How to use the pingouin.utils._is_statsmodels_installed function in pingouin

directory. To change that, specify the filename with full path.

    Returns
    -------
    aov : DataFrame
        ANCOVA summary ::

        'Source' : Names of the factor considered
        'SS' : Sums of squares
        'DF' : Degrees of freedom
        'F' : F-values
        'p-unc' : Uncorrected p-values
    """
    # Check that stasmodels is installed
    from pingouin.utils import _is_statsmodels_installed
    _is_statsmodels_installed(raise_error=True)
    from statsmodels.api import stats
    from statsmodels.formula.api import ols

    # Check that covariates are numeric ('float', 'int')
    assert all([data[covar[i]].dtype.kind in 'fi' for i in range(len(covar))])

    # Fit ANCOVA model
    formula = dv + ' ~ C(' + between + ')'
    for c in covar:
        formula += ' + ' + c
    model = ols(formula, data=data).fit()
    aov = stats.anova_lm(model, typ=2).reset_index()

    aov.rename(columns={'index': 'Source', 'sum_sq': 'SS',
                        'df': 'DF', 'PR(>F)': 'p-unc'}, inplace=True)

def anovan(data=None, dv=None, between=None, ss_type=2, export_filename=None):
    """N-way ANOVA using statsmodels.

    This is an internal function. The main call to this function should be done
    by the :py:func:`pingouin.anova` function.
    """
    # Check that stasmodels is installed
    from pingouin.utils import _is_statsmodels_installed
    _is_statsmodels_installed(raise_error=True)
    from statsmodels.api import stats
    from statsmodels.formula.api import ols

    # Validate the dataframe
    _check_dataframe(dv=dv, between=between, data=data, effects='between')
    all_cols = _flatten_list([dv, between])
    bad_chars = [',', '(', ')', ':']
    if not all([c not in v for c in bad_chars for v in all_cols]):
        err_msg = "comma, bracket, and colon are not allowed in column names."
        raise ValueError(err_msg)

    # Drop missing values
    data = data[all_cols].dropna()
    assert data.shape[0] >= 5, 'Data must have at least 5 non-missing values.'

    # Reset index (avoid duplicate axis error)

With some tweakings

    .. plot::

        >>> import pingouin as pg
        >>> import seaborn as sns
        >>> df = pg.read_dataset('rm_corr')
        >>> sns.set(style='darkgrid', font_scale=1.2)
        >>> g = pg.plot_rm_corr(data=df, x='pH', y='PacO2',
        ...                     subject='Subject', legend=True,
        ...                     kwargs_facetgrid=dict(height=4.5, aspect=1.5,
        ...                                           palette='Spectral'))
    """
    # Check that stasmodels is installed
    from pingouin.utils import _is_statsmodels_installed
    _is_statsmodels_installed(raise_error=True)
    from statsmodels.formula.api import ols

    # Safety check (duplicated from pingouin.rm_corr)
    assert isinstance(data, pd.DataFrame), 'Data must be a DataFrame'
    assert x in data.columns, 'The %s column is not in data.' % x
    assert y in data.columns, 'The %s column is not in data.' % y
    assert data[x].dtype.kind in 'bfi', '%s must be numeric.' % x
    assert data[y].dtype.kind in 'bfi', '%s must be numeric.' % y
    assert subject in data.columns, 'The %s column is not in data.' % subject
    if data[subject].nunique() < 3:
        raise ValueError('rm_corr requires at least 3 unique subjects.')

    # Remove missing values
    data = data[[x, y, subject]].dropna(axis=0)

    # Calculate rm_corr