salakojoshua1234_gmail.com
8acfb436f3
- Added `/load-data` endpoint to load transaction data from either a database or a CSV file. - Updated `SalaryAnalyticsPipeline` and `DataLoader` to support loading from CSV. - Implemented data validation and error handling for loading processes. - Revised README to include new data loading instructions and workflow steps. - Added checks to ensure data is loaded before running analysis endpoints.
280 lines
10 KiB
Python
280 lines
10 KiB
Python
"""
|
|
FastAPI application for salary analytics.
|
|
"""
|
|
|
|
from fastapi import FastAPI, HTTPException, BackgroundTasks, UploadFile, File
|
|
from fastapi.responses import FileResponse
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from pydantic import BaseModel
|
|
from typing import Optional, Dict
|
|
import os
|
|
import socket
|
|
import logging
|
|
import pandas as pd
|
|
import tempfile
|
|
|
|
from .main import SalaryAnalyticsPipeline
|
|
from .config import OUTPUT_PATHS
|
|
from .data_loader import DataLoader
|
|
from .salary_predictor import SalaryPredictor
|
|
from .salary_earner_analyzer import SalaryEarnerAnalyzer
|
|
|
|
# Configure logging
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
|
)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
app = FastAPI(
|
|
title="Salary Analytics API",
|
|
description="API for analyzing and predicting salary patterns from transaction data",
|
|
version="1.0.0"
|
|
)
|
|
|
|
# Add CORS middleware
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"], # Allows all origins
|
|
allow_credentials=True,
|
|
allow_methods=["*"], # Allows all methods
|
|
allow_headers=["*"], # Allows all headers
|
|
)
|
|
|
|
# Global pipeline instance
|
|
pipeline = SalaryAnalyticsPipeline()
|
|
|
|
# Global variables to store loaded data and models
|
|
data_loader = None
|
|
df = None
|
|
salary_predictor = None
|
|
salary_earner_analyzer = None
|
|
|
|
class AnalysisResponse(BaseModel):
|
|
"""Response model for analysis endpoints."""
|
|
message: str
|
|
data: Optional[Dict] = None
|
|
file_path: Optional[str] = None
|
|
|
|
def check_data_loaded():
|
|
"""Check if data is loaded before running analytics."""
|
|
if pipeline.df is None:
|
|
raise HTTPException(
|
|
status_code=400,
|
|
detail="No data loaded. Please load data first using the /load-data endpoint."
|
|
)
|
|
|
|
@app.on_event("startup")
|
|
async def startup_event():
|
|
"""Initialize the pipeline on startup."""
|
|
try:
|
|
logger.info("Initializing pipeline...")
|
|
|
|
# Print network information
|
|
hostname = socket.gethostname()
|
|
ip_address = socket.gethostbyname(hostname)
|
|
logger.info(f"Server running on hostname: {hostname}")
|
|
logger.info(f"Server IP address: {ip_address}")
|
|
logger.info(f"Server is accessible at:")
|
|
logger.info(f"- http://localhost:8000")
|
|
logger.info(f"- http://127.0.0.1:8000")
|
|
logger.info(f"- http://{ip_address}:8000")
|
|
logger.info("Pipeline initialized successfully")
|
|
except Exception as e:
|
|
logger.error(f"Error during startup: {str(e)}")
|
|
raise
|
|
|
|
@app.get("/")
|
|
async def root():
|
|
"""Root endpoint."""
|
|
logger.info("Root endpoint accessed")
|
|
return {"message": "Welcome to Salary Analytics API"}
|
|
|
|
@app.get("/health")
|
|
async def health_check():
|
|
"""Health check endpoint."""
|
|
logger.info("Health check endpoint accessed")
|
|
return {"status": "healthy"}
|
|
|
|
@app.post("/analyze/keyword", response_model=AnalysisResponse)
|
|
async def analyze_keyword():
|
|
"""Run keyword-based salary transaction analysis."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting keyword analysis...")
|
|
data = pipeline.run_keyword_analysis()
|
|
logger.info(f"Keyword analysis completed. Found {len(data)} matches")
|
|
return AnalysisResponse(
|
|
message="Keyword analysis completed successfully",
|
|
data={"count": len(data)}
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in keyword analysis: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/analyze/consistent-amount", response_model=AnalysisResponse)
|
|
async def analyze_consistent_amount():
|
|
"""Run consistent amount transaction analysis."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting consistent amount analysis...")
|
|
data = pipeline.run_consistent_amount_analysis()
|
|
logger.info(f"Consistent amount analysis completed. Found {len(data)} matches")
|
|
return AnalysisResponse(
|
|
message="Consistent amount analysis completed successfully",
|
|
data={"count": len(data)}
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in consistent amount analysis: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/analyze/transaction-type", response_model=AnalysisResponse)
|
|
async def analyze_transaction_type():
|
|
"""Run transaction type analysis."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting transaction type analysis...")
