timetk: A toolkit for time series analysis in R

The time series landscape in R is vast, deep, and complex causing many inconsistencies in data attributes and formats ultimately making it difficult to coerce between the different data structures. The zoo and xts packages solved a number of the issues in dealing with the various classes (ts, zoo, xts, irts, msts, and the list goes on…). However, because these packages deal in classes other than data frame, the issues with conversion between tbl and other time series object classes are still present.

The timetk package provides tools that solve the issues with conversion, maximizing attribute extensibility (the required data attributes are retained during the conversion to each of the primary time series classes). The following tools are available to coerce and retrieve key information:

  • Conversion functions: tk_tbl, tk_ts, tk_xts, tk_zoo, and tk_zooreg. These functions coerce time-based tibbles tbl to and from each of the main time-series data types xts, zoo, zooreg, ts, maintaining the time-based index.

  • Index function: tk_index returns the index. When the argument, timetk_idx = TRUE, A time-based index (non-regularized index) of forecast objects, models, and ts objects is returned if present. Refer to tk_ts() to learn about non-regularized index persistence during the conversion process.

This vignette includes a brief case study on conversion issues and then a detailed explanation of timetk function conversion between time-based tbl objects and several primary time series classes (xts, zoo, zooreg and ts).

Prerequisites

Before we get started, load the following packages.

Data

We’ll use the “Q10” dataset - The first ID from a sample a quarterly datasets (see m4_quarterly) from the M4 Competition. The return structure is a tibble, which is not conducive to many of the popular time series analysis packages including quantmod, TTR, forecast and many others.

q10_quarterly <- m4_quarterly %>% filter(id == "Q10")
q10_quarterly
## # A tibble: 59 x 3
##    id    date       value
##    <fct> <date>     <dbl>
##  1 Q10   2000-01-01 2329 
##  2 Q10   2000-04-01 2350.
##  3 Q10   2000-07-01 2333.
##  4 Q10   2000-10-01 2382.
##  5 Q10   2001-01-01 2383.
##  6 Q10   2001-04-01 2405 
##  7 Q10   2001-07-01 2411 
##  8 Q10   2001-10-01 2428.
##  9 Q10   2002-01-01 2392.
## 10 Q10   2002-04-01 2418.
## # … with 49 more rows

Case Study: Conversion issues with ts()

The ts object class has roots in the stats package and many popular packages use this time series data structure including the popular forecast package. With that said, the ts data structure is the most difficult to coerce back and forth because by default it does not contain a time-based index. Rather it uses a regularized index computed using the start and frequency arguments. Conversion to ts is done using the ts() function from the stats library, which results in various problems.

Problems

First, only numeric columns get coerced. If the user forgets to add the [,"pct"] to drop the “date” column, ts() returns dates in numeric format which is not what the user wants.

# date column gets coerced to numeric
ts(q10_quarterly, start = c(2000, 1), freq = 4) %>%
    head()
##      id  date  value
## [1,]  1 10957 2329.0
## [2,]  1 11048 2349.9
## [3,]  1 11139 2332.9
## [4,]  1 11231 2381.5
## [5,]  1 11323 2382.6
## [6,]  1 11413 2405.0

The correct method is to call the specific column desired. However, this presents a new issue. The date index is lost, and a different “regularized” index is built using the start and frequency attributes.

q10_quarterly_ts <- ts(q10_quarterly$value, start = c(2000, 1), freq  = 4)
q10_quarterly_ts
##        Qtr1   Qtr2   Qtr3   Qtr4
## 2000 2329.0 2349.9 2332.9 2381.5
## 2001 2382.6 2405.0 2411.0 2428.5
## 2002 2391.6 2418.5 2406.5 2418.5
## 2003 2420.4 2438.6 2448.7 2470.6
## 2004 2484.5 2495.9 2492.5 2521.6
## 2005 2538.1 2549.7 2587.2 2585.0
## 2006 2602.6 2615.3 2654.0 2680.8
## 2007 2665.4 2645.1 2647.5 2719.2
## 2008 2677.0 2650.9 2667.8 2660.2
## 2009 2554.7 2522.7 2510.0 2541.7
## 2010 2499.1 2527.9 2519.0 2536.3
## 2011 2493.2 2542.1 2501.6 2516.3
## 2012 2510.5 2548.4 2548.6 2530.7
## 2013 2497.1 2520.4 2516.9 2505.5
## 2014 2513.9 2549.9 2555.3

We can see from the structure (using the str() function) that the regularized time series is present, but there is no date index retained.

