StringArray

class pandas::StringArray

Extension array type for specialized data storage.

Example

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

// Use StringArray
StringArray obj;
// ... operations ...

Constructors

Signature	Location	Example
StringArray(const numpy::NDArray<numpy::vstring_>& data, const numpy::NDArray<numpy::bool_>& mask, bool copy = false)	pd_string_array.h:71
explicit StringArray(const numpy::NDArray<numpy::vstring_>& data)	pd_string_array.h:84
explicit StringArray(const std::vector<std::optional<std::string>>& values)	pd_string_array.h:115
explicit StringArray(const std::vector<std::string>& values)	pd_string_array.h:133

Construction

Signature	Return Type	Location	Example
static StringArray from_sequence(const std::vector<std::optional<std::string>>& scalars)	static StringArray	pd_string_array.h:330

Indexing / Selection

Signature	Return Type	Location	Example
std::string at(size_t index) const	std::string	pd_string_array.h:230	View
const numpy::NDArray<numpy::bool_>& mask() const	const numpy::NDArray<numpy::bool_>&	pd_string_array.h:210	View
StringArray take(const std::vector<size_t>& indices, bool allow_fill = false, std::optional<std::string> fill_value = std::nullopt) const	StringArray	pd_string_array.h:277	View

Data Manipulation

Signature	Return Type	Location	Example
StringArray dropna() const	StringArray	pd_string_array.h:380	View

Missing Data

Signature	Return Type	Location	Example
StringArray fillna(const std::string& value) const	StringArray	pd_string_array.h:366	View
numpy::NDArray<numpy::bool_> isna() const	numpy::NDArray<numpy::bool_>	pd_string_array.h:252	View
numpy::NDArray<numpy::bool_> notna() const	numpy::NDArray<numpy::bool_>	pd_string_array.h:259	View

Statistics

Signature	Return Type	Location	Example
size_t count() const	size_t	pd_string_array.h:411	View

Comparison

Signature	Return Type	Location	Example
size_t len() const	size_t	pd_string_array.h:192	View

Sorting

Signature	Return Type	Location	Example
numpy::NDArray<size_t> argsort(bool ascending = true, const std::string& na_position = "last") const	numpy::NDArray<size_t>	pd_string_array.h:702	View

Combining

Signature	Return Type	Location	Example
static StringArray concat(const std::vector<StringArray>& arrays)	static StringArray	pd_string_array.h:337	View

I/O

Signature	Return Type	Location	Example
numpy::NDArray<U> to_numpy(bool copy = true, U na_value = U{}) const	numpy::NDArray<U>	pd_string_array.h:394	View
std::string to_string() const	std::string	pd_string_array.h:1138	View

Conversion

Signature	Return Type	Location	Example
StringArray copy() const	StringArray	pd_string_array.h:270	View

Set Operations

Signature	Return Type	Location	Example
StringArray unique() const	StringArray	pd_string_array.h:635	View

Type Checking

Signature	Return Type	Location	Example
bool is_na(size_t index) const	bool	pd_string_array.h:241	View

Other Methods

Signature	Return Type	Location	Example
std::optional<bool> all(bool skipna = true) const	std::optional<bool>	pd_string_array.h:1087	View
std::optional<bool> any(bool skipna = true) const	std::optional<bool>	pd_string_array.h:1060	View
std::optional<size_t> argmax() const	std::optional<size_t>	pd_string_array.h:755	View
std::optional<size_t> argmin() const	std::optional<size_t>	pd_string_array.h:734	View
const numpy::NDArray<numpy::vstring_>& data() const	const numpy::NDArray<numpy::vstring_>&	pd_string_array.h:203	View
dtype_type dtype() const	dtype_type	pd_string_array.h:150	View
bool empty() const	bool	pd_string_array.h:185	View
std::pair<numpy::NDArray<numpy::int64>, StringArray> factorize() const	std::pair<numpy::NDArray<numpy::int64>, StringArray>	pd_string_array.h:662	View
bool has_na() const	bool	pd_string_array.h:424	View
size_t nbytes() const	size_t	pd_string_array.h:164	View
constexpr int ndim() const	constexpr int	pd_string_array.h:171	View
std::string repr() const	std::string	pd_string_array.h:1155	View
std::vector<size_t> shape() const	std::vector<size_t>	pd_string_array.h:178	View
size_t size() const	size_t	pd_string_array.h:157	View
StringArray str_cat(const StringArray& other, const std::string& sep = "") const	StringArray	pd_string_array.h:1010	View
StringArray str_cat(const std::string& suffix, const std::string& sep = "") const	StringArray	pd_string_array.h:1036	View
BooleanArray str_contains(const std::string& pat) const	BooleanArray	pd_string_array.h:942	View
BooleanArray str_endswith(const std::string& suffix) const	BooleanArray	pd_string_array.h:986	View
IntegerArray<numpy::int64> str_len() const	IntegerArray<numpy::int64>	pd_string_array.h:780	View
StringArray str_lower() const	StringArray	pd_string_array.h:798	View
StringArray str_lstrip() const	StringArray	pd_string_array.h:865	View
StringArray str_replace(const std::string& old_str, const std::string& new_str, int count = -1) const	StringArray	pd_string_array.h:910	View
StringArray str_rstrip() const	StringArray	pd_string_array.h:886	View
BooleanArray str_startswith(const std::string& prefix) const	BooleanArray	pd_string_array.h:963	View
StringArray str_strip() const	StringArray	pd_string_array.h:840	View
StringArray str_upper() const	StringArray	pd_string_array.h:819	View
void validate_arrays()	void	pd_string_array.h:1168

