ExtensionIndex

class pandas::ExtensionIndex

Index class for axis labels in pandas data structures.

Example

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

// Create ExtensionIndex
ExtensionIndex<int64_t> idx({1, 2, 3}, "my_index");
size_t len = idx.size();

Constructors

Signature	Location	Example
explicit ExtensionIndex(const ArrayType& array, const std::optional<std::string>& name = std::nullopt, bool copy = false)	pd_extension_index.h:350
explicit ExtensionIndex(ArrayType&& array, const std::optional<std::string>& name = std::nullopt)	pd_extension_index.h:361
ExtensionIndex(const ExtensionIndex& other)	pd_extension_index.h:371
ExtensionIndex(ExtensionIndex&& other) noexcept = default	pd_extension_index.h:385

Indexing / Selection

Signature	Return Type	Location	Example
numpy::NDArray<numpy::int64> get_indexer( const ExtensionIndex<ArrayType>& target, const std::string& method = "", std::optional<int> limit = std::nullopt, std::optional<value_type> tolerance = std::nullopt) const	numpy::NDArray<numpy::int64>	pd_extension_index.h:709	View
numpy::NDArray<numpy::int64> get_indexer_for( const std::vector<value_type>& values, const std::vector<value_type>\* target = nullptr) const	numpy::NDArray<numpy::int64>	pd_extension_index.h:747	View
std::variant<size_t, std::vector<size_t>> get_loc(const value_type& key) const	std::variant<size_t, std::vector<size_t>>	pd_extension_index.h:687	View
int64_t get_loc_str(const std::string& key_str) const override	int64_t	pd_extension_index.h:525	View
std::optional<size_t> get_loc_string(const std::string& key) const override	std::optional<size_t>	pd_extension_index.h:547	View
std::string get_value_str(size_t index) const override	std::string	pd_extension_index.h:572	View
oss << get_value_str(i)	oss <<	pd_extension_index.h:607	View
ExtensionIndex take(const std::vector<size_t>& indices, int axis = 0, bool allow_fill = false, std::optional<value_type> fill_value = std::nullopt) const	ExtensionIndex	pd_extension_index.h:838	View
ExtensionIndex take_impl(const std::vector<size_t>& indices) const	ExtensionIndex	pd_extension_index.h:1569

Data Manipulation

Signature	Return Type	Location	Example
ExtensionIndex drop(const std::vector<value_type>& labels, const std::string& errors = "raise") const	ExtensionIndex	pd_extension_index.h:895	View
ExtensionIndex drop_duplicates(const std::string& keep = "first") const	ExtensionIndex	pd_extension_index.h:1020	View
ExtensionIndex dropna() const	ExtensionIndex	pd_extension_index.h:822	View
ExtensionIndex rename(const std::optional<std::string>& new_name) const	ExtensionIndex	pd_extension_index.h:982	View

Missing Data

Signature	Return Type	Location	Example
ExtensionIndex fillna(const value_type& value, const std::string& downcast = "") const	ExtensionIndex	pd_extension_index.h:812	View
numpy::NDArray<numpy::bool_> isna() const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:774	View
numpy::NDArray<numpy::bool_> isnull() const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:781	View
numpy::NDArray<numpy::bool_> notna() const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:788	View
numpy::NDArray<numpy::bool_> notnull() const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:795	View

Statistics

Signature	Return Type	Location	Example
size_t nunique(bool dropna = true) const	size_t	pd_extension_index.h:1128	View
std::pair<std::vector<value_type>, std::vector<int64_t>> value_counts( bool dropna = true, bool ascending = false, const int\* bins = nullptr, bool normalize = false, bool sort = true) const	std::pair<std::vector<value_type>, std::vector<int64_t>>	pd_extension_index.h:1142	View

Comparison

Signature	Return Type	Location	Example
bool equals(const ExtensionIndex& other) const	bool	pd_extension_index.h:1489	View
ArrayType new_array(values)	ArrayType	pd_extension_index.h:1587

Sorting

Signature	Return Type	Location	Example
numpy::NDArray<numpy::int64> argsort(bool ascending = true) const	numpy::NDArray<numpy::int64>	pd_extension_index.h:1385	View
ExtensionIndex sort_values(bool ascending = true, const std::string& na_position = "last", bool return_indexer = false, std::nullptr_t key = nullptr) const	ExtensionIndex	pd_extension_index.h:1428	View

Combining

Signature	Return Type	Location	Example
ExtensionIndex append(const ExtensionIndex& other) const	ExtensionIndex	pd_extension_index.h:1210	View

Time Series

Signature	Return Type	Location	Example
ExtensionIndex difference(const ExtensionIndex& other, bool sort = true) const	ExtensionIndex	pd_extension_index.h:1311	View

I/O

Signature	Return Type	Location	Example
std::vector<std::optional<value_type>> to_list() const	std::vector<std::optional<value_type>>	pd_extension_index.h:658	View
std::string to_string() const override	std::string	pd_extension_index.h:600	View
std::vector<std::string> to_string_vector() const override	std::vector<std::string>	pd_extension_index.h:560	View

Conversion

Signature	Return Type	Location	Example
ExtensionIndex copy() const	ExtensionIndex	pd_extension_index.h:975	View