# No date index attribute
str(q10_quarterly_ts)
##  Time-Series [1:59] from 2000 to 2014: 2329 2350 2333 2382 2383 ...

We can get the index using the index() function from the zoo package. The index retained is a regular sequence of numeric values. In many cases, the regularized values cannot be coerced back to the original time-base because the date and date time data contains significantly more information (i.e. year-month-day, hour-minute-second, and timezone attributes) and the data may not be on a regularized interval (frequency).

# Regularized numeric sequence
zoo::index(q10_quarterly_ts)
##  [1] 2000.00 2000.25 2000.50 2000.75 2001.00 2001.25 2001.50 2001.75 2002.00
## [10] 2002.25 2002.50 2002.75 2003.00 2003.25 2003.50 2003.75 2004.00 2004.25
## [19] 2004.50 2004.75 2005.00 2005.25 2005.50 2005.75 2006.00 2006.25 2006.50
## [28] 2006.75 2007.00 2007.25 2007.50 2007.75 2008.00 2008.25 2008.50 2008.75
## [37] 2009.00 2009.25 2009.50 2009.75 2010.00 2010.25 2010.50 2010.75 2011.00
## [46] 2011.25 2011.50 2011.75 2012.00 2012.25 2012.50 2012.75 2013.00 2013.25
## [55] 2013.50 2013.75 2014.00 2014.25 2014.50

Solution

The timetk package contains a new function, tk_ts(), that enables maintaining the original date index as an attribute. When we repeat the tbl to ts conversion process using the new function, tk_ts(), we can see a few differences.

First, only numeric columns get coerced, which prevents unintended consequences due to R conversion rules (e.g. dates getting unintentionally converted or characters causing the homogeneous data structure converting all numeric values to character). If a column is dropped, the user gets a warning.

# date automatically dropped and user is warned
q10_quarterly_ts_timetk <- tk_ts(q10_quarterly, start = 2000, freq  = 4)
## Warning: Non-numeric columns being dropped: id, date
q10_quarterly_ts_timetk
##        Qtr1   Qtr2   Qtr3   Qtr4
## 2000 2329.0 2349.9 2332.9 2381.5
## 2001 2382.6 2405.0 2411.0 2428.5
## 2002 2391.6 2418.5 2406.5 2418.5
## 2003 2420.4 2438.6 2448.7 2470.6
## 2004 2484.5 2495.9 2492.5 2521.6
## 2005 2538.1 2549.7 2587.2 2585.0
## 2006 2602.6 2615.3 2654.0 2680.8
## 2007 2665.4 2645.1 2647.5 2719.2
## 2008 2677.0 2650.9 2667.8 2660.2
## 2009 2554.7 2522.7 2510.0 2541.7
## 2010 2499.1 2527.9 2519.0 2536.3
## 2011 2493.2 2542.1 2501.6 2516.3
## 2012 2510.5 2548.4 2548.6 2530.7
## 2013 2497.1 2520.4 2516.9 2505.5
## 2014 2513.9 2549.9 2555.3

Second, the data returned has a few additional attributes. The most important of which is a numeric attribute, “index”, which contains the original date information as a number. The ts() function will not preserve this index while tk_ts() will preserve the index in numeric form along with the time zone and class.

# More attributes including time index, time class, time zone
str(q10_quarterly_ts_timetk)
##  Time-Series [1:59, 1] from 2000 to 2014: 2329 2350 2333 2382 2383 ...
##  - attr(*, "dimnames")=List of 2
##   ..$ : NULL
##   ..$ : chr "value"
##  - attr(*, "index")= num [1:59] 9.47e+08 9.55e+08 9.62e+08 9.70e+08 9.78e+08 ...
##   ..- attr(*, "tzone")= chr "UTC"
##   ..- attr(*, "tclass")= chr "Date"

Advantages of conversion with tk_tbl()

Since we used the tk_ts() during conversion, we can extract the original index in date format using tk_index(timetk_idx = TRUE) (the default is timetk_idx = FALSE which returns the default regularized index).

# Can now retrieve the original date index
timetk_index <- q10_quarterly_ts_timetk %>%
    tk_index(timetk_idx = TRUE)
head(timetk_index)
## [1] "2000-01-01" "2000-04-01" "2000-07-01" "2000-10-01" "2001-01-01"
## [6] "2001-04-01"
class(timetk_index)
## [1] "Date"

Next, the tk_tbl() function has an argument timetk_idx also which can be used to select which index to return. First, we show conversion using the default index. Notice that the index returned is “regularized” meaning its actually a numeric index rather than a time-based index.

