

Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1     PYTHONUNBUFFERED=1     PORT=7860
+
+WORKDIR /workspace
+
+RUN apt-get update && apt-get install -y --no-install-recommends     build-essential     curl     && rm -rf /var/lib/apt/lists/*
+
+COPY backend/requirements.txt /workspace/requirements.txt
+RUN pip install --no-cache-dir -r /workspace/requirements.txt
+
+COPY backend /workspace/backend
+COPY scripts /workspace/scripts
+
+RUN mkdir -p /data/uploads /data/artifacts
+
+EXPOSE 7860
+
+CMD ["sh", "-c", "python scripts/migrate_db.py && uvicorn backend.app.main:app --host 0.0.0.0 --port 7860"]

README.md

@@ -0,0 +1,12 @@
+---
+title: ClusterBuster-API
+emoji: 📊
+colorFrom: blue
+colorTo: purple
+sdk: docker
+app_port: 7860
+pinned: false
+---
+
+# ClusterBuster API
+FastAPI backend for clustering.

backend/app/api/datasets.py

@@ -0,0 +1,37 @@
+from fastapi import APIRouter, UploadFile, File, Depends
+from sqlalchemy.orm import Session
+import pandas as pd, json
+from pathlib import Path
+
+from backend.app.db import get_db
+from backend.app.repositories.dataset_repo import create_dataset
+from backend.app.utils.ids import make_dataset_id
+from backend.app.services.profiling_service import profile_dataframe
+
+router = APIRouter()
+
+UPLOAD_DIR = Path("/data/uploads")
+UPLOAD_DIR.mkdir(parents=True, exist_ok=True)
+
+@router.post("/datasets/upload")
+async def upload_dataset(file: UploadFile = File(...), db: Session = Depends(get_db)):
+    dataset_id = make_dataset_id()
+    path = UPLOAD_DIR / f"{dataset_id}.csv"
+    content = await file.read()
+    path.write_bytes(content)
+
+    df = pd.read_csv(path)
+    profile = profile_dataframe(df)
+
+    create_dataset(
+        db,
+        id=dataset_id,
+        name=file.filename,
+        file_path=str(path),
+        row_count=len(df),
+        column_count=len(df.columns),
+        schema_json=json.dumps({"columns": list(df.columns)}),
+        profile_json=json.dumps(profile),
+    )
+
+    return {"dataset_id": dataset_id}

backend/app/api/health.py

@@ -0,0 +1,7 @@
+from fastapi import APIRouter
+
+router = APIRouter()
+
+@router.get("/health")
+def health():
+    return {"ok": True}

backend/app/db.py

@@ -0,0 +1,25 @@
+import os
+from sqlalchemy import create_engine
+from sqlalchemy.orm import declarative_base, sessionmaker
+
+DB_PATH = os.getenv("DB_PATH", "/data/clusterforge.db")
+DATABASE_URL = f"sqlite:///{DB_PATH}"
+
+engine = create_engine(
+    DATABASE_URL,
+    connect_args={"check_same_thread": False},
+)
+
+SessionLocal = sessionmaker(bind=engine)
+Base = declarative_base()
+
+def init_db():
+    import backend.app.models.dataset
+    Base.metadata.create_all(bind=engine)
+
+def get_db():
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()

backend/app/main.py

@@ -0,0 +1,26 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from backend.app.db import init_db
+from backend.app.api.health import router as health_router
+from backend.app.api.datasets import router as datasets_router
+
+app = FastAPI()
+
+@app.on_event("startup")
+def startup():
+    init_db()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.include_router(health_router, prefix="/api")
+app.include_router(datasets_router, prefix="/api")
+
+@app.get("/")
+def root():
+    return {"ok": True}

backend/app/models/dataset.py

@@ -0,0 +1,12 @@
+from sqlalchemy import Column, String, Integer, Text
+from backend.app.db import Base
+
+class Dataset(Base):
+    __tablename__ = "datasets"
+    id = Column(String, primary_key=True)
+    name = Column(String)
+    file_path = Column(String)
+    row_count = Column(Integer)
+    column_count = Column(Integer)
+    schema_json = Column(Text)
+    profile_json = Column(Text)

backend/app/repositories/dataset_repo.py

@@ -0,0 +1,9 @@
+from sqlalchemy.orm import Session
+from backend.app.models.dataset import Dataset
+
+def create_dataset(db: Session, **kwargs):
+    obj = Dataset(**kwargs)
+    db.add(obj)
+    db.commit()
+    db.refresh(obj)
+    return obj

backend/app/services/profiling_service.py

@@ -0,0 +1,2 @@
+def profile_dataframe(df):
+    return {"columns": [{"name": c} for c in df.columns]}

backend/app/utils/ids.py

@@ -0,0 +1,3 @@
+import secrets
+def make_dataset_id():
+    return "ds_" + secrets.token_hex(4)

backend/requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+sqlalchemy
+pandas
+numpy
+scikit-learn
+python-multipart
+openpyxl

scripts/migrate_db.py

@@ -0,0 +1,3 @@
+from backend.app.db import init_db
+init_db()
+print("DB ready")