Glossary

Absolute value the volume, size, or magnitude of an observed event or phenomenon.

Behavioral cohort analysis a type of analysis that involves singling out a cohort of users who performed an action or sequence of actions during a certain time period.

Churn rate the share of users that quit using the product at a particular stage.

Cohort a group of people for whom a certain event took place around the same time. (Cohorts might also be defined by something they have in common — e.g. people with blonde hair.)

Event a recorded instance of a user's performing a certain action.

Heatmap a table visualization whose cells vary in color depending on their proximity to the maximum and minimum values.

Lifetime a metric that tells you how old a cohort is.

Period the span of time during which evens took place.

Relative value the ratio of two other values.

Retention rate tells you how many users from a cohort have remained active out of their initial number.

Practice

COPYpython
1# making a heatmap
2# annot=True - the heatmap cells will display values as text
3# fmt='.1f' -  sets the value printing format (one decimal place)
4# linewidths=1 - the width of the line that will separate heatmap cells (1 pixel)
5# linecolor='gray' - line color (gray)
6
7import seaborn as sns
8
9sns.heatmap(dataframe, annot=True, fmt='.1f', linewidths=1, linecolor='gray')

COPYpython
1# calculating the percentage change compared with the preceding row
2
3cohorts['churn_rate'] = cohorts.groupby(['column1'])['column2'].pct_change()