SparseArray

class pandas::SparseArray

Extension array type for specialized data storage.

Example

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

// Use SparseArray
SparseArray obj;
// ... operations ...

Constructors

Signature	Location	Example
SparseArray(const numpy::NDArray<T>& dense, T fill_value)	pd_sparse_array.h:81
explicit SparseArray(const numpy::NDArray<T>& dense)	pd_sparse_array.h:94
SparseArray(const numpy::NDArray<T>& sp_values, const numpy::NDArray<numpy::int64>& sp_index, T fill_value, size_t length)	pd_sparse_array.h:110
SparseArray(const std::vector<T>& values, T fill_value)	pd_sparse_array.h:125

Construction

Signature	Return Type	Location	Example
static SparseArray<T> from_dense(const numpy::NDArray<T>& dense, T fill_value)	static SparseArray<T>	pd_sparse_array.h:808	View
static SparseArray<T> from_dense(const numpy::NDArray<T>& dense)	static SparseArray<T>	pd_sparse_array.h:815	View

Indexing / Selection

Signature	Return Type	Location	Example
T at(size_t index) const	T	pd_sparse_array.h:269	View

Missing Data

Signature	Return Type	Location	Example
SparseArray<T> fillna(T value) const	SparseArray<T>	pd_sparse_array.h:378	View
numpy::NDArray<numpy::bool_> isna() const	numpy::NDArray<numpy::bool_>	pd_sparse_array.h:334	View
numpy::NDArray<numpy::bool_> notna() const	numpy::NDArray<numpy::bool_>	pd_sparse_array.h:365	View

Statistics

Signature	Return Type	Location	Example
size_t count() const	size_t	pd_sparse_array.h:425	View
std::optional<T> max() const	std::optional<T>	pd_sparse_array.h:667	View
double mean() const	double	pd_sparse_array.h:595	View
std::optional<T> min() const	std::optional<T>	pd_sparse_array.h:630	View
std::optional<double> std(int ddof = 1) const	std::optional<double>	pd_sparse_array.h:704	View
T sum() const	T	pd_sparse_array.h:570	View
std::optional<double> var(int ddof = 1) const	std::optional<double>	pd_sparse_array.h:713	View

Comparison

Signature	Return Type	Location	Example
numpy::NDArray<numpy::bool_> compare_op(const SparseArray<T>& other, Op op) const	numpy::NDArray<numpy::bool_>	pd_sparse_array.h:1043
size_t len() const	size_t	pd_sparse_array.h:195	View

Combining

Signature	Return Type	Location	Example
static SparseArray<T> concat(const std::vector<SparseArray<T>>& arrays)	static SparseArray<T>	pd_sparse_array.h:822	View

I/O

Signature	Return Type	Location	Example
numpy::NDArray<T> to_dense() const	numpy::NDArray<T>	pd_sparse_array.h:298	View
std::string to_string() const	std::string	pd_sparse_array.h:903	View

Conversion

Signature	Return Type	Location	Example
SparseArray<T> copy() const	SparseArray<T>	pd_sparse_array.h:318	View

Type Checking

Signature	Return Type	Location	Example
bool is_fill(size_t index) const	bool	pd_sparse_array.h:276	View
bool is_fill_value(T val) const	bool	pd_sparse_array.h:48

