mirror of
https://github.com/hanzoai/insights.git
synced 2026-10-30 16:15:31 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
137 lines
4.6 KiB
Python
137 lines
4.6 KiB
Python
from dataclasses import dataclass
|
|
from enum import Enum
|
|
from typing import Any, Optional
|
|
|
|
from ..shared.enums import DifferenceType
|
|
from ..shared.statistics import AnyStatistic, StatisticError
|
|
from .tests import SequentialTwoSidedTTest, StatisticalTest, TestResult, TwoSidedTTest
|
|
|
|
|
|
class TestType(Enum):
|
|
"""Available test types."""
|
|
|
|
TWO_SIDED = "two_sided"
|
|
|
|
|
|
DEFAULT_SEQUENTIAL_TUNING_PARAMETER: float = SequentialTwoSidedTTest.DEFAULT_TUNING_PARAMETER
|
|
|
|
|
|
@dataclass
|
|
class FrequentistConfig:
|
|
"""Configuration for frequentist testing."""
|
|
|
|
alpha: float = 0.05
|
|
difference_type: DifferenceType = DifferenceType.RELATIVE
|
|
test_type: TestType = TestType.TWO_SIDED
|
|
sequential_testing_enabled: bool = False
|
|
sequential_tuning_parameter: float = DEFAULT_SEQUENTIAL_TUNING_PARAMETER
|
|
|
|
def __post_init__(self):
|
|
"""Validate configuration parameters."""
|
|
if not (0 < self.alpha < 1):
|
|
raise StatisticError("Alpha must be between 0 and 1")
|
|
if self.sequential_testing_enabled and self.sequential_tuning_parameter <= 0:
|
|
raise StatisticError("Sequential tuning parameter must be positive")
|
|
|
|
|
|
class FrequentistMethod:
|
|
"""
|
|
Main class for frequentist A/B testing.
|
|
|
|
This class provides a high-level interface for running statistical tests
|
|
on A/B experiment data using various test types and configurations.
|
|
|
|
Example:
|
|
# Basic usage
|
|
method = FrequentistMethod()
|
|
result = method.run_test(treatment_stat, control_stat)
|
|
|
|
# With custom configuration
|
|
config = FrequentistConfig(
|
|
alpha=0.01,
|
|
difference_type=DifferenceType.ABSOLUTE,
|
|
test_type=TestType.TWO_SIDED
|
|
)
|
|
method = FrequentistMethod(config)
|
|
result = method.run_test(treatment_stat, control_stat)
|
|
"""
|
|
|
|
def __init__(self, config: Optional[FrequentistConfig] = None):
|
|
"""
|
|
Initialize FrequentistMethod with configuration.
|
|
|
|
Args:
|
|
config: Configuration object (uses defaults if None)
|
|
"""
|
|
self.config = config or FrequentistConfig()
|
|
|
|
def run_test(self, treatment_stat: AnyStatistic, control_stat: AnyStatistic, **kwargs) -> TestResult:
|
|
"""
|
|
Run statistical test comparing treatment vs control.
|
|
|
|
Args:
|
|
treatment_stat: Treatment group statistic
|
|
control_stat: Control group statistic
|
|
**kwargs: Additional parameters (overrides config values)
|
|
|
|
Returns:
|
|
TestResult with all statistical outputs
|
|
|
|
Raises:
|
|
StatisticError: If inputs are invalid or test fails
|
|
"""
|
|
if self.config.test_type == TestType.TWO_SIDED:
|
|
if self.config.sequential_testing_enabled:
|
|
test: StatisticalTest = SequentialTwoSidedTTest(
|
|
alpha=self.config.alpha,
|
|
sequential_tuning_parameter=self.config.sequential_tuning_parameter,
|
|
)
|
|
else:
|
|
test = TwoSidedTTest(self.config.alpha)
|
|
else:
|
|
raise StatisticError(f"Unknown test type: {self.config.test_type}")
|
|
|
|
try:
|
|
return test.run_test(
|
|
treatment_stat=treatment_stat,
|
|
control_stat=control_stat,
|
|
difference_type=self.config.difference_type,
|
|
**kwargs,
|
|
)
|
|
except Exception as e:
|
|
raise StatisticError(f"Test execution failed: {str(e)}") from e
|
|
|
|
def get_summary(self, result: TestResult) -> dict[str, Any]:
|
|
"""
|
|
Get human-readable summary of test result.
|
|
|
|
Args:
|
|
result: TestResult object
|
|
|
|
Returns:
|
|
Dict with summary information
|
|
"""
|
|
summary: dict[str, Any] = {
|
|
"test_type": result.test_type,
|
|
"point_estimate": result.point_estimate,
|
|
"confidence_interval": result.confidence_interval,
|
|
"p_value": result.p_value,
|
|
"is_significant": result.is_significant,
|
|
"alpha": result.alpha,
|
|
"degrees_of_freedom": result.degrees_of_freedom,
|
|
}
|
|
|
|
# Add interpretation
|
|
if self.config.difference_type == DifferenceType.RELATIVE:
|
|
summary["interpretation"] = {
|
|
"effect_size": f"{result.point_estimate:.1%}",
|
|
"effect_direction": "positive" if result.point_estimate > 0 else "negative",
|
|
}
|
|
elif self.config.difference_type == DifferenceType.ABSOLUTE:
|
|
summary["interpretation"] = {
|
|
"effect_size": result.point_estimate,
|
|
"effect_direction": "positive" if result.point_estimate > 0 else "negative",
|
|
}
|
|
|
|
return summary
|