thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-30 03:22:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'changelog-24.2' of github.com:ClickHouse/ClickHouse into changelog-24.2

Browse Source
This commit is contained in:
Alexey Milovidov 2024-02-29 21:57:09 +01:00
commit 3b7d3dbfc9
3 changed files with 19 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/en/sql-reference/functions/time-series-functions.md
View File

@ -22,8 +22,8 @@ seriesOutliersDetectTukey(series, min_percentile, max_percentile, K);
**Arguments**
- `series` - An array of numeric values.
- `min_percentile` - The minimum percentile to be used to calculate inter-quantile range [(IQR)](https://en.wikipedia.org/wiki/Interquartile_range). The value must be in range [2,98]. The default is 25.
- `max_percentile` - The maximum percentile to be used to calculate inter-quantile range (IQR). The value must be in range [2,98]. The default is 75.
- `min_percentile` - The minimum percentile to be used to calculate inter-quantile range [(IQR)](https://en.wikipedia.org/wiki/Interquartile_range). The value must be in range [0.02,0.98]. The default is 0.25.
- `max_percentile` - The maximum percentile to be used to calculate inter-quantile range (IQR). The value must be in range [0.02,0.98]. The default is 0.75.
- `K` - Non-negative constant value to detect mild or stronger outliers. The default value is 1.5.
At least four data points are required in `series` to detect outliers.
@ -53,7 +53,7 @@ Result:
Query:
``` sql
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], 20, 80, 1.5) AS print_0;
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], 0.2, 0.8, 1.5) AS print_0;
```
Result:

36
src/Functions/seriesOutliersDetectTukey.cpp
View File

@ -24,9 +24,6 @@ class FunctionSeriesOutliersDetectTukey : public IFunction
public:
static constexpr auto name = "seriesOutliersDetectTukey";
static constexpr Float64 min_quartile = 0.02;
static constexpr Float64 max_quartile = 0.98;
static FunctionPtr create(ContextPtr) { return std::make_shared<FunctionSeriesOutliersDetectTukey>(); }
std::string getName() const override { return name; }
@ -50,8 +47,8 @@ public:
FunctionArgumentDescriptors mandatory_args{{"time_series", &isArray<IDataType>, nullptr, "Array"}};
FunctionArgumentDescriptors optional_args{
{"min_percentile", &isNativeNumber<IDataType>, isColumnConst, "Number"},
{"max_percentile", &isNativeNumber<IDataType>, isColumnConst, "Number"},
{"min_percentile", &isFloat<IDataType>, isColumnConst, "Number"},
{"max_percentile", &isFloat<IDataType>, isColumnConst, "Number"},
{"k", &isNativeNumber<IDataType>, isColumnConst, "Number"}};
validateFunctionArgumentTypes(*this, arguments, mandatory_args, optional_args);
@ -79,23 +76,20 @@ public:
if (arguments.size() > 1)
{
Float64 p_min = arguments[1].column->getFloat64(0);
if (isnan(p_min) || !isFinite(p_min) || p_min < min_quartile|| p_min > max_quartile)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The second argument of function {} must be in range [2.0, 98.0]", getName());
static constexpr Float64 min_percentile_lower_bound = 0.02;
static constexpr Float64 max_percentile_upper_bound = 0.98;
min_percentile = p_min;
min_percentile = arguments[1].column->getFloat64(0);
if (isnan(min_percentile) || !isFinite(min_percentile) || min_percentile < min_percentile_lower_bound|| min_percentile > max_percentile_upper_bound)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The second argument of function {} must be in range [0.02, 0.98]", getName());
Float64 p_max = arguments[2].column->getFloat64(0);
if (isnan(p_max) || !isFinite(p_max) || p_max < min_quartile || p_max > max_quartile || p_max < min_percentile)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The third argument of function {} must be in range [2.0, 98.0]", getName());
max_percentile = arguments[2].column->getFloat64(0);
if (isnan(max_percentile) || !isFinite(max_percentile) || max_percentile < min_percentile_lower_bound || max_percentile > max_percentile_upper_bound || max_percentile < min_percentile)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The third argument of function {} must be in range [0.02, 0.98]", getName());
max_percentile = p_max;
auto k_val = arguments[3].column->getFloat64(0);
if (k_val < 0.0 || isnan(k_val) || !isFinite(k_val))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The fourth argument of function {} must be a positive number", getName());
k = k_val;
k = arguments[3].column->getFloat64(0);
if (k < 0.0 || isnan(k) || !isFinite(k))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "The fourth argument of function {} must be a non-negative number", getName());
}
if (executeNumber<UInt8>(arr_data, arr_offsets, min_percentile, max_percentile, k, col_res)
@ -216,7 +210,7 @@ seriesOutliersDetectTukey(series, min_percentile, max_percentile, k);
**Arguments**
- `series` - An array of numeric values.
- `min_quantile` - The minimum quantile to be used to calculate inter-quantile range [(IQR)](https://en.wikipedia.org/wiki/Interquartile_range). The value must be in range [2,98]. The default is 25.
- `min_quantile` - The minimum quantile to be used to calculate inter-quantile range [(IQR)](https://en.wikipedia.org/wiki/Interquartile_range). The value must be in range [0.02,0.98]. The default is 0.25.
- `max_quantile` - The maximum quantile to be used to calculate inter-quantile range (IQR). The value must be in range [0.02, 0.98]. The default is 0.75.
- `k` - Non-negative constant value to detect mild or stronger outliers. The default value is 1.5
@ -247,7 +241,7 @@ Result:
Query:
``` sql
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], .2, .8, 1.5) AS print_0;
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], 0.2, 0.8, 1.5) AS print_0;
```
Result:

2
tests/queries/0_stateless/02813_seriesOutliersDetectTukey.sql
View File

@ -19,7 +19,7 @@ SELECT seriesOutliersDetectTukey([-3, 2.40, 15, 3.90, 5, 6, 4.50, 5.20, 12, 60,
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], .25, .75, 1.5);
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], .10, .90, 1.5);
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4.50, 5, 12, 45, 12, 3.40, 3, 4, 5, 6], .02, .98, 1.5);
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3], 2, 98, 1.5);
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3], 0.02, 0.98, 1.5);
SELECT seriesOutliersDetectTukey(arrayMap(x -> sin(x / 10), range(30)));
SELECT seriesOutliersDetectTukey([-3, 2, 15, 3, 5, 6, 4, 5, 12, 45, 12, 3, 3, 4, 5, 6], .25, .75, 3);