Other Methods

Signature	Return Type	Location	Example
bool all() const	bool	pd_sparse_array.h:778	View
bool any() const	bool	pd_sparse_array.h:752	View
SparseArray<T> binary_op(const SparseArray<T>& other, Op op) const	SparseArray<T>	pd_sparse_array.h:1010
build_from_dense(dense)		pd_sparse_array.h:87
build_from_dense(dense)		pd_sparse_array.h:100
build_from_dense(dense)		pd_sparse_array.h:135
void build_from_dense(const numpy::NDArray<T>& dense)	void	pd_sparse_array.h:947
double density() const	double	pd_sparse_array.h:235	View
dtype_type dtype() const	dtype_type	pd_sparse_array.h:145	View
bool empty() const	bool	pd_sparse_array.h:188	View
T fill_value() const	T	pd_sparse_array.h:220	View
T find_value_at(size_t index) const	T	pd_sparse_array.h:988
size_t nbytes() const	size_t	pd_sparse_array.h:159	View
size_t nbytes_dense() const	size_t	pd_sparse_array.h:167
constexpr int ndim() const	constexpr int	pd_sparse_array.h:174	View
size_t npoints() const	size_t	pd_sparse_array.h:227	View
op(dense1.getElementAt({i}), dense2.getElementAt({i})))		pd_sparse_array.h:1022
op(fill_value_, scalar), length_)		pd_sparse_array.h:1039
std::string repr() const	std::string	pd_sparse_array.h:934	View
numpy::NDArray<numpy::bool_> scalar_compare(T scalar, Op op) const	numpy::NDArray<numpy::bool_>	pd_sparse_array.h:1060
SparseArray<T> scalar_op(T scalar, Op op) const	SparseArray<T>	pd_sparse_array.h:1031
std::vector<size_t> shape() const	std::vector<size_t>	pd_sparse_array.h:181	View
size_t size() const	size_t	pd_sparse_array.h:152	View
const numpy::NDArray<numpy::int64>& sp_index() const	const numpy::NDArray<numpy::int64>&	pd_sparse_array.h:213	View
const numpy::NDArray<T>& sp_values() const	const numpy::NDArray<T>&	pd_sparse_array.h:206	View
std::string sparse_dtype_footer() const	std::string	pd_sparse_array.h:890
double sparsity() const	double	pd_sparse_array.h:244	View
void validate_sparse_data()	void	pd_sparse_array.h:968

Internal Methods

1 internal methods (prefixed with underscore)

Code Examples

The following examples are extracted from the test suite.

from_dense (pd_test_1_all.cpp:3164)

    }

    void pd_test_sparse_array_from_dense() {
        std::cout << "========= SparseArray: from_dense ======================= ";

        numpy::NDArray<numpy::float64> dense(std::vector<size_t>{10});
        for (size_t i = 0; i < 10; ++i) {
            dense.setElementAt({i}, (i == 3 || i == 7) ? 5.0 : 0.0);
        }

        auto sparse = pandas::SparseArray<numpy::float64>::from_dense(dense, 0.0);

        if (sparse.size() != 10) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : size != 10" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: size != 10");
        }

        if (sparse.npoints() != 2) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : npoints != 2" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: npoints != 2");
        }

from_dense (pd_test_1_all.cpp:3164)

    }

    void pd_test_sparse_array_from_dense() {
        std::cout << "========= SparseArray: from_dense ======================= ";

        numpy::NDArray<numpy::float64> dense(std::vector<size_t>{10});
        for (size_t i = 0; i < 10; ++i) {
            dense.setElementAt({i}, (i == 3 || i == 7) ? 5.0 : 0.0);
        }

        auto sparse = pandas::SparseArray<numpy::float64>::from_dense(dense, 0.0);

        if (sparse.size() != 10) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : size != 10" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: size != 10");
        }

        if (sparse.npoints() != 2) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : npoints != 2" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: npoints != 2");
        }

at (pd_test_1_all.cpp:6581)

            // Test isna/notna with float data
            {
                std::map<std::string, std::vector<numpy::float64>> float_data;
                float_data["X"] = {1.0, std::nan(""), 3.0};
                float_data["Y"] = {4.0, 5.0, std::nan("")};
                pandas::DataFrame df_na(float_data);

                auto na_mask = df_na.isna();
                // Row 1, col 0 (X) should be NA
                if (!na_mask.getElementAt({1, 0})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : isna at (1,0) should be true" << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: isna at (1,0)");
                }
                // Row 2, col 1 (Y) should be NA
                if (!na_mask.getElementAt({2, 1})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : isna at (2,1) should be true" << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: isna at (2,1)");
                }
                // Row 0, col 0 should NOT be NA
                if (na_mask.getElementAt({0, 0})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : isna at (0,0) should be false" << std::endl;

fillna (pd_test_1_all.cpp:537)

            throw std::runtime_error("pd_test_categorical_array_na_handling failed: isna size != 4");
        }