Internal Methods

1 internal methods (prefixed with underscore)

Code Examples

The following examples are extracted from the test suite.

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;

mask (pd_test_1_all.cpp:9119)

void pd_test_datetime_mixin_array_constructor() {
    std::cout << "========= DatetimeTDMixin array constructor =========================";

    // Create DatetimeArray with some values
    numpy::NDArray<numpy::datetime64> data(std::vector<size_t>{3});
    data.setElementAt({0}, numpy::datetime64(1000000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2001
    data.setElementAt({1}, numpy::datetime64(1500000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2017
    data.setElementAt({2}, numpy::datetime64(1600000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2020

    numpy::NDArray<numpy::bool_> mask(std::vector<size_t>{3});
    mask.setElementAt({0}, numpy::bool_(false));
    mask.setElementAt({1}, numpy::bool_(false));
    mask.setElementAt({2}, numpy::bool_(false));

    pandas::DatetimeArray arr(data, mask);
    pandas::DatetimeTDMixin idx(arr, "timestamps");

    bool passed = (idx.size() == 3 && !idx.empty() &&
                   idx.name().has_value() && *idx.name() == "timestamps" &&
                   idx.inferred_type() == "datetime");

take (pd_test_1_all.cpp:5903)

// Inherited Operations Tests
// ============================================================================

void pd_test_categorical_index_take() {
    std::cout << "========= inherited take ==============================";

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

    std::vector<size_t> indices = {0, 2, 3};
    pandas::ExtensionIndex<pandas::CategoricalArray> taken = idx.take(indices);

    bool passed = (taken.size() == 3);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_take()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_take failed");
    }

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

dropna (pd_test_1_all.cpp:531)

        }

        // 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");
        }

        // 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");

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 ======================= ";

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;

argsort (pd_test_1_all.cpp:1304)

        std::cout << "========= DatetimeArray: sorting ======================= ";

        pandas::DatetimeArray arr(std::vector<std::string>{
            "2023-06-15",
            "NaT",
            "2023-01-01",
            "2023-12-31"
        });

        // argsort ascending
        auto indices = arr.argsort(true, "last");
        // Expected order: 2023-01-01(2), 2023-06-15(0), 2023-12-31(3), NaT(1)
        if (indices.getElementAt({0}) != 2) {
            std::cout << "  [FAIL] : argsort: first should be index 2 (2023-01-01)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argsort first");
        }
        if (indices.getElementAt({3}) != 1) {
            std::cout << "  [FAIL] : argsort: last should be index 1 (NaT)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: NaT position");
        }

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_numpy (pd_test_1_all.cpp:16764)

        // =====================================================================
        // to_numpy Tests
        // =====================================================================

        void pd_test_ndframe_to_numpy() {
            std::cout << "========= to_numpy =============================================" << std::endl;

            pandas::Series<int> s({10, 20, 30});

            auto arr = s.to_numpy();

            bool passed = arr.getSize() == 3;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_ndframe_to_numpy() : size" << std::endl;
                throw std::runtime_error("pd_test_ndframe_to_numpy failed: size");
            }

            passed = arr.getElementAt({0}) == 10 && arr.getElementAt({1}) == 20 && arr.getElementAt({2}) == 30;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_ndframe_to_numpy() : values" << 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];

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;
}

unique (pd_test_1_all.cpp:1345)

        pandas::DatetimeArray arr(std::vector<std::string>{
            "2023-01-01",
            "2023-06-15",
            "2023-01-01",
            "NaT",
            "2023-06-15",
            "NaT"
        });

