Groups¶
Like the cross-sectional operators, but within groups: each stock is compared only with the stocks sharing its label that day. In the toy data, A and B are Tech, C and D are Energy.
groups is a group's name ('sector') or any expression giving labels: quantile(field('mcap'), 5),
coalesce(group('sector'), 'Other'), group_cross(...). A stock with no label, or outside the universe, gets no value.
Labels given on fewer dates than the prices hold from their date until the next, never earlier.
Groups and Labels works through them on an example.
Labels¶
group¶
group('name')
The labels themselves. Labels can be compared with == and !=, used as groups, and passed through where and
coalesce; anything else (arithmetic, rank) is refused when the expression is read.
group('sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | Tech | Tech | Energy | Energy |
| Jan 03 | Tech | Tech | Energy | Energy |
| Jan 04 | Tech | Tech | Energy | Energy |
| Jan 05 | Tech | Tech | Energy | Energy |
| Jan 08 | Tech | Tech | Energy | Energy |
| Jan 09 | Tech | Tech | Energy | Energy |
group('sector') == 'Tech'| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | 1 | 1 | 0 | 0 |
| Jan 03 | 1 | 1 | 0 | 0 |
| Jan 04 | 1 | 1 | 0 | 0 |
| Jan 05 | 1 | 1 | 0 | 0 |
| Jan 08 | 1 | 1 | 0 | 0 |
| Jan 09 | 1 | 1 | 0 | 0 |
identifier¶
identifier()
Each stock's own identifier (its name in the data), as a label, on every date. On its own it says nothing new; its use
is reading a stock's identity through an operator that moves values between stocks. ts_match(identifier(), key,
252) is each stock's twin's identifier: the way to see the twins (Statistical Twins).
identifier()| AAA | BBB | CCC | DDD | EEE | FFF | |
|---|---|---|---|---|---|---|
| Apr 09 | AAA | BBB | CCC | DDD | EEE | FFF |
| Apr 10 | AAA | BBB | CCC | DDD | EEE | FFF |
| Apr 11 | AAA | BBB | CCC | DDD | EEE | FFF |
group_cross¶
group_cross(a, b, ...)
One grouping from several: each stock's labels joined with a bar, such as 'Tech|2'. Below, sector crossed with
beta halves: the high-beta stock in each sector is in half 2.
group_cross('sector', quantile(field('beta'), 2))| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
| Jan 03 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
| Jan 04 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
| Jan 05 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
| Jan 08 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
| Jan 09 | Tech|2 | Tech|1 | Energy|2 | Energy|1 |
group_demean(returns(20), group_cross('sector', quantile(field('mcap'), 3))) # sector- and size-neutral
Within each group¶
group_demean¶
group_demean(x, groups)
x minus its group's mean that day: neutral to the group.
returns(1)| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.100 | −0.050 | 0.017 | 0.050 |
| Jan 04 | 0.091 | −0.053 | · | −0.024 |
| Jan 05 | −0.083 | 0.028 | 0.016 | 0.049 |
| Jan 08 | 0.182 | −0.081 | 0.032 | 0.023 |
| Jan 09 | 0.077 | −0.059 | −0.016 | 0.045 |
group_demean(returns(1), 'sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.075 | −0.075 | −0.017 | 0.017 |
| Jan 04 | 0.072 | −0.072 | · | 0.000 |
| Jan 05 | −0.056 | 0.056 | −0.016 | 0.016 |
| Jan 08 | 0.131 | −0.131 | 0.005 | −0.005 |
| Jan 09 | 0.068 | −0.068 | −0.031 | 0.031 |
group_demean(returns(20), 'sector') # sector-neutral momentum
group_demean(returns(20), quantile(field('mcap'), 5)) # size-neutral momentum
group_rank¶
group_rank(x, groups)
The percentile rank within each group, from 1/n to 1.