        // Test dropna
        pandas::CategoricalArray dropped = arr.dropna();
        if (dropped.size() != 2) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_na_handling() : dropna size != 2" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_na_handling failed: dropna size != 2");
        }

        // Test fillna (fill with existing category)
        pandas::CategoricalArray filled = arr.fillna("a");  // 'a' is in categories
        if (filled.has_na()) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_na_handling() : fillna should have no NA" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_na_handling failed: fillna should have no NA");
        }

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

    void pd_test_categorical_array_add_categories() {

isna (pd_test_1_all.cpp:524)

            throw std::runtime_error("pd_test_categorical_array_na_handling failed: has_na() should be true");
        }

        // Test count (non-NA)
        if (arr.count() != 2) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_na_handling() : count() != 2" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_na_handling failed: count() != 2");
        }

        // Test isna array
        numpy::NDArray<numpy::bool_> na_mask = arr.isna();
        if (na_mask.getSize() != 4) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_na_handling() : isna size != 4" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_na_handling failed: isna size != 4");
        }

        // Test dropna
        pandas::CategoricalArray dropped = arr.dropna();
        if (dropped.size() != 2) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_na_handling() : dropna size != 2" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_na_handling failed: dropna size != 2");

notna (pd_test_1_all.cpp:6595)

                if (!na_mask.getElementAt({2, 1})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : isna at (2,1) should be true" << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: isna at (2,1)");
                }
                // Row 0, col 0 should NOT be NA
                if (na_mask.getElementAt({0, 0})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : isna at (0,0) should be false" << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: isna at (0,0)");
                }

                auto notna_mask = df_na.notna();
                if (notna_mask.getElementAt({1, 0})) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : notna at (1,0) should be false" << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: notna at (1,0)");
                }
            }

            // Test fillna
            {
                std::map<std::string, std::vector<numpy::float64>> float_data;
                float_data["X"] = {1.0, std::nan(""), 3.0};

count (pd_test_1_all.cpp:66)

        if (arr.is_na(0)) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_na_handling() : is_na(0) should be false" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_na_handling failed: is_na(0) should be false");
        }

        if (!arr.has_na()) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_na_handling() : has_na() should be true" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_na_handling failed: has_na() should be true");
        }

        if (arr.count() != 2) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_na_handling() : count() should be 2" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_na_handling failed: count() should be 2");
        }

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

    void pd_test_boolean_array_kleene_and() {
        std::cout << "========= BooleanArray: Kleene AND ======================= ";

max (pd_test_1_all.cpp:771)

        pandas::CategoricalArray arr = pandas::CategoricalArray::from_codes(codes, cats, true);  // ordered

        // Test min
        std::optional<std::string> min_val = arr.min();
        if (!min_val.has_value() || *min_val != "low") {
            std::cout << "  [FAIL] : in pd_test_categorical_array_ordered_operations() : min != 'low'" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: min != 'low'");
        }

        // Test max
        std::optional<std::string> max_val = arr.max();
        if (!max_val.has_value() || *max_val != "high") {
            std::cout << "  [FAIL] : in pd_test_categorical_array_ordered_operations() : max != 'high'" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: max != 'high'");
        }

        // Test unordered throws for min/max
        pandas::CategoricalArray unordered = arr.as_unordered();
        bool threw = false;
        try {
            unordered.min();

mean (pd_test_1_all.cpp:282)

            std::optional<bool>(true),
            std::optional<bool>(true)
        });

        auto s = arr.sum();
        if (!s.has_value() || s.value() != 3) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : sum should be 3" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: sum");
        }

        auto m = arr.mean();
        if (!m.has_value() || std::abs(m.value() - 0.75) > 0.001) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : mean should be 0.75" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: mean");
        }

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

    void pd_test_boolean_array_dtype() {
        std::cout << "========= BooleanArray: dtype ======================= ";

min (pd_test_1_all.cpp:764)