        // unique
        auto uniq = arr.unique();
        // Should have: NaT, 2023-01-01, 2023-06-15 (3 unique values)
        if (uniq.size() != 3) {
            std::cout << "  [FAIL] : unique size should be 3, got " << uniq.size() << std::endl;
            throw std::runtime_error("pd_test_datetime_array_unique failed: size");
        }

        // factorize
        auto [codes, uniques] = arr.factorize();
        // Codes for NaT should be -1
        if (codes.getElementAt({3}) != -1) {

is_na (pd_test_1_all.cpp:51)

    void pd_test_boolean_array_na_handling() {
        std::cout << "========= BooleanArray: NA handling ======================= ";

        pandas::BooleanArray arr({
            std::optional<bool>(true),
            std::nullopt,  // NA at index 1
            std::optional<bool>(false)
        });

        if (!arr.is_na(1)) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_na_handling() : is_na(1) should be true" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_na_handling failed: is_na(1) should be true");
        }

        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()) {

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");
        }

argmax (pd_test_1_all.cpp:1323)

        }

        // argmin
        auto min_idx = arr.argmin();
        if (!min_idx.has_value() || min_idx.value() != 2) {
            std::cout << "  [FAIL] : argmin should be 2 (2023-01-01)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argmin");
        }

        // argmax
        auto max_idx = arr.argmax();
        if (!max_idx.has_value() || max_idx.value() != 3) {
            std::cout << "  [FAIL] : argmax should be 3 (2023-12-31)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argmax");
        }

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

    void pd_test_datetime_array_unique() {
        std::cout << "========= DatetimeArray: unique/factorize ======================= ";

argmin (pd_test_1_all.cpp:1316)

        if (indices.getElementAt({0}) != 2) {
            std::cout << "  [FAIL] : argsort: first should be index 2 (2023-01-01)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argsort first");
        }
        if (indices.getElementAt({3}) != 1) {
            std::cout << "  [FAIL] : argsort: last should be index 1 (NaT)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: NaT position");
        }

        // argmin
        auto min_idx = arr.argmin();
        if (!min_idx.has_value() || min_idx.value() != 2) {
            std::cout << "  [FAIL] : argmin should be 2 (2023-01-01)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argmin");
        }

        // argmax
        auto max_idx = arr.argmax();
        if (!max_idx.has_value() || max_idx.value() != 3) {
            std::cout << "  [FAIL] : argmax should be 3 (2023-12-31)" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_sorting failed: argmax");

data (pd_test_1_all.cpp:9114)

        throw std::runtime_error("pd_test_datetime_mixin_default_constructor failed");
    }

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

void pd_test_datetime_mixin_array_constructor() {
    std::cout << "========= DatetimeTDMixin array constructor =========================";

    // Create DatetimeArray with some values
    numpy::NDArray<numpy::datetime64> data(std::vector<size_t>{3});
    data.setElementAt({0}, numpy::datetime64(1000000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2001
    data.setElementAt({1}, numpy::datetime64(1500000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2017
    data.setElementAt({2}, numpy::datetime64(1600000000000000000LL, numpy::DateTimeUnit::Nanosecond));  // ~2020

    numpy::NDArray<numpy::bool_> mask(std::vector<size_t>{3});
    mask.setElementAt({0}, numpy::bool_(false));
    mask.setElementAt({1}, numpy::bool_(false));
    mask.setElementAt({2}, numpy::bool_(false));

    pandas::DatetimeArray arr(data, mask);

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) {

factorize (pd_test_1_all.cpp:1353)

        // unique
        auto uniq = arr.unique();
        // Should have: NaT, 2023-01-01, 2023-06-15 (3 unique values)
        if (uniq.size() != 3) {
            std::cout << "  [FAIL] : unique size should be 3, got " << uniq.size() << std::endl;
            throw std::runtime_error("pd_test_datetime_array_unique failed: size");
        }

        // factorize
        auto [codes, uniques] = arr.factorize();
        // Codes for NaT should be -1
        if (codes.getElementAt({3}) != -1) {
            std::cout << "  [FAIL] : factorize: NaT code should be -1" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_unique failed: NaT code");
        }
        // Same values should have same codes
        if (codes.getElementAt({0}) != codes.getElementAt({2})) {
            std::cout << "  [FAIL] : factorize: 2023-01-01 values should have same code" << std::endl;
            throw std::runtime_error("pd_test_datetime_array_unique failed: same code");
        }

has_na (pd_test_1_all.cpp:61)

        if (!arr.is_na(1)) {
            std::cout << "  [FAIL] : in pd_test_boolean_array_na_handling() : is_na(1) should be true" << std::endl;
            throw std::runtime_error("pd_test_boolean_array_na_handling failed: is_na(1) should be true");
        }

