rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-21 18:35:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: rmontanana:211
Branches Tags
rmontanana:main rmontanana:211
rmontanana:v2.1.1 rmontanana:v2.1.0 rmontanana:v2.0.1 rmontanana:v2.0.0 rmontanana:v1.2.1 rmontanana:v1.2.0 rmontanana:v1.1.3 rmontanana:v1.1.2 rmontanana:v1.1.1 rmontanana:v1.1.0 rmontanana:v1.0.0.0
...
compare: rmontanana:23a676d65496aa873b0bfae3baa3d0b8e33b5a02
Branches Tags
rmontanana:main rmontanana:211
rmontanana:v2.1.1 rmontanana:v2.1.0 rmontanana:v2.0.1 rmontanana:v2.0.0 rmontanana:v1.2.1 rmontanana:v1.2.0 rmontanana:v1.1.3 rmontanana:v1.1.2 rmontanana:v1.1.1 rmontanana:v1.1.0 rmontanana:v1.0.0.0

4 Commits
211 ... 23a676d654

Author SHA1 Message Date
Ricardo Montañana Gómez
23a676d654 Merge d90e21ec4c into 7b0673fd4b 2024-07-02 18:54:21 +02:00
Ricardo Montañana Gómez
d90e21ec4c Include upper_bound and lower_bound implementation 2024-07-02 18:54:07 +02:00
Ricardo Montañana Gómez
c488ace719 Fix FImdlp tests 2024-07-02 11:50:42 +02:00
Ricardo Montañana Gómez
8f6e16f04f Fix BinDisc quantile mistakes 2024-07-02 09:40:06 +02:00
17 changed files with 1426 additions and 415 deletions
Expand all files Collapse all files

2
.vscode/launch.json vendored
View File

@@ -8,7 +8,7 @@
"name": "C++ Launch config", "name": "C++ Launch config",
"type": "cppdbg", "type": "cppdbg",
"request": "launch", "request": "launch",
"program": "${workspaceFolder}/tests/build/Metrics_unittest", "program": "${workspaceFolder}/tests/build/BinDisc_unittest",
"cwd": "${workspaceFolder}/tests/build", "cwd": "${workspaceFolder}/tests/build",
"args": [], "args": [],
"launchCompleteCommand": "exec-run", "launchCompleteCommand": "exec-run",

30
BinDisc.cpp
View File

@@ -1,5 +1,4 @@
#include <algorithm> #include <algorithm>
#include <limits>
#include <cmath> #include <cmath>
#include "BinDisc.h" #include "BinDisc.h"
#include <iostream> #include <iostream>
@@ -20,12 +19,15 @@ namespace mdlp {
// y is included for compatibility with the Discretizer interface // y is included for compatibility with the Discretizer interface
cutPoints.clear(); cutPoints.clear();
if (X.empty()) { if (X.empty()) {
cutPoints.push_back(std::numeric_limits<precision_t>::max()); cutPoints.push_back(0.0);
cutPoints.push_back(0.0);
return; return;
} }
if (strategy == strategy_t::QUANTILE) { if (strategy == strategy_t::QUANTILE) {
direction = bound_dir_t::RIGHT;
fit_quantile(X); fit_quantile(X);
} else if (strategy == strategy_t::UNIFORM) { } else if (strategy == strategy_t::UNIFORM) {
direction = bound_dir_t::RIGHT;
fit_uniform(X); fit_uniform(X);
} }
} }
@@ -35,13 +37,12 @@ namespace mdlp {
} }
std::vector<precision_t> linspace(precision_t start, precision_t end, int num) std::vector<precision_t> linspace(precision_t start, precision_t end, int num)
{ {
// Doesn't include end point as it is not needed
if (start == end) { if (start == end) {
return { 0 }; return { start, end };
} }
precision_t delta = (end - start) / static_cast<precision_t>(num - 1); precision_t delta = (end - start) / static_cast<precision_t>(num - 1);
std::vector<precision_t> linspc; std::vector<precision_t> linspc;
for (size_t i = 0; i < num - 1; ++i) { for (size_t i = 0; i < num; ++i) {
precision_t val = start + delta * static_cast<precision_t>(i); precision_t val = start + delta * static_cast<precision_t>(i);
linspc.push_back(val); linspc.push_back(val);
} }
@@ -55,6 +56,7 @@ namespace mdlp {
{ {
// Implementation taken from https://dpilger26.github.io/NumCpp/doxygen/html/percentile_8hpp_source.html // Implementation taken from https://dpilger26.github.io/NumCpp/doxygen/html/percentile_8hpp_source.html
std::vector<precision_t> results; std::vector<precision_t> results;
bool first = true;
results.reserve(percentiles.size()); results.reserve(percentiles.size());
for (auto percentile : percentiles) { for (auto percentile : percentiles) {
const size_t i = static_cast<size_t>(std::floor(static_cast<double>(data.size() - 1) * percentile / 100.)); const size_t i = static_cast<size_t>(std::floor(static_cast<double>(data.size() - 1) * percentile / 100.));
@@ -64,8 +66,9 @@ namespace mdlp {
(percentile / 100.0 - percentI) / (percentile / 100.0 - percentI) /
(static_cast<double>(indexLower + 1) / static_cast<double>(data.size() - 1) - percentI); (static_cast<double>(indexLower + 1) / static_cast<double>(data.size() - 1) - percentI);
const auto value = data[indexLower] + (data[indexLower + 1] - data[indexLower]) * fraction; const auto value = data[indexLower] + (data[indexLower + 1] - data[indexLower]) * fraction;
if (value != results.back()) if (value != results.back() || first) // first needed as results.back() return is undefined for empty vectors
results.push_back(value); results.push_back(value);
first = false;
} }
return results; return results;
} }
@@ -75,25 +78,16 @@ namespace mdlp {
auto data = X; auto data = X;
std::sort(data.begin(), data.end()); std::sort(data.begin(), data.end());
if (data.front() == data.back() || data.size() == 1) { if (data.front() == data.back() || data.size() == 1) {
// if X is constant // if X is constant, pass any two given points that shall be ignored in transform
cutPoints.push_back(std::numeric_limits<precision_t>::max()); cutPoints.push_back(data.front());
cutPoints.push_back(data.front());
return; return;
} }
cutPoints = percentile(data, quantiles); cutPoints = percentile(data, quantiles);
normalizeCutPoints();
} }
void BinDisc::fit_uniform(samples_t& X) void BinDisc::fit_uniform(samples_t& X)
{ {
auto minmax = std::minmax_element(X.begin(), X.end()); auto minmax = std::minmax_element(X.begin(), X.end());
cutPoints = linspace(*minmax.first, *minmax.second, n_bins + 1); cutPoints = linspace(*minmax.first, *minmax.second, n_bins + 1);
normalizeCutPoints();
}
void BinDisc::normalizeCutPoints()
{
// Add max value to the end
cutPoints.push_back(std::numeric_limits<precision_t>::max());
// Remove first as it is not needed
cutPoints.erase(cutPoints.begin());
} }
} }

1
BinDisc.h
View File

@@ -20,7 +20,6 @@ namespace mdlp {
private: private:
void fit_uniform(samples_t&); void fit_uniform(samples_t&);
void fit_quantile(samples_t&); void fit_quantile(samples_t&);
void normalizeCutPoints();
int n_bins; int n_bins;
strategy_t strategy; strategy_t strategy;
}; };

7
CPPFImdlp.cpp
View File

@@ -12,6 +12,7 @@ namespace mdlp {
max_depth(max_depth_), max_depth(max_depth_),
proposed_cuts(proposed) proposed_cuts(proposed)
{ {
direction = bound_dir_t::LEFT;
} }
size_t CPPFImdlp::compute_max_num_cut_points() const size_t CPPFImdlp::compute_max_num_cut_points() const
@@ -25,7 +26,7 @@ namespace mdlp {
} }
if (proposed_cuts < 1) if (proposed_cuts < 1)
return static_cast<size_t>(round(static_cast<float>(X.size()) * proposed_cuts)); return static_cast<size_t>(round(static_cast<float>(X.size()) * proposed_cuts));
return static_cast<size_t>(proposed_cuts); return static_cast<size_t>(proposed_cuts); // The 2 extra cutpoints should not be considered here as this parameter is considered before they are added
} }
void CPPFImdlp::fit(samples_t& X_, labels_t& y_) void CPPFImdlp::fit(samples_t& X_, labels_t& y_)
@@ -58,6 +59,10 @@ namespace mdlp {
resizeCutPoints(); resizeCutPoints();
} }
} }
// Insert first & last X value to the cutpoints as them shall be ignored in transform
auto minmax = std::minmax_element(X.begin(), X.end());
cutPoints.push_back(*minmax.second);
cutPoints.insert(cutPoints.begin(), *minmax.first);
} }
pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end) pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end)

49
Discretizer.cpp
View File

@@ -1,13 +1,58 @@
#include "Discretizer.h" #include "Discretizer.h"
namespace mdlp { namespace mdlp {
// The next to templates have been taken to have the chance to customize them to match
// np.searchsorted that is used in scikit-learn KBinsDiscretizer
// Code Taken from https://cplusplus.com/reference/algorithm/upper_bound/?kw=upper_bound
template <class ForwardIterator, class T>
ForwardIterator upper_bound(ForwardIterator first, ForwardIterator last, const T& val)
{
ForwardIterator it;
typename iterator_traits<ForwardIterator>::difference_type count, step;
count = std::distance(first, last);
while (count > 0) {
it = first; step = count / 2; std::advance(it, step);
if (!(val < *it)) // or: if (!comp(val,*it)), for version (2)
{
first = ++it; count -= step + 1;
} else count = step;
}
return first;
}
// Code Taken from https://cplusplus.com/reference/algorithm/lower_bound/?kw=lower_bound
template <class ForwardIterator, class T>
ForwardIterator lower_bound(ForwardIterator first, ForwardIterator last, const T& val)
{
ForwardIterator it;
typename iterator_traits<ForwardIterator>::difference_type count, step;
count = distance(first, last);
while (count > 0) {
it = first; step = count / 2; advance(it, step);
if (*it < val) { // or: if (comp(*it,val)), for version (2)
first = ++it;
count -= step + 1;
} else count = step;
}
return first;
}
labels_t& Discretizer::transform(const samples_t& data) labels_t& Discretizer::transform(const samples_t& data)
{ {
discretizedData.clear(); discretizedData.clear();
discretizedData.reserve(data.size()); discretizedData.reserve(data.size());
// CutPoints always have at least two items
// Have to ignore first and last cut points provided
auto first = cutPoints.begin() + 1;
auto last = cutPoints.end() - 1;
auto bound = direction == bound_dir_t::LEFT ? my_lower_bound<std::vector<float>::iterator, float> : my_upper_bound<std::vector<float>::iterator, float>;
for (const precision_t& item : data) { for (const precision_t& item : data) {
auto upper = std::upper_bound(cutPoints.begin(), cutPoints.end(), item); auto pos = bound(first, last, item);
discretizedData.push_back(upper - cutPoints.begin()); int number = pos - first;
/*
OJO
*/
if (number < 0)
throw std::runtime_error("number is less than 0 in discretizer::transform");
discretizedData.push_back(number);
} }
return discretizedData; return discretizedData;
} }