    }

    void pd_test_categorical_array_ordered_operations() {
        std::cout << "========= CategoricalArray: ordered operations (min/max) ======================= ";

        std::vector<std::string> cats = {"low", "medium", "high"};
        std::vector<numpy::int32> codes = {0, 2, 1, 0, -1};  // low, high, medium, low, NA
        pandas::CategoricalArray arr = pandas::CategoricalArray::from_codes(codes, cats, true);  // ordered

        // Test min
        std::optional<std::string> min_val = arr.min();
        if (!min_val.has_value() || *min_val != "low") {
            std::cout << "  [FAIL] : in pd_test_categorical_array_ordered_operations() : min != 'low'" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: min != 'low'");
        }

        // Test max
        std::optional<std::string> max_val = arr.max();
        if (!max_val.has_value() || *max_val != "high") {
            std::cout << "  [FAIL] : in pd_test_categorical_array_ordered_operations() : max != 'high'" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: max != 'high'");

std (pd_test_1_all.cpp:4526)

#include "../pandas/pd_series.h"

namespace dataframe_tests {
    namespace dataframe_tests_aggregation {

        void pd_test_aggregation_series_sem() {
            std::cout << "========= Series sem ============================";

            pandas::Series<double> s({1.0, 2.0, 3.0, 4.0, 5.0});
            auto sem_val = s.sem();
            // std(ddof=1) = sqrt(2.5), sem = sqrt(2.5)/sqrt(5) ≈ 0.707
            bool passed = sem_val.has_value() && std::abs(*sem_val - 0.707) < 0.01;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_aggregation_series_sem() : sem value incorrect" << std::endl;
                throw std::runtime_error("pd_test_aggregation_series_sem failed: sem value incorrect");
            }

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

        void pd_test_aggregation_series_quantile() {

sum (pd_test_1_all.cpp:276)

        }

        // Test sum/mean
        pandas::BooleanArray arr({
            std::optional<bool>(true),
            std::optional<bool>(false),
            std::optional<bool>(true),
            std::optional<bool>(true)
        });

        auto s = arr.sum();
        if (!s.has_value() || s.value() != 3) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : sum should be 3" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: sum");
        }

        auto m = arr.mean();
        if (!m.has_value() || std::abs(m.value() - 0.75) > 0.001) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : mean should be 0.75" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: mean");
        }

var (pd_test_1_all.cpp:20890)

                throw std::runtime_error("pd_test_expanding_std failed: expanding std values incorrect");
            }

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

        void pd_test_expanding_var() {
            std::cout << "========= Expanding var =========================";

            pandas::Series<double> s({1.0, 2.0, 3.0, 4.0, 5.0});
            auto result = s.expanding().var();

            // Expanding var (ddof=1): NaN, 0.5, 1.0, 1.6667, 2.5
            bool passed = std::isnan(result[0]) &&
                          std::abs(result[1] - 0.5) < 0.001 &&
                          std::abs(result[2] - 1.0) < 0.001 &&
                          std::abs(result[3] - 1.6667) < 0.001 &&
                          std::abs(result[4] - 2.5) < 0.001;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_expanding_var() : expanding var values incorrect" << std::endl;
                throw std::runtime_error("pd_test_expanding_var failed: expanding var values incorrect");

len (pd_test_3_all.cpp:20867)

    auto title_result = s.str().title();
    if (title_result[0] != "Hello World" || title_result[1] != "Hello World" || title_result[2] != "Hello World") {
        std::cout << "  [FAIL] : title() failed" << std::endl;
        throw std::runtime_error("pd_test_str_capitalize_title: title() failed");
    }

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

// ============================================================================
// Test str().len()
// ============================================================================

void pd_test_str_len() {
    std::cout << "========= Series.str().len() ============================";

    pandas::Series<std::string> s({"a", "bb", "ccc", ""});

    auto lens = s.str().len();
    if (lens[0] != 1 || lens[1] != 2 || lens[2] != 3 || lens[3] != 0) {
        std::cout << "  [FAIL] : len() failed" << std::endl;

concat (pd_test_1_all.cpp:17717)

