|
|
|
|
|
from fastapi import FastAPI, HTTPException, File, UploadFile |
|
|
from fastapi.responses import FileResponse |
|
|
from preprocessing import data_quality, standardize_data_types, handle_missing_data, handle_outliers, generate_final_report, save_cleaned_data |
|
|
import pandas as pd |
|
|
import io |
|
|
|
|
|
app = FastAPI(title="Data Preprocessing") |
|
|
|
|
|
@app.get("/") |
|
|
async def root(): |
|
|
return {"message": "Welcome to the Data Preprocessing API!"} |
|
|
|
|
|
@app.post("/preprocess_data/") |
|
|
async def upload_csv(upload_file: UploadFile = File(...)): |
|
|
try: |
|
|
if not upload_file.filename.endswith('.csv'): |
|
|
raise HTTPException(status_code=400, detail="File must be in CSV format!") |
|
|
|
|
|
content = await upload_file.read() |
|
|
df = pd.read_csv(io.BytesIO(content), encoding_errors="replace") |
|
|
|
|
|
if df.empty: |
|
|
raise HTTPException(status_code=400, detail="File is empty, upload the correct file") |
|
|
|
|
|
data_quality(df) |
|
|
df = standardize_data_types(df) |
|
|
df = handle_missing_data(df) |
|
|
df = handle_outliers(df) |
|
|
|
|
|
REPORT_PATH = "output/preprocessing_report.txt" |
|
|
generate_final_report(df, REPORT_PATH) |
|
|
|
|
|
CLEANED_DATA_PATH = "output/cleaned_dataset.csv" |
|
|
save_cleaned_data(df, CLEANED_DATA_PATH) |
|
|
|
|
|
return FileResponse(CLEANED_DATA_PATH, media_type="text/csv", filename="cleaned_dataset.csv") |
|
|
|
|
|
except Exception as e: |
|
|
raise HTTPException(status_code=400, detail=f"Error processing file: {str(e)}") |
|
|
|
