Dataset

class pandas::Dataset

Utility class for pandas operations.

Example

#include <pandas/pandas.h>
using namespace pandas;

// Use Dataset
Dataset obj;
// ... operations ...

Constructors

Signature	Location	Example
Dataset(const std::map<std::string, DataVarVariant>& data_vars, const std::map<std::string, Coordinate>& coords = {}, const std::map<std::string, std::string>& attrs = {})	pd_xarray.h:467

Indexing / Selection

Signature	Return Type	Location	Example
const std::map<std::string, std::string>& attrs() const	const std::map<std::string, std::string>&	pd_xarray.h:503	View
std::map<std::string, std::string>& attrs()	std::map<std::string, std::string>&	pd_xarray.h:504	View

Data Manipulation

Signature	Return Type	Location	Example
void drop_var(const std::string& name)	void	pd_xarray.h:574

Statistics

Signature	Return Type	Location	Example
std::vector<std::string> var_names() const	std::vector<std::string>	pd_xarray.h:514	View

I/O

Signature	Return Type	Location	Example
std::string to_string() const	std::string	pd_xarray.h:625	View

Other Methods

Signature	Return Type	Location	Example
void compute_dims()	void	pd_xarray.h:718
const Coordinate& coord(const std::string& name) const	const Coordinate&	pd_xarray.h:593	View
const std::map<std::string, Coordinate>& coords() const	const std::map<std::string, Coordinate>&	pd_xarray.h:492	View
std::map<std::string, Coordinate>& coords()	std::map<std::string, Coordinate>&	pd_xarray.h:493	View
const std::map<std::string, DataVarVariant>& data_vars() const	const std::map<std::string, DataVarVariant>&	pd_xarray.h:486
std::map<std::string, DataVarVariant>& data_vars()	std::map<std::string, DataVarVariant>&	pd_xarray.h:487
std::vector<std::string> dim_names() const	std::vector<std::string>	pd_xarray.h:526
const std::map<std::string, size_t>& dims() const	const std::map<std::string, size_t>&	pd_xarray.h:498	View
bool empty() const { return data_vars_.empty()	bool	pd_xarray.h:538	View
bool has_coord(const std::string& name) const	bool	pd_xarray.h:586	View
bool has_var(const std::string& name) const	bool	pd_xarray.h:547	View
size_t nvars() const { return data_vars_.size()	size_t	pd_xarray.h:509	View
void recompute_dims()	void	pd_xarray.h:614
void set_coord(const std::string& name, const Coordinate& coord)	void	pd_xarray.h:604
void set_var(const std::string& name, const DataArray<T>& var)	void	pd_xarray.h:566

Code Examples

The following examples are extracted from the test suite.

attrs (pd_test_1_all.cpp:16361)

        // =====================================================================
        // Series Attrs Integration Tests
        // =====================================================================

        void pd_test_ndframe_series_attrs() {
            std::cout << "========= series attrs integration =============================" << std::endl;

            pandas::Series<double> s({1.0, 2.0, 3.0});

            // Test setting attrs on Series
            s.attrs().set("source", std::string("test_data"));
            s.attrs().set("timestamp", 1234567890);

            bool passed = s.attrs().get<std::string>("source") == "test_data";
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_ndframe_series_attrs() : set/get source" << std::endl;
                throw std::runtime_error("pd_test_ndframe_series_attrs failed: set/get source");
            }

            passed = s.attrs().get<int>("timestamp") == 1234567890;
            if (!passed) {

attrs (pd_test_1_all.cpp:16361)

        // =====================================================================
        // Series Attrs Integration Tests
        // =====================================================================

        void pd_test_ndframe_series_attrs() {
            std::cout << "========= series attrs integration =============================" << std::endl;

            pandas::Series<double> s({1.0, 2.0, 3.0});

