Improve AI logic
This commit is contained in:
Urtzi Alfaro
399
services/forecasting/tests/test_dynamic_rules_engine.py
Normal file
399
services/forecasting/tests/test_dynamic_rules_engine.py
Normal file
@@ -0,0 +1,399 @@
|
||||
"""
|
||||
Tests for Dynamic Business Rules Engine
|
||||
"""
|
||||
|
||||
import pytest
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from datetime import datetime, timedelta
|
||||
from app.ml.dynamic_rules_engine import DynamicRulesEngine
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_sales_data():
|
||||
"""Generate sample sales data for testing."""
|
||||
dates = pd.date_range(start='2024-01-01', end='2024-12-31', freq='D')
|
||||
|
||||
# Base demand with day-of-week pattern
|
||||
base = 100
|
||||
quantities = []
|
||||
|
||||
for date in dates:
|
||||
# Day of week pattern (weekends higher)
|
||||
dow_multiplier = 1.3 if date.dayofweek >= 5 else 1.0
|
||||
|
||||
# Monthly seasonality (summer higher)
|
||||
month_multiplier = 1.2 if date.month in [6, 7, 8] else 1.0
|
||||
|
||||
# Random noise
|
||||
noise = np.random.normal(1.0, 0.1)
|
||||
|
||||
quantity = base * dow_multiplier * month_multiplier * noise
|
||||
quantities.append(quantity)
|
||||
|
||||
return pd.DataFrame({
|
||||
'date': dates,
|
||||
'ds': dates,
|
||||
'quantity': quantities,
|
||||
'y': quantities
|
||||
})
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_weather_data():
|
||||
"""Generate sample weather data for testing."""
|
||||
dates = pd.date_range(start='2024-01-01', end='2024-12-31', freq='D')
|
||||
|
||||
weather_conditions = []
|
||||
temperatures = []
|
||||
precipitation = []
|
||||
|
||||
for date in dates:
|
||||
# Simulate weather patterns
|
||||
if np.random.random() < 0.1: # 10% rainy days
|
||||
weather_conditions.append('rain')
|
||||
precipitation.append(np.random.uniform(5, 20))
|
||||
elif np.random.random() < 0.05: # 5% snow
|
||||
weather_conditions.append('snow')
|
||||
precipitation.append(np.random.uniform(2, 10))
|
||||
else:
|
||||
weather_conditions.append('clear')
|
||||
precipitation.append(0)
|
||||
|
||||
# Temperature varies by month
|
||||
base_temp = 10 + (date.month - 1) * 2
|
||||
temperatures.append(base_temp + np.random.normal(0, 5))
|
||||
|
||||
return pd.DataFrame({
|
||||
'date': dates,
|
||||
'weather_condition': weather_conditions,
|
||||
'temperature': temperatures,
|
||||
'precipitation': precipitation
|
||||
})
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_holiday_data():
|
||||
"""Generate sample holiday data for testing."""
|
||||
dates = pd.date_range(start='2024-01-01', end='2024-12-31', freq='D')
|
||||
|
||||
holidays = []
|
||||
|
||||
# Add some holidays
|
||||
holiday_dates = {
|
||||
'2024-01-01': ('New Year', 'national'),
|
||||
'2024-03-29': ('Good Friday', 'religious'),
|
||||
'2024-04-01': ('Easter Monday', 'religious'),
|
||||
'2024-12-25': ('Christmas', 'religious'),
|
||||
'2024-12-26': ('Boxing Day', 'national')
|
||||
}
|
||||
|
||||
for date in dates:
|
||||
date_str = date.strftime('%Y-%m-%d')
|
||||
if date_str in holiday_dates:
|
||||
name, htype = holiday_dates[date_str]
|
||||
holidays.append({
|
||||
'date': date,
|
||||
'is_holiday': True,
|
||||
'holiday_name': name,
|
||||
'holiday_type': htype
|
||||
})
|
||||
else:
|
||||
holidays.append({
|
||||
'date': date,
|
||||
'is_holiday': False,
|
||||
'holiday_name': None,
|
||||
'holiday_type': None
|
||||
})
|
||||
|
||||
return pd.DataFrame(holidays)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sales_with_weather_impact(sample_sales_data, sample_weather_data):
|
||||
"""Generate sales data with weather impact."""