9
Discretizer.h
View File

@@ -7,6 +7,10 @@
#include "typesFImdlp.h" #include "typesFImdlp.h"
namespace mdlp { namespace mdlp {
enum class bound_dir_t {
LEFT,
RIGHT
};
class Discretizer { class Discretizer {
public: public:
Discretizer() = default; Discretizer() = default;
@@ -18,10 +22,11 @@ namespace mdlp {
void fit_t(torch::Tensor& X_, torch::Tensor& y_); void fit_t(torch::Tensor& X_, torch::Tensor& y_);
torch::Tensor transform_t(torch::Tensor& X_); torch::Tensor transform_t(torch::Tensor& X_);
torch::Tensor fit_transform_t(torch::Tensor& X_, torch::Tensor& y_); torch::Tensor fit_transform_t(torch::Tensor& X_, torch::Tensor& y_);
static inline std::string version() { return "1.2.2"; }; static inline std::string version() { return "1.2.3"; };
protected: protected:
labels_t discretizedData = labels_t(); labels_t discretizedData = labels_t();
cutPoints_t cutPoints; cutPoints_t cutPoints; // At least two cutpoints must be provided, the first and the last will be ignored in transform
bound_dir_t direction; // used in transform
}; };
} }
#endif #endif

664
tests/BinDisc_unittest.cpp
View File

@@ -4,6 +4,7 @@
#include "gtest/gtest.h" #include "gtest/gtest.h"
#include "ArffFiles.h" #include "ArffFiles.h"
#include "../BinDisc.h" #include "../BinDisc.h"
#include "Experiments.hpp"
namespace mdlp { namespace mdlp {
const float margin = 1e-4; const float margin = 1e-4;
@@ -34,331 +35,360 @@ namespace mdlp {
public: public:
TestBinDisc4Q(int n_bins = 4) : BinDisc(n_bins, strategy_t::QUANTILE) {}; TestBinDisc4Q(int n_bins = 4) : BinDisc(n_bins, strategy_t::QUANTILE) {};
}; };
TEST_F(TestBinDisc3U, Easy3BinsUniform) // TEST_F(TestBinDisc3U, Easy3BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0 };
// auto y = labels_t();
// fit(X, y);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(3.66667, cuts.at(1), margin);
// EXPECT_NEAR(6.33333, cuts.at(2), margin);
// EXPECT_NEAR(9.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3Q, Easy3BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts[0], margin);
// EXPECT_NEAR(3.666667, cuts[1], margin);
// EXPECT_NEAR(6.333333, cuts[2], margin);
// EXPECT_NEAR(9, cuts[3], margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3U, X10BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(4.0, cuts.at(1), margin);
// EXPECT_NEAR(7.0, cuts.at(2), margin);
// EXPECT_NEAR(10.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3Q, X10BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(4.0, cuts.at(1), margin);
// EXPECT_NEAR(7.0, cuts.at(2), margin);
// EXPECT_NEAR(10.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3U, X11BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(4.33333, cuts.at(1), margin);
// EXPECT_NEAR(7.66667, cuts.at(2), margin);
// EXPECT_NEAR(11.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3U, X11BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(4.33333, cuts.at(1), margin);
// EXPECT_NEAR(7.66667, cuts.at(2), margin);
// EXPECT_NEAR(11.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3U, ConstantUniform)
// {
// samples_t X = { 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(2, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(1, cuts.at(1), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 0, 0 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3Q, ConstantQuantile)
// {
// samples_t X = { 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(2, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(1, cuts.at(1), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 0, 0 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc3U, EmptyUniform)
// {
// samples_t X = {};
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(2, cuts.size());
// EXPECT_NEAR(0, cuts.at(0), margin);
// EXPECT_NEAR(0, cuts.at(1), margin);
// }
// TEST_F(TestBinDisc3Q, EmptyQuantile)
// {
// samples_t X = {};
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(2, cuts.size());
// EXPECT_NEAR(0, cuts.at(0), margin);
// EXPECT_NEAR(0, cuts.at(1), margin);
// }
// TEST(TestBinDisc3, ExceptionNumberBins)
// {
// EXPECT_THROW(BinDisc(2), std::invalid_argument);
// }
// TEST_F(TestBinDisc3U, EasyRepeated)
// {
// samples_t X = { 3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(4, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(1.66667, cuts.at(1), margin);
// EXPECT_NEAR(2.33333, cuts.at(2), margin);
// EXPECT_NEAR(3.0, cuts.at(3), margin);
// auto labels = transform(X);
// labels_t expected = { 2, 0, 0, 2, 0, 0, 2, 0, 0 };
// EXPECT_EQ(expected, labels);
// ASSERT_EQ(3.0, X[0]); // X is not modified
// }
// TEST_F(TestBinDisc3Q, EasyRepeated)
// {
// samples_t X = { 3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(3, cuts.size());
// EXPECT_NEAR(1, cuts.at(0), margin);
// EXPECT_NEAR(1.66667, cuts.at(1), margin);
// EXPECT_NEAR(3.0, cuts.at(2), margin);
// auto labels = transform(X);
// labels_t expected = { 1, 0, 0, 1, 0, 0, 1, 0, 0 };
// EXPECT_EQ(expected, labels);
// ASSERT_EQ(3.0, X[0]); // X is not modified
// }
// TEST_F(TestBinDisc4U, Easy4BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(3.75, cuts.at(1), margin);
// EXPECT_NEAR(6.5, cuts.at(2), margin);
// EXPECT_NEAR(9.25, cuts.at(3), margin);
// EXPECT_NEAR(12.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4Q, Easy4BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(3.75, cuts.at(1), margin);
// EXPECT_NEAR(6.5, cuts.at(2), margin);
// EXPECT_NEAR(9.25, cuts.at(3), margin);
// EXPECT_NEAR(12.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4U, X13BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.0, cuts.at(1), margin);
// EXPECT_NEAR(7.0, cuts.at(2), margin);
// EXPECT_NEAR(10.0, cuts.at(3), margin);
// EXPECT_NEAR(13.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4Q, X13BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.0, cuts.at(1), margin);
// EXPECT_NEAR(7.0, cuts.at(2), margin);
// EXPECT_NEAR(10.0, cuts.at(3), margin);
// EXPECT_NEAR(13.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4U, X14BinsUniform)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.25, cuts.at(1), margin);
// EXPECT_NEAR(7.5, cuts.at(2), margin);
// EXPECT_NEAR(10.75, cuts.at(3), margin);
// EXPECT_NEAR(14.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4Q, X14BinsQuantile)
// {
// samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.25, cuts.at(1), margin);
// EXPECT_NEAR(7.5, cuts.at(2), margin);
// EXPECT_NEAR(10.75, cuts.at(3), margin);
// EXPECT_NEAR(14.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4U, X15BinsUniform)
// {
// samples_t X = { 15.0, 8.0, 12.0, 14.0, 6.0, 1.0, 13.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.5, cuts.at(1), margin);
// EXPECT_NEAR(8, cuts.at(2), margin);
// EXPECT_NEAR(11.5, cuts.at(3), margin);
// EXPECT_NEAR(15.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 3, 1, 3, 3, 1, 0, 3, 2, 2, 2, 1, 0, 0, 1, 0 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4Q, X15BinsQuantile)
// {
// samples_t X = { 15.0, 13.0, 12.0, 14.0, 6.0, 1.0, 8.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0 };
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(1.0, cuts.at(0), margin);
// EXPECT_NEAR(4.5, cuts.at(1), margin);
// EXPECT_NEAR(8, cuts.at(2), margin);
// EXPECT_NEAR(11.5, cuts.at(3), margin);
// EXPECT_NEAR(15.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 3, 3, 3, 3, 1, 0, 1, 2, 2, 2, 1, 0, 0, 1, 0 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4U, RepeatedValuesUniform)
// {
// samples_t X = { 0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0 };
// // 0 1 2 3 4 5 6 7 8 9
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(0.0, cuts.at(0), margin);
// EXPECT_NEAR(1.0, cuts.at(1), margin);
// EXPECT_NEAR(2.0, cuts.at(2), margin);
// EXPECT_NEAR(3.0, cuts.at(3), margin);
// EXPECT_NEAR(4.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 2, 2, 2, 3 };
// EXPECT_EQ(expected, labels);
// }
// TEST_F(TestBinDisc4Q, RepeatedValuesQuantile)
// {
// samples_t X = { 0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0 };
// // 0 1 2 3 4 5 6 7 8 9
// fit(X);
// auto cuts = getCutPoints();
// ASSERT_EQ(5, cuts.size());
// EXPECT_NEAR(0.0, cuts.at(0), margin);
// EXPECT_NEAR(1.0, cuts.at(1), margin);
// EXPECT_NEAR(2.0, cuts.at(2), margin);
// EXPECT_NEAR(3.0, cuts.at(3), margin);
// EXPECT_NEAR(4.0, cuts.at(4), margin);
// auto labels = transform(X);
// labels_t expected = { 0, 0, 0, 0, 1, 1, 2, 2, 2, 3 };
// EXPECT_EQ(expected, labels);
// }
TEST(TestBinDiscGeneric, Fileset)
{ {
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0 }; Experiments exps(data_path + "tests.txt");
auto y = labels_t(); int num = 0;
fit(X, y); while (exps.is_next()) {
auto cuts = getCutPoints(); ++num;
ASSERT_EQ(3, cuts.size()); Experiment exp = exps.next();
EXPECT_NEAR(3.66667, cuts.at(0), margin); BinDisc disc(exp.n_bins_, exp.strategy_[0] == 'Q' ? strategy_t::QUANTILE : strategy_t::UNIFORM);
