Skip to content

tea_tasting.datasets #

Example datasets.

make_users_data(*, covariates=False, seed=None, n_users=4000, ratio=1, sessions_uplift=0.0, orders_uplift=0.1, revenue_uplift=0.1, avg_sessions=2, avg_orders_per_session=0.25, avg_revenue_per_order=10, return_type='arrow') #

Generate simulated data for A/B testing scenarios.

Data mimics what you might encounter in an A/B test for an online store, with a user-level randomization. Each row represents an individual user with information about:

  • user: User identifier.
  • variant: Variant of the test. 0 is control, 1 is treatment.
  • sessions: Number of user's sessions.
  • orders: Number of user's orders.
  • revenue: Revenue generated by the user.

Optionally, pre-experimental data can be generated as well:

  • sessions_covariate: Number of user's sessions before the experiment.
  • orders_covariate: Number of user's orders before the experiment.
  • revenue_covariate: Revenue generated by the user before the experiment.

Parameters:

Name Type Description Default
covariates bool

If True, generates pre-experimental data as the covariates in addition to default columns.

 False
seed int | Generator | SeedSequence | None

Random seed.

 None
n_users int

Number of users.

 4000
ratio float | int

Ratio of the number of users in treatment relative to control.

 1
sessions_uplift float | int

Sessions uplift in the treatment variant, relative to control.

 0.0
orders_uplift float

Orders uplift in the treatment variant, relative to control.

 0.1
revenue_uplift float

Revenue uplift in the treatment variant, relative to control.

 0.1
avg_sessions float | int

Average number of sessions per user.

 2
avg_orders_per_session float

Average number of orders per session. Should be less than 1.

 0.25
avg_revenue_per_order float | int

Average revenue per order.

 10
return_type Literal['arrow', 'pandas', 'polars']

Return type:

  • "arrow": PyArrow Table.
  • "pandas": Pandas DataFrame.
  • "polars": Polars DataFrame.
 'arrow'

Returns:

Type Description
Table | Any | Any

Simulated data for A/B testing scenarios.

Examples:

>>> import tea_tasting as tt

>>> data = tt.make_users_data(seed=42)
>>> print(data)
pyarrow.Table
user: int64
variant: int64
sessions: int64
orders: int64
revenue: double
----
user: [[0,1,2,3,4,...,3995,3996,3997,3998,3999]]
variant: [[1,0,1,1,0,...,0,0,0,0,0]]
sessions: [[2,2,2,2,1,...,2,2,3,1,5]]
orders: [[1,1,1,1,1,...,0,0,0,0,2]]
revenue: [[9.17,6.43,7.94,15.93,7.14,...,0,0,0,0,17.16]]

With covariates:

>>> data = tt.make_users_data(seed=42, covariates=True)
>>> print(data)
pyarrow.Table
user: int64
variant: int64
sessions: int64
orders: int64
revenue: double
sessions_covariate: int64
orders_covariate: int64
revenue_covariate: double
----
user: [[0,1,2,3,4,...,3995,3996,3997,3998,3999]]
variant: [[1,0,1,1,0,...,0,0,0,0,0]]
sessions: [[2,2,2,2,1,...,2,2,3,1,5]]
orders: [[1,1,1,1,1,...,0,0,0,0,2]]
revenue: [[9.17,6.43,7.94,15.93,7.14,...,0,0,0,0,17.16]]
sessions_covariate: [[3,4,4,1,1,...,1,3,2,1,5]]
orders_covariate: [[2,1,2,0,1,...,0,1,0,0,0]]
revenue_covariate: [[19.19,2.77,22.57,0,13.68,...,0,13.52,0,0,0]]

As Pandas DataFrame:

>>> data = tt.make_users_data(seed=42, return_type="pandas")
>>> print(data)
      user  variant  sessions  orders  revenue
0        0        1         2       1     9.17
1        1        0         2       1     6.43
2        2        1         2       1     7.94
3        3        1         2       1    15.93
4        4        0         1       1     7.14
...    ...      ...       ...     ...      ...
3995  3995        0         2       0     0.00
3996  3996        0         2       0     0.00
3997  3997        0         3       0     0.00
3998  3998        0         1       0     0.00
3999  3999        0         5       2    17.16

