/aosp_15_r20/external/guava/guava/src/com/google/common/math/ |
H A D | Quantiles.java | 35 * href="http://en.wikipedia.org/wiki/Quantile">quantiles</a>. 63 * 50, 90, and 99, to their corresponding quantile values. 74 * <p>The definition of the kth q-quantile of N values is as follows: define x = k * (N - 1) / q; if 80 * href="http://stat.ethz.ch/R-manual/R-devel/library/stats/html/quantile.html">R</a>, and it is 82 * href="http://en.wikipedia.org/wiki/Quantile#Estimating_the_quantiles_of_a_population"> 134 /** Specifies the computation of a median (i.e. the 1st 2-quantile). */ 170 checkArgument(scale > 0, "Quantile scale must be positive"); in Scale() 175 * Specifies a single quantile index to be calculated, i.e. the k in the kth q-quantile. 177 * @param index the quantile index, which must be in the inclusive range [0, q] for q-quantiles 184 * Specifies multiple quantile indexes to be calculated, each index being the k in the kth [all …]
|
/aosp_15_r20/external/guava/android/guava/src/com/google/common/math/ |
H A D | Quantiles.java | 35 * href="http://en.wikipedia.org/wiki/Quantile">quantiles</a>. 63 * 50, 90, and 99, to their corresponding quantile values. 74 * <p>The definition of the kth q-quantile of N values is as follows: define x = k * (N - 1) / q; if 80 * href="http://stat.ethz.ch/R-manual/R-devel/library/stats/html/quantile.html">R</a>, and it is 82 * href="http://en.wikipedia.org/wiki/Quantile#Estimating_the_quantiles_of_a_population"> 134 /** Specifies the computation of a median (i.e. the 1st 2-quantile). */ 170 checkArgument(scale > 0, "Quantile scale must be positive"); in Scale() 175 * Specifies a single quantile index to be calculated, i.e. the k in the kth q-quantile. 177 * @param index the quantile index, which must be in the inclusive range [0, q] for q-quantiles 184 * Specifies multiple quantile indexes to be calculated, each index being the k in the kth [all …]
|
/aosp_15_r20/external/apache-commons-math/src/main/java/org/apache/commons/math3/stat/descriptive/rank/ |
H A D | Percentile.java | 76 * <a href="http://en.wikipedia.org/wiki/Quantile">Quantile page(wikipedia)</a>, 117 * with no quantile argument */ 118 private double quantile; field in Percentile 126 * <li>default quantile: 50.0, can be reset with {@link #setQuantile(double)}</li> 141 * Constructs a Percentile with the specific quantile value and the following 147 * @param quantile the quantile 151 public Percentile(final double quantile) throws MathIllegalArgumentException { in Percentile() argument 152 this(quantile, EstimationType.LEGACY, NaNStrategy.REMOVED, in Percentile() 174 setQuantile(original.quantile); in Percentile() 179 * Constructs a Percentile with the specific quantile value, [all …]
|
H A D | PSquarePercentile.java | 65 * A Default quantile needed in case if user prefers to use default no 89 * The quantile needed should be in range of 0-1. The constructor 93 private final double quantile; field in PSquarePercentile 128 this.quantile = p / 100d;// always set it within (0,1] in PSquarePercentile() 133 * default quantile} needed 147 final double[] toHash = {result, quantile, markersHash, countOfObservations}; in hashCode() 180 * approximate quantile. 198 .get((int) (quantile * (initialFive.size() - 1))); in increment() 202 markers = newMarkers(initialFive, quantile); in increment() 210 * of the quantile and all markers. [all …]
|
/aosp_15_r20/external/apache-commons-math/src/main/java/org/apache/commons/math/stat/descriptive/rank/ |
H A D | Percentile.java | 94 * with no quantile argument */ 95 private double quantile = 0.0; field in Percentile 101 * Constructs a Percentile with a default quantile 109 * Constructs a Percentile with the specific quantile value. 110 * @param p the quantile 169 * Calls to this method do not modify the internal <code>quantile</code> 178 * is null or p is not a valid quantile value (p must be greater than 0 197 * Returns an estimate of the <code>quantile</code>th percentile of the 198 * designated values in the <code>values</code> array. The quantile 199 * estimated is determined by the <code>quantile</code> property. [all …]
|
/aosp_15_r20/external/webrtc/rtc_base/numerics/ |
H A D | sample_stats.cc | 27 return Quantile(0.5); in Median() 30 double SampleStats<double>::Quantile(double quantile) { in Quantile() argument 33 return GetPercentile(quantile); in Quantile() 81 return Quantile(0.5); in Median() 84 TimeDelta SampleStats<TimeDelta>::Quantile(double quantile) { in Quantile() argument 85 return TimeDelta::Seconds(stats_.Quantile(quantile)); in Quantile() 129 return Quantile(0.5); in Median() 132 DataRate SampleStats<DataRate>::Quantile(double quantile) { in Quantile() argument 133 return DataRate::BitsPerSec(stats_.Quantile(quantile)); in Quantile()