EXPECT_NEAR(6.33333, cuts.at(1), margin); std::vector<float> test;
EXPECT_EQ(numeric_limits<float>::max(), cuts.at(2)); if (exp.type_ == experiment_t::RANGE) {
auto labels = transform(X); for (float i = exp.from_; i < exp.to_; i += exp.step_) {
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2 }; test.push_back(i);
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3Q, Easy3BinsQuantile) } else {
{ test = exp.dataset_;
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0 };
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_NEAR(3.666667, cuts[0], margin);
EXPECT_NEAR(6.333333, cuts[1], margin);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3U, X10BinsUniform) // show_vector(test, "Test");
{ auto empty = std::vector<int>();
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 }; auto Xt = disc.fit_transform(test, empty);
fit(X); auto cuts = disc.getCutPoints();
auto cuts = getCutPoints(); EXPECT_EQ(exp.discretized_data_.size(), Xt.size());
ASSERT_EQ(3, cuts.size()); auto flag = false;
EXPECT_EQ(4.0, cuts[0]); size_t n_errors = 0;
EXPECT_EQ(7.0, cuts[1]); for (int i = 0; i < exp.discretized_data_.size(); ++i) {
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]); if (exp.discretized_data_.at(i) != Xt.at(i)) {
auto labels = transform(X); if (!flag) {
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 }; std::cout << "Exp #: " << num << " From: " << exp.from_ << " To: " << exp.to_ << " Step: " << exp.step_ << " Bins: " << exp.n_bins_ << " Strategy: " << exp.strategy_ << std::endl;
EXPECT_EQ(expected, labels); std::cout << "Error at " << i << " Expected: " << exp.discretized_data_.at(i) << " Got: " << Xt.at(i) << std::endl;
flag = true;
EXPECT_EQ(exp.discretized_data_.at(i), Xt.at(i));
} }
TEST_F(TestBinDisc3Q, X10BinsQuantile) n_errors++;
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 };
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_EQ(4, cuts[0]);
EXPECT_EQ(7, cuts[1]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3U, X11BinsUniform)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0 };
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_NEAR(4.33333, cuts[0], margin);
EXPECT_NEAR(7.66667, cuts[1], margin);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3U, X11BinsQuantile) if (flag) {
{ std::cout << "*** Found " << n_errors << " mistakes in this experiment dataset" << std::endl;
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0 };
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_NEAR(4.33333, cuts[0], margin);
EXPECT_NEAR(7.66667, cuts[1], margin);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3U, ConstantUniform) EXPECT_EQ(exp.cutpoints_.size(), cuts.size());
{ for (int i = 0; i < exp.cutpoints_.size(); ++i) {
samples_t X = { 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 }; EXPECT_NEAR(exp.cutpoints_.at(i), cuts.at(i), margin);
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(1, cuts.size());
EXPECT_EQ(numeric_limits<float>::max(), cuts[0]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 0, 0 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3Q, ConstantQuantile)
{
samples_t X = { 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(1, cuts.size());
EXPECT_EQ(numeric_limits<float>::max(), cuts[0]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 0, 0 };
EXPECT_EQ(expected, labels);
} }
TEST_F(TestBinDisc3U, EmptyUniform) std::cout << "* Number of experiments tested: " << num << std::endl;
{
samples_t X = {};
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(1, cuts.size());
EXPECT_EQ(numeric_limits<float>::max(), cuts[0]);
}
TEST_F(TestBinDisc3Q, EmptyQuantile)
{
samples_t X = {};
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(1, cuts.size());
EXPECT_EQ(numeric_limits<float>::max(), cuts[0]);
}
TEST(TestBinDisc3, ExceptionNumberBins)
{
EXPECT_THROW(BinDisc(2), std::invalid_argument);
}
TEST_F(TestBinDisc3U, EasyRepeated)
{
samples_t X = { 3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0 };
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_NEAR(1.66667, cuts[0], margin);
EXPECT_NEAR(2.33333, cuts[1], margin);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 2, 0, 0, 2, 0, 0, 2, 0, 0 };
EXPECT_EQ(expected, labels);
ASSERT_EQ(3.0, X[0]); // X is not modified
}
TEST_F(TestBinDisc3Q, EasyRepeated)
{
samples_t X = { 3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(2, cuts.size());
EXPECT_NEAR(1.66667, cuts[0], margin);
EXPECT_EQ(numeric_limits<float>::max(), cuts[1]);
auto labels = transform(X);
labels_t expected = { 1, 0, 0, 1, 0, 0, 1, 0, 0 };
EXPECT_EQ(expected, labels);
ASSERT_EQ(3.0, X[0]); // X is not modified
}
TEST_F(TestBinDisc4U, Easy4BinsUniform)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
ASSERT_EQ(3.75, cuts[0]);
EXPECT_EQ(6.5, cuts[1]);
EXPECT_EQ(9.25, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4Q, Easy4BinsQuantile)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
ASSERT_EQ(3.75, cuts[0]);
EXPECT_EQ(6.5, cuts[1]);
EXPECT_EQ(9.25, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4U, X13BinsUniform)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.0, cuts[0]);
EXPECT_EQ(7.0, cuts[1]);
EXPECT_EQ(10.0, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4Q, X13BinsQuantile)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.0, cuts[0]);
EXPECT_EQ(7.0, cuts[1]);
EXPECT_EQ(10.0, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4U, X14BinsUniform)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.25, cuts[0]);
EXPECT_EQ(7.5, cuts[1]);
EXPECT_EQ(10.75, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4Q, X14BinsQuantile)
{
samples_t X = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.25, cuts[0]);
EXPECT_EQ(7.5, cuts[1]);
EXPECT_EQ(10.75, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4U, X15BinsUniform)
{
samples_t X = { 15.0, 8.0, 12.0, 14.0, 6.0, 1.0, 13.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.5, cuts[0]);
EXPECT_EQ(8, cuts[1]);
EXPECT_EQ(11.5, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 3, 2, 3, 3, 1, 0, 3, 2, 2, 2, 1, 0, 0, 1, 0 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4Q, X15BinsQuantile)
{
samples_t X = { 15.0, 13.0, 12.0, 14.0, 6.0, 1.0, 8.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0 };
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(4.5, cuts[0]);
EXPECT_EQ(8, cuts[1]);
EXPECT_EQ(11.5, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 3, 3, 3, 3, 1, 0, 2, 2, 2, 2, 1, 0, 0, 1, 0 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4U, RepeatedValuesUniform)
{
samples_t X = { 0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0 };
// 0 1 2 3 4 5 6 7 8 9
fit(X);
auto cuts = getCutPoints();
EXPECT_EQ(4, cuts.size());
EXPECT_EQ(1.0, cuts[0]);
EXPECT_EQ(2.0, cuts[1]);
ASSERT_EQ(3.0, cuts[2]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[3]);
auto labels = transform(X);
labels_t expected = { 0, 1, 1, 1, 2, 2, 3, 3, 3, 3 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4Q, RepeatedValuesQuantile)
{
samples_t X = { 0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0 };
// 0 1 2 3 4 5 6 7 8 9
fit(X);
auto cuts = getCutPoints();
ASSERT_EQ(3, cuts.size());
EXPECT_EQ(2.0, cuts[0]);
ASSERT_EQ(3.0, cuts[1]);
EXPECT_EQ(numeric_limits<float>::max(), cuts[2]);
auto labels = transform(X);
labels_t expected = { 0, 0, 0, 0, 1, 1, 2, 2, 2, 2 };
EXPECT_EQ(expected, labels);
}
TEST_F(TestBinDisc4U, irisUniform)
{
ArffFiles file;
file.load(data_path + "iris.arff", true);
vector<samples_t>& X = file.getX();
fit(X[0]);
auto Xt = transform(X[0]);
labels_t expected = { 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 2, 1, 2, 1, 2, 0, 2, 0, 0, 1, 1, 1, 1, 2, 1, 1, 2, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 0, 1, 1, 1, 2, 0, 1, 2, 1, 3, 2, 2, 3, 0, 3, 2, 3, 2, 2, 2, 1, 1, 2, 2, 3, 3, 1, 2, 1, 3, 2, 2, 3, 2, 1, 2, 3, 3, 3, 2, 2, 1, 3, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1 };
EXPECT_EQ(expected, Xt);
auto Xtt = fit_transform(X[0], file.getY());
EXPECT_EQ(expected, Xtt);
auto Xt_t = torch::tensor(X[0], torch::kFloat32);
auto y_t = torch::tensor(file.getY(), torch::kInt32);
auto Xtt_t = fit_transform_t(Xt_t, y_t);
for (int i = 0; i < expected.size(); i++)
EXPECT_EQ(expected[i], Xtt_t[i].item<int>());
}
TEST_F(TestBinDisc4Q, irisQuantile)
{
ArffFiles file;
file.load(data_path + "iris.arff", true);
vector<samples_t>& X = file.getX();
fit(X[0]);
auto Xt = transform(X[0]);
labels_t expected = { 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2 };
EXPECT_EQ(expected, Xt);
auto Xtt = fit_transform(X[0], file.getY());
EXPECT_EQ(expected, Xtt);
auto Xt_t = torch::tensor(X[0], torch::kFloat32);
auto y_t = torch::tensor(file.getY(), torch::kInt32);
auto Xtt_t = fit_transform_t(Xt_t, y_t);
for (int i = 0; i < expected.size(); i++)
EXPECT_EQ(expected[i], Xtt_t[i].item<int>());
fit_t(Xt_t, y_t);
auto Xt_t2 = transform_t(Xt_t);
for (int i = 0; i < expected.size(); i++)
EXPECT_EQ(expected[i], Xt_t2[i].item<int>());
} }
} }

