Trait polars_core::chunked_array::ops::ChunkQuantile
source · pub trait ChunkQuantile<T> {
fn median(&self) -> Option<T> { ... }
fn quantile(
&self,
_quantile: f64,
_interpol: QuantileInterpolOptions
) -> PolarsResult<Option<T>> { ... }
}Expand description
Quantile and median aggregation
Provided Methods§
sourcefn median(&self) -> Option<T>
fn median(&self) -> Option<T>
Returns the mean value in the array.
Returns None if the array is empty or only contains null values.
Examples found in repository?
src/frame/groupby/aggregations/mod.rs (line 1170)
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
pub(crate) unsafe fn agg_median(&self, groups: &GroupsProxy) -> Series {
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<Float64Type, _>(groups, |idx| {
debug_assert!(idx.len() <= self.len());
if idx.is_empty() {
return None;
}
let take = self.take_unchecked(idx.into());
take.median_as_series()
.unpack::<Float64Type>()
.unwrap()
.get(0)
}),
GroupsProxy::Slice {
groups: groups_slice,
..
} => {
if _use_rolling_kernels(groups_slice, self.chunks()) {
let ca = self.cast(&DataType::Float64).unwrap();
ca.agg_median(groups)
} else {
_agg_helper_slice::<Float64Type, _>(groups_slice, |[first, len]| {
debug_assert!(len <= self.len() as IdxSize);
match len {
0 => None,
1 => self.get(first as usize).map(|v| NumCast::from(v).unwrap()),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
arr_group.median()
}
}
})
}
}
}
}sourcefn quantile(
&self,
_quantile: f64,
_interpol: QuantileInterpolOptions
) -> PolarsResult<Option<T>>
fn quantile(
&self,
_quantile: f64,
_interpol: QuantileInterpolOptions
) -> PolarsResult<Option<T>>
Aggregate a given quantile of the ChunkedArray.
Returns None if the array is empty or only contains null values.
Examples found in repository?
src/chunked_array/ops/aggregate.rs (line 290)
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
fn median(&self) -> Option<f64> {
self.quantile(0.5, QuantileInterpolOptions::Linear).unwrap() // unwrap fine since quantile in range
}
}
impl ChunkQuantile<f32> for Float32Chunked {
fn quantile(
&self,
quantile: f64,
interpol: QuantileInterpolOptions,
) -> PolarsResult<Option<f32>> {
if !(0.0..=1.0).contains(&quantile) {
return Err(PolarsError::ComputeError(
"quantile should be between 0.0 and 1.0".into(),
));
}
let null_count = self.null_count();
let length = self.len();
if null_count == length {
return Ok(None);
}
let (idx, float_idx, top_idx) = quantile_idx(quantile, length, null_count, interpol);
let opt = match interpol {
QuantileInterpolOptions::Midpoint => {
if top_idx == idx {
ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float32Type>(|value| value.to_f32().unwrap())
.into_iter()
.next()
.flatten()
} else {
let bounds: Vec<Option<f32>> = ChunkSort::sort(self, false)
.slice(idx, 2)
.apply_cast_numeric::<_, Float32Type>(|value| value.to_f32().unwrap())
.into_iter()
.collect();
Some((bounds[0].unwrap() + bounds[1].unwrap()) / 2.0f32)
}
}
QuantileInterpolOptions::Linear => {
if top_idx == idx {
ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float32Type>(|value| value.to_f32().unwrap())
.into_iter()
.next()
.flatten()
} else {
let bounds: Vec<Option<f32>> = ChunkSort::sort(self, false)
.slice(idx, 2)
.apply_cast_numeric::<_, Float32Type>(|value| value.to_f32().unwrap())
.into_iter()
.collect();
linear_interpol(&bounds, idx, float_idx)
}
}
_ => ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float32Type>(|value| value.to_f32().unwrap())
.into_iter()
.next()
.flatten(),
};
Ok(opt)
}
fn median(&self) -> Option<f32> {
self.quantile(0.5, QuantileInterpolOptions::Linear).unwrap() // unwrap fine since quantile in range
}
}
impl ChunkQuantile<f64> for Float64Chunked {
fn quantile(
&self,
quantile: f64,
interpol: QuantileInterpolOptions,
) -> PolarsResult<Option<f64>> {
if !(0.0..=1.0).contains(&quantile) {
return Err(PolarsError::ComputeError(
"quantile should be between 0.0 and 1.0".into(),
));
}
let null_count = self.null_count();
