DatetimeIndex ============= .. cpp:class:: pandas::DatetimeIndex Index class for axis labels in pandas data structures. Example ------- .. code-block:: cpp #include using namespace pandas; // Create DatetimeIndex DatetimeIndex idx({1, 2, 3}, "my_index"); size_t len = idx.size(); Constructors ------------ .. list-table:: :widths: 55 25 20 :header-rows: 1 * - Signature - Location - Example * - ``explicit DatetimeIndex(const DatetimeArray& arr, const std::optional& name = std::nullopt)`` - pd_datetime_index.h:126 - :ref:`View ` * - ``explicit DatetimeIndex(DatetimeArray&& arr, const std::optional& name = std::nullopt)`` - pd_datetime_index.h:136 - :ref:`View ` * - ``explicit DatetimeIndex(const std::vector& values, const std::optional& name = std::nullopt)`` - pd_datetime_index.h:146 - :ref:`View ` * - ``explicit DatetimeIndex(const std::vector>& values, const std::optional& name = std::nullopt)`` - pd_datetime_index.h:164 - :ref:`View ` * - ``DatetimeIndex(const std::string& start, int periods, const std::string& freq)`` - pd_datetime_index.h:175 - :ref:`View ` * - ``DatetimeIndex(const DatetimeIndex& other)`` - pd_datetime_index.h:180 - :ref:`View ` * - ``DatetimeIndex(DatetimeIndex&& other) noexcept`` - pd_datetime_index.h:187 - :ref:`View ` Indexing / Selection -------------------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``std::optional> get_datetime_ns_at(size_t pos) const override`` - std::optional> - pd_datetime_index.h:334 - :ref:`View ` * - ``numpy::NDArray get_indexer(const DatetimeIndex& target, const std::string& method = "", std::optional limit = std::nullopt, std::optional tolerance = std::nullopt) const`` - numpy::NDArray - pd_datetime_index.h:1590 - :ref:`View ` * - ``numpy::NDArray get_indexer_for(const std::vector& target) const`` - numpy::NDArray - pd_datetime_index.h:1639 - :ref:`View ` * - ``get_indexer_non_unique(const DatetimeIndex& target) const`` - - pd_datetime_index.h:1671 - :ref:`View ` * - ``DatetimeIndex get_level_values(int level) const`` - DatetimeIndex - pd_datetime_index.h:2866 - :ref:`View ` * - ``DatetimeIndex get_level_values(const std::string& level_name) const`` - DatetimeIndex - pd_datetime_index.h:2882 - :ref:`View ` * - ``int64_t get_loc(const numpy::datetime64& key) const`` - int64_t - pd_datetime_index.h:1729 - :ref:`View ` * - ``std::optional get_loc_string(const std::string& key) const override`` - std::optional - pd_datetime_index.h:3671 - :ref:`View ` * - ``int64_t get_loc_string_legacy_int64(const std::string& key) const`` - int64_t - pd_datetime_index.h:3634 - * - ``std::vector> get_names() const`` - std::vector> - pd_datetime_index.h:3474 - * - ``std::vector get_partial_date_indices(const std::string& key) const`` - std::vector - pd_datetime_index.h:3605 - * - ``size_t get_slice_bound(const numpy::datetime64& label, const std::string& side = "left") const`` - size_t - pd_datetime_index.h:1750 - :ref:`View ` * - ``std::string get_string(size_t i) const`` - std::string - pd_datetime_index.h:930 - :ref:`View ` * - ``std::string get_value_str(size_t index) const override`` - std::string - pd_datetime_index.h:806 - :ref:`View ` * - ``DatetimeIndex take(const numpy::NDArray& indices, int axis = 0, bool allow_fill = true, std::optional fill_value = std::nullopt) const`` - DatetimeIndex - pd_datetime_index.h:2472 - :ref:`View ` * - ``DatetimeIndex where(const numpy::NDArray& cond, const numpy::datetime64& other) const`` - DatetimeIndex - pd_datetime_index.h:2807 - :ref:`View ` Data Manipulation ----------------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``DatetimeIndex drop(const std::vector& labels, const std::string& errors = "raise") const`` - DatetimeIndex - pd_datetime_index.h:1255 - :ref:`View ` * - ``DatetimeIndex drop_duplicates(const std::string& keep = "first") const`` - DatetimeIndex - pd_datetime_index.h:1305 - :ref:`View ` * - ``DatetimeIndex droplevel(int level = 0) const`` - DatetimeIndex - pd_datetime_index.h:2849 - :ref:`View ` * - ``DatetimeIndex dropna() const`` - DatetimeIndex - pd_datetime_index.h:1361 - :ref:`View ` * - ``DatetimeIndex insert(size_t loc, const numpy::datetime64& item) const`` - DatetimeIndex - pd_datetime_index.h:1898 - :ref:`View ` * - ``std::pair> reindex( const DatetimeIndex& target, const std::string& method = "", std::optional level = std::nullopt, std::optional limit = std::nullopt, std::optional tolerance = std::nullopt) const`` - std::pair> - pd_datetime_index.h:3147 - :ref:`View ` * - ``DatetimeIndex rename(const std::optional& new_name, bool inplace = false, std::optional name = std::nullopt) const`` - DatetimeIndex - pd_datetime_index.h:597 - :ref:`View ` * - ``DatetimeIndex set_names(const std::optional& names, std::optional level = std::nullopt, bool inplace = false) const`` - DatetimeIndex - pd_datetime_index.h:2295 - :ref:`View ` Missing Data ------------ .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``DatetimeIndex fillna(const numpy::datetime64& value, const std::string& downcast = "") const`` - DatetimeIndex - pd_datetime_index.h:1548 - :ref:`View ` * - ``numpy::NDArray isna() const`` - numpy::NDArray - pd_datetime_index.h:2057 - :ref:`View ` * - ``numpy::NDArray isnull() const`` - numpy::NDArray - pd_datetime_index.h:2070 - :ref:`View ` * - ``numpy::NDArray notna() const`` - numpy::NDArray - pd_datetime_index.h:2143 - :ref:`View ` * - ``numpy::NDArray notnull() const`` - numpy::NDArray - pd_datetime_index.h:2156 - :ref:`View ` Statistics ---------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``std::optional max(bool skipna = true, std::optional axis = std::nullopt) const`` - std::optional - pd_datetime_index.h:441 - :ref:`View ` * - ``std::optional min(bool skipna = true, std::optional axis = std::nullopt) const`` - std::optional - pd_datetime_index.h:407 - :ref:`View ` * - ``size_t nunique(bool dropna = true) const`` - size_t - pd_datetime_index.h:2165 - :ref:`View ` * - ``std::optional std(bool skipna = true) const`` - std::optional - pd_datetime_index.h:522 - :ref:`View ` * - ``std::unordered_map value_counts(bool normalize = false, bool ascending = false, bool dropna = true, std::optional bins = std::nullopt, bool sort = true) const`` - std::unordered_map - pd_datetime_index.h:2764 - :ref:`View ` Aggregation ----------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``std::unordered_map> groupby( const std::vector& values) const`` - std::unordered_map> - pd_datetime_index.h:2913 - :ref:`View ` * - ``DatetimeIndex map(F&& mapper, const std::string& na_action = "") const`` - DatetimeIndex - pd_datetime_index.h:2096 - :ref:`View ` Comparison ---------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``bool equals(const DatetimeIndex& other) const`` - bool - pd_datetime_index.h:1479 - :ref:`View ` * - ``DatetimeArray new_arr(combined)`` - DatetimeArray - pd_datetime_index.h:997 - * - ``DatetimeArray new_arr(values)`` - DatetimeArray - pd_datetime_index.h:1146 - * - ``DatetimeArray new_arr(values)`` - DatetimeArray - pd_datetime_index.h:1166 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1245 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1296 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1353 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1374 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1562 - * - ``DatetimeArray new_arr(values)`` - DatetimeArray - pd_datetime_index.h:1917 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:1955 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2117 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2207 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2249 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2458 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2494 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2739 - * - ``DatetimeArray new_arr(result)`` - DatetimeArray - pd_datetime_index.h:2820 - Sorting ------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``numpy::NDArray argsort() const`` - numpy::NDArray - pd_datetime_index.h:1005 - :ref:`View ` * - ``size_t searchsorted(const numpy::datetime64& value, const std::string& side = "left", std::optional> sorter = std::nullopt) const`` - size_t - pd_datetime_index.h:2260 - :ref:`View ` * - ``DatetimeIndex sort_values(bool ascending = true, const std::string& na_position = "last", bool return_indexer = false, std::nullptr_t key = nullptr) const`` - DatetimeIndex - pd_datetime_index.h:2389 - :ref:`View ` Reshaping --------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``FrameData to_frame(bool index = true, const std::optional& name = std::nullopt) const`` - FrameData - pd_datetime_index.h:2542 - :ref:`View ` * - ``DatetimeIndex transpose() const`` - DatetimeIndex - pd_datetime_index.h:2686 - :ref:`View ` Combining --------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``DatetimeIndex append(const DatetimeIndex& other) const`` - DatetimeIndex - pd_datetime_index.h:983 - :ref:`View ` * - ``join(const DatetimeIndex& other, const std::string& how = "left", std::optional level = std::nullopt, bool return_indexers = true, bool sort = false) const`` - - pd_datetime_index.h:2960 - :ref:`View ` * - ``DatetimeArray joined_arr(joined_values)`` - DatetimeArray - pd_datetime_index.h:3108 - Time Series ----------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``std::optional asof(const numpy::datetime64& where, std::optional label = std::nullopt) const`` - std::optional - pd_datetime_index.h:1037 - :ref:`View ` * - ``numpy::NDArray asof_locs(const std::vector& where, std::optional> mask = std::nullopt) const`` - numpy::NDArray - pd_datetime_index.h:1072 - :ref:`View ` * - ``TimedeltaArray diff(int64_t periods = 1) const`` - TimedeltaArray - pd_datetime_index.h:1175 - :ref:`View ` * - ``DatetimeIndex difference(const DatetimeIndex& other, bool sort = true) const`` - DatetimeIndex - pd_datetime_index.h:1222 - :ref:`View ` * - ``DatetimeIndex shift(int64_t periods, const std::optional& freq = std::nullopt) const`` - DatetimeIndex - pd_datetime_index.h:350 - :ref:`View ` * - ``DatetimeIndex tz_convert(const std::string& tz, const std::string& tz_display = "") const`` - DatetimeIndex - pd_datetime_index.h:390 - :ref:`View ` * - ``DatetimeIndex tz_localize(const std::string& tz, const std::string& ambiguous = "raise", const std::string& nonexistent = "raise", const std::string& tz_display = "") const`` - DatetimeIndex - pd_datetime_index.h:372 - :ref:`View ` I/O --- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``std::vector> to_epoch_components() const`` - std::vector> - pd_datetime_index.h:2620 - :ref:`View ` * - ``DatetimeIndex to_flat_index() const`` - DatetimeIndex - pd_datetime_index.h:2502 - :ref:`View ` * - ``FloatingArray to_julian_date() const`` - FloatingArray - pd_datetime_index.h:3426 - :ref:`View ` * - ``std::vector> to_list() const`` - std::vector> - pd_datetime_index.h:2571 - :ref:`View ` * - ``std::string to_string() const override`` - std::string - pd_datetime_index.h:614 - :ref:`View ` * - ``std::vector to_vector() const`` - std::vector - pd_datetime_index.h:2666 - :ref:`View ` * - ``std::vector> tolist() const`` - std::vector> - pd_datetime_index.h:2585 - :ref:`View ` Conversion ---------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``numpy::NDArray astype(const std::string& dtype = "int64", bool copy = true) const`` - numpy::NDArray - pd_datetime_index.h:1108 - :ref:`View ` * - ``DatetimeIndex copy(const std::optional& name = std::nullopt, bool deep = true) const`` - DatetimeIndex - pd_datetime_index.h:581 - :ref:`View ` * - ``DatetimeIndex infer_objects(bool copy = true) const`` - DatetimeIndex - pd_datetime_index.h:2936 - :ref:`View ` * - ``numpy::NDArray view() const`` - numpy::NDArray - pd_datetime_index.h:2797 - :ref:`View ` Set Operations -------------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``BooleanArray duplicated(const std::string& keep = "first") const`` - BooleanArray - pd_datetime_index.h:1383 - :ref:`View ` * - ``DatetimeIndex