206
tests/Discretizer_unittest.cpp
View File

@@ -21,34 +21,196 @@ namespace mdlp {
} }
const std::string data_path = set_data_path(); const std::string data_path = set_data_path();
TEST(Discretizer, BinIrisUniform) TEST(Discretizer, Version)
{ {
ArffFiles file;
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM); Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
file.load(data_path + "iris.arff", true); auto version = disc->version();
vector<samples_t>& X = file.getX();
auto y = labels_t();
disc->fit(X[0], y);
auto Xt = disc->transform(X[0]);
labels_t expected = { 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 2, 1, 2, 1, 2, 0, 2, 0, 0, 1, 1, 1, 1, 2, 1, 1, 2, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 0, 1, 1, 1, 2, 0, 1, 2, 1, 3, 2, 2, 3, 0, 3, 2, 3, 2, 2, 2, 1, 1, 2, 2, 3, 3, 1, 2, 1, 3, 2, 2, 3, 2, 1, 2, 3, 3, 3, 2, 2, 1, 3, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1 };
delete disc; delete disc;
EXPECT_EQ(expected, Xt); std::cout << "Version computed: " << version;
} EXPECT_EQ("1.2.3", version);
TEST(Discretizer, BinIrisQuantile)
{
ArffFiles file;
Discretizer* disc = new BinDisc(4, strategy_t::QUANTILE);
file.load(data_path + "iris.arff", true);
vector<samples_t>& X = file.getX();
auto y = labels_t();
disc->fit(X[0], y);
auto Xt = disc->transform(X[0]);
labels_t expected = { 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2 };
delete disc;
EXPECT_EQ(expected, Xt);
} }
// TEST(Discretizer, BinIrisUniform)
// {
// ArffFiles file;
// Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
// file.load(data_path + "iris.arff", true);
// vector<samples_t>& X = file.getX();
// auto y = labels_t();
// disc->fit(X[0], y);
// auto Xt = disc->transform(X[0]);
// labels_t expected = { 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 2, 1, 2, 1, 2, 0, 2, 0, 0, 1, 1, 1, 1, 2, 1, 1, 2, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 0, 1, 1, 1, 2, 0, 1, 2, 1, 3, 2, 2, 3, 0, 3, 2, 3, 2, 2, 2, 1, 1, 2, 2, 3, 3, 1, 2, 1, 3, 2, 2, 3, 2, 1, 2, 3, 3, 3, 2, 2, 1, 3, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1 };
// delete disc;
// EXPECT_EQ(expected, Xt);
// }
// TEST(Discretizer, BinIrisQuantile)
// {
// ArffFiles file;
// Discretizer* disc = new BinDisc(4, strategy_t::QUANTILE);
// file.load(data_path + "iris.arff", true);
// vector<samples_t>& X = file.getX();
// auto y = labels_t();
// disc->fit(X[0], y);
// auto Xt = disc->transform(X[0]);
// labels_t expected = { 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2 };
// delete disc;
// EXPECT_EQ(expected, Xt);
// }
TEST(Discretizer, FImdlpIris) TEST(Discretizer, FImdlpIris)
{ {
auto labelsq = {
1,
0,
0,
0,
0,
1,
0,
0,
0,
0,
1,
0,
0,
0,
2,
1,
1,
1,
1,
1,
1,
1,
0,
1,
0,
0,
0,
1,
1,
0,
0,
1,
1,
1,
0,
0,
1,
0,
0,
1,
0,
0,
0,
0,
1,
0,
1,
0,
1,
0,
3,
3,
3,
1,
3,
1,
2,
0,
3,
1,
0,
2,
2,
2,
1,
3,
1,
2,
2,
1,
2,
2,
2,
2,
3,
3,
3,
3,
2,
1,
1,
1,
2,
2,
1,
2,
3,
2,
1,
1,
1,
2,
2,
0,
1,
1,
1,
2,
1,
1,
2,
2,
3,
2,
3,
3,
0,
3,
3,
3,
3,
3,
3,
1,
2,
3,
3,
3,
3,
2,
3,
1,
3,
2,
3,
3,
2,
2,
3,
3,
3,
3,
3,
2,
2,
3,
2,
3,
2,
3,
3,
3,
2,
3,
3,
3,
2,
3,
2,
2,
};
labels_t expected = { labels_t expected = {
5, 3, 4, 4, 5, 5, 5, 5, 2, 4, 5, 5, 3, 3, 5, 5, 5, 5, 5, 5, 5, 5, 5, 3, 4, 4, 5, 5, 5, 5, 2, 4, 5, 5, 3, 3, 5, 5, 5, 5, 5, 5, 5, 5,
5, 4, 5, 3, 5, 5, 5, 4, 4, 5, 5, 5, 4, 4, 5, 4, 3, 5, 5, 0, 4, 5, 5, 4, 5, 3, 5, 5, 5, 4, 4, 5, 5, 5, 4, 4, 5, 4, 3, 5, 5, 0, 4, 5,

133
tests/Experiments.hpp Normal file
View File

@@ -0,0 +1,133 @@
#ifndef EXPERIMENTS_HPP
#define EXPERIMENTS_HPP
#include<sstream>
#include<iostream>
#include<string>
#include<fstream>
#include<vector>
#include<tuple>
#include "../typesFImdlp.h"
template <typename T>
void show_vector(const std::vector<T>& data, std::string title)
{
std::cout << title << ": ";
std::string sep = "";
for (const auto& d : data) {
std::cout << sep << d;
sep = ", ";
}
std::cout << std::endl;
}
enum class experiment_t {
RANGE,
VECTOR
};
class Experiment {
public:
Experiment(float from_, float to_, float step_, int n_bins, std::string strategy, std::vector<int> data_discretized, std::vector<float> cutpoints) :
from_{ from_ }, to_{ to_ }, step_{ step_ }, n_bins_{ n_bins }, strategy_{ strategy }, discretized_data_{ data_discretized }, cutpoints_{ cutpoints }, type_{ experiment_t::RANGE }
{
validate_strategy();
}
Experiment(std::vector<float> dataset, int n_bins, std::string strategy, std::vector<int> data_discretized, std::vector<float> cutpoints) :
n_bins_{ n_bins }, strategy_{ strategy }, dataset_{ dataset }, discretized_data_{ data_discretized }, cutpoints_{ cutpoints }, type_{ experiment_t::VECTOR }
{
validate_strategy();
}
void validate_strategy()
{
if (strategy_ != "Q" && strategy_ != "U") {
throw std::invalid_argument("Invalid strategy " + strategy_);
}
}
float from_;
float to_;
float step_;
int n_bins_;
std::string strategy_;
std::vector<float> dataset_;
std::vector<int> discretized_data_;
std::vector<float> cutpoints_;
experiment_t type_;
};
class Experiments {
public:
Experiments(const std::string filename) : filename{ filename }
{
test_file.open(filename);
if (!test_file.is_open()) {
throw std::runtime_error("File " + filename + " not found");
}
exp_end = false;
}
~Experiments()
{
test_file.close();
}
bool end() const
{
return exp_end;
}
bool is_next()
{
while (std::getline(test_file, line) && line[0] == '#');
if (test_file.eof()) {
exp_end = true;
return false;
}
return true;
}
Experiment next()
{
return parse_experiment(line);
}
private:
std::tuple<float, float, float, int, std::string> parse_header(const std::string& line)
{
std::istringstream iss(line);
std::string from_, to_, step_, n_bins, strategy;
iss >> from_ >> to_ >> step_ >> n_bins >> strategy;
return { std::stof(from_), std::stof(to_), std::stof(step_), std::stoi(n_bins), strategy };
}
template <typename T>
std::vector<T> parse_vector(const std::string& line)
{
std::istringstream iss(line);
std::vector<T> data;
std::string d;
while (iss >> d) {
data.push_back(std::is_same<T, float>::value ? std::stof(d) : std::stoi(d));
}
return data;
}
Experiment parse_experiment(std::string& line)
{
// Read experiment lines
std::string experiment, data, cuts, strategy;
std::getline(test_file, experiment);
std::getline(test_file, data);
std::getline(test_file, cuts);
// split data into variables
float from_, to_, step_;
int n_bins;
std::vector<float> dataset;
auto data_discretized = parse_vector<int>(data);
auto cutpoints = parse_vector<float>(cuts);
if (line == "RANGE") {
tie(from_, to_, step_, n_bins, strategy) = parse_header(experiment);
return Experiment{ from_, to_, step_, n_bins, strategy, data_discretized, cutpoints };
}
strategy = experiment.substr(0, 1);
n_bins = std::stoi(experiment.substr(1, 1));
data = experiment.substr(3, experiment.size() - 4);
dataset = parse_vector<float>(data);
return Experiment(dataset, n_bins, strategy, data_discretized, cutpoints);
}
std::ifstream test_file;
std::string filename;
std::string line;
bool exp_end;
};
#endif