        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;

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");
            }

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)

str_cat (pd_test_1_all.cpp:3822)

            std::nullopt,
            std::optional<std::string>("foo")
        });
        pandas::StringArray arr2({
            std::optional<std::string>("world"),
            std::optional<std::string>("test"),
            std::nullopt
        });

        // Array concatenation
        auto result = arr1.str_cat(arr2, " ");
        if (result[0].value() != "hello world") {
            std::cout << "  [FAIL] : str_cat: expected 'hello world'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_cat failed: array cat");
        }
        if (result[1].has_value()) {
            std::cout << "  [FAIL] : str_cat: NA + value should be NA" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_cat failed: NA + value");
        }
        if (result[2].has_value()) {
            std::cout << "  [FAIL] : str_cat: value + NA should be NA" << std::endl;

str_cat (pd_test_1_all.cpp:3822)

            std::nullopt,
            std::optional<std::string>("foo")
        });
        pandas::StringArray arr2({
            std::optional<std::string>("world"),
            std::optional<std::string>("test"),
            std::nullopt
        });

        // Array concatenation
        auto result = arr1.str_cat(arr2, " ");
        if (result[0].value() != "hello world") {
            std::cout << "  [FAIL] : str_cat: expected 'hello world'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_cat failed: array cat");
        }
        if (result[1].has_value()) {
            std::cout << "  [FAIL] : str_cat: NA + value should be NA" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_cat failed: NA + value");
        }
        if (result[2].has_value()) {
            std::cout << "  [FAIL] : str_cat: value + NA should be NA" << std::endl;

str_contains (pd_test_1_all.cpp:3768)

        std::cout << "========= StringArray: string predicates ======================= ";

        pandas::StringArray arr({
            std::optional<std::string>("hello world"),
            std::nullopt,
            std::optional<std::string>("python"),
            std::optional<std::string>("hello")
        });

        // str_contains
        auto contains = arr.str_contains("llo");
        if (!contains[0].has_value() || !contains[0].value()) {
            std::cout << "  [FAIL] : str_contains: 'hello world' contains 'llo'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: contains");
        }
        if (contains[1].has_value()) {
            std::cout << "  [FAIL] : str_contains: NA should propagate" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: contains NA");
        }
        if (!contains[2].has_value() || contains[2].value()) {
            std::cout << "  [FAIL] : str_contains: 'python' does not contain 'llo'" << std::endl;

str_endswith (pd_test_1_all.cpp:3794)

        if (!starts[0].has_value() || !starts[0].value()) {
            std::cout << "  [FAIL] : str_startswith: 'hello world' starts with 'hello'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: startswith");
        }
        if (!starts[2].has_value() || starts[2].value()) {
            std::cout << "  [FAIL] : str_startswith: 'python' does not start with 'hello'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: startswith python");
        }

        // str_endswith
        auto ends = arr.str_endswith("ld");
        if (!ends[0].has_value() || !ends[0].value()) {
            std::cout << "  [FAIL] : str_endswith: 'hello world' ends with 'ld'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: endswith");
        }
        if (!ends[2].has_value() || ends[2].value()) {
            std::cout << "  [FAIL] : str_endswith: 'python' does not end with 'ld'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: endswith python");
        }

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

str_len (pd_test_1_all.cpp:3728)

    void pd_test_string_array_str_len() {
        std::cout << "========= StringArray: str_len ======================= ";

        pandas::StringArray arr({
            std::optional<std::string>("abc"),
            std::nullopt,
            std::optional<std::string>("hello"),
            std::optional<std::string>("")
        });

        auto lengths = arr.str_len();

        auto len0 = lengths[0];
        if (!len0.has_value() || len0.value() != 3) {
            std::cout << "  [FAIL] : str_len[0] should be 3" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_len failed: len[0]");
        }

        auto len1 = lengths[1];
        if (len1.has_value()) {
            std::cout << "  [FAIL] : str_len[1] should be NA" << std::endl;

str_lower (pd_test_1_all.cpp:3681)

        if (upper[0].value() != "HELLO WORLD") {
            std::cout << "  [FAIL] : str_upper: expected 'HELLO WORLD'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_upper");
        }
        if (upper[1].has_value()) {
            std::cout << "  [FAIL] : str_upper: NA should propagate" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_upper NA");
        }

        // str_lower
        auto lower = arr.str_lower();
        if (lower[0].value() != "hello world") {
            std::cout << "  [FAIL] : str_lower: expected 'hello world'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_lower");
        }