|
||||
merged = sample_sales_data.merge(sample_weather_data, on='date')
|
||||
|
||||
# Apply weather impact
|
||||
for idx, row in merged.iterrows():
|
||||
if row['weather_condition'] == 'rain':
|
||||
merged.at[idx, 'quantity'] *= 0.85 # -15% for rain
|
||||
merged.at[idx, 'y'] *= 0.85
|
||||
elif row['weather_condition'] == 'snow':
|
||||
merged.at[idx, 'quantity'] *= 0.75 # -25% for snow
|
||||
merged.at[idx, 'y'] *= 0.75
|
||||
|
||||
return merged
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sales_with_holiday_impact(sample_sales_data, sample_holiday_data):
|
||||
"""Generate sales data with holiday impact."""
|
||||
merged = sample_sales_data.merge(sample_holiday_data, on='date')
|
||||
|
||||
# Apply holiday impact
|
||||
for idx, row in merged.iterrows():
|
||||
if row['is_holiday'] and row['holiday_type'] == 'religious':
|
||||
merged.at[idx, 'quantity'] *= 1.6 # +60% for religious holidays
|
||||
merged.at[idx, 'y'] *= 1.6
|
||||
elif row['is_holiday']:
|
||||
merged.at[idx, 'quantity'] *= 1.3 # +30% for national holidays
|
||||
merged.at[idx, 'y'] *= 1.3
|
||||
|
||||
return merged
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_learn_weather_rules(sales_with_weather_impact, sample_weather_data):
|
||||
"""Test weather rules learning."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sales_with_weather_impact,
|
||||
external_data=sample_weather_data,
|
||||
min_samples=5
|
||||
)
|
||||
|
||||
# Check weather rules were learned
|
||||
assert 'weather' in results['rules']
|
||||
assert 'baseline_avg' in results['rules']['weather']
|
||||
assert 'conditions' in results['rules']['weather']
|
||||
|
||||
# Check rain rule learned
|
||||
if 'rain' in results['rules']['weather']['conditions']:
|
||||
rain_rule = results['rules']['weather']['conditions']['rain']
|
||||
assert 'learned_multiplier' in rain_rule
|
||||
assert 'learned_impact_pct' in rain_rule
|
||||
assert rain_rule['sample_size'] >= 5
|
||||
|
||||
# Learned multiplier should be close to 0.85 (we applied -15% impact)
|
||||
assert 0.75 < rain_rule['learned_multiplier'] < 0.95
|
||||
|
||||
# Check insights generated
|
||||
assert 'insights' in results
|
||||
assert len(results['insights']) > 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_learn_holiday_rules(sales_with_holiday_impact, sample_holiday_data):
|
||||
"""Test holiday rules learning."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sales_with_holiday_impact,
|
||||
external_data=sample_holiday_data,
|
||||
min_samples=2
|
||||
)
|
||||
|
||||
# Check holiday rules were learned
|
||||
assert 'holidays' in results['rules']
|
||||
assert 'baseline_avg' in results['rules']['holidays']
|
||||
|
||||
if 'holiday_types' in results['rules']['holidays']:
|
||||
holiday_types = results['rules']['holidays']['holiday_types']
|
||||
|
||||
# Check religious holidays learned higher impact than national
|
||||
if 'religious' in holiday_types and 'national' in holiday_types:
|
||||
religious_mult = holiday_types['religious']['learned_multiplier']
|
||||
national_mult = holiday_types['national']['learned_multiplier']
|
||||
|
||||
# Religious should have higher multiplier (we applied 1.6 vs 1.3)
|
||||
assert religious_mult > national_mult
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_learn_day_of_week_rules(sample_sales_data):
|
||||
"""Test day-of-week pattern learning."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sample_sales_data,
|
||||
external_data=None,
|
||||
min_samples=10
|
||||
)
|
||||
|
||||
# Check day-of-week rules learned
|
||||
assert 'day_of_week' in results['rules']
|
||||
assert 'days' in results['rules']['day_of_week']
|
||||
|
||||
days = results['rules']['day_of_week']['days']
|
||||
|
||||
# Weekend should have higher multipliers (we applied 1.3x)
|
||||
if 'Saturday' in days and 'Monday' in days:
|
||||
saturday_mult = days['Saturday']['learned_multiplier']
|
||||
monday_mult = days['Monday']['learned_multiplier']
|
||||
|
||||
assert saturday_mult > monday_mult
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_learn_month_rules(sample_sales_data):
|
||||
"""Test monthly seasonality learning."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sample_sales_data,
|
||||
external_data=None,
|
||||
min_samples=10
|
||||
)
|
||||
|
||||
# Check month rules learned
|
||||
assert 'months' in results['rules']
|
||||
assert 'months' in results['rules']['months']
|
||||
|
||||
months = results['rules']['months']['months']
|
||||
|
||||
# Summer months (June, July, August) should have higher multipliers
|
||||
if 'July' in months and 'January' in months:
|
||||