87
tests/FImdlp_unittest.cpp
View File

@@ -124,7 +124,7 @@ namespace mdlp {
{ {
samples_t X_ = { 1, 2, 2, 3, 4, 2, 3 }; samples_t X_ = { 1, 2, 2, 3, 4, 2, 3 };
labels_t y_ = { 0, 0, 1, 2, 3, 4, 5 }; labels_t y_ = { 0, 0, 1, 2, 3, 4, 5 };
cutPoints_t expected = { 1.5f, 2.5f }; cutPoints_t expected = { 1.0, 1.5f, 2.5f, 4.0 };
fit(X_, y_); fit(X_, y_);
auto computed = getCutPoints(); auto computed = getCutPoints();
EXPECT_EQ(computed.size(), expected.size()); EXPECT_EQ(computed.size(), expected.size());
@@ -167,29 +167,31 @@ namespace mdlp {
y = { 1 }; y = { 1 };
fit(X, y); fit(X, y);
computed = getCutPoints(); computed = getCutPoints();
EXPECT_EQ(computed.size(), 0); EXPECT_EQ(computed.size(), 2);
X = { 1, 3 }; X = { 1, 3 };
y = { 1, 2 }; y = { 1, 2 };
fit(X, y); fit(X, y);
computed = getCutPoints(); computed = getCutPoints();
EXPECT_EQ(computed.size(), 0); EXPECT_EQ(computed.size(), 2);
X = { 2, 4 }; X = { 2, 4 };
y = { 1, 2 }; y = { 1, 2 };
fit(X, y); fit(X, y);
computed = getCutPoints(); computed = getCutPoints();
EXPECT_EQ(computed.size(), 0); EXPECT_EQ(computed.size(), 2);
X = { 1, 2, 3 }; X = { 1, 2, 3 };
y = { 1, 2, 2 }; y = { 1, 2, 2 };
fit(X, y); fit(X, y);
computed = getCutPoints(); computed = getCutPoints();
EXPECT_EQ(computed.size(), 1); EXPECT_EQ(computed.size(), 3);
EXPECT_NEAR(computed[0], 1.5, precision); EXPECT_NEAR(computed[0], 1, precision);
EXPECT_NEAR(computed[1], 1.5, precision);
EXPECT_NEAR(computed[2], 3, precision);
} }
TEST_F(TestFImdlp, TestArtificialDataset) TEST_F(TestFImdlp, TestArtificialDataset)
{ {
fit(X, y); fit(X, y);
cutPoints_t expected = { 5.05f }; cutPoints_t expected = { 4.7, 5.05, 6.0 };
vector<precision_t> computed = getCutPoints(); vector<precision_t> computed = getCutPoints();
EXPECT_EQ(computed.size(), expected.size()); EXPECT_EQ(computed.size(), expected.size());
for (unsigned long i = 0; i < computed.size(); i++) { for (unsigned long i = 0; i < computed.size(); i++) {
@@ -200,10 +202,10 @@ namespace mdlp {
TEST_F(TestFImdlp, TestIris) TEST_F(TestFImdlp, TestIris)
{ {
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f, 5.75f}, {4.3, 5.45f, 5.75f, 7.9},
{2.75f, 2.85f, 2.95f, 3.05f, 3.35f}, {2, 2.75f, 2.85f, 2.95f, 3.05f, 3.35f, 4.4},
{2.45f, 4.75f, 5.05f}, {1, 2.45f, 4.75f, 5.05f, 6.9},
{0.8f, 1.75f} {0.1, 0.8f, 1.75f, 2.5}
}; };
vector<int> depths = { 3, 5, 4, 3 }; vector<int> depths = { 3, 5, 4, 3 };
auto test = CPPFImdlp(); auto test = CPPFImdlp();
@@ -213,7 +215,7 @@ namespace mdlp {
TEST_F(TestFImdlp, ComputeCutPointsGCase) TEST_F(TestFImdlp, ComputeCutPointsGCase)
{ {
cutPoints_t expected; cutPoints_t expected;
expected = { 1.5 }; expected = { 0, 1.5, 2 };
samples_t X_ = { 0, 1, 2, 2, 2 }; samples_t X_ = { 0, 1, 2, 2, 2 };
labels_t y_ = { 1, 1, 1, 2, 2 }; labels_t y_ = { 1, 1, 1, 2, 2 };
fit(X_, y_); fit(X_, y_);
@@ -247,10 +249,10 @@ namespace mdlp {
// Set max_depth to 1 // Set max_depth to 1
auto test = CPPFImdlp(3, 1, 0); auto test = CPPFImdlp(3, 1, 0);
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f}, {4.3, 5.45f, 7.9},
{3.35f}, {2, 3.35f, 4.4},
{2.45f}, {1, 2.45f, 6.9},
{0.8f} {0.1, 0.8f, 2.5}
}; };
vector<int> depths = { 1, 1, 1, 1 }; vector<int> depths = { 1, 1, 1, 1 };
test_dataset(test, "iris", expected, depths); test_dataset(test, "iris", expected, depths);
@@ -261,10 +263,10 @@ namespace mdlp {
auto test = CPPFImdlp(75, 100, 0); auto test = CPPFImdlp(75, 100, 0);
// Set min_length to 75 // Set min_length to 75
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f, 5.75f}, {4.3, 5.45f, 5.75f, 7.9},
{2.85f, 3.35f}, {2, 2.85f, 3.35f, 4.4},
{2.45f, 4.75f}, {1, 2.45f, 4.75f, 6.9},
{0.8f, 1.75f} {0.1, 0.8f, 1.75f, 2.5}
}; };
vector<int> depths = { 3, 2, 2, 2 }; vector<int> depths = { 3, 2, 2, 2 };
test_dataset(test, "iris", expected, depths); test_dataset(test, "iris", expected, depths);
@@ -275,10 +277,10 @@ namespace mdlp {
// Set min_length to 75 // Set min_length to 75
auto test = CPPFImdlp(75, 2, 0); auto test = CPPFImdlp(75, 2, 0);
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f, 5.75f}, {4.3, 5.45f, 5.75f, 7.9},
{2.85f, 3.35f}, {2, 2.85f, 3.35f, 4.4},
{2.45f, 4.75f}, {1, 2.45f, 4.75f, 6.9},
{0.8f, 1.75f} {0.1, 0.8f, 1.75f, 2.5}
}; };
vector<int> depths = { 2, 2, 2, 2 }; vector<int> depths = { 2, 2, 2, 2 };
test_dataset(test, "iris", expected, depths); test_dataset(test, "iris", expected, depths);
@@ -289,10 +291,10 @@ namespace mdlp {
// Set min_length to 75 // Set min_length to 75
auto test = CPPFImdlp(75, 2, 1); auto test = CPPFImdlp(75, 2, 1);
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f}, {4.3, 5.45f, 7.9},
{2.85f}, {2, 2.85f, 4.4},
{2.45f}, {1, 2.45f, 6.9},
{0.8f} {0.1, 0.8f, 2.5}
}; };
vector<int> depths = { 2, 2, 2, 2 }; vector<int> depths = { 2, 2, 2, 2 };
test_dataset(test, "iris", expected, depths); test_dataset(test, "iris", expected, depths);
@@ -304,10 +306,10 @@ namespace mdlp {
// Set min_length to 75 // Set min_length to 75
auto test = CPPFImdlp(75, 2, 0.2f); auto test = CPPFImdlp(75, 2, 0.2f);
vector<cutPoints_t> expected = { vector<cutPoints_t> expected = {
{5.45f, 5.75f}, {4.3, 5.45f, 5.75f, 7.9},
{2.85f, 3.35f}, {2, 2.85f, 3.35f, 4.4},
{2.45f, 4.75f}, {1, 2.45f, 4.75f, 6.9},
{0.8f, 1.75f} {0.1, 0.8f, 1.75f, 2.5}
}; };
vector<int> depths = { 2, 2, 2, 2 }; vector<int> depths = { 2, 2, 2, 2 };
test_dataset(test, "iris", expected, depths); test_dataset(test, "iris", expected, depths);
@@ -327,7 +329,6 @@ namespace mdlp {
computed = compute_max_num_cut_points(); computed = compute_max_num_cut_points();
ASSERT_EQ(expected, computed); ASSERT_EQ(expected, computed);
} }
} }
TEST_F(TestFImdlp, TransformTest) TEST_F(TestFImdlp, TransformTest)
{ {
@@ -345,15 +346,15 @@ namespace mdlp {
vector<samples_t>& X = file.getX(); vector<samples_t>& X = file.getX();
labels_t& y = file.getY(); labels_t& y = file.getY();
fit(X[1], y); fit(X[1], y);
// auto computed = transform(X[1]); auto computed = transform(X[1]);
// EXPECT_EQ(computed.size(), expected.size()); EXPECT_EQ(computed.size(), expected.size());
// for (unsigned long i = 0; i < computed.size(); i++) { for (unsigned long i = 0; i < computed.size(); i++) {
// EXPECT_EQ(computed[i], expected[i]); EXPECT_EQ(computed[i], expected[i]);
// } }
// auto computed_ft = fit_transform(X[1], y); auto computed_ft = fit_transform(X[1], y);
// EXPECT_EQ(computed_ft.size(), expected.size()); EXPECT_EQ(computed_ft.size(), expected.size());
// for (unsigned long i = 0; i < computed_ft.size(); i++) { for (unsigned long i = 0; i < computed_ft.size(); i++) {
// EXPECT_EQ(computed_ft[i], expected[i]); EXPECT_EQ(computed_ft[i], expected[i]);
// } }
} }
} }