Set Operations

Signature	Return Type	Location	Example
numpy::NDArray<numpy::bool_> duplicated(const std::string& keep = "first") const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:1069	View
ExtensionIndex intersection(const ExtensionIndex& other, bool sort = false) const	ExtensionIndex	pd_extension_index.h:1218	View
numpy::NDArray<numpy::bool_> isin(const std::vector<value_type>& values, std::optional<int> level = std::nullopt) const	numpy::NDArray<numpy::bool_>	pd_extension_index.h:870	View
ExtensionIndex symmetric_difference(const ExtensionIndex& other, bool sort = false, const std::string\* result_name = nullptr) const	ExtensionIndex	pd_extension_index.h:1339	View
ExtensionIndex union_(const ExtensionIndex& other, bool sort = false) const	ExtensionIndex	pd_extension_index.h:1251	View
ExtensionIndex unique(std::optional<int> level = std::nullopt) const	ExtensionIndex	pd_extension_index.h:992	View

Type Checking

Signature	Return Type	Location	Example
bool is_monotonic_decreasing() const	bool	pd_extension_index.h:1371	View
bool is_monotonic_increasing() const	bool	pd_extension_index.h:1361	View
bool is_unique() const override	bool	pd_extension_index.h:481	View

Other Methods

Signature	Return Type	Location	Example
const ArrayType& array() const	const ArrayType&	pd_extension_index.h:651	View
void build_hash_table() const	void	pd_extension_index.h:209
size_t cache_memory_usage() const override	size_t	pd_extension_index.h:1548
void clear_cache() const override	void	pd_extension_index.h:1526	View
std::unique_ptr<IndexBase> clone() const override	std::unique_ptr<IndexBase>	pd_extension_index.h:589	View
void compute_monotonicity() const	void	pd_extension_index.h:295
bool contains(const value_type& key) const	bool	pd_extension_index.h:676	View
bool contains_str(const std::string& key_str) const override	bool	pd_extension_index.h:513	View
value_type convert_from_string(const std::string& str) const	value_type	pd_extension_index.h:236
std::string convert_to_string(const value_type& val) const	std::string	pd_extension_index.h:274
ExtensionIndex delete_(size_t loc) const	ExtensionIndex	pd_extension_index.h:937	View
ExtensionIndex delete_(const std::vector<size_t>& locs) const	ExtensionIndex	pd_extension_index.h:955	View
std::string dtype_name() const override	std::string	pd_extension_index.h:437	View
bool empty() const override	bool	pd_extension_index.h:423	View
void ensure_hash_table() const	void	pd_extension_index.h:227
std::pair<numpy::NDArray<numpy::int64>, ExtensionIndex> factorize() const	std::pair<numpy::NDArray<numpy::int64>, ExtensionIndex>	pd_extension_index.h:1169	View
bool has_cached_values() const override	bool	pd_extension_index.h:1535	View
bool has_duplicates() const override	bool	pd_extension_index.h:499	View
bool hasnans() const	bool	pd_extension_index.h:802	View
bool identical(const ExtensionIndex& other) const	bool	pd_extension_index.h:1512	View
std::string inferred_type() const override	std::string	pd_extension_index.h:458	View
void invalidate_caches() const	void	pd_extension_index.h:196
std::optional<std::string> name() const override	std::optional<std::string>	pd_extension_index.h:444	View
size_t nbytes() const override	size_t	pd_extension_index.h:430	View
std::string repr() const override	std::string	pd_extension_index.h:626	View
ExtensionIndex result(\*this)	ExtensionIndex	pd_extension_index.h:983	View
void set_name(const std::optional<std::string>& name) override	void	pd_extension_index.h:451	View
size_t size() const override	size_t	pd_extension_index.h:416	View
IndexTypeId type_id() const override	IndexTypeId	pd_extension_index.h:593	View
ArrayType values() const	ArrayType	pd_extension_index.h:644	View

Code Examples

The following examples are extracted from the test suite.

get_indexer (pd_test_1_all.cpp:10332)

void pd_test_extension_index_get_indexer() {
    std::cout << "========= get_indexer =========================";

    pandas::CategoricalArray arr1({"a", "b", "c", "d"});
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"b", "d", "x"});
    pandas::CategoricalIndex idx2(arr2);

    auto indexer = idx1.get_indexer(idx2);

    bool passed = (indexer.getSize() == 3 &&
                   indexer.getElementAt({0}) == 1 &&
                   indexer.getElementAt({1}) == 3 &&
                   indexer.getElementAt({2}) == -1);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_get_indexer() : get_indexer check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_get_indexer failed");
    }

get_indexer_for (pd_test_3_all.cpp:716)

// ============================================================================
// Category 6: Index Indexer Methods
// ============================================================================

void pd_test_3_all_index_indexers() {
    std::cout << "========= Index.get_indexer_for/non_unique/slice_indexer() ";

    std::vector<std::string> vals = {"a", "b", "c", "d", "e"};
    pandas::Index<std::string> idx(vals);

