rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-20 01:45:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix some sonar issues in the code

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-07-04 12:34:54 +02:00
parent 8c536cfc65
commit 32b956a361
5 changed files with 20 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
BinDisc.cpp
View File

@@ -54,31 +54,30 @@ namespace mdlp {
}
return linspc;
}
size_t clip(const size_t n, size_t lower, size_t upper)
size_t clip(const size_t n, const size_t lower, const size_t upper)
{
return std::max(lower, std::min(n, upper));
}
std::vector<precision_t> percentile(samples_t& data, std::vector<precision_t>& percentiles)
std::vector<precision_t> percentile(samples_t& data, const std::vector<precision_t>& percentiles)
{
// Implementation taken from https://dpilger26.github.io/NumCpp/doxygen/html/percentile_8hpp_source.html
std::vector<precision_t> results;
bool first = true;
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 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() || first) // first needed as results.back() return is undefined for empty vectors
if (const auto value = data[indexLower] + (data[indexLower + 1] - data[indexLower]) * fraction; value != results.back() || first) // first needed as results.back() return is undefined for empty vectors
results.push_back(value);
first = false;
}
return results;
}
void BinDisc::fit_quantile(samples_t& X)
void BinDisc::fit_quantile(const samples_t& X)
{
auto quantiles = linspace(0.0, 100.0, n_bins + 1);
auto data = X;
@@ -91,9 +90,9 @@ namespace mdlp {
}
cutPoints = percentile(data, quantiles);
}
void BinDisc::fit_uniform(samples_t& X)
void BinDisc::fit_uniform(const samples_t& X)
{
auto minmax = std::minmax_element(X.begin(), X.end());
cutPoints = linspace(*minmax.first, *minmax.second, n_bins + 1);
auto [vmin, vmax] = std::minmax_element(X.begin(), X.end());
cutPoints = linspace(*vmin, *vmax, n_bins + 1);
}
}

4
BinDisc.h
View File

@@ -24,8 +24,8 @@ namespace mdlp {
void fit(samples_t& X_, labels_t& y) override;
void fit(samples_t& X);
private:
void fit_uniform(samples_t&);
void fit_quantile(samples_t&);
void fit_uniform(const samples_t&);
void fit_quantile(const samples_t&);
int n_bins;
strategy_t strategy;
};

6
CPPFImdlp.cpp
View File

@@ -66,9 +66,9 @@ namespace mdlp {
}
}
// 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);
auto [vmin, vmax] = std::minmax_element(X.begin(), X.end());
cutPoints.push_back(*vmax);
cutPoints.insert(cutPoints.begin(), *vmin);
}
pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end)

8
Discretizer.cpp
View File

@@ -19,7 +19,7 @@ namespace mdlp {
auto bound = direction == bound_dir_t::LEFT ? std::lower_bound<std::vector<precision_t>::iterator, precision_t> : std::upper_bound<std::vector<precision_t>::iterator, precision_t>;
for (const precision_t& item : data) {
auto pos = bound(first, last, item);
int number = pos - first;
auto number = pos - first;
discretizedData.push_back(number);
}
return discretizedData;
@@ -29,21 +29,21 @@ namespace mdlp {
fit(X_, y_);
return transform(X_);
}
void Discretizer::fit_t(torch::Tensor& X_, torch::Tensor& y_)
void Discretizer::fit_t(const torch::Tensor& X_, const torch::Tensor& y_)
{
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);
labels_t y(y_.data_ptr<int>(), y_.data_ptr<int>() + num_elements);
fit(X, y);
}
torch::Tensor Discretizer::transform_t(torch::Tensor& X_)
torch::Tensor Discretizer::transform_t(const torch::Tensor& X_)
{
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);
auto result = transform(X);
return torch::tensor(result, torch::kInt32);
}
torch::Tensor Discretizer::fit_transform_t(torch::Tensor& X_, torch::Tensor& y_)
torch::Tensor Discretizer::fit_transform_t(const torch::Tensor& X_, const torch::Tensor& y_)
{
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);

6
Discretizer.h
View File

@@ -25,9 +25,9 @@ namespace mdlp {
virtual void fit(samples_t& X_, labels_t& y_) = 0;
labels_t& transform(const samples_t& data);
labels_t& fit_transform(samples_t& X_, labels_t& y_);
void fit_t(torch::Tensor& X_, torch::Tensor& y_);
torch::Tensor transform_t(torch::Tensor& X_);
torch::Tensor fit_transform_t(torch::Tensor& X_, torch::Tensor& y_);
void fit_t(const torch::Tensor& X_, const torch::Tensor& y_);
torch::Tensor transform_t(const torch::Tensor& X_);
torch::Tensor fit_transform_t(const torch::Tensor& X_, const torch::Tensor& y_);
static inline std::string version() { return "1.2.3"; };
protected:
labels_t discretizedData = labels_t();