intersection(const DatetimeIndex& other, bool sort = false) const`` - DatetimeIndex - pd_datetime_index.h:1927 - :ref:`View ` * - ``BooleanArray isin(const std::vector& values, std::optional level = std::nullopt) const`` - BooleanArray - pd_datetime_index.h:2030 - :ref:`View ` * - ``DatetimeIndex symmetric_difference(const DatetimeIndex& other, std::optional result_name = std::nullopt, bool sort = false) const`` - DatetimeIndex - pd_datetime_index.h:2420 - :ref:`View ` * - ``DatetimeIndex union_(const DatetimeIndex& other, bool sort = true) const`` - DatetimeIndex - pd_datetime_index.h:2696 - :ref:`View ` * - ``DatetimeIndex unique(std::optional level = std::nullopt) const`` - DatetimeIndex - pd_datetime_index.h:2748 - :ref:`View ` * - ``DatetimeArray unique_arr(uniques)`` - DatetimeArray - pd_datetime_index.h:1538 - Type Checking ------------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``bool is_(const DatetimeIndex& other) const`` - bool - pd_datetime_index.h:1964 - :ref:`View ` * - ``bool is_boolean() const`` - bool - pd_datetime_index.h:1972 - :ref:`View ` * - ``bool is_categorical() const`` - bool - pd_datetime_index.h:1980 - :ref:`View ` * - ``bool is_floating() const`` - bool - pd_datetime_index.h:1988 - :ref:`View ` * - ``bool is_integer() const`` - bool - pd_datetime_index.h:1996 - :ref:`View ` * - ``bool is_interval() const`` - bool - pd_datetime_index.h:2004 - :ref:`View ` * - ``bool is_numeric() const`` - bool - pd_datetime_index.h:2012 - :ref:`View ` * - ``bool is_object() const`` - bool - pd_datetime_index.h:2020 - :ref:`View ` Other Methods ------------- .. list-table:: :widths: 40 20 15 25 :header-rows: 1 * - Signature - Return Type - Location - Example * - ``bool all() const`` - bool - pd_datetime_index.h:950 - :ref:`View ` * - ``bool any() const`` - bool - pd_datetime_index.h:964 - :ref:`View ` * - ``int64_t argmax() const`` - int64_t - pd_datetime_index.h:497 - :ref:`View ` * - ``int64_t argmin() const`` - int64_t - pd_datetime_index.h:473 - :ref:`View ` * - ``DatetimeArray arr(opt_values)`` - DatetimeArray - pd_datetime_index.h:155 - :ref:`View ` * - ``DatetimeArray arr(values)`` - DatetimeArray - pd_datetime_index.h:168 - :ref:`View ` * - ``DatetimeIndex as_unit(const std::string& target_unit, bool round_ok = true) const`` - DatetimeIndex - pd_datetime_index.h:328 - :ref:`View ` * - ``DatetimeIndex ceil(const std::string& freq, const std::string& ambiguous = "raise", const std::string& nonexistent = "raise") const`` - DatetimeIndex - pd_datetime_index.h:304 - :ref:`View ` * - ``static int classify_partial_date(const std::string& s)`` - static int - pd_datetime_index.h:3486 - * - ``std::unique_ptr clone() const override`` - std::unique_ptr - pd_datetime_index.h:567 - :ref:`View ` * - ``DatetimeIndex delete_(size_t loc) const`` - DatetimeIndex - pd_datetime_index.h:1131 - :ref:`View ` * - ``DatetimeIndex delete_(const std::vector& locs) const`` - DatetimeIndex - pd_datetime_index.h:1155 - :ref:`View ` * - ``std::string dtype_str() const`` - std::string - pd_datetime_index.h:227 - :ref:`View ` * - ``std::pair, DatetimeIndex> factorize() const`` - std::pair, DatetimeIndex> - pd_datetime_index.h:1503 - :ref:`View ` * - ``DatetimeIndex floor(const std::string& freq, const std::string& ambiguous = "raise", const std::string& nonexistent = "raise") const`` - DatetimeIndex - pd_datetime_index.h:288 - :ref:`View ` * - ``std::vector format( const std::string& formatter = "%Y-%m-%d", [[maybe_unused]] const std::string& date_format = "", [[maybe_unused]] const std::string& na_rep = "NaT", [[maybe_unused]] bool name = false) const`` - std::vector - pd_datetime_index.h:1574 - :ref:`View ` * - ``std::unique_ptr freq_offset() const`` - std::unique_ptr - pd_datetime_index.h:252 - :ref:`View ` * - ``bool holds_integer() const`` - bool - pd_datetime_index.h:1779 - :ref:`View ` * - ``bool identical(const DatetimeIndex& other) const`` - bool - pd_datetime_index.h:1788 - :ref:`View ` * - ``numpy::NDArray indexer_at_time(const std::string& time, bool asof = false) const`` - numpy::NDArray - pd_datetime_index.h:1799 - :ref:`View ` * - ``numpy::NDArray indexer_between_time( const std::string& start_time, const std::string& end_time, bool include_start = true, bool include_end = true) const`` - numpy::NDArray - pd_datetime_index.h:1841 - :ref:`View ` * - ``std::string infer_freq_from_data() const`` - std::string - pd_datetime_index.h:751 - * - ``std::string inferred_type() const override`` - std::string - pd_datetime_index.h:219 - :ref:`View ` * - ``numpy::datetime64 item() const`` - numpy::datetime64 - pd_datetime_index.h:2078 - :ref:`View ` * - ``size_t memory_usage(bool deep = false) const`` - size_t - pd_datetime_index.h:2126 - :ref:`View ` * - ``size_t nbytes() const override`` - size_t - pd_datetime_index.h:2135 - :ref:`View ` * - ``size_t nlevels() const`` - size_t - pd_datetime_index.h:3466 - :ref:`View ` * - ``DatetimeIndex normalize() const`` - DatetimeIndex - pd_datetime_index.h:360 - :ref:`View ` * - ``static bool partial_date_to_ns_range(const std::string& s, int64_t& start_ns, int64_t& end_ns)`` - static bool - pd_datetime_index.h:3519 - * - ``DatetimeIndex putmask(const numpy::NDArray& mask, const numpy::datetime64& value) const`` - DatetimeIndex - pd_datetime_index.h:2194 - :ref:`View ` * - ``numpy::NDArray ravel() const`` - numpy::NDArray - pd_datetime_index.h:2215 - :ref:`View ` * - ``DatetimeIndex repeat(size_t repeats, std::optional axis = std::nullopt) const`` - DatetimeIndex - pd_datetime_index.h:2237 - :ref:`View ` * - ``std::string repr() const override`` - std::string - pd_datetime_index.h:796 - :ref:`View ` * - ``static int64_t resolve_datetime_endpoint(const std::string& s, const std::string& side)`` - static int64_t - pd_datetime_index.h:3561 - * - ``DatetimeIndex result(base_result.array(), base_result.name())`` - DatetimeIndex - pd_datetime_index.h:377 - :ref:`View ` * - ``DatetimeIndex result(base_result.array(), base_result.name())`` - DatetimeIndex - pd_datetime_index.h:392 - :ref:`View ` * - ``DatetimeIndex result(DatetimeArray(values), this->name())`` - DatetimeIndex - pd_datetime_index.h:2365 - :ref:`View ` * - ``DatetimeIndex round(const std::string& freq, const std::string& ambiguous = "raise", const std::string& nonexistent = "raise") const`` - DatetimeIndex - pd_datetime_index.h:272 - :ref:`View ` * - ``DatetimeIndex slice(size_t start, size_t stop, size_t step = 1) const`` - DatetimeIndex - pd_datetime_index.h:2357 - :ref:`View ` * - ``std::pair slice_indexer(const std::optional& start, const std::optional& stop, const std::optional& end = std::nullopt, size_t step = 1) const`` - std::pair - pd_datetime_index.h:2315 - :ref:`View ` * - ``std::pair slice_locs(const std::optional& start = std::nullopt, const std::optional& stop = std::nullopt, const std::optional& end = std::nullopt, size_t step = 1) const`` - std::pair - pd_datetime_index.h:2343 - :ref:`View ` * - ``std::pair slice_locs_string( const std::string& start, const std::string& stop) const`` - std::pair - pd_datetime_index.h:3575 - * - ``DatetimeIndex snap(const std::string& freq = "S") const`` - DatetimeIndex - pd_datetime_index.h:316 - :ref:`View ` * - ``DatetimeIndex sort(bool ascending = true) const`` - DatetimeIndex - pd_datetime_index.h:2377 - :ref:`View ` * - ``DatetimeArray sorted_arr(sorted_values)`` - DatetimeArray - pd_datetime_index.h:3338 - * - ``std::pair> sortlevel( int level = 0, bool ascending = true, bool sort_remaining = true, const std::string& na_position = "last") const`` - std::pair> - pd_datetime_index.h:3272 - :ref:`View ` * - ``StringMethods str() const`` - StringMethods - pd_datetime_index.h:938 - :ref:`View ` * - ``pandas::Timestamp ts(s)`` - pandas::Timestamp - pd_datetime_index.h:3567 - :ref:`View ` * - ``pandas::Timestamp ts(key)`` - pandas::Timestamp - pd_datetime_index.h:3640 - :ref:`View ` * - ``pandas::Timestamp ts(key)`` - pandas::Timestamp - pd_datetime_index.h:3681 - :ref:`View ` * - ``IndexTypeId type_id() const override`` - IndexTypeId - pd_datetime_index.h:571 - :ref:`View ` * - ``DatetimeIndex upsample(const DateOffset& freq) const`` - DatetimeIndex - pd_datetime_index.h:3713 - :ref:`View ` * - ``DatetimeIndex upsample(const std::string& freq_str) const`` - DatetimeIndex - pd_datetime_index.h:3719 - :ref:`View ` Code Examples ------------- The following examples are extracted from the test suite. .. _example-datetimeindex-datetimeindex-0: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-1: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-2: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-3: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-4: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-5: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-datetimeindex-6: .. dropdown:: DatetimeIndex (pd_test_2_all.cpp:386) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 376 :emphasize-lines: 11 namespace dataframe_tests { namespace dataframe_tests_asof { void pd_test_asof_scalar_basic() { std::cout << "========= asof scalar basic ==========================="; // Create DataFrame with DatetimeIndex and some NaN values // Similar to pandas example: // df = pd.DataFrame({'a': [10., 20., 30., 40., 50.], // 'b': [None, None, None, None, 500]}, // index=pd.DatetimeIndex(['2018-02-27 09:01:00', ...])) std::map> data; data["a"] = {10.0, 20.0, 30.0, 40.0, 50.0}; data["b"] = {std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), std::numeric_limits::quiet_NaN(), 500.0}; pandas::DataFrame df(data); .. _example-datetimeindex-get_datetime_ns_at-7: .. dropdown:: get_datetime_ns_at (pd_test_3_all.cpp:26202) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 26192 :emphasize-lines: 11 auto [is_dt, data] = s.idxmin_typed(); if (!is_dt) throw std::runtime_error("Expected datetime result"); if (data.first != 2000000000LL) throw std::runtime_error("Expected 2000000000 ns, got " + std::to_string(data.first)); std::cout << "PASSED" << std::endl; } void pd_test_idxmax_min_typed_non_datetime_ns() { std::cout << " pd_test_idxmax_min_typed_non_datetime_ns: "; // RangeIndex's get_datetime_ns_at should return nullopt ::pandas::Series<::numpy::float64> s({1.0, 2.0, 3.0}); auto result = s.index().get_datetime_ns_at(0); if (result.has_value()) throw std::runtime_error("Expected nullopt for non-datetime index"); std::cout << "PASSED" << std::endl; } void pd_test_idxmax_min_typed_string_fallback() { std::cout << " pd_test_idxmax_min_typed_string_fallback: "; // Verify that existing idxmax() string method still works ::pandas::Series<::numpy::float64> s({1.0, 3.0, 2.0}); std::string result = s.idxmax(); if (result != "1") throw std::runtime_error("Expected '1', got '" + result + "'"); .. _example-datetimeindex-get_indexer-8: .. dropdown:: get_indexer (pd_test_1_all.cpp:10332) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10322 :emphasize-lines: 11 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"); } .. _example-datetimeindex-get_indexer_for-9: .. dropdown:: get_indexer_for (pd_test_3_all.cpp:716) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 706 :emphasize-lines: 11 // ============================================================================ // Category 6: Index Indexer Methods // ============================================================================ void pd_test_3_all_index_indexers() { std::cout << "========= Index.get_indexer_for/non_unique/slice_indexer() "; std::vector vals = {"a", "b", "c", "d", "e"}; pandas::Index idx(vals); // Test get_indexer_for() std::vector target = {"b", "d", "f"}; // "f" doesn't exist numpy::NDArray 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"); .. _example-datetimeindex-get_indexer_non_unique-10: .. dropdown:: get_indexer_non_unique (pd_test_3_all.cpp:739) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 729 :emphasize-lines: 11 if (indexer.getElementAt({1}) != 3) { std::cout << " [FAIL] : in pd_test_3_all_index_indexers() : 'd' should be at index 3" << std::endl; throw