returns(1)| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.100 | −0.050 | 0.017 | 0.050 |
| Jan 04 | 0.091 | −0.053 | · | −0.024 |
| Jan 05 | −0.083 | 0.028 | 0.016 | 0.049 |
| Jan 08 | 0.182 | −0.081 | 0.032 | 0.023 |
| Jan 09 | 0.077 | −0.059 | −0.016 | 0.045 |
group_rank(returns(1), 'sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 1.0 | 0.5 | 0.5 | 1.0 |
| Jan 04 | 1.0 | 0.5 | · | 1.0 |
| Jan 05 | 0.5 | 1.0 | 0.5 | 1.0 |
| Jan 08 | 1.0 | 0.5 | 1.0 | 0.5 |
| Jan 09 | 1.0 | 0.5 | 0.5 | 1.0 |
group_gaussrank¶
group_gaussrank(x, groups)
gaussrank within each group: \(\Phi^{-1}((r_i - 0.5)/n)\) with \(r_i\) the stock's
rank and \(n\) the number of stocks with a value in its group that day. Normal scores within each sector, summing to
zero in each; a stock alone in its group gets 0.
returns(1)| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.100 | −0.050 | 0.017 | 0.050 |
| Jan 04 | 0.091 | −0.053 | · | −0.024 |
| Jan 05 | −0.083 | 0.028 | 0.016 | 0.049 |
| Jan 08 | 0.182 | −0.081 | 0.032 | 0.023 |
| Jan 09 | 0.077 | −0.059 | −0.016 | 0.045 |
group_gaussrank(returns(1), 'sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.674 | −0.674 | −0.674 | 0.674 |
| Jan 04 | 0.674 | −0.674 | · | 0.000 |
| Jan 05 | −0.674 | 0.674 | −0.674 | 0.674 |
| Jan 08 | 0.674 | −0.674 | 0.674 | −0.674 |
| Jan 09 | 0.674 | −0.674 | −0.674 | 0.674 |
group_gaussrank(field('book_to_price'), 'sector') + group_gaussrank(returns(231), 'sector') # sector-neutral, on one scale
group_quantile¶
group_quantile(x, groups, n)
The bucket 1 to n within each group: a dependent double sort.
Group statistics¶
Every member of a group gets the group's number, even a member whose own value is missing: C has no dollar volume on Jan 04 and still gets the Energy sum.
group_std¶
group_std(x, groups)
The standard deviation across the group's stocks that day; no value for a group with only one value, as Energy on Jan 04.
returns(1)| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.100 | −0.050 | 0.017 | 0.050 |
| Jan 04 | 0.091 | −0.053 | · | −0.024 |
| Jan 05 | −0.083 | 0.028 | 0.016 | 0.049 |
| Jan 08 | 0.182 | −0.081 | 0.032 | 0.023 |
| Jan 09 | 0.077 | −0.059 | −0.016 | 0.045 |
group_std(returns(1), 'sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | · | · | · | · |
| Jan 03 | 0.106 | 0.106 | 0.024 | 0.024 |
| Jan 04 | 0.101 | 0.101 | · | · |
| Jan 05 | 0.079 | 0.079 | 0.023 | 0.023 |
| Jan 08 | 0.186 | 0.186 | 0.006 | 0.006 |
| Jan 09 | 0.096 | 0.096 | 0.043 | 0.043 |
group_sum¶
group_sum(x, groups)
The sum within the group; no value when the group has no values that day.
adv(1)| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | 1000 | 6000 | 6000 | 16000 |
| Jan 03 | 1320 | 5320 | 6405 | 15960 |
| Jan 04 | 1800 | 4680 | · | 20500 |
| Jan 05 | 1210 | 5550 | 8060 | 18060 |
| Jan 08 | 2600 | 4250 | 7680 | 19360 |
| Jan 09 | 2520 | 3840 | 7245 | 27600 |
group_sum(adv(1), 'sector')| A | B | C | D | |
|---|---|---|---|---|
| Jan 02 | 7000 | 7000 | 22000 | 22000 |
| Jan 03 | 6640 | 6640 | 22365 | 22365 |
| Jan 04 | 6480 | 6480 | 20500 | 20500 |
| Jan 05 | 6760 | 6760 | 26120 | 26120 |
| Jan 08 | 6850 | 6850 | 27040 | 27040 |
| Jan 09 | 6360 | 6360 | 34845 | 34845 |
group_count_valid¶
group_count_valid(x, groups, period)
How many values the group's stocks have had over the last period days.