[4000 rows x 5 columns]

As Polars DataFrame:

>>> data = tt.make_users_data(seed=42, return_type="polars")
>>> print(data)
shape: (4_000, 5)
┌──────┬─────────┬──────────┬────────┬─────────┐
│ user ┆ variant ┆ sessions ┆ orders ┆ revenue │
│ ---  ┆ ---     ┆ ---      ┆ ---    ┆ ---     │
│ i64  ┆ i64     ┆ i64      ┆ i64    ┆ f64     │
╞══════╪═════════╪══════════╪════════╪═════════╡
│ 0    ┆ 1       ┆ 2        ┆ 1      ┆ 9.17    │
│ 1    ┆ 0       ┆ 2        ┆ 1      ┆ 6.43    │
│ 2    ┆ 1       ┆ 2        ┆ 1      ┆ 7.94    │
│ 3    ┆ 1       ┆ 2        ┆ 1      ┆ 15.93   │
│ 4    ┆ 0       ┆ 1        ┆ 1      ┆ 7.14    │
│ …    ┆ …       ┆ …        ┆ …      ┆ …       │
│ 3995 ┆ 0       ┆ 2        ┆ 0      ┆ 0.0     │
│ 3996 ┆ 0       ┆ 2        ┆ 0      ┆ 0.0     │
│ 3997 ┆ 0       ┆ 3        ┆ 0      ┆ 0.0     │
│ 3998 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
│ 3999 ┆ 0       ┆ 5        ┆ 2      ┆ 17.16   │
└──────┴─────────┴──────────┴────────┴─────────┘
Source code in src/tea_tasting/datasets.py 
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
def make_users_data(
    *,
    covariates: bool = False,
    seed: int | np.random.Generator | np.random.SeedSequence | None = None,
    n_users: int = 4000,
    ratio: float | int = 1,
    sessions_uplift: float | int = 0.0,
    orders_uplift: float = 0.1,
    revenue_uplift: float = 0.1,
    avg_sessions: float | int = 2,
    avg_orders_per_session: float = 0.25,
    avg_revenue_per_order: float | int = 10,
    return_type: Literal["arrow", "pandas", "polars"] = "arrow",
) -> pa.Table | PandasDataFrame | PolarsDataFrame:
    """Generate simulated data for A/B testing scenarios.

    Data mimics what you might encounter in an A/B test for an online store,
    with a user-level randomization. Each row represents an individual user
    with information about:

    - `user`: User identifier.
    - `variant`: Variant of the test. 0 is control, 1 is treatment.
    - `sessions`: Number of user's sessions.
    - `orders`: Number of user's orders.
    - `revenue`: Revenue generated by the user.

    Optionally, pre-experimental data can be generated as well:

    - `sessions_covariate`: Number of user's sessions
        before the experiment.
    - `orders_covariate`: Number of user's orders before the experiment.
    - `revenue_covariate`: Revenue generated by the user
        before the experiment.

    Args:
        covariates: If `True`, generates pre-experimental data as the covariates
            in addition to default columns.
        seed: Random seed.
        n_users: Number of users.
        ratio: Ratio of the number of users in treatment relative to control.
        sessions_uplift: Sessions uplift in the treatment variant, relative to control.
        orders_uplift: Orders uplift in the treatment variant, relative to control.
        revenue_uplift: Revenue uplift in the treatment variant, relative to control.
        avg_sessions: Average number of sessions per user.
        avg_orders_per_session: Average number of orders per session.
            Should be less than `1`.
        avg_revenue_per_order: Average revenue per order.
        return_type: Return type:

            - `"arrow"`: PyArrow Table.
            - `"pandas"`: Pandas DataFrame.
            - `"polars"`: Polars DataFrame.

    Returns:
        Simulated data for A/B testing scenarios.