# Conversion back to tibble using the default index (regularized)
q10_quarterly_ts_timetk %>%
    tk_tbl(index_rename = "date", timetk_idx = FALSE)
## # A tibble: 59 x 2
##    index     value
##    <yearqtr> <dbl>
##  1 2000 Q1   2329 
##  2 2000 Q2   2350.
##  3 2000 Q3   2333.
##  4 2000 Q4   2382.
##  5 2001 Q1   2383.
##  6 2001 Q2   2405 
##  7 2001 Q3   2411 
##  8 2001 Q4   2428.
##  9 2002 Q1   2392.
## 10 2002 Q2   2418.
## # … with 49 more rows

We can now get the original date index using the tk_tbl() argument timetk_idx = TRUE.

# Conversion back to tibble now using the timetk index (date / date-time)
q10_quarterly_timetk <- q10_quarterly_ts_timetk %>%
    tk_tbl(timetk_idx = TRUE) %>%
    rename(date = index)
q10_quarterly_timetk
## # A tibble: 59 x 2
##    date       value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

We can see that in this case (and in most cases) you can get the same data frame you began with.

# Comparing the coerced tibble with the original tibble
identical(q10_quarterly_timetk, q10_quarterly %>% select(-id))
## [1] TRUE

Conversion Methods

Using the q10_quarterly, we’ll go through the various conversion methods using tk_tbl, tk_xts, tk_zoo, tk_zooreg, and tk_ts.

From tbl

The starting point is the q10_quarterly. We will coerce this into xts, zoo, zooreg and ts classes.

# Start:
q10_quarterly
## # A tibble: 59 x 3
##    id    date       value
##    <fct> <date>     <dbl>
##  1 Q10   2000-01-01 2329 
##  2 Q10   2000-04-01 2350.
##  3 Q10   2000-07-01 2333.
##  4 Q10   2000-10-01 2382.
##  5 Q10   2001-01-01 2383.
##  6 Q10   2001-04-01 2405 
##  7 Q10   2001-07-01 2411 
##  8 Q10   2001-10-01 2428.
##  9 Q10   2002-01-01 2392.
## 10 Q10   2002-04-01 2418.
## # … with 49 more rows

to xts

Use tk_xts(). By default “date” is used as the date index and the “date” column is dropped from the output. Only numeric columns are coerced to avoid unintentional conversion issues.

# End
q10_quarterly_xts <- tk_xts(q10_quarterly) 
## Warning: Non-numeric columns being dropped: id, date
## Using column `date` for date_var.
head(q10_quarterly_xts)
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

Use the select argument to specify which columns to drop. Use the date_var argument to specify which column to use as the date index. Notice the message and warning are no longer present.

# End - Using `select` and `date_var` args
tk_xts(q10_quarterly, select = -(id:date), date_var = date) %>%
    head()
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

Also, as an alternative, we can set silent = TRUE to bypass the warnings since the default dropping of the “date” column is what is desired. Notice no warnings or messages.

# End - Using `silent` to silence warnings
tk_xts(q10_quarterly, silent = TRUE) %>%
    head()
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

to zoo

Use tk_zoo(). Same as when coercing to xts, the non-numeric “date” column is automatically dropped and the index is automatically selected as the date column.

# End
q10_quarterly_zoo <- tk_zoo(q10_quarterly, silent = TRUE) 
head(q10_quarterly_zoo)
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

to zooreg

Use tk_zooreg(). Same as when coercing to xts, the non-numeric “date” column is automatically dropped. The regularized index is built from the function arguments start and freq.

# End
q10_quarterly_zooreg <- tk_zooreg(q10_quarterly, start = 2000, freq = 4, silent = TRUE) 
head(q10_quarterly_zooreg)
##          value
## 2000 Q1 2329.0
## 2000 Q2 2349.9
## 2000 Q3 2332.9
## 2000 Q4 2381.5
## 2001 Q1 2382.6
## 2001 Q2 2405.0

The original time-based index is retained and can be accessed using tk_index(timetk_idx = TRUE).

# Retrieve original time-based index
tk_index(q10_quarterly_zooreg, timetk_idx = TRUE) %>%
    str()
##  Date[1:59], format: "2000-01-01" "2000-04-01" "2000-07-01" "2000-10-01" "2001-01-01" ...

to ts

Use tk_ts(). The non-numeric “date” column is automatically dropped. The regularized index is built from the function arguments.

