Metadata-Version: 2.1
Name: wstats
Version: 0.0.99
Summary: An implementation of a few weighted statistics
Home-page: https://github.com/scottyler89/weighted_stats/
Author: Scott Tyler
Author-email: scottyler89@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numba
Requires-Dist: numpy
Requires-Dist: scipy

# Weighted statistics

## What?
We've re-implemented some weighted statistics inspired by the weights R package (https://github.com/cran/weights/tree/master).
At the moment, it's just the weighted t-test, but this may expand.

## How?
```python
import numpy as np
from wstats import wtd_t_test

# Example data for testing
x = np.random.normal(0, 1, 100)
y = np.random.normal(0.5, 1, 100)
wx = np.random.rand(100)
wy = np.random.rand(100)

# Execute tests
# Without bootstrapping
result_no_boot = wtd_t_test(x, y, wx, wy, alternative="two-sided", bootse=False)
# With bootstrapping
result_boot = wtd_t_test(x, y, wx, wy, alternative="two-sided", bootse=True, bootn=int(1e4))

(result_no_boot, result_boot)

```