    Examples:
        ```pycon
        >>> import tea_tasting as tt

        >>> data = tt.make_users_data(seed=42)
        >>> print(data)
        pyarrow.Table
        user: int64
        variant: int64
        sessions: int64
        orders: int64
        revenue: double
        ----
        user: [[0,1,2,3,4,...,3995,3996,3997,3998,3999]]
        variant: [[1,0,1,1,0,...,0,0,0,0,0]]
        sessions: [[2,2,2,2,1,...,2,2,3,1,5]]
        orders: [[1,1,1,1,1,...,0,0,0,0,2]]
        revenue: [[9.17,6.43,7.94,15.93,7.14,...,0,0,0,0,17.16]]

        ```

        With covariates:

        ```pycon
        >>> data = tt.make_users_data(seed=42, covariates=True)
        >>> print(data)
        pyarrow.Table
        user: int64
        variant: int64
        sessions: int64
        orders: int64
        revenue: double
        sessions_covariate: int64
        orders_covariate: int64
        revenue_covariate: double
        ----
        user: [[0,1,2,3,4,...,3995,3996,3997,3998,3999]]
        variant: [[1,0,1,1,0,...,0,0,0,0,0]]
        sessions: [[2,2,2,2,1,...,2,2,3,1,5]]
        orders: [[1,1,1,1,1,...,0,0,0,0,2]]
        revenue: [[9.17,6.43,7.94,15.93,7.14,...,0,0,0,0,17.16]]
        sessions_covariate: [[3,4,4,1,1,...,1,3,2,1,5]]
        orders_covariate: [[2,1,2,0,1,...,0,1,0,0,0]]
        revenue_covariate: [[19.19,2.77,22.57,0,13.68,...,0,13.52,0,0,0]]

        ```

        As Pandas DataFrame:

        ```pycon
        >>> data = tt.make_users_data(seed=42, return_type="pandas")
        >>> print(data)
              user  variant  sessions  orders  revenue
        0        0        1         2       1     9.17
        1        1        0         2       1     6.43
        2        2        1         2       1     7.94
        3        3        1         2       1    15.93
        4        4        0         1       1     7.14
        ...    ...      ...       ...     ...      ...
        3995  3995        0         2       0     0.00
        3996  3996        0         2       0     0.00
        3997  3997        0         3       0     0.00
        3998  3998        0         1       0     0.00
        3999  3999        0         5       2    17.16
        <BLANKLINE>
        [4000 rows x 5 columns]

        ```

        As Polars DataFrame:

        ```pycon
        >>> data = tt.make_users_data(seed=42, return_type="polars")
        >>> print(data)
        shape: (4_000, 5)
        ┌──────┬─────────┬──────────┬────────┬─────────┐
        │ user ┆ variant ┆ sessions ┆ orders ┆ revenue │
        │ ---  ┆ ---     ┆ ---      ┆ ---    ┆ ---     │
        │ i64  ┆ i64     ┆ i64      ┆ i64    ┆ f64     │
        ╞══════╪═════════╪══════════╪════════╪═════════╡
        │ 0    ┆ 1       ┆ 2        ┆ 1      ┆ 9.17    │
        │ 1    ┆ 0       ┆ 2        ┆ 1      ┆ 6.43    │
        │ 2    ┆ 1       ┆ 2        ┆ 1      ┆ 7.94    │
        │ 3    ┆ 1       ┆ 2        ┆ 1      ┆ 15.93   │
        │ 4    ┆ 0       ┆ 1        ┆ 1      ┆ 7.14    │
        │ …    ┆ …       ┆ …        ┆ …      ┆ …       │
        │ 3995 ┆ 0       ┆ 2        ┆ 0      ┆ 0.0     │
        │ 3996 ┆ 0       ┆ 2        ┆ 0      ┆ 0.0     │
        │ 3997 ┆ 0       ┆ 3        ┆ 0      ┆ 0.0     │
        │ 3998 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
        │ 3999 ┆ 0       ┆ 5        ┆ 2      ┆ 17.16   │
        └──────┴─────────┴──────────┴────────┴─────────┘

        ```
    """
    return _make_data(
        covariates=covariates,
        seed=seed,
        n_users=n_users,
        ratio=ratio,
        sessions_uplift=sessions_uplift,
        orders_uplift=orders_uplift,
        revenue_uplift=revenue_uplift,
        avg_sessions=avg_sessions,
        avg_orders_per_session=avg_orders_per_session,
        avg_revenue_per_order=avg_revenue_per_order,
        return_type=return_type,
        explode_sessions=False,
    )

make_sessions_data(*, covariates=False, seed=None, n_users=4000, ratio=1, sessions_uplift=0.0, orders_uplift=0.1, revenue_uplift=0.1, avg_sessions=2, avg_orders_per_session=0.25, avg_revenue_per_order=10, return_type='arrow') #

Generate simulated user data for A/B testing scenarios.