    // Test get_indexer_for()
    std::vector<std::string> target = {"b", "d", "f"};  // "f" doesn't exist
    numpy::NDArray<numpy::int64> indexer = idx.get_indexer_for(target);
    if (indexer.getSize() != 3) {
        std::cout << "  [FAIL] : in pd_test_3_all_index_indexers() : get_indexer_for size mismatch" << std::endl;
        throw std::runtime_error("pd_test_3_all_index_indexers failed: get_indexer_for size");
    }
    // "b" is at index 1
    if (indexer.getElementAt({0}) != 1) {
        std::cout << "  [FAIL] : in pd_test_3_all_index_indexers() : 'b' should be at index 1" << std::endl;
        throw std::runtime_error("pd_test_3_all_index_indexers failed: 'b' index");

get_loc (pd_test_1_all.cpp:10281)

    bool passed = (idx.contains("apple") && idx.contains("banana") && !idx.contains("grape"));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_contains() : contains check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_contains failed");
    }

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

void pd_test_extension_index_get_loc_unique() {
    std::cout << "========= get_loc (unique) =========================";

    pandas::CategoricalArray arr({"apple", "banana", "cherry"});
    pandas::CategoricalIndex idx(arr);

    auto loc_apple = idx.get_loc("apple");
    auto loc_banana = idx.get_loc("banana");
    auto loc_cherry = idx.get_loc("cherry");

    bool passed = (std::holds_alternative<size_t>(loc_apple) && std::get<size_t>(loc_apple) == 0 &&
                   std::get<size_t>(loc_banana) == 1 &&

get_loc_str (pd_test_1_all.cpp:10890)

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

void pd_test_extension_index_contains_str_get_loc_str() {
    std::cout << "========= contains_str/get_loc_str =========================";

    pandas::CategoricalArray arr({"apple", "banana", "cherry"});
    pandas::CategoricalIndex idx(arr);

    bool passed = (idx.contains_str("apple") && !idx.contains_str("grape") &&
                   idx.get_loc_str("banana") == 1 && idx.get_loc_str("grape") == -1);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_contains_str_get_loc_str() : contains_str/get_loc_str check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_contains_str_get_loc_str failed");
    }

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

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

get_loc_string (pd_test_3_all.cpp:28108)

        vals.push_back(numpy::timedelta64(ns, numpy::DateTimeUnit::Nanosecond));
    }
    return pandas::TimedeltaArray(vals);
}

void pd_test_getitem_timedelta_str_lookup() {
    std::cout << "  -- pd_test_getitem_timedelta_str_lookup --" << std::endl;
    int fail = 0;
    auto tda = ge_make_tda({1 * GE_NS_PER_DAY, 2 * GE_NS_PER_DAY, 3 * GE_NS_PER_DAY});
    pandas::TimedeltaIndex tdi(tda);
    auto pos = tdi.get_loc_string("2 days");
    if (!pos.has_value()) { std::cout << "    FAIL: '2 days' not found" << std::endl; fail++; }
    else if (*pos != 1) { std::cout << "    FAIL: expected pos=1, got " << *pos << std::endl; fail++; }
    if (fail == 0) std::cout << "    OK" << std::endl;
    if (fail) throw std::runtime_error("pd_test_getitem_timedelta_str_lookup failed");
}

void pd_test_getitem_timedelta_str_not_found() {
    std::cout << "  -- pd_test_getitem_timedelta_str_not_found --" << std::endl;
    int fail = 0;
    auto tda = ge_make_tda({1 * GE_NS_PER_DAY});

get_value_str (pd_test_1_all.cpp:4665)

            auto corr_df = df.corr();

            // Check dimensions
            bool passed = corr_df.nrows() == 2 && corr_df.ncols() == 2;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_aggregation_dataframe_corr() : corr should be 2x2" << std::endl;
                throw std::runtime_error("pd_test_aggregation_dataframe_corr failed: corr should be 2x2");
            }

            // Diagonal should be 1.0
            std::string aa = corr_df["A"].get_value_str(0);
            passed = std::abs(std::stod(aa) - 1.0) < 0.001;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_aggregation_dataframe_corr() : diagonal should be 1.0" << std::endl;
                throw std::runtime_error("pd_test_aggregation_dataframe_corr failed: diagonal should be 1.0");
            }

            // A-B correlation should be 1.0 (perfect correlation)
            std::string ab = corr_df["B"].get_value_str(0);
            passed = std::abs(std::stod(ab) - 1.0) < 0.001;
            if (!passed) {

get_value_str (pd_test_1_all.cpp:4665)

            auto corr_df = df.corr();

            // Check dimensions
            bool passed = corr_df.nrows() == 2 && corr_df.ncols() == 2;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_aggregation_dataframe_corr() : corr should be 2x2" << std::endl;
                throw std::runtime_error("pd_test_aggregation_dataframe_corr failed: corr should be 2x2");
            }

            // Diagonal should be 1.0
            std::string aa = corr_df["A"].get_value_str(0);
            passed = std::abs(std::stod(aa) - 1.0) < 0.001;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_aggregation_dataframe_corr() : diagonal should be 1.0" << std::endl;
                throw std::runtime_error("pd_test_aggregation_dataframe_corr failed: diagonal should be 1.0");
            }