|
H A D | sample_stats.h | 29 double Quantile(double quantile); 46 TimeDelta Quantile(double quantile); 66 DataRate Quantile(double quantile);
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/ |
H A D | Sorting.cpp | 202 … "quantile() interpolation must be one of linear, lower, higher, midpoint or nearest, but got ", in get_quantile_interpolation_mode() 208 TORCH_CHECK(self.numel() > 0, "quantile() input tensor must be non-empty"); in quantile_checks() 209 TORCH_CHECK(q.dim() <= 1, "quantile() q must be a scalar or 1D tensor"); in quantile_checks() 212 "quantile() input tensor must be either float or double dtype"); in quantile_checks() 215 "quantile() q tensor must be same dtype as the input tensor"); in quantile_checks() 218 "quantile() q tensor must be on the same device as the input tensor"); in quantile_checks() 261 "quantile() q values must be in the range [0, 1]"); in quantile_compute() 289 "quantile() input tensor is too large"); in quantile_compute() 295 // If all values are nan, set rank to 0 so the quantile computed is nan. in quantile_compute() 308 // For quantile, compute ranks based on reduction size. If there is nan in quantile_compute() [all …]
|
/aosp_15_r20/external/federated-compute/fcp/secagg/server/ |
H A D | distribution_utilities.cc | 96 double HypergeometricDistribution::FindQuantile(double quantile, in FindQuantile() argument 98 if (quantile > 0.5) { in FindQuantile() 99 quantile = 1 - quantile; in FindQuantile() 103 return sampled_ - FindQuantileImpl(quantile, total_ - marked_) - 1; in FindQuantile() 105 return FindQuantileImpl(quantile, marked_); in FindQuantile() 109 double HypergeometricDistribution::FindQuantileImpl(double quantile, in FindQuantileImpl() argument 115 std::sqrt(-std::log(quantile) / (2 * sampled_))); in FindQuantileImpl() 123 while (current_cdf < quantile && result < sampled_) { in FindQuantileImpl()
|
H A D | distribution_utilities.h | 40 // Finds the value whose cdf is quantile rounded outwards to an integer. 41 // Setting complement to true is equivalent to setting quantile = 1 - quantile 43 double FindQuantile(double quantile, bool complement = false); 57 double FindQuantileImpl(double quantile, int counted);
|
/aosp_15_r20/external/pytorch/torch/_numpy/ |
H A D | _reductions_impl.py | 375 def quantile( function 387 # raise NotImplementedError("overwrite_input in quantile not implemented.") 397 # edge case: torch.quantile only supports float32 and float64 408 # FIXME(Mario) Doesn't np.quantile accept a tuple? 409 # torch.quantile does accept a number. If we don't want to implement the tuple behaviour 415 return torch.quantile(a, q, axis=axis, interpolation=method) 434 return quantile( 452 return quantile(
|
/aosp_15_r20/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1beta1/src/main/java/com/google/cloud/aiplatform/v1beta1/schema/trainingjob/definition/ |
H A D | AutoMlForecastingInputsOrBuilder.java | 203 * * "minimize-quantile-loss" - Minimize the quantile loss at the quantiles 226 * * "minimize-quantile-loss" - Minimize the quantile loss at the quantiles 609 * Quantiles to use for minimize-quantile-loss `optimization_objective`. Up to 611 * the value of optimization_objective is minimize-quantile-loss. Represents 624 * Quantiles to use for minimize-quantile-loss `optimization_objective`. Up to 626 * the value of optimization_objective is minimize-quantile-loss. Represents 639 * Quantiles to use for minimize-quantile-loss `optimization_objective`. Up to 641 * the value of optimization_objective is minimize-quantile-loss. Represents
|
/aosp_15_r20/external/webrtc/modules/audio_coding/neteq/ |
H A D | delay_manager.cc | 50 "quantile", &quantile, // in Config() 63 " quantile=" in Log() 64 << quantile << " forget_factor=" << forget_factor in Log() 76 (1 << 30) * config.quantile, in DelayManager()
|
/aosp_15_r20/external/pytorch/test/torch_np/numpy_tests/lib/ |
H A D | test_function_base.py | 3412 a = np.quantile(x, 0.45) 3420 assert_equal(np.quantile(x, 0), 0.0) 3421 assert_equal(np.quantile(x, 1), 3.5) 3422 assert_equal(np.quantile(x, 0.5), 1.75) 3424 @xfail # (reason="quantile w/integers or bools") 3427 tf_quant = np.quantile(True, False) 3431 quant_res = np.quantile(a, a) 3437 # fractional input, integral quantile 3439 q = np.quantile(x, 0) 3443 q = np.quantile(x, 1) [all …]
|
/aosp_15_r20/external/tensorflow/tensorflow/core/api_def/base_api/ |
H A D | api_def_BoostedTreesFlushQuantileSummaries.pbtxt | 11 summary: "Flush the quantile summaries from each quantile stream resource." 13 An op that outputs a list of quantile summaries of a quantile stream resource.