let length = self.len();
if null_count == length {
return Ok(None);
}
let (idx, float_idx, top_idx) = quantile_idx(quantile, length, null_count, interpol);
let opt = match interpol {
QuantileInterpolOptions::Midpoint => {
if top_idx == idx {
ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float64Type>(|value| value.to_f64().unwrap())
.into_iter()
.next()
.flatten()
} else {
let bounds: Vec<Option<f64>> = ChunkSort::sort(self, false)
.slice(idx, 2)
.apply_cast_numeric::<_, Float64Type>(|value| value.to_f64().unwrap())
.into_iter()
.collect();
Some((bounds[0].unwrap() + bounds[1].unwrap()) / 2.0f64)
}
}
QuantileInterpolOptions::Linear => {
if top_idx == idx {
ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float64Type>(|value| value.to_f64().unwrap())
.into_iter()
.next()
.flatten()
} else {
let bounds: Vec<Option<f64>> = ChunkSort::sort(self, false)
.slice(idx, 2)
.apply_cast_numeric::<_, Float64Type>(|value| value.to_f64().unwrap())
.into_iter()
.collect();
linear_interpol(&bounds, idx, float_idx)
}
}
_ => ChunkSort::sort(self, false)
.slice(idx, 1)
.apply_cast_numeric::<_, Float64Type>(|value| value.to_f64().unwrap())
.into_iter()
.next()
.flatten(),
};
Ok(opt)
}
fn median(&self) -> Option<f64> {
self.quantile(0.5, QuantileInterpolOptions::Linear).unwrap() // unwrap fine since quantile in range
}More examples
src/frame/groupby/aggregations/mod.rs (line 913)
861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141
pub(crate) unsafe fn agg_quantile(
&self,
groups: &GroupsProxy,
quantile: f64,
interpol: QuantileInterpolOptions,
) -> Series {
let ca = &self.0;
let invalid_quantile = !(0.0..=1.0).contains(&quantile);
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<T, _>(groups, |idx| {
debug_assert!(idx.len() <= ca.len());
if idx.is_empty() | invalid_quantile {
return None;
}
let take = { ca.take_unchecked(idx.into()) };
take.quantile_as_series(quantile, interpol)
.unwrap() // checked with invalid quantile check
.unpack::<T>()
.unwrap()
.get(0)
}),
GroupsProxy::Slice { groups, .. } => {
if _use_rolling_kernels(groups, self.chunks()) {
let arr = self.downcast_iter().next().unwrap();
let values = arr.values().as_slice();
let offset_iter = groups.iter().map(|[first, len]| (*first, *len));
let arr = match arr.validity() {
None => rolling::no_nulls::rolling_quantile_by_iter(
values,
quantile,
interpol,
offset_iter,
),
Some(validity) => rolling::nulls::rolling_quantile_by_iter(
values,
validity,
quantile,
interpol,
offset_iter,
),
};
ChunkedArray::<T>::from_chunks("", vec![arr]).into_series()
} else {
_agg_helper_slice::<T, _>(groups, |[first, len]| {
debug_assert!(first + len <= self.len() as IdxSize);
match len {
0 => None,
1 => self.get(first as usize),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
// unwrap checked with invalid quantile check
arr_group
.quantile(quantile, interpol)
.unwrap()
.map(|flt| NumCast::from(flt).unwrap())
}
}
})
}
}
}
}
pub(crate) unsafe fn agg_median(&self, groups: &GroupsProxy) -> Series {
let ca = &self.0;
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<T, _>(groups, |idx| {
debug_assert!(idx.len() <= ca.len());
if idx.is_empty() {
return None;
}
let take = { ca.take_unchecked(idx.into()) };
take.median_as_series().unpack::<T>().unwrap().get(0)
}),
GroupsProxy::Slice { .. } => {
self.agg_quantile(groups, 0.5, QuantileInterpolOptions::Linear)
}
}
}
}
impl<T> ChunkedArray<T>
where
T: PolarsIntegerType,
ChunkedArray<T>: IntoSeries,
T::Native: NumericNative + Ord,
<T::Native as Simd>::Simd: std::ops::Add<Output = <T::Native as Simd>::Simd>
+ arrow::compute::aggregate::Sum<T::Native>
+ arrow::compute::aggregate::SimdOrd<T::Native>,
{
pub(crate) unsafe fn agg_mean(&self, groups: &GroupsProxy) -> Series {
match groups {
GroupsProxy::Idx(groups) => {
_agg_helper_idx::<Float64Type, _>(groups, |(first, idx)| {
// this can fail due to a bug in lazy code.
// here users can create filters in aggregations
// and thereby creating shorter columns than the original group tuples.
