Time Series Feature (Signature) Generator
Source:R/recipes-step_timeseries_signature.R
step_timeseries_signature.Rd
step_timeseries_signature
creates a a specification of a recipe
step that will convert date or date-time data into many
features that can aid in machine learning with time-series data
Arguments
- recipe
A recipe object. The step will be added to the sequence of operations for this recipe.
- ...
One or more selector functions to choose which variables that will be used to create the new variables. The selected variables should have class
Date
orPOSIXct
. Seerecipes::selections()
for more details. For thetidy
method, these are not currently used.- role
For model terms created by this step, what analysis role should they be assigned?. By default, the function assumes that the new variable columns created by the original variables will be used as predictors in a model.
- trained
A logical to indicate if the quantities for preprocessing have been estimated.
- columns
A character string of variables that will be used as inputs. This field is a placeholder and will be populated once
recipes::prep()
is used.- skip
A logical. Should the step be skipped when the recipe is baked by bake.recipe()? While all operations are baked when prep.recipe() is run, some operations may not be able to be conducted on new data (e.g. processing the outcome variable(s)). Care should be taken when using skip = TRUE as it may affect the computations for subsequent operations.
- id
A character string that is unique to this step to identify it.
- x
A
step_timeseries_signature
object.
Value
For step_timeseries_signature
, an updated version of recipe with
the new step added to the sequence of existing steps (if any).
For the tidy
method, a tibble with columns terms
(the selectors or variables selected), value
(the feature
names).
Details
Date Variable
Unlike other steps, step_timeseries_signature
does not
remove the original date variables. recipes::step_rm()
can be
used for this purpose.
Scaling index.num
The index.num
feature created has a large magnitude (number of seconds since 1970-01-01).
It's a good idea to scale and center this feature (e.g. use recipes::step_normalize()
).
Removing Unnecessary Features
By default, many features are created automatically. Unnecessary features can
be removed using recipes::step_rm()
.
See also
Time Series Analysis:
Engineered Features:
step_timeseries_signature()
,step_holiday_signature()
,step_fourier()
Diffs & Lags
step_diff()
,recipes::step_lag()
Smoothing:
step_slidify()
,step_smooth()
Variance Reduction:
step_box_cox()
Imputation:
step_ts_impute()
,step_ts_clean()
Padding:
step_ts_pad()
Main Recipe Functions:
Examples
library(recipes)
library(dplyr)
FB_tbl <- FANG %>% dplyr::filter(symbol == "FB")
# Create a recipe object with a timeseries signature step
rec_obj <- recipe(adjusted ~ ., data = FB_tbl) %>%
step_timeseries_signature(date)
# View the recipe object
rec_obj
#>
#> ── Recipe ──────────────────────────────────────────────────────────────────────
#>
#> ── Inputs
#> Number of variables by role
#> outcome: 1
#> predictor: 7
#>
#> ── Operations
#> • Timeseries signature features from: date
# Prepare the recipe object
prep(rec_obj)
#>
#> ── Recipe ──────────────────────────────────────────────────────────────────────
#>
#> ── Inputs
#> Number of variables by role
#> outcome: 1
#> predictor: 7
#>
#> ── Training information
#> Training data contained 1008 data points and no incomplete rows.
#>
#> ── Operations
#> • Timeseries signature features from: date | Trained
# Bake the recipe object - Adds the Time Series Signature
bake(prep(rec_obj), FB_tbl)
#> # A tibble: 1,008 × 35
#> symbol date open high low close volume adjusted date_index.num
#> <fct> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 FB 2013-01-02 27.4 28.2 27.4 28 69846400 28 1357084800
#> 2 FB 2013-01-03 27.9 28.5 27.6 27.8 63140600 27.8 1357171200
#> 3 FB 2013-01-04 28.0 28.9 27.8 28.8 72715400 28.8 1357257600
#> 4 FB 2013-01-07 28.7 29.8 28.6 29.4 83781800 29.4 1357516800
#> 5 FB 2013-01-08 29.5 29.6 28.9 29.1 45871300 29.1 1357603200
#> 6 FB 2013-01-09 29.7 30.6 29.5 30.6 104787700 30.6 1357689600
#> 7 FB 2013-01-10 30.6 31.5 30.3 31.3 95316400 31.3 1357776000
#> 8 FB 2013-01-11 31.3 32.0 31.1 31.7 89598000 31.7 1357862400
#> 9 FB 2013-01-14 32.1 32.2 30.6 31.0 98892800 31.0 1358121600
#> 10 FB 2013-01-15 30.6 31.7 29.9 30.1 173242600 30.1 1358208000
#> # ℹ 998 more rows
#> # ℹ 26 more variables: date_year <int>, date_year.iso <int>, date_half <int>,
#> # date_quarter <int>, date_month <int>, date_month.xts <int>,
#> # date_month.lbl <ord>, date_day <int>, date_hour <int>, date_minute <int>,
#> # date_second <int>, date_hour12 <int>, date_am.pm <int>, date_wday <int>,
#> # date_wday.xts <int>, date_wday.lbl <ord>, date_mday <int>, date_qday <int>,
#> # date_yday <int>, date_mweek <int>, date_week <int>, date_week.iso <int>, …
# Tidy shows which features have been added during the 1st step
# in this case, step 1 is the step_timeseries_signature step
tidy(rec_obj)
#> # A tibble: 1 × 6
#> number operation type trained skip id
#> <int> <chr> <chr> <lgl> <lgl> <chr>
#> 1 1 step timeseries_signature FALSE FALSE timeseries_signature_qcwig
tidy(rec_obj, number = 1)
#> # A tibble: 27 × 3
#> terms value id
#> <fct> <fct> <chr>
#> 1 date index.num timeseries_signature_qcwig
#> 2 date year timeseries_signature_qcwig
#> 3 date year.iso timeseries_signature_qcwig
#> 4 date half timeseries_signature_qcwig
#> 5 date quarter timeseries_signature_qcwig
#> 6 date month timeseries_signature_qcwig
#> 7 date month.xts timeseries_signature_qcwig
#> 8 date month.lbl timeseries_signature_qcwig
#> 9 date day timeseries_signature_qcwig
#> 10 date hour timeseries_signature_qcwig
#> # ℹ 17 more rows