|
H A D | api_def_BoostedTreesQuantileStreamResourceAddSummaries.pbtxt | 17 summary: "Add the quantile summaries to each quantile stream resource." 19 An op that adds a list of quantile summaries to a quantile stream resource. Each
|
H A D | api_def_IsBoostedTreesQuantileStreamResourceInitialized.pbtxt | 7 resource; The reference to quantile stream resource handle. 16 summary: "Checks whether a quantile stream has been initialized." 18 An Op that checks if quantile stream resource is initialized.
|
H A D | api_def_BoostedTreesQuantileStreamResourceFlush.pbtxt | 21 entry is the ith quantile of the input with an approximation error of epsilon. 28 summary: "Flush the summaries for a quantile stream resource." 30 An op that flushes the summaries for a quantile stream resource.
|
/aosp_15_r20/external/skia/tools/calmbench/ |
H A D | ab.py | 13 # If range (1/3 quantile, 2/3 quantile) is completely disjoint between A and B, 18 # out benches and only take more measurements for benches whose current quantile 49 FACTOR = 3 # lower/upper quantile factor 378 "%(A)s quantile (ns), %(B)s quantile (ns), " +
|
/aosp_15_r20/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1beta1/src/main/proto/google/cloud/aiplatform/v1beta1/schema/trainingjob/definition/ |
H A D | automl_time_series_forecasting.proto | 198 // * "minimize-quantile-loss" - Minimize the quantile loss at the quantiles 261 // Quantiles to use for minimize-quantile-loss `optimization_objective`. Up to 263 // the value of optimization_objective is minimize-quantile-loss. Represents
|
/aosp_15_r20/external/googleapis/google/cloud/aiplatform/v1beta1/schema/trainingjob/definition/ |
H A D | automl_time_series_forecasting.proto | 198 // * "minimize-quantile-loss" - Minimize the quantile loss at the quantiles 261 // Quantiles to use for minimize-quantile-loss `optimization_objective`. Up to 263 // the value of optimization_objective is minimize-quantile-loss. Represents
|
/aosp_15_r20/packages/modules/StatsD/lib/libkll/include/ |
D | kll.h | 23 // KLL Quantile - Implementation of Approximate quantiles algorithm based on 106 // When a user queries for a quantile phi, the rank of the returned 110 // with delta probability, at most one out of all possible quantile
|
/aosp_15_r20/external/tensorflow/tensorflow/python/ops/distributions/ |
H A D | transformed_distribution.py | 517 raise NotImplementedError("quantile is not implemented when overriding " 520 raise NotImplementedError("quantile is not implemented when " 522 # x_q is the "qth quantile" of X iff q = P[X <= x_q]. Now, since X = 524 # implies the qth quantile of Y is g(x_q). 525 inv_cdf = self.distribution.quantile(value)
|
H A D | distribution.py | 990 raise NotImplementedError("quantile is not implemented: {}".format( 999 def quantile(self, value, name="quantile"): member in Distribution 1000 """Quantile function. Aka "inverse cdf" or "percent point function". 1002 Given random variable `X` and `p in [0, 1]`, the `quantile` is: 1005 quantile(p) := x such that P[X <= x] == p 1013 quantile: a `Tensor` of shape `sample_shape(x) + self.batch_shape` with
|
/aosp_15_r20/external/google-cloud-java/java-automl/proto-google-cloud-automl-v1beta1/src/main/java/com/google/cloud/automl/v1beta1/ |
H A D | Float64StatsOrBuilder.java | 56 * Ordered from 0 to k k-quantile values of the data series of n values. 71 * Ordered from 0 to k k-quantile values of the data series of n values. 86 * Ordered from 0 to k k-quantile values of the data series of n values.
|