}

void pd_test_period_index_concat() {
    std::cout << "========= concat factory ==============================";

    std::vector<int64_t> ordinals1 = {0, 1};
    std::vector<int64_t> ordinals2 = {2, 3};
    pandas::PeriodIndex idx1(ordinals1, "D");
    pandas::PeriodIndex idx2(ordinals2, "D");

    pandas::PeriodIndex concatenated = pandas::PeriodIndex::concat({idx1, idx2});

    bool passed = (concatenated.size() == 4);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_period_index_concat()" << std::endl;
        throw std::runtime_error("pd_test_period_index_concat failed");
    }

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

to_dense (pd_test_1_all.cpp:3272)

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

    void pd_test_sparse_array_to_dense() {
        std::cout << "========= SparseArray: to_dense ======================= ";

        std::vector<numpy::float64> data = {0.0, 1.0, 0.0, 2.0, 0.0};
        pandas::SparseArray<numpy::float64> arr(data, 0.0);

        auto dense = arr.to_dense();
        if (dense.getSize() != 5) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_to_dense() : dense size != 5" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_to_dense failed: dense size != 5");
        }

        if (dense.getElementAt({0}) != 0.0 ||
            dense.getElementAt({1}) != 1.0 ||
            dense.getElementAt({2}) != 0.0 ||
            dense.getElementAt({3}) != 2.0 ||
            dense.getElementAt({4}) != 0.0) {

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];

copy (pd_test_1_all.cpp:5798)

// ============================================================================
// Copy/Rename Tests
// ============================================================================

void pd_test_categorical_index_copy() {
    std::cout << "========= copy ========================================";

    pandas::CategoricalArray arr({"a", "b", "c"});
    pandas::CategoricalIndex idx(arr, "original");

    pandas::CategoricalIndex copied = idx.copy();

    bool passed = (copied.size() == idx.size() && copied.name() == idx.name() &&
                   copied.categories() == idx.categories() && copied.ordered() == idx.ordered());
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_copy()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_copy failed");
    }

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

is_fill (pd_test_1_all.cpp:3314)

            throw std::runtime_error("pd_test_sparse_array_element_access failed: arr[3] != 10.0");
        }

        // Access fill values
        if (arr[0] != 0.0) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_element_access() : arr[0] != fill_value" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_element_access failed: arr[0] != fill_value");
        }

        // Test is_fill
        if (!arr.is_fill(0)) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_element_access() : is_fill(0) should be true" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_element_access failed: is_fill(0) should be true");
        }

        if (arr.is_fill(1)) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_element_access() : is_fill(1) should be false" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_element_access failed: is_fill(1) should be false");
        }

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

all (pd_test_1_all.cpp:247)

        pandas::BooleanArray has_true({
            std::optional<bool>(false),
            std::optional<bool>(true)
        });
        any_result = has_true.any();
        if (!any_result.has_value() || !any_result.value()) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : any() with True" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: any() with True");
        }

        // Test all()
        pandas::BooleanArray all_true({
            std::optional<bool>(true),
            std::optional<bool>(true)
        });
        auto all_result = all_true.all();
        if (!all_result.has_value() || !all_result.value()) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : all() of all True" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: all() all True");
        }

any (pd_test_1_all.cpp:226)

            std::cout << "  [FAIL] : in pd_test_boolean_array_kleene_not() : ~NA should be NA" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_kleene_not failed: ~NA");
        }

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

    void pd_test_boolean_array_reductions() {
        std::cout << "========= BooleanArray: reductions ======================= ";

        // Test any()
        pandas::BooleanArray all_false({
            std::optional<bool>(false),
            std::optional<bool>(false)
        });
        auto any_result = all_false.any();
        if (!any_result.has_value() || any_result.value()) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_reductions() : any() of all False" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_reductions failed: any() all False");
        }

density (pd_test_1_all.cpp:3247)

            std::cout << "  [FAIL] : in pd_test_sparse_array_fill_value_property() : default float fill_value should be NaN" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_fill_value_property failed: default float fill_value should be NaN");
        }

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

    void pd_test_sparse_array_density() {
        std::cout << "========= SparseArray: density ======================= ";