// the group tuples are modified, but if that's done incorrect there can be out of bounds
// access
debug_assert!(idx.len() <= self.len());
if idx.is_empty() {
None
} else if idx.len() == 1 {
self.get(first as usize).map(|sum| sum.to_f64().unwrap())
} else {
match (self.has_validity(), self.chunks.len()) {
(false, 1) => {
take_agg_no_null_primitive_iter_unchecked(
self.downcast_iter().next().unwrap(),
idx.iter().map(|i| *i as usize),
|a, b| a + b,
0.0f64,
)
}
.to_f64()
.map(|sum| sum / idx.len() as f64),
(_, 1) => {
{
take_agg_primitive_iter_unchecked_count_nulls::<
T::Native,
f64,
_,
_,
>(
self.downcast_iter().next().unwrap(),
idx.iter().map(|i| *i as usize),
|a, b| a + b,
0.0,
idx.len() as IdxSize,
)
}
.map(|(sum, null_count)| {
sum / (idx.len() as f64 - null_count as f64)
})
}
_ => {
let take = { self.take_unchecked(idx.into()) };
take.mean()
}
}
}
})
}
GroupsProxy::Slice {
groups: groups_slice,
..
} => {
if _use_rolling_kernels(groups_slice, self.chunks()) {
let ca = self.cast(&DataType::Float64).unwrap();
ca.agg_mean(groups)
} else {
_agg_helper_slice::<Float64Type, _>(groups_slice, |[first, len]| {
debug_assert!(first + len <= self.len() as IdxSize);
match len {
0 => None,
1 => self.get(first as usize).map(|v| NumCast::from(v).unwrap()),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
arr_group.mean()
}
}
})
}
}
}
}
pub(crate) unsafe fn agg_var(&self, groups: &GroupsProxy, ddof: u8) -> Series {
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<Float64Type, _>(groups, |idx| {
debug_assert!(idx.len() <= self.len());
if idx.is_empty() {
return None;
}
let take = { self.take_unchecked(idx.into()) };
take.var_as_series(ddof)
.unpack::<Float64Type>()
.unwrap()
.get(0)
}),
GroupsProxy::Slice {
groups: groups_slice,
..
} => {
if _use_rolling_kernels(groups_slice, self.chunks()) {
let ca = self.cast(&DataType::Float64).unwrap();
ca.agg_var(groups, ddof)
} else {
_agg_helper_slice::<Float64Type, _>(groups_slice, |[first, len]| {
debug_assert!(first + len <= self.len() as IdxSize);
match len {
0 => None,
1 => NumCast::from(0),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
arr_group.var(ddof)
}
}
})
}
}
}
}
pub(crate) unsafe fn agg_std(&self, groups: &GroupsProxy, ddof: u8) -> Series {
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<Float64Type, _>(groups, |idx| {
debug_assert!(idx.len() <= self.len());
if idx.is_empty() {
return None;
}
let take = { self.take_unchecked(idx.into()) };
take.std_as_series(ddof)
.unpack::<Float64Type>()
.unwrap()
.get(0)
}),
GroupsProxy::Slice {
groups: groups_slice,
..
} => {
if _use_rolling_kernels(groups_slice, self.chunks()) {
let ca = self.cast(&DataType::Float64).unwrap();
ca.agg_std(groups, ddof)
} else {
_agg_helper_slice::<Float64Type, _>(groups_slice, |[first, len]| {
debug_assert!(first + len <= self.len() as IdxSize);
match len {
0 => None,
1 => NumCast::from(0),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
arr_group.std(ddof)
}
}
})
}
}
}
}
pub(crate) unsafe fn agg_quantile(
&self,
groups: &GroupsProxy,
quantile: f64,
interpol: QuantileInterpolOptions,
) -> Series {
match groups {
GroupsProxy::Idx(groups) => agg_helper_idx_on_all::<Float64Type, _>(groups, |idx| {
debug_assert!(idx.len() <= self.len());
if idx.is_empty() {
return None;
}
let take = self.take_unchecked(idx.into());
take.quantile_as_series(quantile, interpol)
.unwrap()
.unpack::<Float64Type>()
.unwrap()
.get(0)
}),
GroupsProxy::Slice {
groups: groups_slice,
..
} => {
if _use_rolling_kernels(groups_slice, self.chunks()) {
let ca = self.cast(&DataType::Float64).unwrap();
ca.agg_quantile(groups, quantile, interpol)
} else {
_agg_helper_slice::<Float64Type, _>(groups_slice, |[first, len]| {
debug_assert!(len <= self.len() as IdxSize);
match len {
0 => None,
1 => self.get(first as usize).map(|v| NumCast::from(v).unwrap()),
_ => {
let arr_group = _slice_from_offsets(self, first, len);
arr_group.quantile(quantile, interpol).unwrap()
}
}
})
}
}
}
}