vivainsights.identify_inactiveweeks¶

Identify weeks where collaboration hours fall far below the mean.

The function identify_inactiveweeks identifies weeks where collaboration hours are more than a specified number of standard deviations below the mean and returns the result in the specified format.

vivainsights.identify_inactiveweeks.identify_inactiveweeks(data, sd=2, return_type='text')[source]¶

Identify weeks where collaboration hours fall far below the mean.

Uses z-scores per person to flag weeks with abnormally low collaboration activity.

Parameters:

data (pandas.DataFrame) – Person query data. Must contain PersonId and Collaboration_hours.
sd (int, default 2) – Number of standard deviations below the mean to flag as inactive.
return_type (str, default "text") – "text" for a diagnostic message, "data_dirty" / "dirty_data" for inactive rows only, "data_cleaned" / "cleaned_data" for active rows only, or "data" for the full dataset with an inactiveweek flag.

Returns:

A diagnostic message or a filtered / labelled DataFrame depending on return_type.

Return type:

str or pandas.DataFrame

Examples

Return a diagnostic text summary:

>>> import vivainsights as vi
>>> pq_data = vi.load_pq_data()
>>> vi.identify_inactiveweeks(pq_data, sd=2, return_type="text")

Return the full dataset with inactive weeks flagged:

>>> vi.identify_inactiveweeks(pq_data, sd=2, return_type="data")

Return only the cleaned dataset (inactive weeks removed):

>>> vi.identify_inactiveweeks(pq_data, sd=2, return_type="data_cleaned")

Return only the dirty rows (inactive weeks):

>>> vi.identify_inactiveweeks(pq_data, sd=2, return_type="data_dirty")