        // str_strip
        auto stripped = arr.str_strip();
        if (stripped[2].value() != "spaced") {
            std::cout << "  [FAIL] : str_strip: expected 'spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_strip");

str_lstrip (pd_test_1_all.cpp:3695)

        }

        // str_strip
        auto stripped = arr.str_strip();
        if (stripped[2].value() != "spaced") {
            std::cout << "  [FAIL] : str_strip: expected 'spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_strip");
        }

        // str_lstrip
        auto lstripped = arr.str_lstrip();
        if (lstripped[2].value() != "spaced  ") {
            std::cout << "  [FAIL] : str_lstrip: expected 'spaced  '" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_lstrip");
        }

        // str_rstrip
        auto rstripped = arr.str_rstrip();
        if (rstripped[2].value() != "  spaced") {
            std::cout << "  [FAIL] : str_rstrip: expected '  spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_rstrip");

str_replace (pd_test_1_all.cpp:3709)

        }

        // str_rstrip
        auto rstripped = arr.str_rstrip();
        if (rstripped[2].value() != "  spaced") {
            std::cout << "  [FAIL] : str_rstrip: expected '  spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_rstrip");
        }

        // str_replace
        auto replaced = arr.str_replace("World", "Universe");
        if (replaced[0].value() != "Hello Universe") {
            std::cout << "  [FAIL] : str_replace: expected 'Hello Universe'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_replace");
        }

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

    void pd_test_string_array_str_len() {
        std::cout << "========= StringArray: str_len ======================= ";

str_rstrip (pd_test_1_all.cpp:3702)

        }

        // str_lstrip
        auto lstripped = arr.str_lstrip();
        if (lstripped[2].value() != "spaced  ") {
            std::cout << "  [FAIL] : str_lstrip: expected 'spaced  '" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_lstrip");
        }

        // str_rstrip
        auto rstripped = arr.str_rstrip();
        if (rstripped[2].value() != "  spaced") {
            std::cout << "  [FAIL] : str_rstrip: expected '  spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_rstrip");
        }

        // str_replace
        auto replaced = arr.str_replace("World", "Universe");
        if (replaced[0].value() != "Hello Universe") {
            std::cout << "  [FAIL] : str_replace: expected 'Hello Universe'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_replace");

str_startswith (pd_test_1_all.cpp:3783)

        if (contains[1].has_value()) {
            std::cout << "  [FAIL] : str_contains: NA should propagate" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: contains NA");
        }
        if (!contains[2].has_value() || contains[2].value()) {
            std::cout << "  [FAIL] : str_contains: 'python' does not contain 'llo'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: contains python");
        }

        // str_startswith
        auto starts = arr.str_startswith("hello");
        if (!starts[0].has_value() || !starts[0].value()) {
            std::cout << "  [FAIL] : str_startswith: 'hello world' starts with 'hello'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: startswith");
        }
        if (!starts[2].has_value() || starts[2].value()) {
            std::cout << "  [FAIL] : str_startswith: 'python' does not start with 'hello'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_predicates failed: startswith python");
        }

        // str_endswith

str_strip (pd_test_1_all.cpp:3688)

        }

        // str_lower
        auto lower = arr.str_lower();
        if (lower[0].value() != "hello world") {
            std::cout << "  [FAIL] : str_lower: expected 'hello world'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_lower");
        }

        // str_strip
        auto stripped = arr.str_strip();
        if (stripped[2].value() != "spaced") {
            std::cout << "  [FAIL] : str_strip: expected 'spaced'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_strip");
        }

        // str_lstrip
        auto lstripped = arr.str_lstrip();
        if (lstripped[2].value() != "spaced  ") {
            std::cout << "  [FAIL] : str_lstrip: expected 'spaced  '" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_lstrip");

str_upper (pd_test_1_all.cpp:3670)

    void pd_test_string_array_str_methods() {
        std::cout << "========= StringArray: string methods ======================= ";

        pandas::StringArray arr({
            std::optional<std::string>("Hello World"),
            std::nullopt,
            std::optional<std::string>("  spaced  ")
        });

        // str_upper
        auto upper = arr.str_upper();
        if (upper[0].value() != "HELLO WORLD") {
            std::cout << "  [FAIL] : str_upper: expected 'HELLO WORLD'" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_upper");
        }
        if (upper[1].has_value()) {
            std::cout << "  [FAIL] : str_upper: NA should propagate" << std::endl;
            throw std::runtime_error("pd_test_string_array_str_methods failed: str_upper NA");
        }

        // str_lower