Data mimics what you might encounter in an A/B test for an online store, with a user-level randomization. Each row represents a user's session with information about:

  • user: User identifier.
  • variant: Variant of the test. 0 is control, 1 is treatment.
  • sessions: Number of user's sessions.
  • orders: Number of user's orders.
  • revenue: Revenue generated by the user.

Optionally, pre-experimental data can be generated as well:

  • sessions_covariate: Number of user's sessions before the experiment.
  • orders_covariate: Number of user's orders before the experiment.
  • revenue_covariate: Revenue generated by the user before the experiment.

Parameters:

Name Type Description Default
covariates bool

If True, generates pre-experimental data as the covariates in addition to default columns.

 False
seed int | Generator | SeedSequence | None

Random seed.

 None
n_users int

Number of users.

 4000
ratio float | int

Ratio of the number of users in treatment relative to control.

 1
sessions_uplift float | int

Sessions uplift in the treatment variant, relative to control.

 0.0
orders_uplift float

Orders uplift in the treatment variant, relative to control.

 0.1
revenue_uplift float

Revenue uplift in the treatment variant, relative to control.

 0.1
avg_sessions float | int

Average number of sessions per user.

 2
avg_orders_per_session float

Average number of orders per session. Should be less than 1.

 0.25
avg_revenue_per_order float | int

Average revenue per order.

 10
return_type Literal['arrow', 'pandas', 'polars']

Return type:

  • "arrow": PyArrow Table.
  • "pandas": Pandas DataFrame.
  • "polars": Polars DataFrame.
 'arrow'

Returns:

Type Description
Table | Any | Any

Simulated data for A/B testing scenarios.

Examples:

>>> import tea_tasting as tt

>>> data = tt.make_sessions_data(seed=42)
>>> data
pyarrow.Table
user: int64
variant: int64
sessions: int64
orders: int64
revenue: double
----
user: [[0,0,1,1,2,...,3999,3999,3999,3999,3999]]
variant: [[1,1,0,0,1,...,0,0,0,0,0]]
sessions: [[1,1,1,1,1,...,1,1,1,1,1]]
orders: [[1,1,1,1,1,...,1,0,1,1,0]]
revenue: [[5.89,6.13,2.61,12.3,11.57,...,23.63,0,2.4,24.54,0]]

With covariates:

>>> data = tt.make_sessions_data(seed=42, covariates=True)
>>> data
pyarrow.Table
user: int64
variant: int64
sessions: int64
orders: int64
revenue: double
sessions_covariate: double
orders_covariate: double
revenue_covariate: double
----
user: [[0,0,1,1,2,...,3999,3999,3999,3999,3999]]
variant: [[1,1,0,0,1,...,0,0,0,0,0]]
sessions: [[1,1,1,1,1,...,1,1,1,1,1]]
orders: [[1,1,1,1,1,...,1,0,1,1,0]]
revenue: [[5.89,6.13,2.61,12.3,11.57,...,23.63,0,2.4,24.54,0]]
sessions_covariate: [[1.5,1.5,0,0,1.5,...,0.2,0.2,0.2,0.2,0.2]]
orders_covariate: [[0.5,0.5,0,0,1.5,...,0,0,0,0,0]]
revenue_covariate: [[1.24,1.24,0,0,12.32,...,0,0,0,0,0]]

As Pandas DataFrame:

