Spaces:
Sleeping
Sleeping
File size: 2,540 Bytes
8675ade badef87 8675ade 4caacc1 badef87 a49614b 4caacc1 8675ade badef87 8675ade 286933c 8675ade badef87 8675ade |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import os
import math
import shutil
from src.core.utils import logger
from fastapi.responses import JSONResponse
from fastapi import APIRouter, UploadFile, File, HTTPException, Form
from src.app.pipelines.modules import UnivariateAnalysisWorkflow
univariate_analysis_router = APIRouter()
def delete_dir_contents(directory: str)->None:
for filename in os.listdir(directory):
file_path = os.path.join(directory, filename)
if os.path.isfile(file_path):
os.remove(file_path)
def sanitize_for_json(data):
if isinstance(data, dict):
return {k: sanitize_for_json(v) for k, v in data.items()}
elif isinstance(data, list):
return [sanitize_for_json(v) for v in data]
elif isinstance(data, float):
if math.isinf(data) or math.isnan(data):
return None
return data
return data
@univariate_analysis_router.post('/')
async def main(file: UploadFile = File(...), ml_task: str = Form(None)):
''' ## This endpoint accepts a CSV file upload to initiate the Univarite Analysis Workflow.
### Parameters:
-----------
- file : CSV File for the dataset
\n
- ml_task : Final machine learning task/target
### Returns:
--------
- dict: Markdown Report
'''
if not file.filename.endswith('.csv'):
raise HTTPException(status_code=400, detail="Only CSV files are allowed.")
'''Clears the /downloads folder and stores the recieved file under 'dataset.csv' '''
downloads_path = "src/core/cache/downloads"
# os.makedirs(downloads_path, exist_ok=True)
delete_dir_contents(downloads_path)
destination_path = os.path.join(downloads_path, "dataset.csv")
with open(destination_path, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
logger.info(f"CSV file saved to {destination_path}", log_type='eda-engine/univariate_analysis', console=True)
'''Runs the data univariate analysis workflow'''
try:
ua_wf = UnivariateAnalysisWorkflow(data_source=f'{downloads_path}/dataset.csv', llm_choice="gpt-4o-mini", ml_task=ml_task)
results = ua_wf.run(verbose=True)
sanitized_data = sanitize_for_json(results)
return JSONResponse(content=sanitized_data)
except Exception as e:
logger.error(f"UnivariateAnalysisWorkflow failed with error: {e}", log_type='eda-engine/dataunivariate_analysis_statistics', console=True)
return {
"status": "Pipeline failed to finish"
}
|