            // Test setting attrs on Series
            s.attrs().set("source", std::string("test_data"));
            s.attrs().set("timestamp", 1234567890);

            bool passed = s.attrs().get<std::string>("source") == "test_data";
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_ndframe_series_attrs() : set/get source" << std::endl;
                throw std::runtime_error("pd_test_ndframe_series_attrs failed: set/get source");
            }

            passed = s.attrs().get<int>("timestamp") == 1234567890;
            if (!passed) {

var_names (pd_test_2_all.cpp:17312)

            pandas::DataFrame df(data);
            pandas::Dataset ds = df.to_xarray();

            // Verify single variable
            bool passed = (ds.nvars() == 1 && ds.has_var("value"));
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_single_column() : expected single 'value' variable" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_single_column failed");
            }

            // Verify var_names()
            auto names = ds.var_names();
            passed = (names.size() == 1 && names[0] == "value");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_single_column() : wrong var_names" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_single_column failed: wrong var_names");
            }

            std::cout << " -> tests passed" << std::endl;
        }

to_string (pd_test_1_all.cpp:2693)

        pandas::PeriodArray arr_m(std::vector<std::string>{
            "2020-01",
            "NaT",
            "2025-06"
        }, "M");

        // Year
        auto years = arr_m.year();
        auto y0 = years[0];
        if (!y0.has_value() || y0.value() != 2020) {
            std::cout << "  [FAIL] : year[0] should be 2020, got " << (y0.has_value() ? std::to_string(y0.value()) : "NA") << std::endl;
            throw std::runtime_error("pd_test_period_array_year_month_quarter failed: year[0]");
        }

        auto y1 = years[1];
        if (y1.has_value()) {
            std::cout << "  [FAIL] : year[1] should be NA (NaT)" << std::endl;
            throw std::runtime_error("pd_test_period_array_year_month_quarter failed: year[1] should be NA");
        }

        auto y2 = years[2];

coord (pd_test_2_all.cpp:17025)

            // Create DataFrame with RangeIndex (default)
            std::map<std::string, std::vector<numpy::float64>> data = {
                {"val", {1.0, 2.0, 3.0}}
            };

            pandas::DataFrame df(data);
            pandas::Dataset ds = df.to_xarray();

            // Get index coordinate
            const pandas::Coordinate& idx_coord = ds.coord("index");

            // Verify coordinate size
            bool passed = (idx_coord.size() == 3);
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_coordinate_values() : wrong coordinate size" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_coordinate_values failed: wrong size");
            }

            // Verify coordinate values (0, 1, 2 for RangeIndex)
            passed = (idx_coord.get_value_str(0) == "0" &&

coords (pd_test_3_all.cpp:14912)

/**
 * Test Series.to_xarray() coordinates
 */
void pd_test_series_to_xarray_coordinates() {
    std::cout << "========= Series.to_xarray() coordinates ===============";

    pandas::Series<double> s({100.0, 200.0, 300.0}, "prices");
    pandas::DataArray<double> da = s.to_xarray();

    // Verify coordinate exists
    auto& coords = da.coords();
    if (coords.find("index") == coords.end()) {
        std::cout << "  [FAIL] : should have 'index' coordinate" << std::endl;
        throw std::runtime_error("pd_test_series_to_xarray_coordinates failed: missing coord");
    }

    // Verify coordinate size matches Series
    const pandas::Coordinate& coord = coords.at("index");
    if (coord.size() != 3) {
        std::cout << "  [FAIL] : coordinate size should be 3, got " << coord.size() << std::endl;
        throw std::runtime_error("pd_test_series_to_xarray_coordinates failed: coord size");

coords (pd_test_3_all.cpp:14912)

/**
 * Test Series.to_xarray() coordinates
 */
void pd_test_series_to_xarray_coordinates() {
    std::cout << "========= Series.to_xarray() coordinates ===============";

    pandas::Series<double> s({100.0, 200.0, 300.0}, "prices");
    pandas::DataArray<double> da = s.to_xarray();

