Scatter stats

fleur.scatterstats.ScatterStats

Statistical correlation and plotting class for numerical variables.

Attributes:

Name	Type	Description
n_obs	int	Total number of observations.
alpha	float	Probability of rejecting a true null hypothesis
dof	int	Degrees of freedom for t-test.
pvalue	float	P-value of the t-test.
intercept	float	The intercept (estimation of beta2) in the model.
slope	float	The slope (estimation of beta1) in the model.
stderr_slope	float	Standard error of the slope.
ci_lower	float	Lower bound of the confidence interval.
ci_upper	float	Upper bound of the confidence interval.
ax	Axes	The main matplotlib axes.
fig	Figure	The matplotlib figure.

__init__(x, y, data=None, alternative='two-sided', correlation_measure='pearson', ci=95)

Initialize a ScatterStats() instance.

Parameters:

Name	Type	Description	Default
x	Union[str, SeriesT, Iterable]	Colname of data or a Series or array-like.	required
y	Union[str, SeriesT, Iterable]	Colname of data or a Series or array-like.	required
data	Optional[Frame]	An optional dataframe.	None
alternative	str	Defines the alternative hypothesis. Default is 'two-sided'. Must be one of 'two-sided', 'less' and 'greater'.	'two-sided'
correlation_measure	str	The correlation measure to use. Default is 'pearson'. Must be one of 'pearson', 'kendall', 'spearman'.	'pearson'
ci	Number	Confidence level for the top label and the regression plot. The default value is 95 (for a 95% confidence level).	95

plot(*, marginal=True, bins=None, scatter_kws=None, line_kws=None, area_kws=None, hist_kws=None, subplot_mosaic_kwargs=None, show_stats=True)

Plot a scatter plot of two variables, with a linear regression line and annotate it with main statistical results.

Parameters:

Name	Type	Description	Default
bins	Union[int, List[int]]	Number of bins for the marginal distributions. This can be an integer or a list of two integers (the first for the top distribution and the second for the other).	None
marginal	bool	Whether to include marginal histograms. Default is True.	True
line_kws	Union[dict, None]	Additional parameters which will be passed to the plot() function in matplotlib.	None
scatter_kws	Union[dict, None]	Additional parameters which will be passed to the scatter() function in matplotlib.	None
area_kws	Union[dict, None]	Additional parameters which will be passed to the fill_between() function in matplotlib.	None
hist_kws	Union[dict, None]	Additional parameters which will be passed to the hist() function in matplotlib.	None
subplot_mosaic_kwargs	Union[dict, None]	Additional keyword arguments to pass to plt.subplot_mosaic(). Default is None.	None
show_stats	bool	If True, display statistics on the plot.	True

summary()

Print a text summary of the statistical test performed.

Displays the formatted test statistic with p-value, CI, etc.

Raises:

Type	Description
RuntimeError	If plot() was not called before summary().

Examples

• Minimalist example

# mkdocs: render
from fleur import ScatterStats
from fleur import datasets

df = datasets.load_iris()

ScatterStats(x=df["sepal_length"], y=df["sepal_width"]).plot()