MATERIAL_AND_SALE_PREDICTION / api /get_features.py
TrBn17
clean repo without secrets
9bc522a
Raw History Blame Contribute Delete
4.34 kB
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
import pandas as pd
import os
from typing import List, Dict, Any
# Response models
class FeatureExample(BaseModel):
category: str
region: str
inventory_level: float
units_ordered: int
demand_forecast: float
class FeaturesResponse(BaseModel):
available_categories: List[str]
available_regions: List[str]
sample_data: List[FeatureExample]
statistics: Dict[str, Any]
class SampleDataResponse(BaseModel):
total_records: int
sample_records: List[Dict[str, Any]]
# Create router
router = APIRouter()
def load_sample_data():
"""Load sample data from CSV file"""
try:
data_path = "data/sample_data.csv"
if os.path.exists(data_path):
df = pd.read_csv(data_path)
return df
else:
# Return mock data if file doesn't exist
return pd.DataFrame({
'Category': ['Electronics', 'Clothing', 'Home & Garden', 'Sports'],
'Region': ['North', 'South', 'East', 'West'],
'Inventory Level': [150.5, 89.2, 205.7, 125.8],
'Units Ordered': [25, 15, 40, 30],
'Demand Forecast': [200.0, 120.5, 300.2, 180.4]
})
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error loading data: {str(e)}")
@router.get("/get-features", response_model=FeaturesResponse)
async def get_features():
"""
Get available feature values and sample data for prediction.
Returns categories, regions, and example data for users.
"""
try:
df = load_sample_data()
# Get unique values
categories = df['Category'].unique().tolist() if 'Category' in df.columns else []
regions = df['Region'].unique().tolist() if 'Region' in df.columns else []
# Create sample examples (first 3 records)
sample_data = []
for _, row in df.head(3).iterrows():
sample_data.append(FeatureExample(
category=row.get('Category', 'Electronics'),
region=row.get('Region', 'North'),
inventory_level=float(row.get('Inventory Level', 100.0)),
units_ordered=int(row.get('Units Ordered', 20)),
demand_forecast=float(row.get('Demand Forecast', 150.0))
))
# Calculate basic statistics
statistics = {}
if 'Inventory Level' in df.columns:
statistics['inventory_level'] = {
'min': float(df['Inventory Level'].min()),
'max': float(df['Inventory Level'].max()),
'mean': float(df['Inventory Level'].mean())
}
if 'Units Ordered' in df.columns:
statistics['units_ordered'] = {
'min': int(df['Units Ordered'].min()),
'max': int(df['Units Ordered'].max()),
'mean': float(df['Units Ordered'].mean())
}
if 'Demand Forecast' in df.columns:
statistics['demand_forecast'] = {
'min': float(df['Demand Forecast'].min()),
'max': float(df['Demand Forecast'].max()),
'mean': float(df['Demand Forecast'].mean())
}
return FeaturesResponse(
available_categories=categories,
available_regions=regions,
sample_data=sample_data,
statistics=statistics
)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error getting features: {str(e)}")
@router.get("/sample-data", response_model=SampleDataResponse)
async def get_sample_data(limit: int = 5):
"""
Get raw sample data from the dataset.
Args:
limit: Number of records to return (default: 5, max: 20)
"""
try:
if limit > 20:
limit = 20
df = load_sample_data()
# Convert to dict records
sample_records = df.head(limit).to_dict('records')
return SampleDataResponse(
total_records=len(df),
sample_records=sample_records
)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error getting sample data: {str(e)}")