            // A-B correlation should be 1.0 (perfect correlation)
            std::string ab = corr_df["B"].get_value_str(0);
            passed = std::abs(std::stod(ab) - 1.0) < 0.001;
            if (!passed) {

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;
}

drop (pd_test_1_all.cpp:6558)

            if (df.ncols() != 2) {
                std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : pop ncols != 2" << std::endl;
                throw std::runtime_error("pd_test_dataframe_manipulation failed: pop ncols != 2");
            }
            if (!popped) {
                std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : popped is null" << std::endl;
                throw std::runtime_error("pd_test_dataframe_manipulation failed: popped is null");
            }

            // Test drop columns
            auto dropped = df.drop(std::vector<std::string>{"B"}, 1);
            if (dropped.ncols() != 1) {
                std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : drop ncols != 1" << std::endl;
                throw std::runtime_error("pd_test_dataframe_manipulation failed: drop ncols != 1");
            }

            // Test rename
            auto renamed = df.rename_columns(std::map<std::string, std::string>{{"A", "X"}});
            if (!renamed.has_column("X")) {
                std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : rename failed" << std::endl;
                throw std::runtime_error("pd_test_dataframe_manipulation failed: rename failed");

drop_duplicates (pd_test_1_all.cpp:6639)

                }
            }

            // Test drop_duplicates
            {
                std::map<std::string, std::vector<numpy::int64>> dup_data;
                dup_data["A"] = {1, 1, 2, 2};
                dup_data["B"] = {1, 1, 2, 3};
                pandas::DataFrame df_dup(dup_data);

                auto deduped = df_dup.drop_duplicates();
                // Rows 0 and 1 are duplicates (A=1, B=1), so should have 3 rows
                if (deduped.nrows() != 3) {
                    std::cout << "  [FAIL] : in pd_test_dataframe_manipulation() : drop_duplicates nrows != 3, got " << deduped.nrows() << std::endl;
                    throw std::runtime_error("pd_test_dataframe_manipulation failed: drop_duplicates");
                }
            }

            // Test assign
            {
                std::map<std::string, std::vector<numpy::int64>> assign_data;

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");

rename (pd_test_1_all.cpp:5816)

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

void pd_test_categorical_index_rename() {
    std::cout << "========= rename ======================================";

    pandas::CategoricalArray arr({"x", "y"});
    pandas::CategoricalIndex idx(arr, "old_name");

    pandas::CategoricalIndex renamed = idx.rename("new_name");

    bool passed = (renamed.name().has_value() && *renamed.name() == "new_name" &&
                   renamed.size() == idx.size() && renamed.categories() == idx.categories());
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_rename()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_rename failed");
    }

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

isnull (pd_test_3_all.cpp:671)

// Category 5: Index Null Detection
// ============================================================================

void pd_test_3_all_index_null_detection() {
    std::cout << "========= Index.isnull/notnull() =====================";

    // Test with float index (can have NaN)
    std::vector<double> vals = {1.0, std::nan(""), 3.0, std::nan("")};
    pandas::Index<double> idx(vals);

    numpy::NDArray<numpy::bool_> isnull_result = idx.isnull();
    if (isnull_result.getSize() != 4) {
        std::cout << "  [FAIL] : in pd_test_3_all_index_null_detection() : isnull() size mismatch" << std::endl;
        throw std::runtime_error("pd_test_3_all_index_null_detection failed: isnull() size");
    }
    // Index 0: 1.0 -> not null
    if (isnull_result.getElementAt({0})) {
        std::cout << "  [FAIL] : in pd_test_3_all_index_null_detection() : index 0 should not be null" << std::endl;
        throw std::runtime_error("pd_test_3_all_index_null_detection failed: index 0");
    }
    // Index 1: NaN -> null

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};

notnull (pd_test_3_all.cpp:665)

    }

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

// ============================================================================
// Category 5: Index Null Detection
// ============================================================================

void pd_test_3_all_index_null_detection() {
    std::cout << "========= Index.isnull/notnull() =====================";

    // Test with float index (can have NaN)
    std::vector<double> vals = {1.0, std::nan(""), 3.0, std::nan("")};
    pandas::Index<double> idx(vals);

    numpy::NDArray<numpy::bool_> isnull_result = idx.isnull();
    if (isnull_result.getSize() != 4) {
        std::cout << "  [FAIL] : in pd_test_3_all_index_null_detection() : isnull() size mismatch" << std::endl;
        throw std::runtime_error("pd_test_3_all_index_null_detection failed: isnull() size");
    }

nunique (pd_test_1_all.cpp:10604)

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

void pd_test_extension_index_nunique() {
    std::cout << "========= nunique =========================";

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

    bool passed = (idx.nunique(true) == 3 && idx.nunique(false) == 4);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_nunique() : nunique check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_nunique failed");
    }

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

void pd_test_extension_index_factorize() {
    std::cout << "========= factorize =========================";

value_counts (pd_test_1_all.cpp:865)

        std::vector<std::optional<std::string>> values = {
            std::optional<std::string>("a"),
            std::optional<std::string>("b"),
            std::optional<std::string>("a"),
            std::optional<std::string>("a"),
            std::optional<std::string>("b"),
            std::nullopt  // NA not counted
        };
        pandas::CategoricalArray arr(values);

        auto [cats, counts] = arr.value_counts();

