Median stat calculation fails when a column has a single value

[nnansters]

Describe the bug Median stat calculation fails when a column has a single value due to sampling error component calculation.

To Reproduce

import pandas as pd

import nannyml as nml

ref = pd.DataFrame({'y_true': [1 for _ in range(1000)]})

calc = nml.stats.median.SummaryStatsMedianCalculator(
    column_names=[
        "y_true"
    ],
    timestamp_column_name='timestamp',
    chunk_period='M',
)
calc.fit(ref)

This will raise the following exception:

nannyml.exceptions.CalculatorException: failed while fitting <nannyml.stats.median.calculator.SummaryStatsMedianCalculator object at 0x7f1ae9560f40>.
The data appears to lie in a lower-dimensional subspace of the space in which it is expressed. This has resulted in a singular data covariance matrix, which cannot be treated using the algorithms implemented in `gaussian_kde`. Consider performing principle component analysis / dimensionality reduction and using `gaussian_kde` with the transformed data.

Expected behavior Sampling error should be 0

Additional context The issue is being caused by the following snippet (in summary_stats.py):

    """
    Calculate sampling error components for Summary Stats Median
    using reference data.

    Parameters
    ----------
    col: pd.Series
        column for which we are calculating sampling error components

    Returns
    -------
    (median, pdf(median): Tuple[np.ndarray]
    """
    median = col.median()
    kernel = gaussian_kde(col)
    fmedian = kernel.evaluate(median)[0]
    return (median, fmedian)

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.