# End
q10_quarterly_ts <- tk_ts(q10_quarterly, start = 2000, freq = 4, silent = TRUE) 
q10_quarterly_ts
##        Qtr1   Qtr2   Qtr3   Qtr4
## 2000 2329.0 2349.9 2332.9 2381.5
## 2001 2382.6 2405.0 2411.0 2428.5
## 2002 2391.6 2418.5 2406.5 2418.5
## 2003 2420.4 2438.6 2448.7 2470.6
## 2004 2484.5 2495.9 2492.5 2521.6
## 2005 2538.1 2549.7 2587.2 2585.0
## 2006 2602.6 2615.3 2654.0 2680.8
## 2007 2665.4 2645.1 2647.5 2719.2
## 2008 2677.0 2650.9 2667.8 2660.2
## 2009 2554.7 2522.7 2510.0 2541.7
## 2010 2499.1 2527.9 2519.0 2536.3
## 2011 2493.2 2542.1 2501.6 2516.3
## 2012 2510.5 2548.4 2548.6 2530.7
## 2013 2497.1 2520.4 2516.9 2505.5
## 2014 2513.9 2549.9 2555.3

The original time-based index is retained and can be accessed using tk_index(timetk_idx = TRUE).

# Retrieve original time-based index
tk_index(q10_quarterly_ts, timetk_idx = TRUE) %>%
    str()
##  Date[1:59], format: "2000-01-01" "2000-04-01" "2000-07-01" "2000-10-01" "2001-01-01" ...

To tbl

Going back to tibble is just as easy using tk_tbl().

From xts

# Start
head(q10_quarterly_xts)
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

Notice no loss of data going back to tbl.

# End
tk_tbl(q10_quarterly_xts)
## # A tibble: 59 x 2
##    index      value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

From zoo

# Start
head(q10_quarterly_zoo)
##             value
## 2000-01-01 2329.0
## 2000-04-01 2349.9
## 2000-07-01 2332.9
## 2000-10-01 2381.5
## 2001-01-01 2382.6
## 2001-04-01 2405.0

Notice no loss of data going back to tbl.

# End
tk_tbl(q10_quarterly_zoo)
## # A tibble: 59 x 2
##    index      value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

From zooreg

# Start
head(q10_quarterly_zooreg)
##          value
## 2000 Q1 2329.0
## 2000 Q2 2349.9
## 2000 Q3 2332.9
## 2000 Q4 2381.5
## 2001 Q1 2382.6
## 2001 Q2 2405.0

Notice that the index is a regularized numeric sequence by default.

# End - with default regularized index
tk_tbl(q10_quarterly_zooreg)
## # A tibble: 59 x 2
##    index     value
##    <yearqtr> <dbl>
##  1 2000 Q1   2329 
##  2 2000 Q2   2350.
##  3 2000 Q3   2333.
##  4 2000 Q4   2382.
##  5 2001 Q1   2383.
##  6 2001 Q2   2405 
##  7 2001 Q3   2411 
##  8 2001 Q4   2428.
##  9 2002 Q1   2392.
## 10 2002 Q2   2418.
## # … with 49 more rows

With timetk_idx = TRUE the index is the original date sequence. The result is the original tbl that we started with!

# End - with timetk index that is the same as original time-based index
tk_tbl(q10_quarterly_zooreg, timetk_idx = TRUE)
## # A tibble: 59 x 2
##    index      value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

From ts

# Start
q10_quarterly_ts
##        Qtr1   Qtr2   Qtr3   Qtr4
## 2000 2329.0 2349.9 2332.9 2381.5
## 2001 2382.6 2405.0 2411.0 2428.5
## 2002 2391.6 2418.5 2406.5 2418.5
## 2003 2420.4 2438.6 2448.7 2470.6
## 2004 2484.5 2495.9 2492.5 2521.6
## 2005 2538.1 2549.7 2587.2 2585.0
## 2006 2602.6 2615.3 2654.0 2680.8
## 2007 2665.4 2645.1 2647.5 2719.2
## 2008 2677.0 2650.9 2667.8 2660.2
## 2009 2554.7 2522.7 2510.0 2541.7
## 2010 2499.1 2527.9 2519.0 2536.3
## 2011 2493.2 2542.1 2501.6 2516.3
## 2012 2510.5 2548.4 2548.6 2530.7
## 2013 2497.1 2520.4 2516.9 2505.5
## 2014 2513.9 2549.9 2555.3

Notice that the index is a regularized numeric sequence by default.

