data_wrangling.hpp File Reference

Data wrangling (data manipulation and transformation) functions. More...

#include <algorithm>
#include <cmath>
#include <cstddef>
#include <functional>
#include <limits>
#include <map>
#include <numeric>
#include <random>
#include <stdexcept>
#include <type_traits>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
#include "statcpp/basic_statistics.hpp"
#include "statcpp/random_engine.hpp"

Include dependency graph for data_wrangling.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	statcpp::group_result< K, V >
	Grouping result. More...
struct	statcpp::aggregation_result< K >
	Aggregation result per group. More...
struct	statcpp::label_encoding_result< T >
	Label encoding result. More...
struct	statcpp::validation_result
	Data validation result. More...

Namespaces
namespace	statcpp

Functions
bool	statcpp::is_na (double x)
	Check if a value is NA.
template<typename T >
std::vector< std::vector< T > >	statcpp::dropna (const std::vector< std::vector< T > > &data)
	Drop rows containing NA.
template<typename T >
std::vector< T >	statcpp::dropna (const std::vector< T > &data)
	Drop NA from a 1-dimensional vector.
template<typename T >
std::vector< T >	statcpp::fillna (const std::vector< T > &data, T fill_value)
	Fill NA with a specified value.
std::vector< double >	statcpp::fillna_mean (const std::vector< double > &data)
	Fill NA with mean.
std::vector< double >	statcpp::fillna_median (const std::vector< double > &data)
	Fill NA with median.
std::vector< double >	statcpp::fillna_ffill (const std::vector< double > &data)
	Fill NA with forward fill.
std::vector< double >	statcpp::fillna_bfill (const std::vector< double > &data)
	Fill NA with backward fill.
std::vector< double >	statcpp::fillna_interpolate (const std::vector< double > &data)
	Fill NA with linear interpolation.
template<typename T , typename Predicate >
std::vector< T >	statcpp::filter (const std::vector< T > &data, Predicate pred)
	Filter elements that match a condition.
template<typename T , typename Predicate >
std::vector< std::vector< T > >	statcpp::filter_rows (const std::vector< std::vector< T > > &data, Predicate pred)
	Filter rows that match a condition (2-dimensional)
template<typename T >
std::vector< T >	statcpp::filter_range (const std::vector< T > &data, T min_val, T max_val)
	Filter values within a range.
std::vector< double >	statcpp::log_transform (const std::vector< double > &data)
	Logarithmic transformation (natural logarithm)
std::vector< double >	statcpp::log1p_transform (const std::vector< double > &data)
	Logarithmic transformation (log1p: log(1 + x))
std::vector< double >	statcpp::sqrt_transform (const std::vector< double > &data)
	Square root transformation.
std::vector< double >	statcpp::boxcox_transform (const std::vector< double > &data, double lambda)
	Box-Cox transformation.
std::vector< double >	statcpp::rank_transform (const std::vector< double > &data)
	Rank transformation.
template<typename K , typename V >
group_result< K, V >	statcpp::group_by (const std::vector< K > &keys, const std::vector< V > &values)
	Group by.
template<typename K >
aggregation_result< K >	statcpp::group_mean (const std::vector< K > &keys, const std::vector< double > &values)
	Mean per group.
template<typename K >
aggregation_result< K >	statcpp::group_sum (const std::vector< K > &keys, const std::vector< double > &values)
	Sum per group.
template<typename K >
aggregation_result< K >	statcpp::group_count (const std::vector< K > &keys, const std::vector< double > &values)
	Count per group.
template<typename T >
std::vector< T >	statcpp::sort_values (const std::vector< T > &data, bool ascending=true)
	Return a sorted vector (ascending)
template<typename T >
std::vector< std::size_t >	statcpp::argsort (const std::vector< T > &data, bool ascending=true)
	Return indices in sorted order.
template<typename T >
std::vector< T >	statcpp::sample_with_replacement (const std::vector< T > &data, std::size_t n)
	Random sampling (with replacement)
template<typename T >
std::vector< T >	statcpp::sample_without_replacement (const std::vector< T > &data, std::size_t n)
	Random sampling (without replacement)
template<typename K , typename V >
std::vector< V >	statcpp::stratified_sample (const std::vector< K > &strata, const std::vector< V > &data, double sample_ratio)
	Stratified sampling.
template<typename T >
std::vector< T >	statcpp::drop_duplicates (const std::vector< T > &data)
	Drop duplicates.
template<typename T >
std::map< T, std::size_t >	statcpp::value_counts (const std::vector< T > &data)
	Count duplicates.
template<typename T >
std::vector< T >	statcpp::get_duplicates (const std::vector< T > &data)
	Get duplicate values.
std::vector< double >	statcpp::rolling_mean (const std::vector< double > &data, std::size_t window)
	Moving average.
std::vector< double >	statcpp::rolling_std (const std::vector< double > &data, std::size_t window)
	Moving standard deviation.
std::vector< double >	statcpp::rolling_min (const std::vector< double > &data, std::size_t window)
	Moving minimum.
std::vector< double >	statcpp::rolling_max (const std::vector< double > &data, std::size_t window)
	Moving maximum.
std::vector< double >	statcpp::rolling_sum (const std::vector< double > &data, std::size_t window)
	Moving sum.
template<typename T >
label_encoding_result< T >	statcpp::label_encode (const std::vector< T > &data)
	Label encoding.
template<typename T >
std::vector< std::vector< double > >	statcpp::one_hot_encode (const std::vector< T > &data)
	One-hot encoding.
std::vector< std::size_t >	statcpp::bin_equal_width (const std::vector< double > &data, std::size_t n_bins)
	Binning (equal width)
std::vector< std::size_t >	statcpp::bin_equal_freq (const std::vector< double > &data, std::size_t n_bins)
	Binning (equal frequency)
validation_result	statcpp::validate_data (const std::vector< double > &data, bool allow_missing=false, bool allow_infinite=false, bool allow_negative=true)
	Data validation.
bool	statcpp::validate_range (const std::vector< double > &data, double min_val=-std::numeric_limits< double >::infinity(), double max_val=std::numeric_limits< double >::infinity())
	Range validation.

Variables
constexpr double	statcpp::NA = std::numeric_limits<double>::quiet_NaN()
	Constant representing NA (NaN)

Detailed Description

Data wrangling (data manipulation and transformation) functions.

Provides missing value handling, filtering, transformation, grouping, aggregation, sampling, rolling aggregations, categorical encoding, and other functions.

Definition in file data_wrangling.hpp.