std::runtime_error("pd_test_3_all_index_indexers failed: 'd' index"); } // "f" doesn't exist -> -1 if (indexer.getElementAt({2}) != -1) { std::cout << " [FAIL] : in pd_test_3_all_index_indexers() : 'f' should be -1" << std::endl; throw std::runtime_error("pd_test_3_all_index_indexers failed: 'f' index"); } // Test get_indexer_non_unique() std::vector target2 = {"a", "c", "z"}; // "z" doesn't exist pandas::Index target_idx(target2); auto [indexer2, missing] = idx.get_indexer_non_unique(target_idx); if (indexer2.getSize() < 2) { std::cout << " [FAIL] : in pd_test_3_all_index_indexers() : get_indexer_non_unique size too small" << std::endl; throw std::runtime_error("pd_test_3_all_index_indexers failed: get_indexer_non_unique size"); } // Test slice_indexer() .. _example-datetimeindex-get_level_values-11: .. dropdown:: get_level_values (pd_test_3_all.cpp:4524) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4514 :emphasize-lines: 11 } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_interval_index_get_level_values_droplevel() { std::cout << "========= IntervalIndex.get_level_values/droplevel() "; pandas::IntervalIndex64 idx = pandas::IntervalIndex64::from_breaks({0, 10, 20, 30}); // get_level_values(0) should work pandas::IntervalIndex64 level_vals = idx.get_level_values(0); if (level_vals.size() != idx.size()) { throw std::runtime_error("get_level_values(0) size mismatch"); } // get_level_values(1) should throw bool threw = false; try { idx.get_level_values(1); } catch (const std::out_of_range&) { .. _example-datetimeindex-get_level_values-12: .. dropdown:: get_level_values (pd_test_3_all.cpp:4524) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4514 :emphasize-lines: 11 } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_interval_index_get_level_values_droplevel() { std::cout << "========= IntervalIndex.get_level_values/droplevel() "; pandas::IntervalIndex64 idx = pandas::IntervalIndex64::from_breaks({0, 10, 20, 30}); // get_level_values(0) should work pandas::IntervalIndex64 level_vals = idx.get_level_values(0); if (level_vals.size() != idx.size()) { throw std::runtime_error("get_level_values(0) size mismatch"); } // get_level_values(1) should throw bool threw = false; try { idx.get_level_values(1); } catch (const std::out_of_range&) { .. _example-datetimeindex-get_loc-13: .. dropdown:: get_loc (pd_test_1_all.cpp:10281) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10271 :emphasize-lines: 11 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(loc_apple) && std::get(loc_apple) == 0 && std::get(loc_banana) == 1 && .. _example-datetimeindex-get_loc_string-14: .. dropdown:: get_loc_string (pd_test_3_all.cpp:28108) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 28098 :emphasize-lines: 11 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}); .. _example-datetimeindex-get_slice_bound-15: .. dropdown:: get_slice_bound (pd_test_3_all.cpp:3644) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3634 :emphasize-lines: 11 formatted = idx.format(custom_formatter); if (formatted[0] != "val:1") { throw std::runtime_error("custom formatter failed"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_get_slice_bound() { std::cout << "========= Index.get_slice_bound() =================="; pandas::Index idx({10, 20, 30, 40, 50}); // Exact match, left side size_t bound = idx.get_slice_bound(30, "left"); if (bound != 2) { throw std::runtime_error("left bound for 30 should be 2"); } // Exact match, right side .. _example-datetimeindex-get_string-16: .. dropdown:: get_string (pd_test_3_all.cpp:27746) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 27736 :emphasize-lines: 11 } } pandas::Series si({10, 20, 30}, "ints"); auto result2 = si.astype("str"); auto* str_s2 = dynamic_cast*>(result2.get()); if (!str_s2) { std::cout << " FAIL: expected Series from int" << std::endl; fail++; } else { if (str_s2->get_string(0) != "10") { std::cout << " FAIL: expected '10', got '" << str_s2->get_string(0) << "'" << std::endl; fail++; } } if (fail == 0) std::cout << " OK" << std::endl; } void pd_test_astype_datetime_to_string() { std::cout << " -- pd_test_astype_datetime_to_string --" << std::endl; .. _example-datetimeindex-get_value_str-17: .. dropdown:: get_value_str (pd_test_1_all.cpp:4665) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4655 :emphasize-lines: 11 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) { .. _example-datetimeindex-take-18: .. dropdown:: take (pd_test_1_all.cpp:5903) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5893 :emphasize-lines: 11 // 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 indices = {0, 2, 3}; pandas::ExtensionIndex 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; } .. _example-datetimeindex-where-19: .. dropdown:: where (pd_test_1_all.cpp:22018) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 22008 :emphasize-lines: 11 data["B"] = {5.0, 6.0, 7.0, 8.0}; pandas::DataFrame df(data); // Create condition DataFrame (values > 2) std::map> cond_data; cond_data["A"] = {false, false, true, true}; // 1<=2, 2<=2, 3>2, 4>2 cond_data["B"] = {true, true, true, true}; // all >2 pandas::DataFrame cond(cond_data); // Apply where with replacement value -1 pandas::DataFrame result = df.where(cond, -1.0); // Get column index for A - it's sorted alphabetically in std::map size_t col_a_idx = df.get_column_index("A"); size_t col_b_idx = df.get_column_index("B"); bool passed = true; std::string error_msg; // Check A column values std::string a0 = result.iat(0, col_a_idx) == -1.0 ? "ok" : "fail"; .. _example-datetimeindex-drop-20: .. dropdown:: drop (pd_test_1_all.cpp:6558) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6548 :emphasize-lines: 11 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{"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{{"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"); .. _example-datetimeindex-drop_duplicates-21: .. dropdown:: drop_duplicates (pd_test_1_all.cpp:6639) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6629 :emphasize-lines: 11 } } // Test drop_duplicates { std::map> 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> assign_data; .. _example-datetimeindex-droplevel-22: .. dropdown:: droplevel (pd_test_1_all.cpp:14428) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 14418 :emphasize-lines: 11 void pd_test_multiindex_droplevel() { std::cout << "========= droplevel =================================== "; std::vector> arrays = { {"a", "a", "b"}, {"x", "y", "z"}, {"1", "2", "3"} }; pandas::MultiIndex mi = pandas::MultiIndex::from_arrays(arrays); pandas::MultiIndex dropped = mi.droplevel(1); bool passed = true; if (dropped.nlevels() != 2) { std::cout << " [FAIL] : nlevels should be 2 after drop" << std::endl; passed = false; } // Check remaining levels auto tup = dropped[0]; .. _example-datetimeindex-dropna-23: .. dropdown:: dropna (pd_test_1_all.cpp:531) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 521 :emphasize-lines: 11 } // Test isna array numpy::NDArray 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"); .. _example-datetimeindex-insert-24: .. dropdown:: insert (pd_test_1_all.cpp:12028) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 12018 :emphasize-lines: 11 } std::cout << " -> tests passed" << std::endl; } void pd_test_index_insert_delete() { std::cout << "========= insert and delete ==========================="; pandas::Index idx{1, 2, 4, 5}; auto inserted = idx.insert(2, 3); bool passed = (inserted.size() == 5); passed = passed && (inserted[2] == 3); auto deleted = inserted.delete_(2); passed = passed && (deleted.size() == 4); passed = passed && deleted.equals(idx); if (!passed) { std::cout << " [FAIL] : in pd_test_index_insert_delete() : insert/delete failed" << std::endl; throw std::runtime_error("pd_test_index_insert_delete failed"); .. _example-datetimeindex-reindex-25: .. dropdown:: reindex (pd_test_1_all.cpp:6708) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6698 :emphasize-lines: 11 } } // Test reindex rows { std::map> data; data["A"] = {1.0, 2.0, 3.0}; pandas::DataFrame df(data); df = df.set_axis({"x", "y", "z"}, 0); auto reindexed = df.reindex({"x", "z", "w"}, 0); if (reindexed.nrows() != 3) { std::cout << " [FAIL] : in pd_test_dataframe_index_ops() : reindex wrong nrows" << std::endl; throw std::runtime_error("pd_test_dataframe_index_ops failed: reindex nrows"); } // 'w' should have NaN std::string val = reindexed["A"].get_value_str(2); if (!std::isnan(std::stod(val))) { std::cout << " [FAIL] : in pd_test_dataframe_index_ops() : missing label should be NaN" << std::endl; throw std::runtime_error("pd_test_dataframe_index_ops failed: reindex NaN"); } .. _example-datetimeindex-rename-26: .. dropdown:: rename (pd_test_1_all.cpp:5816) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5806 :emphasize-lines: 11 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; } .. _example-datetimeindex-set_names-27: .. dropdown:: set_names (pd_test_1_all.cpp:14519) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 14509 :emphasize-lines: 11 std::cout << "-> tests passed" << std::endl; } void pd_test_multiindex_set_names() { std::cout << "========= set_names =================================== "; std::vector> arrays = {{"a", "b"}, {"x", "y"}}; pandas::MultiIndex mi = pandas::MultiIndex::from_arrays(arrays); std::vector> new_names = {"level_a", "level_b"}; pandas::MultiIndex named = mi.set_names(new_names); bool passed = (named.names()[0] == "level_a" && named.names()[1] == "level_b"); if (!passed) { std::cout << " [FAIL] : names not set correctly" << std::endl; throw std::runtime_error("pd_test_multiindex_set_names failed"); } std::cout << "-> tests passed" << std::endl; } .. _example-datetimeindex-fillna-28: .. dropdown:: fillna (pd_test_1_all.cpp:537) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 527 :emphasize-lines: 11 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() { .. _example-datetimeindex-isna-29: .. dropdown:: isna (pd_test_1_all.cpp:524) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 514 :emphasize-lines: 11 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 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"); .. _example-datetimeindex-isnull-30: .. dropdown:: isnull (pd_test_3_all.cpp:671) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 661 :emphasize-lines: 11 // 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 vals = {1.0, std::nan(""), 3.0, std::nan("")}; pandas::Index idx(vals); numpy::NDArray 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 .. _example-datetimeindex-notna-31: .. dropdown:: notna (pd_test_1_all.cpp:6595) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6585 :emphasize-lines: 11 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> float_data; float_data["X"] = {1.0, std::nan(""), 3.0}; .. _example-datetimeindex-notnull-32: .. dropdown:: notnull (pd_test_3_all.cpp:665) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 655 :emphasize-lines: 11 } 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 vals = {1.0, std::nan(""), 3.0, std::nan("")}; pandas::Index idx(vals); numpy::NDArray 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"); } .. _example-datetimeindex-max-33: .. dropdown:: max (pd_test_1_all.cpp:771) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 761 :emphasize-lines: 11 pandas::CategoricalArray arr = pandas::CategoricalArray::from_codes(codes, cats, true); // ordered // Test min std::optional min_val = arr.min(); if (!min_val.has_value() || *min_val != "low") { std::cout << " [FAIL] : in pd_test_categorical_array_ordered_operations() : min != 'low'" << std::endl; throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: min != 'low'"); } // Test max std::optional max_val = arr.max(); if (!max_val.has_value() || *max_val != "high") { std::cout << " [FAIL] : in pd_test_categorical_array_ordered_operations() : max != 'high'" << std::endl; throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: max != 'high'"); } // Test