Processes a dataset to create user sessions based on time gaps, ordering columns, or actor groupings. It supports different ways to understand order in user behavior and provides flexibility when widening the data.
Usage
prepare_data(
data,
actor,
time,
action,
order,
time_threshold = 900,
custom_format = NULL,
is_unix_time = FALSE,
unix_time_unit = "seconds",
unused_fn = dplyr::first
)Arguments
- data
A
data.frameor containing the action/event data.- actor
A
characterstring giving the name of the column that represents a user/actor identifier. If not provided and neithertimenororderis specified, the entire dataset is treated as a single session.- time
A
characterstring giving the name of the column representing timestamps of the action events.- action
A
characterstring giving the name of the column holding the information about the action taken.- order
A
characterstring giving the name of a column with sequence numbers or non-unique orderable values that indicate order within anactorgroup, if not present it will be ordered with all the data if noactoris available, used when widening the data. If bothactorandtimeare specified, then the sequence order should be specified such that it determines the order of events withinactorand each session.- time_threshold
An
integerspecifying the time threshold in seconds for creating new time-based sessions. Defaults to 900 seconds.- custom_format
A
characterstring giving the format used to parse thetimecolumn.- is_unix_time
A
logicalvalue indicating whether thetimecolumn is in Unix time. The default isFALSE.- unix_time_unit
A
characterstring giving the Unix time unit whenis_unix_timeisTRUE. The default is"seconds". Valid options are"seconds","milliseconds", or"microseconds".- unused_fn
How to handle extra columns when pivoting to wide format. See
tidyr::pivot_wider(). The default is to keep all columns and to use the first value.
Value
A tna_data object, which is a list with the following elements:
long_data: The processed data in long format.sequence_data: The processed data on the sequences in wide format, with actions/events as different variables structured with sequences.meta_data: Other variables from the original data in wide format.statistics: Alistcontaining summary statistics: total sessions, total actions, unique users, time range (if applicable), and top sessions and user by activities.
See also
Basic functions
build_model(),
hist.group_tna(),
hist.tna(),
plot.group_tna(),
plot.tna(),
plot_mosaic(),
plot_mosaic.group_tna(),
plot_mosaic.tna_data(),
print.group_tna(),
print.summary.group_tna(),
print.summary.tna(),
print.tna(),
print.tna_data(),
summary.group_tna(),
summary.tna(),
tna-package
Examples
data <- tibble::tibble(
user = c("A", "A", "A", "B", "B", "C", "C", "C"),
time = c(
"2023-01-01 10:00:00", "2023-01-01 10:05:00",
"2023-01-01 10:20:00", "2023-01-01 12:00:00",
"2023-01-01 12:02:00", "2023-01-01 14:00:00",
"2023-01-01 14:05:00", "2023-01-01 14:10:00"
),
action = c(
"view", "click", "add_cart", "view",
"checkout", "view", "click", "share"
)
)
results <- prepare_data(
data, actor = "user", time = "time", action = "action"
)
#>
#> Initializing session computation...
#>
#> Input data dimensions: 8 rows, 3 columns
#>
#> Parsing time values...
#>
#> First few time values: "2023-01-01 10:00:00", "2023-01-01 10:05:00", and
#> "2023-01-01 10:20:00"
#>
#> Starting time parsing process...
#>
#> Number of values to parse: 8
#>
#> Sample values: "2023-01-01 10:00:00", "2023-01-01 10:05:00", and "2023-01-01
#> 10:20:00"
#>
#> Successfully parsed using format: "%Y-%m-%d %H:%M:%S"
#>
#> Sample parsed time: "2023-01-01 10:00:00"
#>
#> Sample of parsed times: 2023-01-01 10:00:00, 2023-01-01 10:05:00, and
#> 2023-01-01 10:20:00
#>
#> Creating sessions based on time threshold...
#>
#> Time threshold for new session: 900 seconds
#>
#> Creating wide format view of sessions...