# End - with default regularized index
tk_tbl(q10_quarterly_ts)
## # A tibble: 59 x 2
##    index     value
##    <yearqtr> <dbl>
##  1 2000 Q1   2329 
##  2 2000 Q2   2350.
##  3 2000 Q3   2333.
##  4 2000 Q4   2382.
##  5 2001 Q1   2383.
##  6 2001 Q2   2405 
##  7 2001 Q3   2411 
##  8 2001 Q4   2428.
##  9 2002 Q1   2392.
## 10 2002 Q2   2418.
## # … with 49 more rows

With timetk_idx = TRUE the index is the original date sequence. The result is the original tbl that we started with!

# End - with timetk index 
tk_tbl(q10_quarterly_ts, timetk_idx = TRUE)
## # A tibble: 59 x 2
##    index      value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

Testing if an object has a timetk index

The function has_timetk_idx() can be used to test whether toggling the timetk_idx argument in the tk_index() and tk_tbl() functions will have an effect on the output. Here are several examples using the ten year treasury data used in the case study:

tk_ts()

The tk_ts() function returns an object with the “timetk index” attribute.

# Data coerced with tk_ts() has timetk index
has_timetk_idx(q10_quarterly_ts)
## [1] TRUE

If we toggle timetk_idx = TRUE when retrieving the index with tk_index(), we get the index of dates rather than the regularized time series.

tk_index(q10_quarterly_ts, timetk_idx = TRUE)
##  [1] "2000-01-01" "2000-04-01" "2000-07-01" "2000-10-01" "2001-01-01"
##  [6] "2001-04-01" "2001-07-01" "2001-10-01" "2002-01-01" "2002-04-01"
## [11] "2002-07-01" "2002-10-01" "2003-01-01" "2003-04-01" "2003-07-01"
## [16] "2003-10-01" "2004-01-01" "2004-04-01" "2004-07-01" "2004-10-01"
## [21] "2005-01-01" "2005-04-01" "2005-07-01" "2005-10-01" "2006-01-01"
## [26] "2006-04-01" "2006-07-01" "2006-10-01" "2007-01-01" "2007-04-01"
## [31] "2007-07-01" "2007-10-01" "2008-01-01" "2008-04-01" "2008-07-01"
## [36] "2008-10-01" "2009-01-01" "2009-04-01" "2009-07-01" "2009-10-01"
## [41] "2010-01-01" "2010-04-01" "2010-07-01" "2010-10-01" "2011-01-01"
## [46] "2011-04-01" "2011-07-01" "2011-10-01" "2012-01-01" "2012-04-01"
## [51] "2012-07-01" "2012-10-01" "2013-01-01" "2013-04-01" "2013-07-01"
## [56] "2013-10-01" "2014-01-01" "2014-04-01" "2014-07-01"

If we toggle timetk_idx = TRUE during conversion to tbl using tk_tbl(), we get the index of dates rather than the regularized index in the returned tbl.

tk_tbl(q10_quarterly_ts, timetk_idx = TRUE)
## # A tibble: 59 x 2
##    index      value
##    <date>     <dbl>
##  1 2000-01-01 2329 
##  2 2000-04-01 2350.
##  3 2000-07-01 2333.
##  4 2000-10-01 2382.
##  5 2001-01-01 2383.
##  6 2001-04-01 2405 
##  7 2001-07-01 2411 
##  8 2001-10-01 2428.
##  9 2002-01-01 2392.
## 10 2002-04-01 2418.
## # … with 49 more rows

Testing other data types

The timetk_idx argument will only have an effect on objects that use regularized time series. Therefore, has_timetk_idx() returns FALSE for other object types (e.g. tbl, xts, zoo) since toggling the argument has no effect on these classes.

has_timetk_idx(q10_quarterly_xts)
## [1] FALSE

Toggling the timetk_idx argument has no effect on the output. Output with timetk_idx = TRUE is the same as with timetk_idx = FALSE.