|
|
data = pipeline.run_transaction_type_analysis()
|
|
logger.info(f"Transaction type analysis completed. Found {len(data)} matches")
|
|
return AnalysisResponse(
|
|
message="Transaction type analysis completed successfully",
|
|
data={"count": len(data)}
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in transaction type analysis: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/generate/reports", response_model=AnalysisResponse)
|
|
async def generate_reports(background_tasks: BackgroundTasks):
|
|
"""Generate salary earner reports."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting report generation...")
|
|
reports = pipeline.generate_salary_earner_reports()
|
|
logger.info("Reports generated successfully")
|
|
return AnalysisResponse(
|
|
message="Reports generated successfully",
|
|
data={
|
|
"verified_salary_earners": len(reports['final_table']),
|
|
"likely_salary_earners": len(reports['likely_salary_earner']),
|
|
"high_earners": reports['total_high_earners']
|
|
}
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in report generation: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/train/models", response_model=AnalysisResponse)
|
|
async def train_models():
|
|
"""Train salary prediction models."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting model training...")
|
|
pipeline.train_salary_prediction_models()
|
|
logger.info("Models trained successfully")
|
|
return AnalysisResponse(
|
|
message="Models trained successfully"
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in model training: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.get("/download/{report_type}")
|
|
async def download_report(report_type: str):
|
|
"""Download generated reports."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info(f"Attempting to download report: {report_type}")
|
|
file_paths = {
|
|
"high_earners": OUTPUT_PATHS["high_earner_details"],
|
|
"likely_earners": OUTPUT_PATHS["likely_salary_earner"],
|
|
"final_table": OUTPUT_PATHS["final_table"],
|
|
"consistent_plot": OUTPUT_PATHS["consistent_earners_plot"],
|
|
"inconsistent_plot": OUTPUT_PATHS["inconsistent_earners_plot"],
|
|
"hypothesis_plot": OUTPUT_PATHS["hypothesis_overlap_plot"]
|
|
}
|
|
|
|
if report_type not in file_paths:
|
|
logger.error(f"Report type not found: {report_type}")
|
|
raise HTTPException(status_code=404, detail="Report type not found")
|
|
|
|
file_path = file_paths[report_type]
|
|
if not os.path.exists(file_path):
|
|
logger.error(f"Report file not found: {file_path}")
|
|
raise HTTPException(status_code=404, detail="Report file not found")
|
|
|
|
logger.info(f"Successfully found report file: {file_path}")
|
|
return FileResponse(
|
|
path=file_path,
|
|
filename=os.path.basename(file_path),
|
|
media_type="application/octet-stream"
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error downloading report: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/run/pipeline", response_model=AnalysisResponse)
|
|
async def run_full_pipeline():
|
|
"""Run the complete salary analytics pipeline."""
|
|
try:
|
|
check_data_loaded()
|
|
logger.info("Starting full pipeline...")
|
|
success = pipeline.run_full_pipeline()
|
|
if not success:
|
|
logger.error("Pipeline failed")
|
|
raise HTTPException(status_code=500, detail="Pipeline failed")
|
|
|
|
logger.info("Pipeline completed successfully")
|
|
return AnalysisResponse(
|
|
message="Pipeline completed successfully"
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error in pipeline: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
@app.post("/load-data")
|
|
async def load_data(source: str = "db", file: UploadFile = None):
|
|
"""
|
|
Load data from either database or CSV file.
|
|
|
|
Args:
|
|
source (str): Source of data ('db' or 'csv')
|
|
file (UploadFile): CSV file to load (required if source is 'csv')
|
|
|
|
Returns:
|
|
dict: Status of data loading
|
|
"""
|
|
try:
|
|
if source not in ['db', 'csv']:
|
|
raise HTTPException(status_code=400, detail="Source must be either 'db' or 'csv'")
|
|
|
|
if source == 'csv' and not file:
|
|
raise HTTPException(status_code=400, detail="File must be provided when loading from CSV")
|
|
|
|
if source == 'csv':
|
|
# Save uploaded file temporarily
|
|
with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as temp_file:
|
|
content = await file.read()
|
|
temp_file.write(content)
|
|
temp_file_path = temp_file.name
|
|
|
|
try:
|
|
success = pipeline.load_data(source='csv', file_path=temp_file_path)
|
|
finally:
|
|
# Clean up temporary file
|
|
os.unlink(temp_file_path)
|
|
else:
|
|
success = pipeline.load_data(source='db')
|
|
|
|
if not success:
|
|
raise HTTPException(status_code=500, detail="Failed to load data")
|
|
|
|
return {
|
|
"status": "success",
|
|
"message": f"Successfully loaded {len(pipeline.df)} rows of data",
|
|
"columns": pipeline.df.columns.tolist(),
|
|
"row_count": len(pipeline.df)
|
|
}
|
|
except Exception as e:
|
|
logger.error(f"Error loading data: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=str(e)) |