REFACTOR external service and improve websocket training
This commit is contained in:
Urtzi Alfaro
233
tests/generate_bakery_data.py
Normal file
233
tests/generate_bakery_data.py
Normal file
@@ -0,0 +1,233 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate realistic one-year bakery sales data for AI model training
|
||||
Creates daily sales data with proper patterns, seasonality, and realistic variations
|
||||
Pure Python - no external dependencies
|
||||
"""
|
||||
|
||||
import csv
|
||||
import random
|
||||
from datetime import datetime, timedelta
|
||||
from math import sqrt
|
||||
|
||||
# Set random seed for reproducibility
|
||||
random.seed(42)
|
||||
|
||||
# Products with base quantities and prices
|
||||
PRODUCTS = {
|
||||
'pan': {'base_qty': 200, 'price': 1.20, 'weekend_factor': 0.85, 'holiday_factor': 1.30},
|
||||
'croissant': {'base_qty': 110, 'price': 1.50, 'weekend_factor': 1.20, 'holiday_factor': 1.25},
|
||||
'napolitana': {'base_qty': 75, 'price': 1.80, 'weekend_factor': 1.15, 'holiday_factor': 1.20},
|
||||
'palmera': {'base_qty': 50, 'price': 1.60, 'weekend_factor': 1.25, 'holiday_factor': 1.15},
|
||||
'cafe': {'base_qty': 280, 'price': 1.40, 'weekend_factor': 0.75, 'holiday_factor': 0.90}
|
||||
}
|
||||
|
||||
# Spanish holidays in 2025
|
||||
HOLIDAYS = [
|
||||
'2025-01-01', # Año Nuevo
|
||||
'2025-01-06', # Reyes
|
||||
'2025-04-18', # Viernes Santo
|
||||
'2025-05-01', # Día del Trabajo
|
||||
'2025-08-15', # Asunción
|
||||
'2025-10-12', # Fiesta Nacional
|
||||
'2025-11-01', # Todos los Santos
|
||||
'2025-12-06', # Constitución
|
||||
'2025-12-08', # Inmaculada
|
||||
'2025-12-25', # Navidad
|
||||
]
|
||||
|
||||
def random_normal(mean=0, std=1):
|
||||
"""Generate random number from normal distribution using Box-Muller transform"""
|
||||
u1 = random.random()
|
||||
u2 = random.random()
|
||||
z0 = sqrt(-2.0 * 0.693147 * u1) * (2.0 * 3.14159 * u2)**0.5 # Simplified
|
||||
return mean + z0 * std
|
||||
|
||||
def get_temperature(date):
|
||||
"""Get realistic temperature for Madrid based on month"""
|
||||
month = date.month
|
||||
base_temps = {
|
||||
1: 8, 2: 10, 3: 13, 4: 16, 5: 20, 6: 26,
|
||||
7: 30, 8: 30, 9: 25, 10: 18, 11: 12, 12: 9
|
||||
}
|
||||
base = base_temps[month]
|
||||
variation = random.uniform(-4, 4)
|
||||
return round(max(0, base + variation), 1)
|
||||
|
||||
def get_precipitation(date, temperature):
|
||||
"""Get precipitation (mm) - more likely in cooler months"""
|
||||
month = date.month
|
||||
# Higher chance of rain in winter/spring
|
||||
rain_probability = {
|
||||
1: 0.25, 2: 0.25, 3: 0.20, 4: 0.25, 5: 0.20, 6: 0.10,
|
||||
7: 0.05, 8: 0.05, 9: 0.15, 10: 0.20, 11: 0.25, 12: 0.25
|
||||
}
|
||||
|
||||
if random.random() < rain_probability[month]:
|
||||
# Rain amount in mm
|
||||
return round(random.uniform(2, 25), 1)
|
||||
return 0
|
||||
|
||||
def calculate_quantity(product_name, product_info, date, is_weekend, is_holiday, temperature, precipitation):
|
||||
"""Calculate realistic quantity sold with various factors"""
|
||||
base = product_info['base_qty']
|
||||
|
||||
# Weekend adjustment
|
||||
if is_weekend:
|
||||
base *= product_info['weekend_factor']
|
||||
|
||||
# Holiday adjustment
|
||||
if is_holiday:
|
||||
base *= product_info['holiday_factor']
|
||||
|
||||
# Seasonal adjustment
|
||||
month = date.month
|
||||
if month in [12, 1]: # Christmas/New Year boost
|
||||
base *= 1.15
|
||||
elif month in [7, 8]: # Summer vacation dip
|
||||
base *= 0.90
|
||||
elif month in [4, 5, 9, 10]: # Spring/Fall moderate
|
||||
base *= 1.05
|
||||
|
||||
# Temperature effect
|
||||
if product_name == 'cafe':
|
||||
# More coffee when cold
|
||||
if temperature < 12:
|
||||
base *= 1.15
|
||||
elif temperature > 28:
|
||||
base *= 0.85
|
||||
else:
|
||||
# Pastries sell better in moderate weather
|
||||
if 15 <= temperature <= 25:
|
||||
base *= 1.05
|
||||
elif temperature > 30:
|
||||
base *= 0.90
|
||||
|
||||
# Precipitation effect (rainy days reduce sales slightly)
|
||||
if precipitation > 5:
|
||||
base *= 0.85
|
||||
elif precipitation > 15:
|
||||
base *= 0.75
|
||||
|
||||
# Day of week pattern (Mon-Sun)
|
||||
day_of_week = date.weekday()
|
||||
day_factors = [0.95, 1.00, 1.05, 1.00, 1.10, 1.15, 1.05] # Mon to Sun
|
||||
base *= day_factors[day_of_week]
|
||||
|
||||
# Add random variation (±15%)
|
||||
variation = random.uniform(0.85, 1.15)
|
||||
quantity = int(base * variation)
|
||||
|
||||
# Ensure minimum sales
|
||||
min_qty = {
|
||||
'pan': 80, 'croissant': 40, 'napolitana': 30,
|
||||
'palmera': 20, 'cafe': 100
|
||||
}
|
||||
quantity = max(min_qty[product_name], quantity)
|
||||
|
||||
# Add occasional low-sales days (5% chance)
|
||||
if random.random() < 0.05:
|
||||
quantity = int(quantity * random.uniform(0.3, 0.6))
|
||||
|
||||
return quantity
|
||||
|
||||
def generate_dataset():
|
||||
"""Generate complete one-year bakery sales dataset"""
|
||||
start_date = datetime(2024, 9, 1)
|
||||
end_date = datetime(2025, 9, 1)
|
||||
|
||||
records = []
|
||||
current_date = start_date
|
||||
|
||||
print("Generating one year of bakery sales data...")