222
tests/datasets/tests.txt Normal file
View File

@@ -0,0 +1,222 @@
#
# from, to, step, #bins, Q/U
# discretized data
# cut points
#
#
# Range experiments
#
RANGE
0, 100, 1, 4, Q
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3
0.0, 24.75, 49.5, 74.25, 99.0
RANGE
0, 50, 1, 4, Q
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3
0.0, 12.25, 24.5, 36.75, 49.0
RANGE
0, 100, 1, 3, Q
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.0, 33.0, 66.0, 99.0
RANGE
0, 50, 1, 3, Q
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.0, 16.33333, 32.66667, 49.0
RANGE
0, 10, 1, 3, Q
0, 0, 0, 0, 1, 1, 1, 2, 2, 2
0.0, 3.0, 6.0, 9.0
RANGE
0, 100, 1, 4, U
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3
0.0, 24.75, 49.5, 74.25, 99.0
RANGE
0, 50, 1, 4, U
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3
0.0, 12.25, 24.5, 36.75, 49.0
RANGE
0, 100, 1, 3, U
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.0, 33.0, 66.0, 99.0
RANGE
0, 50, 1, 3, U
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.0, 16.33333, 32.66667, 49.0
RANGE
0, 10, 1, 3, U
0, 0, 0, 1, 1, 1, 2, 2, 2, 2
0.0, 3.0, 6.0, 9.0
RANGE
1, 10, 1, 3, Q
0, 0, 0, 1, 1, 1, 2, 2, 2
1.0, 3.66667, 6.33333, 9.0
RANGE
1, 10, 1, 3, U
0, 0, 0, 1, 1, 1, 2, 2, 2
1.0, 3.66667, 6.33333, 9.0
RANGE
1, 11, 1, 3, Q
0, 0, 0, 1, 1, 1, 1, 2, 2, 2
1.0, 4.0, 7.0, 10.0
RANGE
1, 11, 1, 3, U
0, 0, 0, 1, 1, 1, 2, 2, 2, 2
1.0, 4.0, 7.0, 10.0
RANGE
1, 12, 1, 3, Q
0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2
1.0, 4.33333, 7.66667, 11.0
RANGE
1, 12, 1, 3, U
0, 0, 0, 0, 1, 1, 1, 2, 2, 2, 2
1.0, 4.33333, 7.66667, 11.0
RANGE
1, 13, 1, 3, Q
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2
1.0, 4.66667, 8.33333, 12.0
RANGE
1, 13, 1, 3, U
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2
1.0, 4.66667, 8.33333, 12.0
RANGE
1, 14, 1, 3, Q
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.0, 9.0, 13.0
RANGE
1, 14, 1, 3, U
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.0, 9.0, 13.0
RANGE
1, 15, 1, 3, Q
0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.33333, 9.66667, 14.0
RANGE
1, 15, 1, 3, U
0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.33333, 9.66667, 14.0
#
# Vector experiments
#
VECTOR
Q3[3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0]
1, 0, 0, 1, 0, 0, 1, 0, 0
1.0, 1.66667, 3.0
VECTOR
U3[3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0]
2, 0, 0, 2, 0, 0, 2, 0, 0
1.0, 1.66667, 2.33333, 3.0
VECTOR
Q3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0]
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2
1.0, 4.66667, 8.33333, 12.0
VECTOR
U3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0]
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2
1.0, 4.66667, 8.33333, 12.0
VECTOR
Q3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0]
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.0, 9.0, 13.0
VECTOR
U3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0]
0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.0, 9.0, 13.0
VECTOR
Q3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0]
0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.33333, 9.66667, 14.0
VECTOR
U3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0]
0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.33333, 9.66667, 14.0
VECTOR
Q3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0, 15.0]
0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.66667, 10.33333, 15.0
VECTOR
U3[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0, 15.0]
0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2
1.0, 5.66667, 10.33333, 15.0
VECTOR
Q3[15.0, 8.0, 12.0, 14.0, 6.0, 1.0, 13.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0]
2, 1, 2, 2, 1, 0, 2, 2, 1, 1, 1, 0, 0, 0, 0
1.0, 5.66667, 10.33333, 15.0
VECTOR
U3[15.0, 8.0, 12.0, 14.0, 6.0, 1.0, 13.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0]
2, 1, 2, 2, 1, 0, 2, 2, 1, 1, 1, 0, 0, 0, 0
1.0, 5.66667, 10.33333, 15.0
VECTOR
Q3[0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0]
0, 0, 0, 0, 1, 1, 2, 2, 2, 2
0.0, 1.0, 3.0, 4.0
VECTOR
U3[0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0]
0, 0, 0, 0, 1, 1, 2, 2, 2, 2
0.0, 1.33333, 2.66667, 4.0
#
# Vector experiments with iris
#
VECTOR
Q3[5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5.0, 5.0, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5.0, 5.5, 4.9, 4.4, 5.1, 5.0, 4.5, 4.4, 5.0, 5.1, 4.8, 5.1, 4.6, 5.3, 5.0, 7.0, 6.4, 6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5.0, 5.9, 6.0, 6.1, 5.6, 6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7, 6.0, 5.7, 5.5, 5.5, 5.8, 6.0, 5.4, 6.0, 6.7, 6.3, 5.6, 5.5, 5.5, 6.1, 5.8, 5.0, 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3, 6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5, 7.7, 7.7, 6.0, 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2, 7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6.0, 6.9, 6.7, 6.9, 5.8, 6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9]
0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 1, 2, 1, 2, 0, 2, 0, 0, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 2, 1, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1, 2, 2, 2, 2, 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 1
4.3, 5.4, 6.3, 7.9
VECTOR
U3[5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5.0, 5.0, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5.0, 5.5, 4.9, 4.4, 5.1, 5.0, 4.5, 4.4, 5.0, 5.1, 4.8, 5.1, 4.6, 5.3, 5.0, 7.0, 6.4, 6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5.0, 5.9, 6.0, 6.1, 5.6, 6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7, 6.0, 5.7, 5.5, 5.5, 5.8, 6.0, 5.4, 6.0, 6.7, 6.3, 5.6, 5.5, 5.5, 6.1, 5.8, 5.0, 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3, 6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5, 7.7, 7.7, 6.0, 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2, 7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6.0, 6.9, 6.7, 6.9, 5.8, 6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 2, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 0, 1, 2, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 2, 1, 1, 2, 0, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 2, 2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 1, 2, 1, 1, 1, 2, 2, 2, 1, 2, 2, 2, 1, 1, 1, 1
4.3, 5.5, 6.7, 7.9
VECTOR
Q4[5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5.0, 5.0, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5.0, 5.5, 4.9, 4.4, 5.1, 5.0, 4.5, 4.4, 5.0, 5.1, 4.8, 5.1, 4.6, 5.3, 5.0, 7.0, 6.4, 6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5.0, 5.9, 6.0, 6.1, 5.6, 6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7, 6.0, 5.7, 5.5, 5.5, 5.8, 6.0, 5.4, 6.0, 6.7, 6.3, 5.6, 5.5, 5.5, 6.1, 5.8, 5.0, 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3, 6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5, 7.7, 7.7, 6.0, 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2, 7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6.0, 6.9, 6.7, 6.9, 5.8, 6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9]
1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 3, 3, 3, 1, 3, 1, 2, 0, 3, 1, 0, 2, 2, 2, 1, 3, 1, 2, 2, 1, 2, 2, 2, 2, 3, 3, 3, 3, 2, 1, 1, 1, 2, 2, 1, 2, 3, 2, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2, 1, 1, 2, 2, 3, 2, 3, 3, 0, 3, 3, 3, 3, 3, 3, 1, 2, 3, 3, 3, 3, 2, 3, 1, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 2, 3, 2, 3, 2, 3, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2
4.3, 5.1, 5.8, 6.4, 7.9
VECTOR
U4[5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5.0, 5.0, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5.0, 5.5, 4.9, 4.4, 5.1, 5.0, 4.5, 4.4, 5.0, 5.1, 4.8, 5.1, 4.6, 5.3, 5.0, 7.0, 6.4, 6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5.0, 5.9, 6.0, 6.1, 5.6, 6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7, 6.0, 5.7, 5.5, 5.5, 5.8, 6.0, 5.4, 6.0, 6.7, 6.3, 5.6, 5.5, 5.5, 6.1, 5.8, 5.0, 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3, 6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5, 7.7, 7.7, 6.0, 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2, 7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6.0, 6.9, 6.7, 6.9, 5.8, 6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9]
0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 3, 2, 2, 1, 2, 1, 2, 0, 2, 1, 0, 1, 1, 2, 1, 2, 1, 1, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 2, 1, 0, 1, 1, 1, 2, 0, 1, 2, 1, 3, 2, 2, 3, 0, 3, 2, 3, 2, 2, 2, 1, 1, 2, 2, 3, 3, 1, 2, 1, 3, 2, 2, 3, 2, 2, 2, 3, 3, 3, 2, 2, 2, 3, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1
4.3, 5.2, 6.1, 7.0, 7.9
VECTOR
Q3[3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3.0, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.6, 3.0, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3.0, 3.8, 3.2, 3.7, 3.3, 3.2, 3.2, 3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2.0, 3.0, 2.2, 2.9, 2.9, 3.1, 3.0, 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3.0, 2.8, 3.0, 2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3.0, 3.4, 3.1, 2.3, 3.0, 2.5, 2.6, 3.0, 2.6, 2.3, 2.7, 3.0, 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3.0, 2.9, 3.0, 3.0, 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3.0, 2.5, 2.8, 3.2, 3.0, 3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3.0, 2.8, 3.0, 2.8, 3.8, 2.8, 2.8, 2.6, 3.0, 3.4, 3.1, 3.0, 3.1, 3.1, 3.1, 2.7, 3.2, 3.3, 3.0, 2.5, 3.0, 3.4, 3.0]
2, 1, 2, 1, 2, 2, 2, 2, 1, 1, 2, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 0, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1, 0, 0, 0, 2, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 2, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 2, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 2, 0, 1, 1, 1, 1, 0, 1, 0, 2, 2, 0, 1, 0, 0, 2, 1, 2, 0, 0, 2, 0, 0, 0, 2, 2, 0, 1, 0, 1, 0, 2, 0, 0, 0, 1, 2, 1, 1, 1, 1, 1, 0, 2, 2, 1, 0, 1, 2, 1
2.0, 2.9, 3.2, 4.4
VECTOR