tk_index(q10_quarterly_xts, timetk_idx = TRUE)
##  [1] "2000-01-01" "2000-04-01" "2000-07-01" "2000-10-01" "2001-01-01"
##  [6] "2001-04-01" "2001-07-01" "2001-10-01" "2002-01-01" "2002-04-01"
## [11] "2002-07-01" "2002-10-01" "2003-01-01" "2003-04-01" "2003-07-01"
## [16] "2003-10-01" "2004-01-01" "2004-04-01" "2004-07-01" "2004-10-01"
## [21] "2005-01-01" "2005-04-01" "2005-07-01" "2005-10-01" "2006-01-01"
## [26] "2006-04-01" "2006-07-01" "2006-10-01" "2007-01-01" "2007-04-01"
## [31] "2007-07-01" "2007-10-01" "2008-01-01" "2008-04-01" "2008-07-01"
## [36] "2008-10-01" "2009-01-01" "2009-04-01" "2009-07-01" "2009-10-01"
## [41] "2010-01-01" "2010-04-01" "2010-07-01" "2010-10-01" "2011-01-01"
## [46] "2011-04-01" "2011-07-01" "2011-10-01" "2012-01-01" "2012-04-01"
## [51] "2012-07-01" "2012-10-01" "2013-01-01" "2013-04-01" "2013-07-01"
## [56] "2013-10-01" "2014-01-01" "2014-04-01" "2014-07-01"

Working with zoo::yearmon and zoo::yearqtr index

The zoo package has the yearmon and yearqtr classes for working with regularized monthly and quarterly data, respectively. The “timetk index” tracks the format during conversion. Here’s and example with yearqtr.

yearqtr_tbl <- q10_quarterly %>%
    mutate(date = zoo::as.yearqtr(date))
yearqtr_tbl
## # A tibble: 59 x 3
##    id    date      value
##    <fct> <yearqtr> <dbl>
##  1 Q10   2000 Q1   2329 
##  2 Q10   2000 Q2   2350.
##  3 Q10   2000 Q3   2333.
##  4 Q10   2000 Q4   2382.
##  5 Q10   2001 Q1   2383.
##  6 Q10   2001 Q2   2405 
##  7 Q10   2001 Q3   2411 
##  8 Q10   2001 Q4   2428.
##  9 Q10   2002 Q1   2392.
## 10 Q10   2002 Q2   2418.
## # … with 49 more rows

We can coerce to xts and the yearqtr class is intact.

yearqtr_xts <- tk_xts(yearqtr_tbl)
## Warning: Non-numeric columns being dropped: id, date
## Using column `date` for date_var.
yearqtr_xts %>% head()
##          value
## 2000 Q1 2329.0
## 2000 Q2 2349.9
## 2000 Q3 2332.9
## 2000 Q4 2381.5
## 2001 Q1 2382.6
## 2001 Q2 2405.0

We can coerce to ts and, although the “timetk index” is hidden, the yearqtr class is intact.

yearqtr_ts <- tk_ts(yearqtr_xts, start = 1997, freq = 4)
yearqtr_ts %>% head()
##       value
## [1,] 2329.0
## [2,] 2349.9
## [3,] 2332.9
## [4,] 2381.5
## [5,] 2382.6
## [6,] 2405.0

Coercing from ts to tbl using timetk_idx = TRUE shows that the original index was maintained through each of the conversion steps.

yearqtr_ts %>% tk_tbl(timetk_idx = TRUE)
## # A tibble: 59 x 2
##    index     value
##    <yearqtr> <dbl>
##  1 2000 Q1   2329 
##  2 2000 Q2   2350.
##  3 2000 Q3   2333.
##  4 2000 Q4   2382.
##  5 2001 Q1   2383.
##  6 2001 Q2   2405 
##  7 2001 Q3   2411 
##  8 2001 Q4   2428.
##  9 2002 Q1   2392.
## 10 2002 Q2   2418.
## # … with 49 more rows

Learning More

My Talk on High-Performance Time Series Forecasting

Time series is changing. Businesses now need 10,000+ time series forecasts every day.

High-Performance Forecasting Systems will save companies MILLIONS of dollars. Imagine what will happen to your career if you can provide your organization a “High-Performance Time Series Forecasting System” (HPTSF System).

I teach how to build a HPTFS System in my High-Performance Time Series Forecasting Course. If interested in learning Scalable High-Performance Forecasting Strategies then take my course. You will learn:

  • Time Series Machine Learning (cutting-edge) with Modeltime - 30+ Models (Prophet, ARIMA, XGBoost, Random Forest, & many more)
  • NEW - Deep Learning with GluonTS (Competition Winners)
  • Time Series Preprocessing, Noise Reduction, & Anomaly Detection
  • Feature engineering using lagged variables & external regressors
  • Hyperparameter Tuning
  • Time series cross-validation
  • Ensembling Multiple Machine Learning & Univariate Modeling Techniques (Competition Winner)
  • Scalable Forecasting - Forecast 1000+ time series in parallel
  • and more.

Unlock the High-Performance Time Series Forecasting Course