july_mult = months['July']['learned_multiplier']
|
||||
january_mult = months['January']['learned_multiplier']
|
||||
|
||||
assert july_mult > january_mult
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_insight_generation_weather_mismatch(sales_with_weather_impact, sample_weather_data):
|
||||
"""Test that insights are generated when learned rules differ from hardcoded."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sales_with_weather_impact,
|
||||
external_data=sample_weather_data,
|
||||
min_samples=5
|
||||
)
|
||||
|
||||
# Should generate insights comparing learned vs hardcoded
|
||||
insights = results['insights']
|
||||
|
||||
# Check for weather-related insights
|
||||
weather_insights = [i for i in insights if 'weather' in i.get('title', '').lower()]
|
||||
|
||||
if weather_insights:
|
||||
insight = weather_insights[0]
|
||||
assert 'type' in insight
|
||||
assert 'priority' in insight
|
||||
assert 'confidence' in insight
|
||||
assert 'metrics_json' in insight
|
||||
assert 'actionable' in insight
|
||||
assert 'recommendation_actions' in insight
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_confidence_calculation():
|
||||
"""Test confidence score calculation."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
# High confidence: large sample, low p-value
|
||||
high_conf = engine._calculate_confidence(sample_size=150, p_value=0.001)
|
||||
assert high_conf >= 90
|
||||
|
||||
# Medium confidence: moderate sample, moderate p-value
|
||||
med_conf = engine._calculate_confidence(sample_size=50, p_value=0.03)
|
||||
assert 60 <= med_conf < 90
|
||||
|
||||
# Low confidence: small sample, high p-value
|
||||
low_conf = engine._calculate_confidence(sample_size=15, p_value=0.12)
|
||||
assert low_conf < 60
|
||||
|
||||
|
||||
def test_get_rule():
|
||||
"""Test getting learned rules."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
# Manually set some rules for testing
|
||||
engine.weather_rules['product-1'] = {
|
||||
'conditions': {
|
||||
'rain': {
|
||||
'learned_multiplier': 0.85
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
engine.dow_rules['product-1'] = {
|
||||
'days': {
|
||||
'Saturday': {
|
||||
'learned_multiplier': 1.25
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Test retrieval
|
||||
rain_mult = engine.get_rule('product-1', 'weather', 'rain')
|
||||
assert rain_mult == 0.85
|
||||
|
||||
saturday_mult = engine.get_rule('product-1', 'day_of_week', 'Saturday')
|
||||
assert saturday_mult == 1.25
|
||||
|
||||
# Test non-existent rule
|
||||
unknown = engine.get_rule('product-1', 'weather', 'tornado')
|
||||
assert unknown is None
|
||||
|
||||
|
||||
def test_export_rules_for_prophet():
|
||||
"""Test exporting rules for Prophet integration."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
# Set up some test rules
|
||||
engine.weather_rules['product-1'] = {'conditions': {'rain': {'learned_multiplier': 0.85}}}
|
||||
engine.holiday_rules['product-1'] = {'holiday_types': {'Christmas': {'learned_multiplier': 1.7}}}
|
||||
|
||||
# Export
|
||||
exported = engine.export_rules_for_prophet('product-1')
|
||||
|
||||
assert 'weather' in exported
|
||||
assert 'holidays' in exported
|
||||
assert 'events' in exported
|
||||
assert 'day_of_week' in exported
|
||||
assert 'months' in exported
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_external_data(sample_sales_data):
|
||||
"""Test that engine works with sales data only (no external data)."""
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=sample_sales_data,
|
||||
external_data=None,
|
||||
min_samples=10
|
||||
)
|
||||
|
||||
# Should still learn DOW and month patterns
|
||||
assert 'day_of_week' in results['rules']
|
||||
assert 'months' in results['rules']
|
||||
|
||||
# Weather/holiday/event rules should not be present
|
||||
assert 'weather' not in results['rules'] or len(results['rules']['weather'].get('conditions', {})) == 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_insufficient_samples(sample_sales_data):
|
||||
"""Test handling of insufficient sample sizes."""
|
||||
# Use only 30 days of data
|
||||
small_data = sample_sales_data.head(30)
|
||||
|
||||
engine = DynamicRulesEngine()
|
||||
|
||||
results = await engine.learn_all_rules(
|
||||
tenant_id='test-tenant',
|
||||
inventory_product_id='test-product',
|
||||
sales_data=small_data,
|
||||
external_data=None,
|
||||
min_samples=50 # Require more samples than available
|
||||
)
|
||||
|
||||
# Should still return results but with fewer learned rules
|
||||
assert 'rules' in results
|
||||
assert 'insights' in results
|
||||
Reference in New Issue
Block a user