        // Should have 2 categories
        if (cats.size() != 2 || counts.size() != 2) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_value_counts() : wrong size" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_value_counts failed: wrong size");
        }

        // Find 'a' count
        int64_t a_count = 0, b_count = 0;
        for (size_t i = 0; i < cats.size(); ++i) {

equals (pd_test_1_all.cpp:5866)

    std::cout << "========= equals ======================================";

    pandas::CategoricalArray arr1({"a", "b", "a"});
    pandas::CategoricalArray arr2({"a", "b", "a"});
    pandas::CategoricalArray arr3({"a", "b", "c"});

    pandas::CategoricalIndex idx1(arr1);
    pandas::CategoricalIndex idx2(arr2);
    pandas::CategoricalIndex idx3(arr3);

    bool passed = (idx1.equals(idx2) && !idx1.equals(idx3));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_equals()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_equals failed");
    }

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

void pd_test_categorical_index_identical() {
    std::cout << "========= identical ===================================";

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");
        }

sort_values (pd_test_1_all.cpp:6408)

        void pd_test_dataframe_sorting() {
            std::cout << "========= sorting ==========================";

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

            pandas::DataFrame df(data);

            // Test sort_values ascending
            auto sorted_asc = df.sort_values("A", true);
            // First value should be smallest (1.0)
            std::string first_val = sorted_asc["A"].get_value_str(0);
            if (std::stod(first_val) != 1.0) {
                std::cout << "  [FAIL] : in pd_test_dataframe_sorting() : sort_values asc first != 1" << std::endl;
                throw std::runtime_error("pd_test_dataframe_sorting failed: sort_values asc first != 1");
            }

            // Test sort_values descending
            auto sorted_desc = df.sort_values("A", false);
            first_val = sorted_desc["A"].get_value_str(0);

append (pd_test_1_all.cpp:10650)

    std::cout << "========= append =========================";

    // Use same categories for both arrays (required by CategoricalArray::concat)
    std::vector<std::string> cats = {"a", "b", "c", "d"};
    pandas::CategoricalArray arr1({"a", "b"}, cats);
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"c", "d"}, cats);
    pandas::CategoricalIndex idx2(arr2);

    auto appended = idx1.append(idx2);

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

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

difference (pd_test_1_all.cpp:10718)

    std::cout << "========= difference =========================";

    // Use same categories for both arrays
    std::vector<std::string> cats = {"a", "b", "c", "d"};
    pandas::CategoricalArray arr1({"a", "b", "c", "d"}, cats);
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"b", "d"}, cats);
    pandas::CategoricalIndex idx2(arr2);

    auto diff = idx1.difference(idx2);

    bool passed = (diff.size() == 2 &&
                   diff.contains("a") && diff.contains("c") &&
                   !diff.contains("b") && !diff.contains("d"));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_difference() : difference check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_difference failed");
    }

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

to_list (pd_test_1_all.cpp:10247)

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

void pd_test_extension_index_to_list() {
    std::cout << "========= to_list =========================";

    pandas::CategoricalArray arr({"x", "y", "z"});
    pandas::CategoricalIndex idx(arr);

    auto list = idx.to_list();

    bool passed = (list.size() == 3 &&
                   list[0].has_value() && *list[0] == "x" &&
                   list[1].has_value() && *list[1] == "y" &&
                   list[2].has_value() && *list[2] == "z");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_to_list() : to_list check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_to_list failed");
    }

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];

to_string_vector (pd_test_1_all.cpp:10871)

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

void pd_test_extension_index_to_string_vector() {
    std::cout << "========= to_string_vector =========================";

    pandas::CategoricalArray arr({"a", std::nullopt, "c"});
    pandas::CategoricalIndex idx(arr);

    auto str_vec = idx.to_string_vector();

    bool passed = (str_vec.size() == 3 &&
                   str_vec[0] == "a" && str_vec[1] == "NA" && str_vec[2] == "c");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_to_string_vector() : to_string_vector check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_to_string_vector failed");
    }

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

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;
}

duplicated (pd_test_1_all.cpp:10583)

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

void pd_test_extension_index_duplicated() {
    std::cout << "========= duplicated =========================";

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

    auto dup_mask = idx.duplicated("first");

    bool passed = (dup_mask.getElementAt({0}) == false &&
                   dup_mask.getElementAt({1}) == false &&
                   dup_mask.getElementAt({2}) == true &&
                   dup_mask.getElementAt({3}) == false &&
                   dup_mask.getElementAt({4}) == true);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_duplicated() : duplicated check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_duplicated failed");
    }

intersection (pd_test_1_all.cpp:10672)

    std::cout << "========= intersection =========================";

    // Use same categories for both arrays
    std::vector<std::string> cats = {"a", "b", "c", "d", "e", "f"};
    pandas::CategoricalArray arr1({"a", "b", "c", "d"}, cats);
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"b", "c", "e", "f"}, cats);
    pandas::CategoricalIndex idx2(arr2);

    auto inter = idx1.intersection(idx2);

    bool passed = (inter.size() == 2 && inter.contains("b") && inter.contains("c"));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_intersection() : intersection check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_intersection failed");
    }