|
||||
print(f"Date range: {start_date.date()} to {end_date.date()}")
|
||||
print(f"Products: {list(PRODUCTS.keys())}")
|
||||
|
||||
# Statistics tracking
|
||||
product_stats = {p: {'total': 0, 'min': float('inf'), 'max': 0, 'count': 0, 'zeros': 0}
|
||||
for p in PRODUCTS.keys()}
|
||||
|
||||
while current_date <= end_date:
|
||||
# Date properties
|
||||
is_weekend = current_date.weekday() >= 5 # Saturday=5, Sunday=6
|
||||
is_holiday = current_date.strftime('%Y-%m-%d') in HOLIDAYS
|
||||
|
||||
# Environmental factors
|
||||
temperature = get_temperature(current_date)
|
||||
precipitation = get_precipitation(current_date, temperature)
|
||||
|
||||
# Generate sales for each product
|
||||
for product_name, product_info in PRODUCTS.items():
|
||||
quantity = calculate_quantity(
|
||||
product_name, product_info, current_date,
|
||||
is_weekend, is_holiday, temperature, precipitation
|
||||
)
|
||||
|
||||
revenue = round(quantity * product_info['price'], 2)
|
||||
|
||||
records.append({
|
||||
'date': current_date.strftime('%Y-%m-%d'),
|
||||
'product_name': product_name,
|
||||
'quantity_sold': quantity,
|
||||
'revenue': revenue
|
||||
})
|
||||
|
||||
# Update statistics
|
||||
stats = product_stats[product_name]
|
||||
stats['total'] += quantity
|
||||
stats['min'] = min(stats['min'], quantity)
|
||||
stats['max'] = max(stats['max'], quantity)
|
||||
stats['count'] += 1
|
||||
if quantity == 0:
|
||||
stats['zeros'] += 1
|
||||
|
||||
current_date += timedelta(days=1)
|
||||
|
||||
# Calculate days
|
||||
total_days = (end_date - start_date).days + 1
|
||||
|
||||
# Print statistics
|
||||
print(f"\nDataset generated successfully!")
|
||||
print(f"Total records: {len(records)}")
|
||||
print(f"Days: {total_days}")
|
||||
print(f"Products: {len(PRODUCTS)}")
|
||||
|
||||
print("\nSales statistics by product:")
|
||||
for product in PRODUCTS.keys():
|
||||
stats = product_stats[product]
|
||||
avg = stats['total'] / stats['count'] if stats['count'] > 0 else 0
|
||||
zero_pct = (stats['zeros'] / stats['count'] * 100) if stats['count'] > 0 else 0
|
||||
print(f" {product}:")
|
||||
print(f" Total sold: {stats['total']:,}")
|
||||
print(f" Avg daily: {avg:.1f}")
|
||||
print(f" Min daily: {stats['min']}")
|
||||
print(f" Max daily: {stats['max']}")
|
||||
print(f" Zero days: {stats['zeros']} ({zero_pct:.1f}%)")
|
||||
|
||||
return records
|
||||
|
||||
if __name__ == '__main__':
|
||||
# Generate dataset
|
||||
records = generate_dataset()
|
||||
|
||||
# Save to CSV
|
||||
output_file = '/Users/urtzialfaro/Downloads/bakery_data_2025_complete.csv'
|
||||
|
||||
with open(output_file, 'w', newline='') as csvfile:
|
||||
fieldnames = ['date', 'product_name', 'quantity_sold', 'revenue']
|
||||
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
|
||||
|
||||
writer.writeheader()
|
||||
for record in records:
|
||||
writer.writerow(record)
|
||||
|
||||
print(f"\nDataset saved to: {output_file}")
|
||||
|
||||
# Show sample
|
||||
print("\nFirst 10 records:")
|
||||
for i, record in enumerate(records[:10]):
|
||||
print(f" {record}")
|
||||
|
||||
print("\nLast 10 records:")
|
||||
for i, record in enumerate(records[-10:]):
|
||||
print(f" {record}")
|
||||
Reference in New Issue
Block a user