        // 20% density (2 non-fill out of 10)
        std::vector<numpy::float64> data = {0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.0, 0.0};
        pandas::SparseArray<numpy::float64> arr(data, 0.0);

        double density = arr.density();
        if (std::abs(density - 0.2) > 0.001) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_density() : density != 0.2, got " << density << std::endl;
            throw std::runtime_error("pd_test_sparse_array_density failed: density != 0.2");
        }

        double sparsity = arr.sparsity();

dtype (pd_test_1_all.cpp:295)

            throw std::runtime_error("pd_test_boolean_array_reductions failed: mean");
        }

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

    void pd_test_boolean_array_dtype() {
        std::cout << "========= BooleanArray: dtype ======================= ";

        pandas::BooleanArray arr;
        if (arr.dtype().name() != "boolean") {
            std::cout << "  [FAIL] : in pd_test_boolean_array_dtype() : dtype name should be 'boolean'" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_dtype failed: dtype name");
        }

        if (arr.dtype().kind() != "b") {
            std::cout << "  [FAIL] : in pd_test_boolean_array_dtype() : dtype kind should be 'b'" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_dtype failed: dtype kind");
        }

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

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) {

fill_value (pd_test_1_all.cpp:3229)

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

    void pd_test_sparse_array_fill_value_property() {
        std::cout << "========= SparseArray: fill_value property ======================= ";

        std::vector<numpy::int64> data = {-1, 5, -1, 10, -1};
        pandas::SparseArray<numpy::int64> arr(data, static_cast<numpy::int64>(-1));

        if (arr.fill_value() != -1) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_fill_value_property() : fill_value != -1" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_fill_value_property failed: fill_value != -1");
        }

        // Test default fill_value for float (NaN)
        pandas::SparseArray<numpy::float64> arr_float;
        if (!std::isnan(arr_float.fill_value())) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_fill_value_property() : default float fill_value should be NaN" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_fill_value_property failed: default float fill_value should be NaN");
        }

nbytes (pd_test_1_all.cpp:6214)

            }

            // Test empty DataFrame
            pandas::DataFrame empty_df;
            if (!empty_df.empty()) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : should be empty" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: should be empty");
            }

            // Test nbytes > 0 for non-empty
            if (df.nbytes() == 0) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : nbytes should be > 0" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: nbytes should be > 0");
            }

            // Test columns index
            if (df.columns().size() != 3) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : columns size != 3" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: columns size != 3");
            }

ndim (pd_test_1_all.cpp:6195)

            pandas::DataFrame df(data);

            // Test shape
            auto shape = df.shape();
            if (shape.size() != 2 || shape[0] != 4 || shape[1] != 3) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : shape mismatch" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: shape mismatch");
            }

            // Test ndim
            if (df.ndim() != 2) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : ndim != 2" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: ndim != 2");
            }

            // Test empty
            if (df.empty()) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : should not be empty" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: should not be empty");
            }

npoints (pd_test_1_all.cpp:3171)

            dense.setElementAt({i}, (i == 3 || i == 7) ? 5.0 : 0.0);
        }

        auto sparse = pandas::SparseArray<numpy::float64>::from_dense(dense, 0.0);

        if (sparse.size() != 10) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : size != 10" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: size != 10");
        }

        if (sparse.npoints() != 2) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_from_dense() : npoints != 2" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_from_dense failed: npoints != 2");
        }

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

    void pd_test_sparse_array_sp_values_property() {
        std::cout << "========= SparseArray: sp_values property ======================= ";

repr (pd_test_1_all.cpp:10906)

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

void pd_test_extension_index_repr() {
    std::cout << "========= repr =========================";

    pandas::CategoricalArray arr({"a", "b", "c"});
    // Use ExtensionIndex<CategoricalArray> directly to test base class repr
    pandas::ExtensionIndex<pandas::CategoricalArray> idx(arr, "test");

    std::string repr_str = idx.repr();

    bool passed = (!repr_str.empty() && repr_str.find("ExtensionIndex") != std::string::npos);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_repr() : repr check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_repr failed");
    }