>>> data = tt.make_sessions_data(seed=42, return_type="pandas")
>>> print(data)
      user  variant  sessions  orders  revenue
0        0        1         1       1     5.89
1        0        1         1       1     6.13
2        1        0         1       1     2.61
3        1        0         1       1    12.30
4        2        1         1       1    11.57
...    ...      ...       ...     ...      ...
7953  3999        0         1       1    23.63
7954  3999        0         1       0     0.00
7955  3999        0         1       1     2.40
7956  3999        0         1       1    24.54
7957  3999        0         1       0     0.00

[7958 rows x 5 columns]

As Polars DataFrame:

>>> data = tt.make_sessions_data(seed=42, return_type="polars")
>>> print(data)
shape: (7_958, 5)
┌──────┬─────────┬──────────┬────────┬─────────┐
│ user ┆ variant ┆ sessions ┆ orders ┆ revenue │
│ ---  ┆ ---     ┆ ---      ┆ ---    ┆ ---     │
│ i64  ┆ i64     ┆ i64      ┆ i64    ┆ f64     │
╞══════╪═════════╪══════════╪════════╪═════════╡
│ 0    ┆ 1       ┆ 1        ┆ 1      ┆ 5.89    │
│ 0    ┆ 1       ┆ 1        ┆ 1      ┆ 6.13    │
│ 1    ┆ 0       ┆ 1        ┆ 1      ┆ 2.61    │
│ 1    ┆ 0       ┆ 1        ┆ 1      ┆ 12.3    │
│ 2    ┆ 1       ┆ 1        ┆ 1      ┆ 11.57   │
│ …    ┆ …       ┆ …        ┆ …      ┆ …       │
│ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 23.63   │
│ 3999 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
│ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 2.4     │
│ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 24.54   │
│ 3999 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
└──────┴─────────┴──────────┴────────┴─────────┘
Source code in src/tea_tasting/datasets.py 
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
def make_sessions_data(
    *,
    covariates: bool = False,
    seed: int | np.random.Generator | np.random.SeedSequence | None = None,
    n_users: int = 4000,
    ratio: float | int = 1,
    sessions_uplift: float | int = 0.0,
    orders_uplift: float = 0.1,
    revenue_uplift: float = 0.1,
    avg_sessions: float | int = 2,
    avg_orders_per_session: float = 0.25,
    avg_revenue_per_order: float | int = 10,
    return_type: Literal["arrow", "pandas", "polars"] = "arrow",
) -> pa.Table | PandasDataFrame | PolarsDataFrame:
    """Generate simulated user data for A/B testing scenarios.

    Data mimics what you might encounter in an A/B test for an online store,
    with a user-level randomization. Each row represents a user's session
    with information about:

    - `user`: User identifier.
    - `variant`: Variant of the test. 0 is control, 1 is treatment.
    - `sessions`: Number of user's sessions.
    - `orders`: Number of user's orders.
    - `revenue`: Revenue generated by the user.

    Optionally, pre-experimental data can be generated as well:

    - `sessions_covariate`: Number of user's sessions
        before the experiment.
    - `orders_covariate`: Number of user's orders before the experiment.
    - `revenue_covariate`: Revenue generated by the user
        before the experiment.

    Args:
        covariates: If `True`, generates pre-experimental data as the covariates
            in addition to default columns.
        seed: Random seed.
        n_users: Number of users.
        ratio: Ratio of the number of users in treatment relative to control.
        sessions_uplift: Sessions uplift in the treatment variant, relative to control.
        orders_uplift: Orders uplift in the treatment variant, relative to control.
        revenue_uplift: Revenue uplift in the treatment variant, relative to control.
        avg_sessions: Average number of sessions per user.
        avg_orders_per_session: Average number of orders per session.
            Should be less than `1`.
        avg_revenue_per_order: Average revenue per order.
        return_type: Return type:

            - `"arrow"`: PyArrow Table.
            - `"pandas"`: Pandas DataFrame.
            - `"polars"`: Polars DataFrame.

    Returns:
        Simulated data for A/B testing scenarios.