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

isin (pd_test_1_all.cpp:5938)

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

void pd_test_categorical_index_isin() {
    std::cout << "========= inherited isin ==============================";

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

    std::vector<std::string> values = {"a", "c"};
    numpy::NDArray<numpy::bool_> mask = idx.isin(values);

    bool passed = (mask.getSize() == 4 &&
                   mask.getElementAt({0}) == true &&   // a
                   mask.getElementAt({1}) == false &&  // b
                   mask.getElementAt({2}) == true &&   // c
                   mask.getElementAt({3}) == false);   // d
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_isin()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_isin failed");
    }

symmetric_difference (pd_test_1_all.cpp:10742)

    std::cout << "========= symmetric_difference =========================";

    // Use same categories for both arrays
    std::vector<std::string> cats = {"a", "b", "c", "d"};
    pandas::CategoricalArray arr1({"a", "b", "c"}, cats);
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"b", "c", "d"}, cats);
    pandas::CategoricalIndex idx2(arr2);

    auto sym_diff = idx1.symmetric_difference(idx2);

    bool passed = (sym_diff.size() == 2 &&
                   sym_diff.contains("a") && sym_diff.contains("d") &&
                   !sym_diff.contains("b") && !sym_diff.contains("c"));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_symmetric_difference() : symmetric_difference check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_symmetric_difference failed");
    }

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

union_ (pd_test_1_all.cpp:10694)

    std::cout << "========= union =========================";

    // Use same categories for both arrays
    std::vector<std::string> cats = {"a", "b", "c", "d", "e"};
    pandas::CategoricalArray arr1({"a", "b", "c"}, cats);
    pandas::CategoricalIndex idx1(arr1);

    pandas::CategoricalArray arr2({"b", "c", "d", "e"}, cats);
    pandas::CategoricalIndex idx2(arr2);

    auto uni = idx1.union_(idx2);

    bool passed = (uni.size() == 5 &&
                   uni.contains("a") && uni.contains("b") && uni.contains("c") &&
                   uni.contains("d") && uni.contains("e"));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_union() : union check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_union 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_monotonic_decreasing (pd_test_1_all.cpp:10203)

}

void pd_test_extension_index_monotonicity() {
    std::cout << "========= monotonicity =========================";

    pandas::CategoricalArray arr1({"a", "b", "c"});
    pandas::CategoricalIndex idx1(arr1);

    // Just test that the methods work (result depends on internal ordering)
    bool inc = idx1.is_monotonic_increasing();
    bool dec = idx1.is_monotonic_decreasing();

    bool passed = (inc || dec || (!inc && !dec));  // Any result is valid
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_monotonicity() : monotonicity check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_monotonicity failed");
    }

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

is_monotonic_increasing (pd_test_1_all.cpp:10202)

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

void pd_test_extension_index_monotonicity() {
    std::cout << "========= monotonicity =========================";

    pandas::CategoricalArray arr1({"a", "b", "c"});
    pandas::CategoricalIndex idx1(arr1);

    // Just test that the methods work (result depends on internal ordering)
    bool inc = idx1.is_monotonic_increasing();
    bool dec = idx1.is_monotonic_decreasing();

    bool passed = (inc || dec || (!inc && !dec));  // Any result is valid
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_monotonicity() : monotonicity check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_monotonicity failed");
    }

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

is_unique (pd_test_1_all.cpp:5962)

void pd_test_categorical_index_is_unique() {
    std::cout << "========= inherited is_unique =========================";

    pandas::CategoricalArray arr_unique({"a", "b", "c"});
    pandas::CategoricalArray arr_dups({"a", "b", "a"});

    pandas::CategoricalIndex idx_unique(arr_unique);
    pandas::CategoricalIndex idx_dups(arr_dups);

    bool passed = (idx_unique.is_unique() && !idx_dups.is_unique());
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_is_unique()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_is_unique failed");
    }

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

void pd_test_categorical_index_hasnans() {
    std::cout << "========= inherited hasnans ===========================";

array (pd_test_1_all.cpp:7343)

    };
    pandas::DatetimeIndex idx(values, "with_nat");

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

    // Check that middle element is NA
    bool has_na = idx.array().is_na(1);
    passed = passed && has_na;
    if (!passed) {
        std::cout << "  [FAIL] : NA not preserved" << std::endl;
        throw std::runtime_error("pd_test_datetime_index_optional_vector_constructor failed");
    }

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

void pd_test_datetime_index_copy_constructor() {

clear_cache (pd_test_1_all.cpp:19413)

            s.mean();
            s.min();
            s.max();

            passed = s.has_cached_values() == true;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_series_cache() : cache not populated" << std::endl;
                throw std::runtime_error("pd_test_series_cache failed: cache not populated");
            }

            s.clear_cache();
            passed = s.has_cached_values() == false;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_series_cache() : cache not cleared" << std::endl;
                throw std::runtime_error("pd_test_series_cache failed: cache not cleared");
            }

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

        void pd_test_series_string_repr() {

clone (pd_test_1_all.cpp:5776)