U3[3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3.0, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.6, 3.0, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3.0, 3.8, 3.2, 3.7, 3.3, 3.2, 3.2, 3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2.0, 3.0, 2.2, 2.9, 2.9, 3.1, 3.0, 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3.0, 2.8, 3.0, 2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3.0, 3.4, 3.1, 2.3, 3.0, 2.5, 2.6, 3.0, 2.6, 2.3, 2.7, 3.0, 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3.0, 2.9, 3.0, 3.0, 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3.0, 2.5, 2.8, 3.2, 3.0, 3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3.0, 2.8, 3.0, 2.8, 3.8, 2.8, 2.8, 2.6, 3.0, 3.4, 3.1, 3.0, 3.1, 3.1, 3.1, 2.7, 3.2, 3.3, 3.0, 2.5, 3.0, 3.4, 3.0]
1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 2, 1, 2, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 2, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 2, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1
2.0, 2.8, 3.6, 4.4
VECTOR
Q4[3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3.0, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.6, 3.0, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3.0, 3.8, 3.2, 3.7, 3.3, 3.2, 3.2, 3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2.0, 3.0, 2.2, 2.9, 2.9, 3.1, 3.0, 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3.0, 2.8, 3.0, 2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3.0, 3.4, 3.1, 2.3, 3.0, 2.5, 2.6, 3.0, 2.6, 2.3, 2.7, 3.0, 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3.0, 2.9, 3.0, 3.0, 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3.0, 2.5, 2.8, 3.2, 3.0, 3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3.0, 2.8, 3.0, 2.8, 3.8, 2.8, 2.8, 2.6, 3.0, 3.4, 3.1, 3.0, 3.1, 3.1, 3.1, 2.7, 3.2, 3.3, 3.0, 2.5, 3.0, 3.4, 3.0]
3, 2, 2, 2, 3, 3, 3, 3, 1, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 2, 2, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3, 0, 2, 3, 3, 2, 3, 2, 3, 3, 2, 2, 2, 0, 1, 1, 3, 0, 1, 0, 0, 2, 0, 1, 1, 2, 2, 0, 0, 0, 2, 1, 0, 1, 1, 2, 1, 2, 1, 0, 0, 0, 0, 0, 2, 3, 2, 0, 2, 0, 0, 2, 0, 0, 0, 2, 1, 1, 0, 1, 3, 0, 2, 1, 2, 2, 0, 1, 0, 3, 2, 0, 2, 0, 1, 2, 2, 3, 0, 0, 2, 1, 1, 0, 3, 2, 1, 2, 1, 2, 1, 3, 1, 1, 0, 2, 3, 2, 2, 2, 2, 2, 0, 2, 3, 2, 0, 2, 3, 2
2.0, 2.8, 3.0, 3.3, 4.4
VECTOR
U4[3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3.0, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.6, 3.0, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3.0, 3.8, 3.2, 3.7, 3.3, 3.2, 3.2, 3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2.0, 3.0, 2.2, 2.9, 2.9, 3.1, 3.0, 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3.0, 2.8, 3.0, 2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3.0, 3.4, 3.1, 2.3, 3.0, 2.5, 2.6, 3.0, 2.6, 2.3, 2.7, 3.0, 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3.0, 2.9, 3.0, 3.0, 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3.0, 2.5, 2.8, 3.2, 3.0, 3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3.0, 2.8, 3.0, 2.8, 3.8, 2.8, 2.8, 2.6, 3.0, 3.4, 3.1, 3.0, 3.1, 3.1, 3.1, 2.7, 3.2, 3.3, 3.0, 2.5, 3.0, 3.4, 3.0]
2, 1, 2, 1, 2, 3, 2, 2, 1, 1, 2, 2, 1, 1, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 1, 2, 3, 3, 1, 2, 2, 2, 1, 2, 2, 0, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1, 0, 1, 1, 2, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 2, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 2, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 2, 1, 1, 1, 1, 1, 0, 1, 0, 2, 2, 1, 1, 0, 1, 2, 1, 2, 1, 0, 2, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 2, 1, 0, 1, 2, 1
2.0, 2.6, 3.2, 3.8, 4.4
VECTOR
Q3[1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4, 4.7, 4.5, 4.9, 4.0, 4.6, 4.5, 4.7, 3.3, 4.6, 3.9, 3.5, 4.2, 4.0, 4.7, 3.6, 4.4, 4.5, 4.1, 4.5, 3.9, 4.8, 4.0, 4.9, 4.7, 4.3, 4.4, 4.8, 5.0, 4.5, 3.5, 3.8, 3.7, 3.9, 5.1, 4.5, 4.5, 4.7, 4.4, 4.1, 4.0, 4.4, 4.6, 4.0, 3.3, 4.2, 4.2, 4.2, 4.3, 3.0, 4.1, 6.0, 5.1, 5.9, 5.6, 5.8, 6.6, 4.5, 6.3, 5.8, 6.1, 5.1, 5.3, 5.5, 5.0, 5.1, 5.3, 5.5, 6.7, 6.9, 5.0, 5.7, 4.9, 6.7, 4.9, 5.7, 6.0, 4.8, 4.9, 5.6, 5.8, 6.1, 6.4, 5.6, 5.1, 5.6, 6.1, 5.6, 5.5, 4.8, 5.4, 5.6, 5.1, 5.1, 5.9, 5.7, 5.2, 5.0, 5.2, 5.4, 5.1]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
1.0, 2.63333, 4.9, 6.9
VECTOR
U3[1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4, 4.7, 4.5, 4.9, 4.0, 4.6, 4.5, 4.7, 3.3, 4.6, 3.9, 3.5, 4.2, 4.0, 4.7, 3.6, 4.4, 4.5, 4.1, 4.5, 3.9, 4.8, 4.0, 4.9, 4.7, 4.3, 4.4, 4.8, 5.0, 4.5, 3.5, 3.8, 3.7, 3.9, 5.1, 4.5, 4.5, 4.7, 4.4, 4.1, 4.0, 4.4, 4.6, 4.0, 3.3, 4.2, 4.2, 4.2, 4.3, 3.0, 4.1, 6.0, 5.1, 5.9, 5.6, 5.8, 6.6, 4.5, 6.3, 5.8, 6.1, 5.1, 5.3, 5.5, 5.0, 5.1, 5.3, 5.5, 6.7, 6.9, 5.0, 5.7, 4.9, 6.7, 4.9, 5.7, 6.0, 4.8, 4.9, 5.6, 5.8, 6.1, 6.4, 5.6, 5.1, 5.6, 6.1, 5.6, 5.5, 4.8, 5.4, 5.6, 5.1, 5.1, 5.9, 5.7, 5.2, 5.0, 5.2, 5.4, 5.1]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
1.0, 2.96667, 4.93333, 6.9
VECTOR
Q4[1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4, 4.7, 4.5, 4.9, 4.0, 4.6, 4.5, 4.7, 3.3, 4.6, 3.9, 3.5, 4.2, 4.0, 4.7, 3.6, 4.4, 4.5, 4.1, 4.5, 3.9, 4.8, 4.0, 4.9, 4.7, 4.3, 4.4, 4.8, 5.0, 4.5, 3.5, 3.8, 3.7, 3.9, 5.1, 4.5, 4.5, 4.7, 4.4, 4.1, 4.0, 4.4, 4.6, 4.0, 3.3, 4.2, 4.2, 4.2, 4.3, 3.0, 4.1, 6.0, 5.1, 5.9, 5.6, 5.8, 6.6, 4.5, 6.3, 5.8, 6.1, 5.1, 5.3, 5.5, 5.0, 5.1, 5.3, 5.5, 6.7, 6.9, 5.0, 5.7, 4.9, 6.7, 4.9, 5.7, 6.0, 4.8, 4.9, 5.6, 5.8, 6.1, 6.4, 5.6, 5.1, 5.6, 6.1, 5.6, 5.5, 4.8, 5.4, 5.6, 5.1, 5.1, 5.9, 5.7, 5.2, 5.0, 5.2, 5.4, 5.1]
0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 2, 2, 2, 1, 2, 2, 2, 1, 2, 1, 1, 1, 1, 2, 1, 2, 2, 1, 2, 1, 2, 1, 2, 2, 1, 2, 2, 2, 2, 1, 1, 1, 1, 3, 2, 2, 2, 2, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 2, 3, 2, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3
1.0, 1.6, 4.35, 5.1, 6.9
VECTOR
U4[1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4, 4.7, 4.5, 4.9, 4.0, 4.6, 4.5, 4.7, 3.3, 4.6, 3.9, 3.5, 4.2, 4.0, 4.7, 3.6, 4.4, 4.5, 4.1, 4.5, 3.9, 4.8, 4.0, 4.9, 4.7, 4.3, 4.4, 4.8, 5.0, 4.5, 3.5, 3.8, 3.7, 3.9, 5.1, 4.5, 4.5, 4.7, 4.4, 4.1, 4.0, 4.4, 4.6, 4.0, 3.3, 4.2, 4.2, 4.2, 4.3, 3.0, 4.1, 6.0, 5.1, 5.9, 5.6, 5.8, 6.6, 4.5, 6.3, 5.8, 6.1, 5.1, 5.3, 5.5, 5.0, 5.1, 5.3, 5.5, 6.7, 6.9, 5.0, 5.7, 4.9, 6.7, 4.9, 5.7, 6.0, 4.8, 4.9, 5.6, 5.8, 6.1, 6.4, 5.6, 5.1, 5.6, 6.1, 5.6, 5.5, 4.8, 5.4, 5.6, 5.1, 5.1, 5.9, 5.7, 5.2, 5.0, 5.2, 5.4, 5.1]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 1, 2, 1, 1, 2, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 1, 2, 3, 2, 3, 3, 3, 3, 2, 3, 3, 3, 2, 2, 3, 2, 2, 2, 3, 3, 3, 2, 3, 2, 3, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 2, 2
1.0, 2.475, 3.95, 5.425, 6.9
VECTOR
Q3[0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2, 1.4, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6, 1.0, 1.3, 1.4, 1.0, 1.5, 1.0, 1.4, 1.3, 1.4, 1.5, 1.0, 1.5, 1.1, 1.8, 1.3, 1.5, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.0, 1.1, 1.0, 1.2, 1.6, 1.5, 1.6, 1.5, 1.3, 1.3, 1.3, 1.2, 1.4, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1, 1.3, 2.5, 1.9, 2.1, 1.8, 2.2, 2.1, 1.7, 1.8, 1.8, 2.5, 2.0, 1.9, 2.1, 2.0, 2.4, 2.3, 1.8, 2.2, 2.3, 1.5, 2.3, 2.0, 2.0, 1.8, 2.1, 1.8, 1.8, 1.8, 2.1, 1.6, 1.9, 2.0, 2.2, 1.5, 1.4, 2.3, 2.4, 1.8, 1.8, 2.1, 2.4, 2.3, 1.9, 2.3, 2.5, 2.3, 1.9, 2.0, 2.3, 1.8]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.1, 0.86667, 1.6, 2.5
VECTOR
U3[0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2, 1.4, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6, 1.0, 1.3, 1.4, 1.0, 1.5, 1.0, 1.4, 1.3, 1.4, 1.5, 1.0, 1.5, 1.1, 1.8, 1.3, 1.5, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.0, 1.1, 1.0, 1.2, 1.6, 1.5, 1.6, 1.5, 1.3, 1.3, 1.3, 1.2, 1.4, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1, 1.3, 2.5, 1.9, 2.1, 1.8, 2.2, 2.1, 1.7, 1.8, 1.8, 2.5, 2.0, 1.9, 2.1, 2.0, 2.4, 2.3, 1.8, 2.2, 2.3, 1.5, 2.3, 2.0, 2.0, 1.8, 2.1, 1.8, 1.8, 1.8, 2.1, 1.6, 1.9, 2.0, 2.2, 1.5, 1.4, 2.3, 2.4, 1.8, 1.8, 2.1, 2.4, 2.3, 1.9, 2.3, 2.5, 2.3, 1.9, 2.0, 2.3, 1.8]
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
0.1, 0.9, 1.7, 2.5
VECTOR
Q4[0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2, 1.4, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6, 1.0, 1.3, 1.4, 1.0, 1.5, 1.0, 1.4, 1.3, 1.4, 1.5, 1.0, 1.5, 1.1, 1.8, 1.3, 1.5, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.0, 1.1, 1.0, 1.2, 1.6, 1.5, 1.6, 1.5, 1.3, 1.3, 1.3, 1.2, 1.4, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1, 1.3, 2.5, 1.9, 2.1, 1.8, 2.2, 2.1, 1.7, 1.8, 1.8, 2.5, 2.0, 1.9, 2.1, 2.0, 2.4, 2.3, 1.8, 2.2, 2.3, 1.5, 2.3, 2.0, 2.0, 1.8, 2.1, 1.8, 1.8, 1.8, 2.1, 1.6, 1.9, 2.0, 2.2, 1.5, 1.4, 2.3, 2.4, 1.8, 1.8, 2.1, 2.4, 2.3, 1.9, 2.3, 2.5, 2.3, 1.9, 2.0, 2.3, 1.8]
0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 1, 2, 1, 3, 2, 2, 1, 2, 2, 2, 2, 2, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 1, 2, 1, 1, 2, 1, 2, 2, 1, 2, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3
0.1, 0.3, 1.3, 1.8, 2.5
VECTOR
U4[0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2, 1.4, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6, 1.0, 1.3, 1.4, 1.0, 1.5, 1.0, 1.4, 1.3, 1.4, 1.5, 1.0, 1.5, 1.1, 1.8, 1.3, 1.5, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.0, 1.1, 1.0, 1.2, 1.6, 1.5, 1.6, 1.5, 1.3, 1.3, 1.3, 1.2, 1.4, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1, 1.3, 2.5, 1.9, 2.1, 1.8, 2.2, 2.1, 1.7, 1.8, 1.8, 2.5, 2.0, 1.9, 2.1, 2.0, 2.4, 2.3, 1.8, 2.2, 2.3, 1.5, 2.3, 2.0, 2.0, 1.8, 2.1, 1.8, 1.8, 1.8, 2.1, 1.6, 1.9, 2.0, 2.2, 1.5, 1.4, 2.3, 2.4, 1.8, 1.8, 2.1, 2.4, 2.3, 1.9, 2.3, 2.5, 2.3, 1.9, 2.0, 2.3, 1.8]
0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 1, 2, 1, 1, 2, 1, 2, 2, 1, 2, 3, 3, 3, 2, 3, 3, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 2, 3, 3, 3, 2, 3, 2, 2, 2, 3, 2, 3, 3, 3, 2, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2
0.1, 0.7, 1.3, 1.9, 2.5