    Examples:
        ```pycon
        >>> import tea_tasting as tt

        >>> data = tt.make_sessions_data(seed=42)
        >>> data
        pyarrow.Table
        user: int64
        variant: int64
        sessions: int64
        orders: int64
        revenue: double
        ----
        user: [[0,0,1,1,2,...,3999,3999,3999,3999,3999]]
        variant: [[1,1,0,0,1,...,0,0,0,0,0]]
        sessions: [[1,1,1,1,1,...,1,1,1,1,1]]
        orders: [[1,1,1,1,1,...,1,0,1,1,0]]
        revenue: [[5.89,6.13,2.61,12.3,11.57,...,23.63,0,2.4,24.54,0]]

        ```

        With covariates:

        ```pycon
        >>> data = tt.make_sessions_data(seed=42, covariates=True)
        >>> data
        pyarrow.Table
        user: int64
        variant: int64
        sessions: int64
        orders: int64
        revenue: double
        sessions_covariate: double
        orders_covariate: double
        revenue_covariate: double
        ----
        user: [[0,0,1,1,2,...,3999,3999,3999,3999,3999]]
        variant: [[1,1,0,0,1,...,0,0,0,0,0]]
        sessions: [[1,1,1,1,1,...,1,1,1,1,1]]
        orders: [[1,1,1,1,1,...,1,0,1,1,0]]
        revenue: [[5.89,6.13,2.61,12.3,11.57,...,23.63,0,2.4,24.54,0]]
        sessions_covariate: [[1.5,1.5,0,0,1.5,...,0.2,0.2,0.2,0.2,0.2]]
        orders_covariate: [[0.5,0.5,0,0,1.5,...,0,0,0,0,0]]
        revenue_covariate: [[1.24,1.24,0,0,12.32,...,0,0,0,0,0]]

        ```

        As Pandas DataFrame:

        ```pycon
        >>> data = tt.make_sessions_data(seed=42, return_type="pandas")
        >>> print(data)
              user  variant  sessions  orders  revenue
        0        0        1         1       1     5.89
        1        0        1         1       1     6.13
        2        1        0         1       1     2.61
        3        1        0         1       1    12.30
        4        2        1         1       1    11.57
        ...    ...      ...       ...     ...      ...
        7953  3999        0         1       1    23.63
        7954  3999        0         1       0     0.00
        7955  3999        0         1       1     2.40
        7956  3999        0         1       1    24.54
        7957  3999        0         1       0     0.00
        <BLANKLINE>
        [7958 rows x 5 columns]

        ```

        As Polars DataFrame:

        ```pycon
        >>> data = tt.make_sessions_data(seed=42, return_type="polars")
        >>> print(data)
        shape: (7_958, 5)
        ┌──────┬─────────┬──────────┬────────┬─────────┐
        │ user ┆ variant ┆ sessions ┆ orders ┆ revenue │
        │ ---  ┆ ---     ┆ ---      ┆ ---    ┆ ---     │
        │ i64  ┆ i64     ┆ i64      ┆ i64    ┆ f64     │
        ╞══════╪═════════╪══════════╪════════╪═════════╡
        │ 0    ┆ 1       ┆ 1        ┆ 1      ┆ 5.89    │
        │ 0    ┆ 1       ┆ 1        ┆ 1      ┆ 6.13    │
        │ 1    ┆ 0       ┆ 1        ┆ 1      ┆ 2.61    │
        │ 1    ┆ 0       ┆ 1        ┆ 1      ┆ 12.3    │
        │ 2    ┆ 1       ┆ 1        ┆ 1      ┆ 11.57   │
        │ …    ┆ …       ┆ …        ┆ …      ┆ …       │
        │ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 23.63   │
        │ 3999 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
        │ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 2.4     │
        │ 3999 ┆ 0       ┆ 1        ┆ 1      ┆ 24.54   │
        │ 3999 ┆ 0       ┆ 1        ┆ 0      ┆ 0.0     │
        └──────┴─────────┴──────────┴────────┴─────────┘

        ```
    """
    return _make_data(
        covariates=covariates,
        seed=seed,
        n_users=n_users,
        ratio=ratio,
        sessions_uplift=sessions_uplift,
        orders_uplift=orders_uplift,
        revenue_uplift=revenue_uplift,
        avg_sessions=avg_sessions,
        avg_orders_per_session=avg_orders_per_session,
        avg_revenue_per_order=avg_revenue_per_order,
        return_type=return_type,
        explode_sessions=True,
    )