unordered throws for min/max pandas::CategoricalArray unordered = arr.as_unordered(); bool threw = false; try { unordered.min(); .. _example-datetimeindex-min-34: .. dropdown:: min (pd_test_1_all.cpp:764) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 754 :emphasize-lines: 11 } void pd_test_categorical_array_ordered_operations() { std::cout << "========= CategoricalArray: ordered operations (min/max) ======================= "; std::vector cats = {"low", "medium", "high"}; std::vector codes = {0, 2, 1, 0, -1}; // low, high, medium, low, NA pandas::CategoricalArray arr = pandas::CategoricalArray::from_codes(codes, cats, true); // ordered // Test min std::optional min_val = arr.min(); if (!min_val.has_value() || *min_val != "low") { std::cout << " [FAIL] : in pd_test_categorical_array_ordered_operations() : min != 'low'" << std::endl; throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: min != 'low'"); } // Test max std::optional max_val = arr.max(); if (!max_val.has_value() || *max_val != "high") { std::cout << " [FAIL] : in pd_test_categorical_array_ordered_operations() : max != 'high'" << std::endl; throw std::runtime_error("pd_test_categorical_array_ordered_operations failed: max != 'high'"); .. _example-datetimeindex-nunique-35: .. dropdown:: nunique (pd_test_1_all.cpp:10604) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10594 :emphasize-lines: 11 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 ========================="; .. _example-datetimeindex-std-36: .. dropdown:: std (pd_test_1_all.cpp:4526) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4516 :emphasize-lines: 11 #include "../pandas/pd_series.h" namespace dataframe_tests { namespace dataframe_tests_aggregation { void pd_test_aggregation_series_sem() { std::cout << "========= Series sem ============================"; pandas::Series s({1.0, 2.0, 3.0, 4.0, 5.0}); auto sem_val = s.sem(); // std(ddof=1) = sqrt(2.5), sem = sqrt(2.5)/sqrt(5) ≈ 0.707 bool passed = sem_val.has_value() && std::abs(*sem_val - 0.707) < 0.01; if (!passed) { std::cout << " [FAIL] : in pd_test_aggregation_series_sem() : sem value incorrect" << std::endl; throw std::runtime_error("pd_test_aggregation_series_sem failed: sem value incorrect"); } std::cout << " -> tests passed" << std::endl; } void pd_test_aggregation_series_quantile() { .. _example-datetimeindex-value_counts-37: .. dropdown:: value_counts (pd_test_1_all.cpp:865) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 855 :emphasize-lines: 11 std::vector> values = { std::optional("a"), std::optional("b"), std::optional("a"), std::optional("a"), std::optional("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) { .. _example-datetimeindex-groupby-38: .. dropdown:: groupby (pd_test_1_all.cpp:11495) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 11485 :emphasize-lines: 11 std::cout << "========= GroupBy basic ========================="; // Create DataFrame with category column std::map> data = { {"category", {1.0, 1.0, 2.0, 2.0, 2.0}}, {"value", {10.0, 20.0, 30.0, 40.0, 50.0}} }; pandas::DataFrame df(data); // Test groupby auto grouped = df.groupby("category"); bool passed = grouped.ngroups() == 2; if (!passed) { std::cout << " [FAIL] : in pd_test_groupby_basic() : ngroups should be 2" << std::endl; throw std::runtime_error("pd_test_groupby_basic failed: ngroups should be 2"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-map-39: .. dropdown:: map (pd_test_1_all.cpp:5839) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5829 :emphasize-lines: 11 // Map Tests // ============================================================================ void pd_test_categorical_index_map() { std::cout << "========= map ========================================="; pandas::CategoricalArray arr({"yes", "no", "yes"}); pandas::CategoricalIndex idx(arr); std::unordered_map mapping = {{"yes", "1"}, {"no", "0"}}; pandas::CategoricalIndex mapped = idx.map(mapping); bool passed = (mapped.has_category("1") && mapped.has_category("0") && !mapped.has_category("yes") && !mapped.has_category("no")); if (!passed) { std::cout << " [FAIL] : in pd_test_categorical_index_map()" << std::endl; throw std::runtime_error("pd_test_categorical_index_map failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-equals-40: .. dropdown:: equals (pd_test_1_all.cpp:5866) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5856 :emphasize-lines: 11 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 ==================================="; .. _example-datetimeindex-argsort-41: .. dropdown:: argsort (pd_test_1_all.cpp:1304) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1294 :emphasize-lines: 11 std::cout << "========= DatetimeArray: sorting ======================= "; pandas::DatetimeArray arr(std::vector{ "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"); } .. _example-datetimeindex-searchsorted-42: .. dropdown:: searchsorted (pd_test_1_all.cpp:18958) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 18948 :emphasize-lines: 11 // ========================================================================= // Search Tests // ========================================================================= void pd_test_range_index_searchsorted() { std::cout << "========= searchsorted ================================ "; pandas::RangeIndex ri(0, 10, 2); // [0, 2, 4, 6, 8] bool passed = (ri.searchsorted(4, "left") == 2 && ri.searchsorted(4, "right") == 3 && ri.searchsorted(3, "left") == 2 && // 3 would go between 2 and 4 ri.searchsorted(-1, "left") == 0 && // Before all ri.searchsorted(10, "left") == 5); // After all if (!passed) { std::cout << " [FAIL] : searchsorted" << std::endl; throw std::runtime_error("pd_test_range_index_searchsorted failed"); } .. _example-datetimeindex-sort_values-43: .. dropdown:: sort_values (pd_test_1_all.cpp:6408) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6398 :emphasize-lines: 11 void pd_test_dataframe_sorting() { std::cout << "========= sorting =========================="; std::map> 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); .. _example-datetimeindex-to_frame-44: .. dropdown:: to_frame (pd_test_3_all.cpp:4931) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4921 :emphasize-lines: 11 size_t usage = mi.memory_usage(true); if (usage == 0) { throw std::runtime_error("memory_usage() should return > 0"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_multiindex_to_frame() { std::cout << "========= MultiIndex.to_frame() ======================="; std::vector> arrays = {{"a", "b"}, {"x", "y"}}; std::vector> names = {"first", "second"}; pandas::MultiIndex mi = pandas::MultiIndex::from_arrays(arrays, names); auto frame = mi.to_frame(); if (frame.find("first") == frame.end() || frame.find("second") == frame.end()) { throw std::runtime_error("to_frame() missing columns"); } .. _example-datetimeindex-transpose-45: .. dropdown:: transpose (pd_test_1_all.cpp:16648) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 16638 :emphasize-lines: 11 std::cout << " [FAIL] : in pd_test_ndframe_transpose() : T_() size" << std::endl; throw std::runtime_error("pd_test_ndframe_transpose failed: T_() size"); } passed = transposed[0] == 1 && transposed[1] == 2 && transposed[2] == 3; if (!passed) { std::cout << " [FAIL] : in pd_test_ndframe_transpose() : T_() values" << std::endl; throw std::runtime_error("pd_test_ndframe_transpose failed: T_() values"); } // Test transpose() alias auto transposed2 = s.transpose(); passed = transposed2.size() == s.size(); if (!passed) { std::cout << " [FAIL] : in pd_test_ndframe_transpose() : transpose() size" << std::endl; throw std::runtime_error("pd_test_ndframe_transpose failed: transpose() size"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-append-46: .. dropdown:: append (pd_test_1_all.cpp:10650) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10640 :emphasize-lines: 11 std::cout << "========= append ========================="; // Use same categories for both arrays (required by CategoricalArray::concat) std::vector 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; } .. _example-datetimeindex-join-47: .. dropdown:: join (pd_test_1_all.cpp:12353) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 12343 :emphasize-lines: 11 std::cout << " -> tests passed" << std::endl; } void pd_test_index_join() { std::cout << "========= join ========================================"; pandas::Index idx1{1, 2, 3}; pandas::Index idx2{2, 3, 4}; auto [inner_joined, left_idx, right_idx] = idx1.join(idx2, "inner"); bool passed = (inner_joined.size() == 2); // {2, 3} auto [outer_joined, ol_idx, or_idx] = idx1.join(idx2, "outer"); passed = passed && (outer_joined.size() == 4); // {1, 2, 3, 4} if (!passed) { std::cout << " [FAIL] : in pd_test_index_join() : join failed" << std::endl; throw std::runtime_error("pd_test_index_join failed"); } .. _example-datetimeindex-asof-48: .. dropdown:: asof (pd_test_2_all.cpp:366) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 356 :emphasize-lines: 11 std::cout << "====================================== [OK] pd_test_add_prefix test suite ========================== " << std::endl; return 0; } } // namespace dataframe_tests // ------------------- pd_test_add_prefix.cpp (end) ----------------------------- // ------------------- pd_test_asof.cpp (start) ----------------------------- // dataframe_tests/pd_test_asof.cpp // Test for DataFrame.asof() method #include #include #include #include #include "../pandas/pd_dataframe.h" // CRITICAL: No using namespace directives namespace dataframe_tests { .. _example-datetimeindex-asof_locs-49: .. dropdown:: asof_locs (pd_test_3_all.cpp:3557) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3547 :emphasize-lines: 11 throw std::runtime_error("all() should be true for empty index"); } if (empty_idx.any()) { throw std::runtime_error("any() should be false for empty index"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_asof() { std::cout << "========= Index.asof()/asof_locs() ================="; // Test with monotonically increasing index pandas::Index idx({10, 20, 30, 40, 50}); // Exact match auto result = idx.asof(30); if (!result.has_value() || result.value() != 30) { throw std::runtime_error("asof() exact match should return 30"); } .. _example-datetimeindex-diff-50: .. dropdown:: diff (pd_test_1_all.cpp:5171) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5161 :emphasize-lines: 11 } void pd_test_arithmetic_dataframe_diff_shift() { std::cout << "========= DataFrame diff/shift =================="; std::map> data; data["A"] = {1.0, 3.0, 6.0, 10.0}; pandas::DataFrame df(data); // diff: [NaN, 2, 3, 4] auto d = df.diff(); std::string val = d["A"].get_value_str(1); bool passed = std::abs(std::stod(val) - 2.0) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_dataframe_diff_shift() : diff failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_dataframe_diff_shift failed: diff failed"); } // First element should be NaN val = d["A"].get_value_str(0); passed = std::isnan(std::stod(val)); .. _example-datetimeindex-difference-51: .. dropdown:: difference (pd_test_1_all.cpp:10718) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10708 :emphasize-lines: 11 std::cout << "========= difference ========================="; // Use same categories for both arrays std::vector 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; .. _example-datetimeindex-shift-52: .. dropdown:: shift (pd_test_1_all.cpp:5188) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5178 :emphasize-lines: 11 // First element should be NaN val = d["A"].get_value_str(0); passed = std::isnan(std::stod(val)); if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_dataframe_diff_shift() : diff NaN failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_dataframe_diff_shift failed: diff NaN failed"); } // shift: [NaN, 1, 3, 6] auto s = df.shift(); val = s["A"].get_value_str(1); passed = std::abs(std::stod(val) - 1.0) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_dataframe_diff_shift() : shift failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_dataframe_diff_shift failed: shift failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-tz_convert-53: .. dropdown:: tz_convert (pd_test_2_all.cpp:17874) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 17864 :emphasize-lines: 11 std::cout << "====================================== [OK] pd_test_transform test suite ========================== " << std::endl; return 0; } } // namespace dataframe_tests // ------------------- pd_test_transform.cpp (end) ----------------------------- // ------------------- pd_test_tz_convert.cpp (start) ----------------------------- // dataframe_tests/pd_test_tz_convert.cpp // Test for DataFrame.tz_convert() method #include #include #include #include "../pandas/pd_dataframe.h" namespace dataframe_tests { namespace dataframe_tests_tz_convert { void pd_test_tz_convert_basic() { .. _example-datetimeindex-tz_localize-54: .. dropdown:: tz_localize (pd_test_1_all.cpp:1431) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1421 :emphasize-lines: 11 "2023-06-15" }); // Initially should be timezone-naive if (arr.is_tz_aware()) { std::cout << " [FAIL] : array should be timezone-naive initially" << std::endl; throw std::runtime_error("pd_test_datetime_array_timezone failed: naive"); } // Localize to UTC auto localized = arr.tz_localize("UTC"); if (!localized.is_tz_aware()) { std::cout << " [FAIL] : localized array should be timezone-aware" << std::endl; throw std::runtime_error("pd_test_datetime_array_timezone failed: localize"); } // Verify timezone name in dtype auto dt = localized.dtype(); if (!dt.is_tz_aware()) { std::cout << " [FAIL] : dtype should be timezone-aware" << std::endl; throw std::runtime_error("pd_test_datetime_array_timezone failed: dtype tz"); .. _example-datetimeindex-to_epoch_components-55: .. dropdown:: to_epoch_components (pd_test_5_all.cpp:46367) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 46357 :emphasize-lines: 11 numpy::datetime64(NS_2020, numpy::DateTimeUnit::Nanosecond)}, }; } void f_d5_case_1_nat_propagation(int& local_fail) { std::cout << "-- case_1_nat_propagation\n"; auto values = make_edge_case_values(); pandas::DatetimeArray arr(values); pandas::DatetimeIndex idx(arr, std::optional{"t"}); auto comps = idx.to_epoch_components(); pandas_tests::check(comps.size() == 5, "d5_case_1.size_eq_5", local_fail); pandas_tests::check(!comps[0].has_value(), "d5_case_1.slot0_is_nullopt_NaT", local_fail); } void f_d5_case_2_pre_1970_floor_div(int& local_fail) { std::cout << "-- case_2_pre_1970_floor_div\n"; auto values = make_edge_case_values(); pandas::DatetimeArray arr(values); pandas::DatetimeIndex idx(arr); .. _example-datetimeindex-to_flat_index-56: .. dropdown:: to_flat_index (pd_test_1_all.cpp:14733) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 14723 :emphasize-lines: 11 void pd_test_multiindex_to_flat_index() { std::cout << "========= to_flat_index =============================== "; std::vector> arrays = { {"a", "b"}, {"x", "y"} }; pandas::MultiIndex mi = pandas::MultiIndex::from_arrays(arrays); auto flat = mi.to_flat_index(); bool passed = (flat.size() == 2 && flat[0][0] == "a" && flat[0][1] == "x" && flat[1][0] == "b" && flat[1][1] == "y"); if (!passed) { std::cout << " [FAIL] : to_flat_index incorrect" << std::endl; throw std::runtime_error("pd_test_multiindex_to_flat_index failed"); } .. _example-datetimeindex-to_julian_date-57: .. dropdown:: to_julian_date (pd_test_3_all.cpp:20400) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 20390 :emphasize-lines: 11 // CRITICAL: No using namespace directives namespace dataframe_tests { namespace dataframe_tests_misc { // ============================================================================ // Test DatetimeIndex.to_julian_date // ============================================================================ void pd_test_to_julian_date() { std::cout << "========= DatetimeIndex.to_julian_date() =================="; // Create DatetimeIndex with known dates std::vector> dates = { numpy::datetime64("2000-01-01"), numpy::datetime64("2000-01-02"), numpy::datetime64("2000-01-03") }; pandas::DatetimeArray arr(dates); pandas::DatetimeIndex idx(arr, "test_dates"); .. _example-datetimeindex-to_list-58: .. dropdown:: to_list (pd_test_1_all.cpp:10247) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10237 :emphasize-lines: 11 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"); } .. _example-datetimeindex-to_string-59: .. dropdown:: to_string (pd_test_1_all.cpp:2693) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 2683 :emphasize-lines: 11 pandas::PeriodArray arr_m(std::vector{ "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]; .. _example-datetimeindex-to_vector-60: .. dropdown:: to_vector (pd_test_3_all.cpp:10723) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10713 :emphasize-lines: 11 // ============================================================================ void pd_test_3_all_niche_residual_fixes() { std::cout << "========= niche residual fixes ============"; // --- Case 1: DatetimeIndex::to_vector --- { pandas::DatetimeIndex dt_idx("2023-01-01", 3, "D"); pandas::DataFrame df; df.add_column("id", {1, 2, 3}); df.add_column("Date", dt_idx.to_vector()); if (df.nrows() != 3) { std::cout << " [FAIL] : in pd_test_3_all_niche_residual_fixes() : Case 1 nrows" << std::endl; throw std::runtime_error("pd_test_3_all_niche_residual_fixes failed: Case 1 nrows"); } if (df.ncols() != 2) { std::cout << " [FAIL] : in pd_test_3_all_niche_residual_fixes() : Case 1 ncols" << std::endl; throw std::runtime_error("pd_test_3_all_niche_residual_fixes failed: Case 1 ncols"); } } .. _example-datetimeindex-tolist-61: .. dropdown:: tolist (pd_test_3_all.cpp:2300) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 2290 :emphasize-lines: 11 threw = true; } if (!threw) { throw std::runtime_error("swapaxes should throw for invalid axes"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_categorical_to_list() { std::cout << "========= CategoricalArray.to_list()/tolist() ========="; std::vector> values = {"a", "b", std::nullopt, "c"}; pandas::CategoricalArray arr(values); auto list = arr.to_list(); if (list.size() != 4 || *list[0] != "a" || *list[1] != "b" || list[2].has_value() || *list[3] != "c") { throw std::runtime_error("to_list failed"); } .. _example-datetimeindex-astype-62: .. dropdown:: astype (pd_test_1_all.cpp:21292) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 21282 :emphasize-lines: 11 std::cout << "========= astype all columns to float64 ============="; // Create DataFrame with int64 columns std::map> data; data["A"] = {1, 2, 3, 4, 5}; data["B"] = {10, 20, 30, 40, 50}; pandas::DataFrame df(data); // Convert all columns to float64 pandas::DataFrame df_float = df.astype("float64"); // Verify dtype changed pandas::Series dtypes = df_float.dtypes(); bool passed = true; if (dtypes[static_cast(0)] != "float64") { std::cout << " [FAIL] : in pd_test_astype_all_columns_to_float64() : column A dtype is " << dtypes[static_cast(0)] << ", expected float64" << std::endl; passed = false; } if (dtypes[static_cast(1)] != "float64") { .. _example-datetimeindex-copy-63: .. dropdown:: copy (pd_test_1_all.cpp:5798) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5788 :emphasize-lines: 11 // ============================================================================ // 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; } .. _example-datetimeindex-infer_objects-64: .. dropdown:: infer_objects (pd_test_1_all.cpp:27595) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 27585 :emphasize-lines: 11 // Create DataFrame with string column containing integers std::map> data; data["A"] = {"1", "2", "3", "4", "5"}; pandas::DataFrame df(data); // Before inference, dtype should be string/object std::string before_dtype = df["A"].dtype_name(); // Apply infer_objects pandas::DataFrame result = df.infer_objects(); // After inference, dtype should be int64 std::string after_dtype = result["A"].dtype_name(); bool passed = (after_dtype == "int64"); if (!passed) { std::cout << " [FAIL] : in pd_test_infer_objects_integer_column() : expected int64, got " << after_dtype << std::endl; throw std::runtime_error("pd_test_infer_objects_integer_column failed"); } .. _example-datetimeindex-view-65: .. dropdown:: view (pd_test_3_all.cpp:2147) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 2137 :emphasize-lines: 11 throw std::runtime_error("memory_usage shallow too small"); } if (deep < shallow) { throw std::runtime_error("memory_usage deep should be >= shallow"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_categorical_ravel_view() { std::cout << "========= CategoricalArray.ravel()/view() ============="; std::vector> values = {"a", "b", "c"}; pandas::CategoricalArray arr(values); auto raveled = arr.ravel(); if (raveled.size() != 3 || !raveled.equals(arr)) { throw std::runtime_error("ravel failed"); } auto viewed = arr.view(); .. _example-datetimeindex-duplicated-66: .. dropdown:: duplicated (pd_test_1_all.cpp:10583) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10573 :emphasize-lines: 11 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"); } .. _example-datetimeindex-intersection-67: .. dropdown:: intersection (pd_test_1_all.cpp:10672) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10662 :emphasize-lines: 11 std::cout << "========= intersection ========================="; // Use same categories for both arrays std::vector 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; } .. _example-datetimeindex-isin-68: .. dropdown:: isin (pd_test_1_all.cpp:5938) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5928 :emphasize-lines: 11 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 values = {"a", "c"}; numpy::NDArray 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"); } .. _example-datetimeindex-symmetric_difference-69: .. dropdown:: symmetric_difference (pd_test_1_all.cpp:10742) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10732 :emphasize-lines: 11 std::cout << "========= symmetric_difference ========================="; // Use same categories for both arrays std::vector 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; .. _example-datetimeindex-union_-70: .. dropdown:: union_ (pd_test_1_all.cpp:10694) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10684 :emphasize-lines: 11 std::cout << "========= union ========================="; // Use same categories for both arrays std::vector 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; .. _example-datetimeindex-unique-71: .. dropdown:: unique (pd_test_1_all.cpp:1345) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1335 :emphasize-lines: 11 pandas::DatetimeArray arr(std::vector{ "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) { .. _example-datetimeindex-is_-72: .. dropdown:: is_ (pd_test_3_all.cpp:3972) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3962 :emphasize-lines: 11 // For typed Index, this is a no-op if (result.size() != 5) { throw std::runtime_error("infer_objects size should be 5"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_is_() { std::cout << "========= Index.is_() =============================="; pandas::Index idx1({1, 2, 3, 4, 5}); pandas::Index idx2({1, 2, 3, 4, 5}); // Different object // Different objects should not be the same if (idx1.is_(idx2)) { throw std::runtime_error("different objects should not be is_() equal"); } // Same object should be the same .. _example-datetimeindex-is_boolean-73: .. dropdown:: is_boolean (pd_test_3_all.cpp:3290) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3280 :emphasize-lines: 11 std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_datetime_index_type_checks() { std::cout << "========= DatetimeIndex type checks ======================"; pandas::DatetimeIndex idx = pandas::date_range("2024-01-01", "2024-01-05", std::nullopt, "D"); // Type check methods if (idx.is_boolean()) { throw