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

void pd_test_categorical_index_clone() {
    std::cout << "========= clone =======================================";

    pandas::CategoricalArray arr({"p", "q", "r"});
    pandas::CategoricalIndex idx(arr, "original");

    std::unique_ptr<pandas::IndexBase> cloned = idx.clone();

    bool passed = (cloned != nullptr && cloned->size() == idx.size() &&
                   cloned->name() == idx.name());
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_clone()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_clone failed");
    }

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

contains (pd_test_1_all.cpp:2200)

// Test: contains method
// ============================================================================
void test_contains() {
    std::cout << "========= IntervalArray: contains ======================= ";

    std::vector<numpy::float64> breaks = {0.0, 1.0, 2.0, 3.0};

    // Right-closed intervals: (0, 1], (1, 2], (2, 3]
    auto arr_right = pandas::IntervalArrayFloat64::from_breaks(breaks, pandas::IntervalClosed::Right);

    // Test contains(1.0) - should be in interval 0 but not 1 (since 1 is exclusive on left of interval 1)
    auto contains_1 = arr_right.contains(1.0);
    // (0, 1] contains 1: yes, (1, 2] contains 1: no (open on left), (2, 3] contains 1: no
    if (contains_1[0].value_or(false) != true ||
        contains_1[1].value_or(true) != false ||
        contains_1[2].value_or(true) != false) {
        std::cout << "[FAIL] : in test_contains() : right-closed contains 1.0" << std::endl;
        return;
    }

    // Left-closed intervals: [0, 1), [1, 2), [2, 3)

contains_str (pd_test_1_all.cpp:10889)

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

void pd_test_extension_index_contains_str_get_loc_str() {
    std::cout << "========= contains_str/get_loc_str =========================";

    pandas::CategoricalArray arr({"apple", "banana", "cherry"});
    pandas::CategoricalIndex idx(arr);

    bool passed = (idx.contains_str("apple") && !idx.contains_str("grape") &&
                   idx.get_loc_str("banana") == 1 && idx.get_loc_str("grape") == -1);
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_contains_str_get_loc_str() : contains_str/get_loc_str check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_contains_str_get_loc_str failed");
    }

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

void pd_test_extension_index_repr() {

delete_ (pd_test_1_all.cpp:10501)

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

void pd_test_extension_index_delete() {
    std::cout << "========= delete_ =========================";

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

    auto deleted = idx.delete_(1);
    auto v0 = deleted[0];
    auto v1 = deleted[1];
    auto v2 = deleted[2];

    bool passed = (deleted.size() == 3 &&
                   v0.has_value() && *v0 == "a" &&
                   v1.has_value() && *v1 == "c" &&
                   v2.has_value() && *v2 == "d");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_delete() : delete_ check failed" << std::endl;

delete_ (pd_test_1_all.cpp:10501)

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

void pd_test_extension_index_delete() {
    std::cout << "========= delete_ =========================";

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

    auto deleted = idx.delete_(1);
    auto v0 = deleted[0];
    auto v1 = deleted[1];
    auto v2 = deleted[2];

    bool passed = (deleted.size() == 3 &&
                   v0.has_value() && *v0 == "a" &&
                   v1.has_value() && *v1 == "c" &&
                   v2.has_value() && *v2 == "d");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_delete() : delete_ check failed" << std::endl;

dtype_name (pd_test_1_all.cpp:10104)

}

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

    pandas::CategoricalArray arr({"apple", "banana", "apple", "cherry"});
    pandas::CategoricalIndex idx(arr, "fruits");

    bool passed = (idx.size() == 4 && !idx.empty() &&
                   idx.name().has_value() && *idx.name() == "fruits" &&
                   idx.dtype_name() == "category");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_extension_index_array_constructor() : array constructor check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_array_constructor failed");
    }

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

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

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_cached_values (pd_test_1_all.cpp:19395)

            }

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

        void pd_test_series_cache() {
            std::cout << "========= cache management =========================================";

            pandas::Series<double> s({1.0, 2.0, 3.0, 4.0, 5.0});

            bool passed = s.has_cached_values() == false;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_series_cache() : initial cache not empty" << std::endl;
                throw std::runtime_error("pd_test_series_cache failed: initial cache not empty");
            }

            // Trigger cache
            s.sum();
            s.mean();
            s.min();
            s.max();

has_duplicates (pd_test_1_all.cpp:10176)

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

void pd_test_extension_index_uniqueness() {
    std::cout << "========= uniqueness =========================";

    // Unique values
    pandas::CategoricalArray arr1({"a", "b", "c"});
    pandas::CategoricalIndex idx1(arr1);

    bool passed1 = (idx1.is_unique() && !idx1.has_duplicates());
    if (!passed1) {
        std::cout << "  [FAIL] : in pd_test_extension_index_uniqueness() : unique check failed" << std::endl;
        throw std::runtime_error("pd_test_extension_index_uniqueness failed");
    }