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

shape (pd_test_1_all.cpp:6188)

            std::cout << "========= properties =======================";

            std::map<std::string, std::vector<numpy::float64>> data;
            data["A"] = {1.0, 2.0, 3.0, 4.0};
            data["B"] = {5.0, 6.0, 7.0, 8.0};
            data["C"] = {9.0, 10.0, 11.0, 12.0};

            pandas::DataFrame df(data);

            // Test shape
            auto shape = df.shape();
            if (shape.size() != 2 || shape[0] != 4 || shape[1] != 3) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : shape mismatch" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: shape mismatch");
            }

            // Test ndim
            if (df.ndim() != 2) {
                std::cout << "  [FAIL] : in pd_test_dataframe_properties() : ndim != 2" << std::endl;
                throw std::runtime_error("pd_test_dataframe_properties failed: ndim != 2");
            }

size (pd_test_1_all.cpp:22)

#include "../pandas/pd_boolean_array.h"

namespace dataframe_tests {

namespace dataframe_tests_boolean_array {
    void pd_test_boolean_array_constructors() {
        std::cout << "========= BooleanArray: constructors ======================= ";

        // Default constructor
        pandas::BooleanArray arr1;
        if (arr1.size() != 0) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_constructors() : default constructor size != 0" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_constructors failed: default constructor size != 0");
        }

        // Initializer list constructor
        pandas::BooleanArray arr2({
            std::optional<bool>(true),
            std::optional<bool>(false),
            std::nullopt,
            std::optional<bool>(true)

sp_index (pd_test_1_all.cpp:3207)

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

    void pd_test_sparse_array_sp_index_property() {
        std::cout << "========= SparseArray: sp_index property ======================= ";

        std::vector<numpy::float64> data = {0.0, 1.0, 0.0, 2.0, 0.0, 3.0};
        pandas::SparseArray<numpy::float64> arr(data, 0.0);

        const auto& sp_idx = arr.sp_index();
        if (sp_idx.getSize() != 3) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_sp_index_property() : sp_index size != 3" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_sp_index_property failed: sp_index size != 3");
        }

        if (sp_idx.getElementAt({0}) != 1 ||
            sp_idx.getElementAt({1}) != 3 ||
            sp_idx.getElementAt({2}) != 5) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_sp_index_property() : sp_index content mismatch" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_sp_index_property failed: sp_index content mismatch");

sp_values (pd_test_1_all.cpp:3185)

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

    void pd_test_sparse_array_sp_values_property() {
        std::cout << "========= SparseArray: sp_values property ======================= ";

        std::vector<numpy::float64> data = {0.0, 1.0, 0.0, 2.0, 0.0, 3.0};
        pandas::SparseArray<numpy::float64> arr(data, 0.0);

        const auto& sp_vals = arr.sp_values();
        if (sp_vals.getSize() != 3) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_sp_values_property() : sp_values size != 3" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_sp_values_property failed: sp_values size != 3");
        }

        if (sp_vals.getElementAt({0}) != 1.0 ||
            sp_vals.getElementAt({1}) != 2.0 ||
            sp_vals.getElementAt({2}) != 3.0) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_sp_values_property() : sp_values content mismatch" << std::endl;
            throw std::runtime_error("pd_test_sparse_array_sp_values_property failed: sp_values content mismatch");

sparsity (pd_test_1_all.cpp:3257)

        // 20% density (2 non-fill out of 10)
        std::vector<numpy::float64> data = {0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.0, 0.0};
        pandas::SparseArray<numpy::float64> arr(data, 0.0);

        double density = arr.density();
        if (std::abs(density - 0.2) > 0.001) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_density() : density != 0.2, got " << density << std::endl;
            throw std::runtime_error("pd_test_sparse_array_density failed: density != 0.2");
        }

        double sparsity = arr.sparsity();
        if (std::abs(sparsity - 0.8) > 0.001) {
            std::cout << "  [FAIL] : in pd_test_sparse_array_density() : sparsity != 0.8, got " << sparsity << std::endl;
            throw std::runtime_error("pd_test_sparse_array_density failed: sparsity != 0.8");
        }

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

    void pd_test_sparse_array_to_dense() {
        std::cout << "========= SparseArray: to_dense ======================= ";