std::runtime_error("is_boolean() should be false"); } if (idx.is_categorical()) { throw std::runtime_error("is_categorical() should be false"); } if (idx.is_floating()) { throw std::runtime_error("is_floating() should be false"); } if (idx.is_integer()) { throw std::runtime_error("is_integer() should be false"); .. _example-datetimeindex-is_categorical-74: .. dropdown:: is_categorical (pd_test_3_all.cpp:3293) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3283 :emphasize-lines: 11 void pd_test_3_all_datetime_index_type_checks() { std::cout << "========= DatetimeIndex type checks ======================"; pandas::DatetimeIndex idx = pandas::date_range("2024-01-01", "2024-01-05", std::nullopt, "D"); // Type check methods if (idx.is_boolean()) { throw std::runtime_error("is_boolean() should be false"); } if (idx.is_categorical()) { throw std::runtime_error("is_categorical() should be false"); } if (idx.is_floating()) { throw std::runtime_error("is_floating() should be false"); } if (idx.is_integer()) { throw std::runtime_error("is_integer() should be false"); } if (idx.is_interval()) { throw std::runtime_error("is_interval() should be false"); .. _example-datetimeindex-is_floating-75: .. dropdown:: is_floating (pd_test_3_all.cpp:622) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 612 :emphasize-lines: 11 // Test with integer index pandas::IndexDtype int_dtype; if (!int_dtype.is_numeric()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be numeric" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_numeric"); } if (!int_dtype.is_integer()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be integer" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_integer"); } if (int_dtype.is_floating()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be floating" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_floating"); } if (int_dtype.is_object()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be object" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_object"); } // Test with float index pandas::IndexDtype float_dtype; .. _example-datetimeindex-is_integer-76: .. dropdown:: is_integer (pd_test_3_all.cpp:618) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 608 :emphasize-lines: 11 void pd_test_3_all_index_dtype_checks() { std::cout << "========= IndexDtype.is_numeric/integer/floating/object() "; // Test with integer index pandas::IndexDtype int_dtype; if (!int_dtype.is_numeric()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be numeric" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_numeric"); } if (!int_dtype.is_integer()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be integer" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_integer"); } if (int_dtype.is_floating()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be floating" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_floating"); } if (int_dtype.is_object()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be object" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_object"); .. _example-datetimeindex-is_interval-77: .. dropdown:: is_interval (pd_test_3_all.cpp:3302) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3292 :emphasize-lines: 11 } if (idx.is_categorical()) { throw std::runtime_error("is_categorical() should be false"); } if (idx.is_floating()) { throw std::runtime_error("is_floating() should be false"); } if (idx.is_integer()) { throw std::runtime_error("is_integer() should be false"); } if (idx.is_interval()) { throw std::runtime_error("is_interval() should be false"); } if (idx.is_numeric()) { throw std::runtime_error("is_numeric() should be false"); } if (idx.is_object()) { throw std::runtime_error("is_object() should be false"); } if (idx.holds_integer()) { throw std::runtime_error("holds_integer() should be false"); .. _example-datetimeindex-is_numeric-78: .. dropdown:: is_numeric (pd_test_3_all.cpp:614) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 604 :emphasize-lines: 11 // ============================================================================ // Category 4: Index Type Checking (IndexDtype) // ============================================================================ void pd_test_3_all_index_dtype_checks() { std::cout << "========= IndexDtype.is_numeric/integer/floating/object() "; // Test with integer index pandas::IndexDtype int_dtype; if (!int_dtype.is_numeric()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be numeric" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_numeric"); } if (!int_dtype.is_integer()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be integer" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_integer"); } if (int_dtype.is_floating()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be floating" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_floating"); .. _example-datetimeindex-is_object-79: .. dropdown:: is_object (pd_test_3_all.cpp:626) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 616 :emphasize-lines: 11 throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_numeric"); } if (!int_dtype.is_integer()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should be integer" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_integer"); } if (int_dtype.is_floating()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be floating" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_floating"); } if (int_dtype.is_object()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : int should not be object" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: int is_object"); } // Test with float index pandas::IndexDtype float_dtype; if (!float_dtype.is_numeric()) { std::cout << " [FAIL] : in pd_test_3_all_index_dtype_checks() : float should be numeric" << std::endl; throw std::runtime_error("pd_test_3_all_index_dtype_checks failed: float is_numeric"); } .. _example-datetimeindex-all-80: .. dropdown:: all (pd_test_1_all.cpp:247) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 237 :emphasize-lines: 11 pandas::BooleanArray has_true({ std::optional(false), std::optional(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(true), std::optional(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"); } .. _example-datetimeindex-any-81: .. dropdown:: any (pd_test_1_all.cpp:226) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 216 :emphasize-lines: 11 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(false), std::optional(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"); } .. _example-datetimeindex-argmax-82: .. dropdown:: argmax (pd_test_1_all.cpp:1323) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1313 :emphasize-lines: 11 } // 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 ======================= "; .. _example-datetimeindex-argmin-83: .. dropdown:: argmin (pd_test_1_all.cpp:1316) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1306 :emphasize-lines: 11 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"); .. _example-datetimeindex-arr-84: .. dropdown:: arr (pd_test_1_all.cpp:45) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 35 :emphasize-lines: 11 std::cout << " [FAIL] : in pd_test_boolean_array_constructors() : initializer_list size != 4" << std::endl; throw std::runtime_error("pd_test_boolean_array_constructors failed: initializer_list size != 4"); } std::cout << " -> tests passed" << std::endl; } void pd_test_boolean_array_na_handling() { std::cout << "========= BooleanArray: NA handling ======================= "; pandas::BooleanArray arr({ std::optional(true), std::nullopt, // NA at index 1 std::optional(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"); } .. _example-datetimeindex-arr-85: .. dropdown:: arr (pd_test_1_all.cpp:45) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 35 :emphasize-lines: 11 std::cout << " [FAIL] : in pd_test_boolean_array_constructors() : initializer_list size != 4" << std::endl; throw std::runtime_error("pd_test_boolean_array_constructors failed: initializer_list size != 4"); } std::cout << " -> tests passed" << std::endl; } void pd_test_boolean_array_na_handling() { std::cout << "========= BooleanArray: NA handling ======================= "; pandas::BooleanArray arr({ std::optional(true), std::nullopt, // NA at index 1 std::optional(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"); } .. _example-datetimeindex-as_unit-86: .. dropdown:: as_unit (pd_test_1_all.cpp:9361) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 9351 :emphasize-lines: 11 data.setElementAt({1}, numpy::datetime64(2000000000LL, numpy::DateTimeUnit::Nanosecond)); // 2 seconds in ns numpy::NDArray mask(std::vector{2}); mask.setElementAt({0}, numpy::bool_(false)); mask.setElementAt({1}, numpy::bool_(false)); pandas::DatetimeArray arr(data, mask); pandas::DatetimeTDMixin idx(arr, "test"); // Convert to microseconds pandas::DatetimeTDMixin us_idx = idx.as_unit("us"); // Convert to same unit (should return identical) pandas::DatetimeTDMixin same_idx = idx.as_unit("ns"); bool passed = (us_idx.size() == 2 && same_idx.size() == 2 && us_idx.name().has_value() && *us_idx.name() == "test"); if (!passed) { std::cout << " [FAIL] : in pd_test_datetime_as_unit() : as_unit check failed" << std::endl; throw std::runtime_error("pd_test_datetime_as_unit failed"); } .. _example-datetimeindex-ceil-87: .. dropdown:: ceil (pd_test_1_all.cpp:4949) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4939 :emphasize-lines: 11 throw std::runtime_error("pd_test_arithmetic_series_round failed: round failed"); } auto f = a.floor(); passed = std::abs(f[0] - 1.0) < 0.001 && std::abs(f[2] - 3.0) < 0.001 && std::abs(f[3] - (-2.0)) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_series_round() : floor failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_series_round failed: floor failed"); } auto c = a.ceil(); passed = std::abs(c[0] - 2.0) < 0.001 && std::abs(c[2] - 4.0) < 0.001 && std::abs(c[3] - (-1.0)) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_series_round() : ceil failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_series_round failed: ceil failed"); } // Round with decimals pandas::Series b({1.234, 2.567, 3.891}); auto r2 = b.round(2); passed = std::abs(r2[0] - 1.23) < 0.001 && std::abs(r2[1] - 2.57) < 0.001; .. _example-datetimeindex-clone-88: .. dropdown:: clone (pd_test_1_all.cpp:5776) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5766 :emphasize-lines: 11 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 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; } .. _example-datetimeindex-delete_-89: .. dropdown:: delete_ (pd_test_1_all.cpp:10501) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10491 :emphasize-lines: 11 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; .. _example-datetimeindex-delete_-90: .. dropdown:: delete_ (pd_test_1_all.cpp:10501) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10491 :emphasize-lines: 11 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; .. _example-datetimeindex-dtype_str-91: .. dropdown:: dtype_str (pd_test_1_all.cpp:17251) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 17241 :emphasize-lines: 11 std::cout << " -> tests passed" << std::endl; } void pd_test_period_index_dtype_str() { std::cout << "========= dtype_str property =========================="; std::vector ordinals = {0, 1}; pandas::PeriodIndex idx = pandas::PeriodIndex::from_ordinals(ordinals, "M"); std::string dt_str = idx.dtype_str(); bool passed = (dt_str.find("period[") != std::string::npos); if (!passed) { std::cout << " [FAIL] : in pd_test_period_index_dtype_str() got: " << dt_str << std::endl; throw std::runtime_error("pd_test_period_index_dtype_str failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-factorize-92: .. dropdown:: factorize (pd_test_1_all.cpp:1353) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1343 :emphasize-lines: 11 // 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"); } .. _example-datetimeindex-floor-93: .. dropdown:: floor (pd_test_1_all.cpp:4942) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 4932 :emphasize-lines: 11 pandas::Series a({1.4, 2.5, 3.6, -1.4, -2.5}); auto r = a.round(); bool passed = std::abs(r[0] - 1.0) < 0.001 && std::abs(r[2] - 4.0) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_series_round() : round failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_series_round failed: round failed"); } auto f = a.floor(); passed = std::abs(f[0] - 1.0) < 0.001 && std::abs(f[2] - 3.0) < 0.001 && std::abs(f[3] - (-2.0)) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_series_round() : floor failed" << std::endl; throw std::runtime_error("pd_test_arithmetic_series_round failed: floor failed"); } auto c = a.ceil(); passed = std::abs(c[0] - 2.0) < 0.001 && std::abs(c[2] - 4.0) < 0.001 && std::abs(c[3] - (-1.0)) < 0.001; if (!passed) { std::cout << " [FAIL] : in pd_test_arithmetic_series_round() : ceil failed" << std::endl; .. _example-datetimeindex-format-94: .. dropdown:: format (main.cpp:20) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10 :emphasize-lines: 11 int main() { // Automatically log all output to temp/pd_test_output.log numpy::TestLogger logger("temp/pd_test_output.log"); int res = 0; int res1 = 0; std::string resS = ""; // call all the tests res1 = dataframe_tests::pd_test_main(); resS += std::format(" pd_test_main: {} errors\n", res1); res += res1; std::cout << "\n------------------------- main --------------------------------------------\n"; std::cout << std::endl << "All tests completed. Nb errors = " << res << std::endl; std::cout << "Details: \n" << resS; std::cout << "\n---------------------------------------------------------------------------\n"; return res; } .. _example-datetimeindex-freq_offset-95: .. dropdown:: freq_offset (pd_test_5_all.cpp:89280) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 89270 :emphasize-lines: 11 } out_msg = ""; return false; } template static void check_offset_typed(const std::string& label, const pandas::DatetimeIndex& idx, int expected_n, int& local_fail) { std::unique_ptr off = idx.freq_offset(); pandas_tests::check(off != nullptr, label + ".not_null", local_fail); if (!off) return; const Concrete* cast = dynamic_cast(off.get()); pandas_tests::check(cast != nullptr, label + ".dynamic_cast", local_fail); if (!cast) { std::cout << " got name=\"" << off->name() << "\"\n"; return; } pandas_tests::check(cast->n() == expected_n, label + ".n_matches", local_fail); if (cast->n() != expected_n) { .. _example-datetimeindex-holds_integer-96: .. dropdown:: holds_integer (pd_test_3_all.cpp:3311) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3301 :emphasize-lines: 11 } if (idx.is_interval()) { throw std::runtime_error("is_interval() should be false"); } if (idx.is_numeric()) { throw std::runtime_error("is_numeric() should be false"); } if (idx.is_object()) { throw std::runtime_error("is_object() should be false"); } if (idx.holds_integer()) { throw std::runtime_error("holds_integer() should be false"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_datetime_index_sort() { std::cout << "========= DatetimeIndex.sort_values() ===================="; pandas::DatetimeIndex idx = pandas::date_range("2024-01-01", "2024-01-05", std::nullopt, "D"); .. _example-datetimeindex-identical-97: .. dropdown:: identical (pd_test_1_all.cpp:5883) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5873 :emphasize-lines: 11 } 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 .. _example-datetimeindex-indexer_at_time-98: .. dropdown:: indexer_at_time (pd_test_3_all.cpp:3274) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3264 :emphasize-lines: 11 std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_datetime_index_time_operations() { std::cout << "========= DatetimeIndex time operations =================="; // Create datetime index with specific times (using hourly freq) pandas::DatetimeIndex idx = pandas::date_range("2024-01-01 09:00:00", "2024-01-01 17:00:00", std::nullopt, "H"); // Test indexer_at_time numpy::NDArray at_time = idx.indexer_at_time("12:00:00"); // Should find the 12:00 entry // Test indexer_between_time numpy::NDArray between_time = idx.indexer_between_time("10:00:00", "14:00:00"); // Should find entries between 10:00 and 14:00 std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_datetime_index_type_checks() { .. _example-datetimeindex-indexer_between_time-99: .. dropdown:: indexer_between_time (pd_test_3_all.cpp:3278) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3268 :emphasize-lines: 11 std::cout << "========= DatetimeIndex time operations =================="; // Create datetime index with specific times (using hourly freq) pandas::DatetimeIndex idx = pandas::date_range("2024-01-01 09:00:00", "2024-01-01 17:00:00", std::nullopt, "H"); // Test indexer_at_time numpy::NDArray at_time = idx.indexer_at_time("12:00:00"); // Should find the 12:00 entry // Test indexer_between_time numpy::NDArray between_time = idx.indexer_between_time("10:00:00", "14:00:00"); // Should find entries between 10:00 and 14:00 std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_datetime_index_type_checks() { std::cout << "========= DatetimeIndex type checks ======================"; pandas::DatetimeIndex idx = pandas::date_range("2024-01-01", "2024-01-05", std::nullopt, "D"); .. _example-datetimeindex-inferred_type-100: .. dropdown:: inferred_type (pd_test_1_all.cpp:5270) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 5260 :emphasize-lines: 11 } 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 =========================="; .. _example-datetimeindex-item-101: .. dropdown:: item (pd_test_3_all.cpp:3712) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3702 :emphasize-lines: 11 // Test is_interval (always false for base Index) if (int_idx.is_interval()) { throw std::runtime_error("base Index should not be interval"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_item() { std::cout << "========= Index.item() ============================="; pandas::Index idx1({42}); numpy::int64 val = idx1.item(); if (val != 42) { throw std::runtime_error("item() should return 42"); } // Test error for size != 1 pandas::Index idx2({1, 2, 3}); .. _example-datetimeindex-memory_usage-102: .. dropdown:: memory_usage (pd_test_1_all.cpp:27063) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 27053 :emphasize-lines: 11 } std::cout << "====================================== [OK] pd_test_value_counts test suite ========================== " << std::endl; return 0; } } // namespace dataframe_tests // ------------------- pd_test_value_counts.cpp (end) ----------------------------- // ------------------- pd_test_memory_usage.cpp (start) ----------------------------- // Tests for DataFrame.memory_usage() - pandas-compatible memory usage reporting namespace dataframe_tests { namespace dataframe_tests_memory_usage { void pd_test_memory_usage_basic() { std::cout << "========= basic memory_usage ======================="; // Create a simple DataFrame with multiple columns std::map> data; data["A"] = {1.0, 2.0, 3.0, 4.0, 5.0}; .. _example-datetimeindex-nbytes-103: .. dropdown:: nbytes (pd_test_1_all.cpp:6214) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 6204 :emphasize-lines: 11 } // 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"); } .. _example-datetimeindex-nlevels-104: .. dropdown:: nlevels (pd_test_1_all.cpp:14138) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 14128 :emphasize-lines: 11 // ===================================================================== // Constructor Tests // ===================================================================== void pd_test_multiindex_default_constructor() { std::cout << "========= default constructor ========================= "; pandas::MultiIndex mi; bool passed = (mi.nlevels() == 0) && (mi.size() == 0) && mi.empty(); if (!passed) { std::cout << " [FAIL] : in pd_test_multiindex_default_constructor()" << std::endl; throw std::runtime_error("pd_test_multiindex_default_constructor failed"); } std::cout << "-> tests passed" << std::endl; } void pd_test_multiindex_from_arrays() { .. _example-datetimeindex-normalize-105: .. dropdown:: normalize (pd_test_1_all.cpp:8723) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 8713 :emphasize-lines: 11 void pd_test_datetime_mixin_normalize() { std::cout << "========= normalize ==================================="; // Create datetime with time component std::vector> values = { numpy::datetime64(86400000000000LL + 3600000000000LL, numpy::DateTimeUnit::Nanosecond) // 1 day + 1 hour }; pandas::DatetimeArray arr(values); pandas::DatetimeMixinIndex idx(arr); pandas::DatetimeMixinIndex normalized = idx.normalize(); bool passed = (normalized.size() == 1); if (!passed) { std::cout << " [FAIL] : in pd_test_datetime_mixin_normalize()" << std::endl; throw std::runtime_error("pd_test_datetime_mixin_normalize failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-putmask-106: .. dropdown:: putmask (pd_test_3_all.cpp:3752) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3742 :emphasize-lines: 11 // Should be at least sizeof index + 5 * sizeof(int64) if (usage < 5 * sizeof(numpy::int64)) { throw std::runtime_error("memory_usage too small"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_putmask() { std::cout << "========= Index.putmask() =========================="; pandas::Index idx({1, 2, 3, 4, 5}); numpy::NDArray mask(std::vector{5}); mask.setElementAt({0}, numpy::bool_(true)); mask.setElementAt({1}, numpy::bool_(false)); mask.setElementAt({2}, numpy::bool_(true)); mask.setElementAt({3}, numpy::bool_(false)); mask.setElementAt({4}, numpy::bool_(true)); auto result = idx.putmask(mask, numpy::int64(99)); .. _example-datetimeindex-ravel-107: .. dropdown:: ravel (pd_test_3_all.cpp:2147) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 2137 :emphasize-lines: 11 throw std::runtime_error("memory_usage shallow too small"); } if (deep < shallow) { throw std::runtime_error("memory_usage deep should be >= shallow"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_categorical_ravel_view() { std::cout << "========= CategoricalArray.ravel()/view() ============="; std::vector> values = {"a", "b", "c"}; pandas::CategoricalArray arr(values); auto raveled = arr.ravel(); if (raveled.size() != 3 || !raveled.equals(arr)) { throw std::runtime_error("ravel failed"); } auto viewed = arr.view(); .. _example-datetimeindex-repeat-108: .. dropdown:: repeat (pd_test_3_all.cpp:2166) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 2156 :emphasize-lines: 11 auto viewed = arr.view(); if (viewed.size() != 3 || !viewed.equals(arr)) { throw std::runtime_error("view failed"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_categorical_repeat() { std::cout << "========= CategoricalArray.repeat() ==================="; std::vector> values = {"a", "b"}; pandas::CategoricalArray arr(values); auto result = arr.repeat(3); if (result.size() != 6 || *result[0] != "a" || *result[2] != "a" || *result[3] != "b" || *result[5] != "b") { throw std::runtime_error("repeat scalar failed"); } .. _example-datetimeindex-repr-109: .. dropdown:: repr (pd_test_1_all.cpp:10906) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 10896 :emphasize-lines: 11 std::cout << " -> tests passed" << std::endl; } void pd_test_extension_index_repr() { std::cout << "========= repr ========================="; pandas::CategoricalArray arr({"a", "b", "c"}); // Use ExtensionIndex directly to test base class repr pandas::ExtensionIndex 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; } .. _example-datetimeindex-result-110: .. dropdown:: result (pd_test_1_all.cpp:15406) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 15396 :emphasize-lines: 11 data.setElementAt({0}, numpy::datetime64(100LL, numpy::DateTimeUnit::Nanosecond)); data.setElementAt({1}, numpy::datetime64(200LL, numpy::DateTimeUnit::Nanosecond)); numpy::NDArray mask(std::vector{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 