    // With duplicates
    pandas::CategoricalArray arr2({"a", "b", "a", "c"});
    pandas::CategoricalIndex idx2(arr2);

    bool passed2 = (!idx2.is_unique() && idx2.has_duplicates());

hasnans (pd_test_1_all.cpp:5363)

void pd_test_categorical_index_from_codes() {
    std::cout << "========= from_codes =================================";

    std::vector<numpy::int32> codes = {0, 1, 0, 2, -1};  // -1 = NA
    std::vector<std::string> categories = {"low", "medium", "high"};

    pandas::CategoricalIndex idx = pandas::CategoricalIndex::from_codes(codes, categories, true, "level");

    bool passed = (idx.size() == 5 && idx.num_categories() == 3 &&
                   idx.ordered() && idx.name().has_value() && *idx.name() == "level" &&
                   idx.hasnans());  // has NA from code -1
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_from_codes()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_from_codes failed");
    }

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

void pd_test_categorical_index_simple_new() {
    std::cout << "========= _simple_new =================================";

identical (pd_test_1_all.cpp:5883)

}

void pd_test_categorical_index_identical() {
    std::cout << "========= identical ===================================";

    pandas::CategoricalArray arr({"a", "b"});
    pandas::CategoricalIndex idx1(arr, "same_name");
    pandas::CategoricalIndex idx2(arr, "same_name");
    pandas::CategoricalIndex idx3(arr, "diff_name");

    bool passed = (idx1.identical(idx2) && !idx1.identical(idx3));
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_identical()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_identical failed");
    }

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

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

inferred_type (pd_test_1_all.cpp:5270)

}

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

    pandas::CategoricalArray arr({"apple", "banana", "apple", "cherry"});
    pandas::CategoricalIndex idx(arr, "fruits");

    bool passed = (idx.size() == 4 && !idx.empty() &&
                   idx.name().has_value() && *idx.name() == "fruits" &&
                   idx.inferred_type() == "categorical");
    if (!passed) {
        std::cout << "  [FAIL] : in pd_test_categorical_index_array_constructor()" << std::endl;
        throw std::runtime_error("pd_test_categorical_index_array_constructor failed");
    }

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

void pd_test_categorical_index_values_constructor() {
    std::cout << "========= values constructor ==========================";

name (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;

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");
            }

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;
}

result (pd_test_1_all.cpp:15406)

    data.setElementAt({0}, numpy::datetime64(100LL, numpy::DateTimeUnit::Nanosecond));
    data.setElementAt({1}, numpy::datetime64(200LL, numpy::DateTimeUnit::Nanosecond));

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

    pandas::DatetimeArray arr(data, mask);
    pandas::DatetimeIndexBase idx(arr, "original");

    // Create join result (int64 values)
    numpy::NDArray<numpy::int64> join_result(std::vector<size_t>{3});
    join_result.setElementAt({0}, numpy::int64(500LL));
    join_result.setElementAt({1}, numpy::int64(600LL));
    join_result.setElementAt({2}, numpy::int64(700LL));

    auto new_idx = idx._from_join_target(join_result);

    bool passed = (new_idx.size() == 3 &&
                   new_idx.name().has_value() && *new_idx.name() == "original");
    if (!passed) {

set_name (pd_test_1_all.cpp:11798)

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

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

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

            pandas::Index<numpy::int64> idx1{1, 2, 3};
            idx1.set_name("original");

            pandas::Index<numpy::int64> idx2(idx1);

            bool passed = (idx2.size() == 3);
            passed = passed && (idx2.name().value() == "original");
            passed = passed && idx2.equals(idx1);

            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_index_copy_constructor() : copy failed" << std::endl;
                throw std::runtime_error("pd_test_index_copy_constructor failed");

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)

type_id (pd_test_3_all.cpp:25592)

// ------------------- pd_test_value_classify (end) ------------------

// ------------------- pd_test_index_type_id (start) ------------------
namespace dataframe_tests_index_type_id {

void pd_test_index_type_id_dispatch() {
    std::cout << "========= IndexTypeId dispatch =======================";

    // RangeIndex
    ::pandas::RangeIndex ri(0, 5);
    if (ri.type_id() != ::pandas::IndexTypeId::RangeIndex)
        throw std::runtime_error("RangeIndex type_id failed");

    // Index<string>
    ::pandas::Index<std::string> si(std::vector<std::string>{"a", "b", "c"});
    if (si.type_id() != ::pandas::IndexTypeId::IndexString)
        throw std::runtime_error("Index<string> type_id failed");

    // Index<int64>
    ::pandas::Index<numpy::int64> ii(std::vector<numpy::int64>{1, 2, 3});
    if (ii.type_id() != ::pandas::IndexTypeId::IndexInt64)

values (pd_test_1_all.cpp:364)

        pandas::CategoricalArray arr1;
        if (arr1.size() != 0) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_constructors() : default constructor size != 0" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_constructors failed: default constructor size != 0");
        }
        if (arr1.ordered()) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_constructors() : default should be unordered" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_constructors failed: default should be unordered");
        }

        // Constructor from values (infer categories)
        std::vector<std::optional<std::string>> values = {
            std::optional<std::string>("a"),
            std::optional<std::string>("b"),
            std::optional<std::string>("a"),
            std::optional<std::string>("c")
        };
        pandas::CategoricalArray arr2(values);
        if (arr2.size() != 4) {
            std::cout << "  [FAIL] : in pd_test_categorical_array_constructors() : values constructor size != 4" << std::endl;
            throw std::runtime_error("pd_test_categorical_array_constructors failed: values constructor size != 4");