#>
#> Session Analysis Summary
#>
#> ------------------------
#>
#> Total number of sessions: 3
#>
#> Number of unique users: 3
#>
#> Total number of actions: 8
#>
#> Maximum sequence length: 3 actions
#>
#> Time range: 2023-01-01 10:00:00 to 2023-01-01 14:10:00
#>
#> Sessions per user:
#> # A tibble: 3 × 2
#> user n_sessions
#> <chr> <int>
#> 1 A 1
#> 2 B 1
#> 3 C 1
#>
#> Top 5 longest sessions:
#> # A tibble: 3 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 A session1 3
#> 2 C session1 3
#> 3 B session1 2
print(results$sequence_data)
#> # A tibble: 3 × 3
#> T1 T2 T3
#> <chr> <chr> <chr>
#> 1 view click add_cart
#> 2 view checkout NA
#> 3 view click share
print(results$meta_data)
#> # A tibble: 3 × 5
#> .session_id user time .standardized_time .session_nr
#> <chr> <chr> <chr> <dttm> <int>
#> 1 A session1 A 2023-01-01 10:00:00 2023-01-01 10:00:00 1
#> 2 B session1 B 2023-01-01 12:00:00 2023-01-01 12:00:00 1
#> 3 C session1 C 2023-01-01 14:00:00 2023-01-01 14:00:00 1
print(results$statistics)
#> $total_sessions
#> [1] 3
#>
#> $total_actions
#> [1] 8
#>
#> $max_sequence_length
#> [1] 3
#>
#> $unique_users
#> [1] 3
#>
#> $sessions_per_user
#> # A tibble: 3 × 2
#> user n_sessions
#> <chr> <int>
#> 1 A 1
#> 2 B 1
#> 3 C 1
#>
#> $actions_per_session
#> # A tibble: 3 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 A session1 3
#> 2 C session1 3
#> 3 B session1 2
#>
#> $time_range
#> [1] "2023-01-01 10:00:00 UTC" "2023-01-01 14:10:00 UTC"
#>
data_ordered <- tibble::tibble(
user = c("A", "A", "A", "B", "B", "C", "C", "C"),
order = c(1, 2, 3, 1, 2, 1, 2, 3),
action = c(
"view", "click", "add_cart", "view",
"checkout", "view", "click", "share"
)
)
results_ordered <- prepare_data(
data_ordered, actor = "user", order = "order", action = "action"
)
#>
#> Initializing session computation...
#>
#> Input data dimensions: 8 rows, 3 columns
#> Using provided `order` column to create sequences.
#>
#> Creating wide format view of sessions...
#>
#> Session Analysis Summary
#>
#> ------------------------
#>
#> Total number of sessions: 3
#>
#> Number of unique users: 3
#>
#> Total number of actions: 8
#>
#> Maximum sequence length: 3 actions
#>
#> Sessions per user:
#> # A tibble: 3 × 2
#> user n_sessions
#> <chr> <int>
#> 1 A 1
#> 2 B 1
#> 3 C 1
#>
#> Top 5 longest sessions:
#> # A tibble: 3 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 A 3
#> 2 C 3
#> 3 B 2
print(results_ordered$sequence_data)
#> # A tibble: 3 × 3
#> T1 T2 T3
#> <chr> <chr> <chr>
#> 1 view click add_cart
#> 2 view checkout NA
#> 3 view click share
print(results_ordered$meta_data)
#> # A tibble: 3 × 3
#> .session_id user order
#> <chr> <chr> <dbl>
#> 1 A A 1
#> 2 B B 1
#> 3 C C 1
print(results_ordered$statistics)
#> $total_sessions
#> [1] 3
#>
#> $total_actions
#> [1] 8
#>
#> $max_sequence_length
#> [1] 3
#>
#> $unique_users
#> [1] 3
#>
#> $sessions_per_user
#> # A tibble: 3 × 2
#> user n_sessions
#> <chr> <int>
#> 1 A 1
#> 2 B 1
#> 3 C 1
#>
#> $actions_per_session
#> # A tibble: 3 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 A 3
#> 2 C 3
#> 3 B 2
#>
data_single_session <- tibble::tibble(
action = c(
"view", "click", "add_cart", "view", "checkout", "view", "click", "share"
)
)
results_single <- prepare_data(data_single_session, action = "action")
#>
#> Initializing session computation...
#>
#> Input data dimensions: 8 rows, 1 columns
#>
#> No `time` or `order` column provided. Treating the entire dataset as one
#> session.
#>
#> Creating wide format view of sessions...
#>
#> Session Analysis Summary
#>
#> ------------------------
#>
#> Total number of sessions: 1
#>
#> Total number of actions: 8
#>
#> Maximum sequence length: 8 actions
#>
#> Top 5 longest sessions:
#> # A tibble: 1 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 session 8
print(results_single$sequence_data)
#> # A tibble: 1 × 8
#> T1 T2 T3 T4 T5 T6 T7 T8
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 view click add_cart view checkout view click share
print(results_single$meta_data)
#> # A tibble: 1 × 1
#> .session_id
#> <chr>
#> 1 session
print(results_single$statistics)
#> $total_sessions
#> [1] 1
#>
#> $total_actions
#> [1] 8
#>
#> $max_sequence_length
#> [1] 8
#>
#> $actions_per_session
#> # A tibble: 1 × 2
#> .session_id n_actions
#> <chr> <int>
#> 1 session 8
#>