join_result(std::vector{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) { .. _example-datetimeindex-result-111: .. dropdown:: result (pd_test_1_all.cpp:15406) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 15396 :emphasize-lines: 11 data.setElementAt({0}, numpy::datetime64(100LL, numpy::DateTimeUnit::Nanosecond)); data.setElementAt({1}, numpy::datetime64(200LL, numpy::DateTimeUnit::Nanosecond)); numpy::NDArray mask(std::vector{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 join_result(std::vector{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) { .. _example-datetimeindex-result-112: .. dropdown:: result (pd_test_1_all.cpp:15406) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 15396 :emphasize-lines: 11 data.setElementAt({0}, numpy::datetime64(100LL, numpy::DateTimeUnit::Nanosecond)); data.setElementAt({1}, numpy::datetime64(200LL, numpy::DateTimeUnit::Nanosecond)); numpy::NDArray mask(std::vector{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 join_result(std::vector{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) { .. _example-datetimeindex-round-113: .. dropdown:: round (pd_test_1_all.cpp:1688) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 1678 :emphasize-lines: 11 void pd_test_floating_array_rounding() { std::cout << "========= FloatingArray: rounding ======================= "; pandas::FloatingArray arr({ std::optional(1.234), std::optional(2.567), std::nullopt }); auto rounded = arr.round(2); if (std::abs(rounded[0].value() - 1.23) > 0.001 || std::abs(rounded[1].value() - 2.57) > 0.001) { std::cout << " [FAIL] : in pd_test_floating_array_rounding() : round(2)" << std::endl; throw std::runtime_error("pd_test_floating_array_rounding failed: round(2)"); } if (!rounded.is_na(2)) { std::cout << " [FAIL] : in pd_test_floating_array_rounding() : round should preserve NA" << std::endl; throw std::runtime_error("pd_test_floating_array_rounding failed: NA preservation"); } .. _example-datetimeindex-slice-114: .. dropdown:: slice (pd_test_1_all.cpp:17546) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 17536 :emphasize-lines: 11 // ============================================================================ // Slicing / Indexing Tests // ============================================================================ void pd_test_period_index_slice() { std::cout << "========= slice method ================================"; std::vector ordinals = {0, 1, 2, 3, 4}; pandas::PeriodIndex idx(ordinals, "D"); pandas::PeriodIndex sliced = idx.slice(1, 4); bool passed = (sliced.size() == 3 && sliced[0].has_value() && *sliced[0] == 1); if (!passed) { std::cout << " [FAIL] : in pd_test_period_index_slice()" << std::endl; throw std::runtime_error("pd_test_period_index_slice failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-slice_indexer-115: .. dropdown:: slice_indexer (pd_test_3_all.cpp:711) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 701 :emphasize-lines: 11 } std::cout << " -> tests passed" << std::endl; } // ============================================================================ // Category 6: Index Indexer Methods // ============================================================================ void pd_test_3_all_index_indexers() { std::cout << "========= Index.get_indexer_for/non_unique/slice_indexer() "; std::vector vals = {"a", "b", "c", "d", "e"}; pandas::Index idx(vals); // Test get_indexer_for() std::vector target = {"b", "d", "f"}; // "f" doesn't exist numpy::NDArray 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"); .. _example-datetimeindex-slice_locs-116: .. dropdown:: slice_locs (pd_test_1_all.cpp:18275) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 18265 :emphasize-lines: 11 } std::cout << "-> tests passed" << std::endl; } void pd_test_range_index_slice_locs() { std::cout << "========= slice_locs ================================== "; pandas::RangeIndex ri(0, 10); // [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] auto [start_idx, stop_idx] = ri.slice_locs(3, 7); bool passed = (start_idx == 3 && stop_idx == 8); if (!passed) { std::cout << " [FAIL] : slice_locs" << std::endl; throw std::runtime_error("pd_test_range_index_slice_locs failed"); } std::cout << "-> tests passed" << std::endl; } .. _example-datetimeindex-snap-117: .. dropdown:: snap (pd_test_1_all.cpp:8364) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 8354 :emphasize-lines: 11 void pd_test_datetime_mixin_snap() { std::cout << "========= snap ========================================"; std::vector> values = { numpy::datetime64(1000000000123456789LL, numpy::DateTimeUnit::Nanosecond) }; pandas::DatetimeArray arr(values); pandas::DatetimeMixinIndex idx(arr); pandas::DatetimeMixinIndex snapped = idx.snap("s"); bool passed = (snapped.size() == 1); if (!passed) { std::cout << " [FAIL] : in pd_test_datetime_mixin_snap()" << std::endl; throw std::runtime_error("pd_test_datetime_mixin_snap failed"); } std::cout << " -> tests passed" << std::endl; } .. _example-datetimeindex-sort-118: .. dropdown:: sort (pd_test_3_all.cpp:3869) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 3859 :emphasize-lines: 11 throw std::runtime_error("last 2 positions should be NaN"); } if (std::abs(result[0] - 3.0) > 0.001) { throw std::runtime_error("shift(-2) [0] should be 3.0"); } std::cout << " -> tests passed" << std::endl; } void pd_test_3_all_index_sort() { std::cout << "========= Index.sort() ============================="; pandas::Index idx({3, 1, 4, 1, 5, 9, 2, 6}); auto result = idx.sort(); if (result[0] != 1 || result[1] != 1 || result[7] != 9) { throw std::runtime_error("sort() not working correctly"); } // Test descending result = idx.sort(false); .. _example-datetimeindex-sortlevel-119: .. dropdown:: sortlevel (pd_test_1_all.cpp:14676) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 14666 :emphasize-lines: 11 void pd_test_multiindex_sortlevel() { std::cout << "========= sortlevel =================================== "; std::vector> arrays = { {"b", "a", "c"}, {"2", "1", "3"} }; pandas::MultiIndex mi = pandas::MultiIndex::from_arrays(arrays); auto [sorted, indices] = mi.sortlevel(0); bool passed = true; // After sorting by level 0: a, b, c if (sorted[0][0] != "a" || sorted[1][0] != "b" || sorted[2][0] != "c") { std::cout << " [FAIL] : not sorted correctly by level 0" << std::endl; passed = false; } if (!passed) { .. _example-datetimeindex-str-120: .. dropdown:: str (pd_test_1_all.cpp:7137) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 7127 :emphasize-lines: 11 // Test basic info() with stringstream std::map> data = { {"A", {1, 2, 3, 4, 5}}, {"B", {10, 20, 30, 40, 50}}, {"C", {100, 200, 300, 400, 500}} }; pandas::DataFrame df(data); std::ostringstream oss; df.info(oss); std::string output = oss.str(); // Verify key components if (output.find("") == std::string::npos) { std::cout << " [FAIL] : info missing class name" << std::endl; throw std::runtime_error("pd_test_dataframe_info failed: missing class name"); } if (output.find("RangeIndex:") == std::string::npos) { std::cout << " [FAIL] : info missing RangeIndex" << std::endl; throw std::runtime_error("pd_test_dataframe_info failed: missing RangeIndex"); } .. _example-datetimeindex-ts-121: .. dropdown:: ts (pd_test_2_all.cpp:22590) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 22580 :emphasize-lines: 11 void test_to_datetime_numeric_seconds() { std::cout << " -- test_to_datetime_numeric_seconds --" << std::endl; // 1490195805 seconds = 2017-03-22 15:16:45 UTC std::vector vals = {1490195805.0}; auto arr = pandas::to_datetime_numeric(vals, "s"); check(arr.size() == 1, "size==1"); auto v = arr[0]; check(v.has_value(), "has_value"); if (v.has_value()) { pandas::Timestamp ts(v->getValue()); check(ts.year() == 2017, "year==2017"); check(ts.month() == 3, "month==3"); check(ts.day() == 22, "day==22"); check(ts.hour() == 15, "hour==15"); check(ts.minute() == 16, "min==16"); check(ts.second() == 45, "sec==45"); } } void test_to_datetime_numeric_millis() { .. _example-datetimeindex-ts-122: .. dropdown:: ts (pd_test_2_all.cpp:22590) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 22580 :emphasize-lines: 11 void test_to_datetime_numeric_seconds() { std::cout << " -- test_to_datetime_numeric_seconds --" << std::endl; // 1490195805 seconds = 2017-03-22 15:16:45 UTC std::vector vals = {1490195805.0}; auto arr = pandas::to_datetime_numeric(vals, "s"); check(arr.size() == 1, "size==1"); auto v = arr[0]; check(v.has_value(), "has_value"); if (v.has_value()) { pandas::Timestamp ts(v->getValue()); check(ts.year() == 2017, "year==2017"); check(ts.month() == 3, "month==3"); check(ts.day() == 22, "day==22"); check(ts.hour() == 15, "hour==15"); check(ts.minute() == 16, "min==16"); check(ts.second() == 45, "sec==45"); } } void test_to_datetime_numeric_millis() { .. _example-datetimeindex-ts-123: .. dropdown:: ts (pd_test_2_all.cpp:22590) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 22580 :emphasize-lines: 11 void test_to_datetime_numeric_seconds() { std::cout << " -- test_to_datetime_numeric_seconds --" << std::endl; // 1490195805 seconds = 2017-03-22 15:16:45 UTC std::vector vals = {1490195805.0}; auto arr = pandas::to_datetime_numeric(vals, "s"); check(arr.size() == 1, "size==1"); auto v = arr[0]; check(v.has_value(), "has_value"); if (v.has_value()) { pandas::Timestamp ts(v->getValue()); check(ts.year() == 2017, "year==2017"); check(ts.month() == 3, "month==3"); check(ts.day() == 22, "day==22"); check(ts.hour() == 15, "hour==15"); check(ts.minute() == 16, "min==16"); check(ts.second() == 45, "sec==45"); } } void test_to_datetime_numeric_millis() { .. _example-datetimeindex-type_id-124: .. dropdown:: type_id (pd_test_3_all.cpp:25592) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 25582 :emphasize-lines: 11 // ------------------- 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 ::pandas::Index si(std::vector{"a", "b", "c"}); if (si.type_id() != ::pandas::IndexTypeId::IndexString) throw std::runtime_error("Index type_id failed"); // Index ::pandas::Index ii(std::vector{1, 2, 3}); if (ii.type_id() != ::pandas::IndexTypeId::IndexInt64) .. _example-datetimeindex-upsample-125: .. dropdown:: upsample (pd_test_5_all.cpp:87061) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 87051 :emphasize-lines: 11 pandas::DataFrame df; std::vector v(idx.size(), 0); df.add_column("v", v); df.set_index(std::make_unique(idx)); return df; } void f_core_05_upsample_05f4ab_case_1_hourly_of_daily(int& local_fail) { std::cout << "-- case_1_hourly_of_daily\n"; auto idx = mk_idx({"2020-01-01", "2020-01-02", "2020-01-03"}); auto up = idx.upsample(pandas::Hour(1)); pandas_tests::check(up.size() == 49, "case_1.hourly_of_daily.size==49", local_fail); } void f_core_05_upsample_05f4ab_case_2_minute_of_hourly(int& local_fail) { std::cout << "-- case_2_minute_of_hourly\n"; auto idx = mk_idx({"2020-01-01T00:00:00", "2020-01-01T02:00:00"}); auto up = idx.upsample(pandas::Minute(1)); pandas_tests::check(up.size() == 121, "case_2.minute_of_hourly.size==121", local_fail); .. _example-datetimeindex-upsample-126: .. dropdown:: upsample (pd_test_5_all.cpp:87061) :class-title: example-dropdown .. code-block:: cpp :linenos: :lineno-start: 87051 :emphasize-lines: 11 pandas::DataFrame df; std::vector v(idx.size(), 0); df.add_column("v", v); df.set_index(std::make_unique(idx)); return df; } void f_core_05_upsample_05f4ab_case_1_hourly_of_daily(int& local_fail) { std::cout << "-- case_1_hourly_of_daily\n"; auto idx = mk_idx({"2020-01-01", "2020-01-02", "2020-01-03"}); auto up = idx.upsample(pandas::Hour(1)); pandas_tests::check(up.size() == 49, "case_1.hourly_of_daily.size==49", local_fail); } void f_core_05_upsample_05f4ab_case_2_minute_of_hourly(int& local_fail) { std::cout << "-- case_2_minute_of_hourly\n"; auto idx = mk_idx({"2020-01-01T00:00:00", "2020-01-01T02:00:00"}); auto up = idx.upsample(pandas::Minute(1)); pandas_tests::check(up.size() == 121, "case_2.minute_of_hourly.size==121", local_fail);