BIN
tests/k Executable file
View File

Binary file not shown.

32
tests/k.cpp Normal file
View File

@@ -0,0 +1,32 @@
#include <iostream>
#include <vector>
#include <algorithm> // For std::lower_bound
std::vector<int> searchsorted(const std::vector<float>& cuts, const std::vector<float>& data) {
std::vector<int> indices;
indices.reserve(data.size());
for (const float& value : data) {
// Find the first position in 'a' where 'value' could be inserted to maintain order
auto it = std::lower_bound(cuts.begin(), cuts.end(), value);
// Calculate the index
int index = it - cuts.begin();
indices.push_back(index);
}
return indices;
}
int main() {
std::vector<float> cuts = { 10.0 };
std::vector<float> data = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0 };
std::vector<int> result = searchsorted(cuts, data);
for (int idx : result) {
std::cout << idx << " ";
}
return 0;
}

BIN
tests/t Executable file
View File

Binary file not shown.

102
tests/t.cpp Normal file
View File

@@ -0,0 +1,102 @@
#include <iostream>
#include <algorithm>
#include <cmath>
#include <vector>
#include <string>
typedef float precision_t;
std::vector<int> transform(const std::vector<float> cutPoints, const std::vector<float>& data)
{
std::vector<int> discretizedData;
discretizedData.reserve(data.size());
for (const float& item : data) {
auto upper = std::lower_bound(cutPoints.begin(), cutPoints.end(), item);
discretizedData.push_back(upper - cutPoints.begin());
}
return discretizedData;
}
template <typename T>
void show_vector(const std::vector<T>& data, std::string title)
{
std::cout << title << ": ";
std::string sep = "";
for (const auto& d : data) {
std::cout << sep << d;
sep = ", ";
}
std::cout << std::endl;
}
std::vector<precision_t> linspace(precision_t start, precision_t end, int num)
{
if (start == end) {
return { start, end };
}
precision_t delta = (end - start) / static_cast<precision_t>(num - 1);
std::vector<precision_t> linspc;
for (size_t i = 0; i < num - 1; ++i) {
precision_t val = start + delta * static_cast<precision_t>(i);
linspc.push_back(val);
}
return linspc;
}
size_t clip(const size_t n, size_t lower, size_t upper)
{
return std::max(lower, std::min(n, upper));
}
std::vector<precision_t> percentile(std::vector<precision_t>& data, std::vector<precision_t>& percentiles)
{
// Implementation taken from https://dpilger26.github.io/NumCpp/doxygen/html/percentile_8hpp_source.html
std::vector<precision_t> results;
results.reserve(percentiles.size());
for (auto percentile : percentiles) {
const size_t i = static_cast<size_t>(std::floor(static_cast<double>(data.size() - 1) * percentile / 100.));
const auto indexLower = clip(i, 0, data.size() - 2);
const double percentI = static_cast<double>(indexLower) / static_cast<double>(data.size() - 1);
const double fraction =
(percentile / 100.0 - percentI) /
(static_cast<double>(indexLower + 1) / static_cast<double>(data.size() - 1) - percentI);
const auto value = data[indexLower] + (data[indexLower + 1] - data[indexLower]) * fraction;
if (value != results.back())
results.push_back(value);
}
return results;
}
int main()
{
// std::vector<float> test;
// std::vector<float> cuts = { 0, 24.75, 49.5, 74.25, 10000 };
// for (int i = 0; i < 100; ++i) {
// test.push_back(i);
// }
// auto Xt = transform(cuts, test);
// show_vector(Xt, "Discretized data:");
// std::vector<float> test2 = { 0,1,2,3,4,5,6,7,8,9,10,11 };
// std::vector<float> cuts2 = { 0,1,2,3,4,5,6,7,8,9 };
// auto Xt2 = transform(cuts2, test2);
// show_vector(Xt2, "discretized data2: ");
auto quantiles = linspace(0.0, 100.0, 3 + 1);
std::vector<float> data = { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0 };
std::vector<float> cutPoints;
std::sort(data.begin(), data.end());
cutPoints = percentile(data, quantiles);
cutPoints.push_back(std::numeric_limits<precision_t>::max());
data.push_back(15);
data.push_back(0);
cutPoints.pop_back();
cutPoints.erase(cutPoints.begin());
cutPoints.clear();
cutPoints.push_back(9.0);
auto Xt = transform(cutPoints, data);
show_vector(data, "Original data");
show_vector(Xt, "Discretized data");
show_vector(cutPoints, "Cutpoints");
return 0;
}
/*
n_bins = 3
data = [1,2,3,4,5,6,7,8,9,10]
quantiles = np.linspace(0, 100, n_bins + 1)
bin_edges = np.percentile(data, quantiles)
*/

59
tests/tests_do.py Normal file
View File

@@ -0,0 +1,59 @@
import json
from sklearn.preprocessing import KBinsDiscretizer
with open("datasets/tests.txt") as f:
data = f.readlines()
data = [x.strip() for x in data if x[0] != "#"]
errors = False
for i in range(0, len(data), 4):
experiment_type = data[i]
print("Experiment:", data[i + 1])
if experiment_type == "RANGE":
range_data = data[i + 1]
from_, to_, step_, n_bins_, strategy_ = range_data.split(",")
X = [[float(x)] for x in range(int(from_), int(to_), int(step_))]
else:
strategy_ = data[i + 1][0]
n_bins_ = data[i + 1][1]
vector = data[i + 1][2:]
X = [[float(x)] for x in json.loads(vector)]
strategy = "quantile" if strategy_.strip() == "Q" else "uniform"
disc = KBinsDiscretizer(
n_bins=int(n_bins_),
encode="ordinal",
strategy=strategy,
)
expected_data = data[i + 2]
cuts_data = data[i + 3]
disc.fit(X)
result = disc.transform(X)
result = [int(x) for x in result.flatten()]
expected = [int(x) for x in expected_data.split(",")]
#
# Check the Results
#
assert len(result) == len(expected)
for j in range(len(result)):
if result[j] != expected[j]:
print("* Error at", j, "Expected=", expected[j], "Result=", result[j])
errors = True
expected_cuts = disc.bin_edges_[0]
computed_cuts = [float(x) for x in cuts_data.split(",")]
assert len(expected_cuts) == len(computed_cuts)
for j in range(len(expected_cuts)):
if round(expected_cuts[j], 5) != computed_cuts[j]:
print(
"* Error at",
j,
"Expected=",
expected_cuts[j],
"Result=",
computed_cuts[j],
)
errors = True
if errors:
raise Exception("There were errors!")
print("*** All tests run succesfully! ***")

222
tests/tests_generate.ipynb Normal file
View File

@@ -0,0 +1,222 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import KBinsDiscretizer\n",
"from sklearn.datasets import load_iris"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"experiments_range = [\n",
" [0, 100, 1, 4, \"Q\"],\n",
" [0, 50, 1, 4, \"Q\"],\n",
" [0, 100, 1, 3, \"Q\"],\n",
" [0, 50, 1, 3, \"Q\"],\n",
" [0, 10, 1, 3, \"Q\"],\n",
" [0, 100, 1, 4, \"U\"],\n",
" [0, 50, 1, 4, \"U\"],\n",
" [0, 100, 1, 3, \"U\"],\n",
" [0, 50, 1, 3, \"U\"],\n",
"# \n",
" [0, 10, 1, 3, \"U\"],\n",
" [1, 10, 1, 3, \"Q\"],\n",
" [1, 10, 1, 3, \"U\"],\n",
" [1, 11, 1, 3, \"Q\"],\n",
" [1, 11, 1, 3, \"U\"],\n",
" [1, 12, 1, 3, \"Q\"],\n",
" [1, 12, 1, 3, \"U\"],\n",
" [1, 13, 1, 3, \"Q\"],\n",
" [1, 13, 1, 3, \"U\"],\n",
" [1, 14, 1, 3, \"Q\"],\n",
" [1, 14, 1, 3, \"U\"],\n",
" [1, 15, 1, 3, \"Q\"],\n",
" [1, 15, 1, 3, \"U\"]\n",
"]\n",
"experiments_vectors = [\n",
" (3, [3.0, 1.0, 1.0, 3.0, 1.0, 1.0, 3.0, 1.0, 1.0]),\n",
" (3, [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0]),\n",
" (3, [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0]),\n",
" (3, [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0]),\n",
" (3, [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0, 15.0]),\n",
" (3, [15.0, 8.0, 12.0, 14.0, 6.0, 1.0, 13.0, 11.0, 10.0, 9.0, 7.0, 4.0, 3.0, 5.0, 2.0]),\n",
" (3, [0.0, 1.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 3.0, 4.0])\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/rmontanana/miniconda3/lib/python3.11/site-packages/sklearn/preprocessing/_discretization.py:307: UserWarning: Bins whose width are too small (i.e., <= 1e-8) in feature 0 are removed. Consider decreasing the number of bins.\n",
" warnings.warn(\n"
]
}
],
"source": [
"def write_lists(file, data, cuts):\n",
" sep = \"\"\n",
" for res in data:\n",
" file.write(f\"{sep}{int(res):d}\")\n",
" sep= \", \"\n",
" file.write(\"\\n\")\n",
" sep = \"\"\n",
" for res in cuts:\n",
" file.write(sep + str(round(res,5)))\n",
" sep = \", \"\n",
" file.write(\"\\n\")\n",
"\n",
"with open(\"datasets/tests.txt\", \"w\") as file:\n",
" file.write(\"#\\n\")\n",
" file.write(\"# from, to, step, #bins, Q/U\\n\")\n",
" file.write(\"# discretized data\\n\")\n",
" file.write(\"# cut points\\n\")\n",
" file.write(\"#\\n\")\n",
" #\n",
" # Range experiments\n",
" #\n",
" file.write(\"#\\n\")\n",
" file.write(\"# Range experiments\\n\")\n",
" file.write(\"#\\n\")\n",
" for experiment in experiments_range:\n",
" file.write(\"RANGE\\n\")\n",
" (from_, to_, step_, bins_, strategy) = experiment\n",
" disc = KBinsDiscretizer(n_bins=bins_, encode='ordinal', strategy='quantile' if strategy.strip() == \"Q\" else 'uniform')\n",
" data = [[x] for x in range(from_, to_, step_)]\n",
" disc.fit(data)\n",
" result = disc.transform(data)\n",
" file.write(f\"{from_}, {to_}, {step_}, {bins_}, {strategy}\\n\")\n",
" write_lists(file, result, disc.bin_edges_[0])\n",
" #\n",
" # Vector experiments\n",
" #\n",
" file.write(\"#\\n\")\n",
" file.write(\"# Vector experiments\\n\")\n",
" file.write(\"#\\n\")\n",
" for n_bins, experiment in experiments_vectors:\n",
" for strategy in [\"Q\", \"U\"]:\n",
" file.write(\"VECTOR\\n\")\n",
" file.write(f\"{strategy}{n_bins}{experiment}\\n\")\n",
" disc = KBinsDiscretizer(\n",
" n_bins=n_bins,\n",
" encode=\"ordinal\",\n",
" \n",
" strategy=\"quantile\" if strategy.strip() == \"Q\" else \"uniform\",\n",
" )\n",
" data = [[x] for x in experiment]\n",
" result = disc.fit_transform(data)\n",
" write_lists(file, result, disc.bin_edges_[0])\n",
" #\n",
" # Vector experiments iris\n",
" #\n",
" file.write(\"#\\n\");\n",
" file.write(\"# Vector experiments with iris\\n\");\n",
" file.write(\"#\\n\");\n",
" X, y = load_iris(return_X_y=True)\n",
" for i in range(X.shape[1]):\n",
" for n_bins in [3, 4]:\n",
" for strategy in [\"Q\", \"U\"]:\n",
" file.write(\"VECTOR\\n\")\n",
" experiment = X[:, i]\n",
" file.write(f\"{strategy}{n_bins}{experiment.tolist()}\\n\")\n",
" disc = KBinsDiscretizer(\n",
" n_bins=n_bins,\n",
" encode=\"ordinal\",\n",
" strategy=\"quantile\" if strategy.strip() == \"Q\" else \"uniform\")\n",
" data = [[x] for x in experiment]\n",
" result = disc.fit_transform(data)\n",
" write_lists(file, result, disc.bin_edges_[0])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cut points [array([ 0., 33., 66., 99.])]\n",
"i=32 X[32]=[32] result[32]=[0.]\n",
"i=33 X[33]=[33] result[33]=[1.]\n",
"i=34 X[34]=[34] result[34]=[1.]\n",
"i=65 X[65]=[65] result[65]=[1.]\n",
"i=66 X[66]=[66] result[66]=[2.]\n",
"i=67 X[67]=[67] result[67]=[2.]\n"
]
}
],
"source": [
"X = [[x] for x in range(100)]\n",
"disc = KBinsDiscretizer(n_bins=3, encode=\"ordinal\", strategy=\"uniform\")\n",
"result = disc.fit_transform(X)\n",
"print(\"Cut points\", disc.bin_edges_)\n",
"test = [32, 33, 34, 65, 66, 67]\n",
"for i in test:\n",
" print(f\"{i=} X[{i}]={X[i]} result[{i}]={result[i]}\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"right [0 1 1 1 2 2]\n",
"left [0 0 1 1 1 2]\n"
]
}
],
"source": [
"import numpy as np\n",
"print(\"right\", np.searchsorted(disc.bin_edges_[0][1:-1],test, side=\"right\"))\n",
"print(\"left \", np.searchsorted(disc.bin_edges_[0][1:-1],test))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}