    // Verify coordinate exists
    auto& coords = da.coords();
    if (coords.find("index") == coords.end()) {
        std::cout << "  [FAIL] : should have 'index' coordinate" << std::endl;
        throw std::runtime_error("pd_test_series_to_xarray_coordinates failed: missing coord");
    }

    // Verify coordinate size matches Series
    const pandas::Coordinate& coord = coords.at("index");
    if (coord.size() != 3) {
        std::cout << "  [FAIL] : coordinate size should be 3, got " << coord.size() << std::endl;
        throw std::runtime_error("pd_test_series_to_xarray_coordinates failed: coord size");

dims (pd_test_2_all.cpp:16997)

            // Create DataFrame with 4 rows
            std::map<std::string, std::vector<numpy::int64>> data = {
                {"x", {10, 20, 30, 40}},
                {"y", {100, 200, 300, 400}}
            };

            pandas::DataFrame df(data);
            pandas::Dataset ds = df.to_xarray();

            // Verify dimensions
            auto dims = ds.dims();
            bool passed = (dims.size() == 1 && dims.count("index") == 1 && dims.at("index") == 4);
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_dimensions() : wrong dimensions" << std::endl;
                std::cout << "    Expected: index: 4" << std::endl;
                std::cout << "    Got: ";
                for (const auto& [name, size] : dims) {
                    std::cout << name << ": " << size << " ";
                }
                std::cout << std::endl;
                throw std::runtime_error("pd_test_to_xarray_dimensions failed");

empty (pd_test_1_all.cpp:941)

#include "../pandas/pd_config.h"

namespace dataframe_tests {

namespace dataframe_tests_config {

    void pd_test_config_version() {
        std::cout << "========= df_config: version info ======================= ";
        const char* version = pandas::DataFrameInfo::version();
        if (version == nullptr || std::string(version).empty()) {
            std::cout << "[FAIL] : in pd_test_config_version() : version is null or empty" << std::endl;
            throw std::runtime_error("pd_test_config_version failed: version is null or empty");
        }
        std::cout << "-> tests passed" << std::endl;
    }

    void pd_test_config_na_repr() {
        std::cout << "========= df_config: NA representation ======================= ";
        const char* na_repr = pandas::DataFrameConfig::get_na_repr();
        if (na_repr == nullptr) {

has_coord (pd_test_2_all.cpp:16975)

            }

            // Verify variable names
            passed = ds.has_var("A") && ds.has_var("B");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : missing variable A or B" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: missing variables");
            }

            // Verify coordinate exists
            passed = ds.has_coord("index");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : missing index coordinate" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: missing index coordinate");
            }

            std::cout << " -> tests passed" << std::endl;
        }

        void pd_test_to_xarray_dimensions() {
            std::cout << "========= to_xarray dimensions =========================";

has_var (pd_test_2_all.cpp:16968)

            // Verify Dataset has correct structure
            bool passed = (ds.nvars() == 2);
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : expected 2 variables, got "
                          << ds.nvars() << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: wrong number of variables");
            }

            // Verify variable names
            passed = ds.has_var("A") && ds.has_var("B");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : missing variable A or B" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: missing variables");
            }

            // Verify coordinate exists
            passed = ds.has_coord("index");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : missing index coordinate" << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: missing index coordinate");

nvars (pd_test_2_all.cpp:16960)

                {"A", {1.0, 2.0, 3.0}},
                {"B", {4.0, 5.0, 6.0}}
            };

            pandas::DataFrame df(data);

            // Convert to xarray Dataset
            pandas::Dataset ds = df.to_xarray();

            // Verify Dataset has correct structure
            bool passed = (ds.nvars() == 2);
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : expected 2 variables, got "
                          << ds.nvars() << std::endl;
                throw std::runtime_error("pd_test_to_xarray_basic failed: wrong number of variables");
            }

            // Verify variable names
            passed = ds.has_var("A") && ds.has_var("B");
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_to_xarray_basic() : missing variable A or B" << std::endl;