SeriesResampler

class pandas::SeriesResampler

Window operation class for rolling/expanding calculations.

Example

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

// Use SeriesResampler
SeriesResampler obj;
// ... operations ...

Constructors

Signature	Location	Example
SeriesResampler(const Series<T>& series, const std::string& freq, const std::string& closed = "", const std::string& label = "", const std::string& origin = "epoch", int64_t offset_nanos = 0)	pd_resampler.h:456

Indexing / Selection

Signature	Return Type	Location	Example
Series<T> first() const	Series<T>	pd_resampler.h:493	View
int64_t get_period_key(int64_t epoch_ns) const	int64_t	pd_resampler.h:525
Series<T> last() const	Series<T>	pd_resampler.h:494	View

Missing Data

Signature	Return Type	Location	Example
Series<T> bfill() const	Series<T>	pd_resampler.h:498	View
Series<T> ffill(int limit = -1) const	Series<T>	pd_resampler.h:497	View

Statistics

Signature	Return Type	Location	Example
Series<int64_t> count() const	Series<int64_t>	pd_resampler.h:482	View
Series<T> max() const	Series<T>	pd_resampler.h:475	View
Series<double> mean() const	Series<double>	pd_resampler.h:473	View
Series<double> median() const	Series<double>	pd_resampler.h:483	View
Series<T> min() const	Series<T>	pd_resampler.h:474	View
Series<double> prod() const	Series<double>	pd_resampler.h:484	View
Series<double> std_(int ddof = 1) const	Series<double>	pd_resampler.h:476	View
Series<double> sum() const	Series<double>	pd_resampler.h:472	View
Series<double> var(int ddof = 1) const	Series<double>	pd_resampler.h:477	View

Aggregation

Signature	Return Type	Location	Example
Series<double> agg(const std::string& func) const	Series<double>	pd_resampler.h:487	View
DataFrame agg_dict(const std::vector<std::pair<std::string, std::vector<std::string>>>& col_funcs) const	DataFrame	pd_resampler.h:490
Series<T> apply( const std::function<pandas::ApplyCellResult(const Series<T>&)>& cb) const	Series<T>	pd_resampler.h:512	View

Comparison

Signature	Return Type	Location	Example
Series<T> nearest() const	Series<T>	pd_resampler.h:500

Time Series

Signature	Return Type	Location	Example
Series<T> asfreq() const	Series<T>	pd_resampler.h:499	View

Other Methods

Signature	Return Type	Location	Example
void build_groups()	void	pd_resampler.h:524
const std::vector<int64_t>& group_keys() const	const std::vector<int64_t>&	pd_resampler.h:520
const std::unordered_map<int64_t, std::vector<size_t>>& groups() const	const std::unordered_map<int64_t, std::vector<size_t>>&	pd_resampler.h:519	View
size_t ngroups() const { return group_keys_order_.size()	size_t	pd_resampler.h:516	View
int64_t period_key_to_timestamp(int64_t key) const	int64_t	pd_resampler.h:526
const Series<T>& series() const	const Series<T>&	pd_resampler.h:521	View
void set_result_datetime_index(Series<ResultT>& result) const	void	pd_resampler.h:529

Code Examples

The following examples are extracted from the test suite.

first (pd_test_1_all.cpp:11616)

        void pd_test_groupby_first_last() {
            std::cout << "========= GroupBy first/last ====================";

            std::map<std::string, std::vector<double>> data = {
                {"category", {1.0, 1.0, 2.0, 2.0}},
                {"value", {10.0, 20.0, 30.0, 40.0}}
            };
            pandas::DataFrame df(data);

            auto first_result = df.groupby("category").first();
            auto last_result = df.groupby("category").last();

            // First for group 1: 10, group 2: 30
            // Last for group 1: 20, group 2: 40
            double first1 = std::stod(first_result["value"].get_value_str(0));
            double first2 = std::stod(first_result["value"].get_value_str(1));

            bool passed = ((std::abs(first1 - 10.0) < 0.001 && std::abs(first2 - 30.0) < 0.001) ||
                          (std::abs(first1 - 30.0) < 0.001 && std::abs(first2 - 10.0) < 0.001));
            if (!passed) {

last (pd_test_1_all.cpp:11617)

        void pd_test_groupby_first_last() {
            std::cout << "========= GroupBy first/last ====================";

            std::map<std::string, std::vector<double>> data = {
                {"category", {1.0, 1.0, 2.0, 2.0}},
                {"value", {10.0, 20.0, 30.0, 40.0}}
            };
            pandas::DataFrame df(data);

            auto first_result = df.groupby("category").first();
            auto last_result = df.groupby("category").last();

            // First for group 1: 10, group 2: 30
            // Last for group 1: 20, group 2: 40
            double first1 = std::stod(first_result["value"].get_value_str(0));
            double first2 = std::stod(first_result["value"].get_value_str(1));

            bool passed = ((std::abs(first1 - 10.0) < 0.001 && std::abs(first2 - 30.0) < 0.001) ||
                          (std::abs(first1 - 30.0) < 0.001 && std::abs(first2 - 10.0) < 0.001));
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_groupby_first_last() : first values incorrect" << std::endl;

bfill (pd_test_1_all.cpp:23603)

        std::cout << "====================================== [OK] pd_test_equals test suite ========================== " << std::endl;
        return 0;
    }

} // namespace dataframe_tests
// ------------------- pd_test_equals.cpp (end) -----------------------------

// ------------------- pd_test_ffill_bfill.cpp (start) -----------------------------
// dataframe_tests/pd_test_ffill_bfill.cpp
// Test file for DataFrame.ffill() and DataFrame.bfill() methods

#include <iostream>
#include <stdexcept>
#include <cmath>
#include <limits>
#include <map>
#include "../pandas/pd_dataframe.h"

// CRITICAL: No using namespace directives

ffill (pd_test_1_all.cpp:23603)

        std::cout << "====================================== [OK] pd_test_equals test suite ========================== " << std::endl;
        return 0;
    }

} // namespace dataframe_tests
// ------------------- pd_test_equals.cpp (end) -----------------------------

// ------------------- pd_test_ffill_bfill.cpp (start) -----------------------------
// dataframe_tests/pd_test_ffill_bfill.cpp
// Test file for DataFrame.ffill() and DataFrame.bfill() methods

#include <iostream>
#include <stdexcept>
#include <cmath>
#include <limits>
#include <map>
#include "../pandas/pd_dataframe.h"

// CRITICAL: No using namespace directives

count (pd_test_1_all.cpp:66)

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

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

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

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

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

max (pd_test_1_all.cpp:771)

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

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

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

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

mean (pd_test_1_all.cpp:282)

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

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

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

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

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

median (pd_test_1_all.cpp:20910)

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

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

        void pd_test_expanding_median() {
            std::cout << "========= Expanding median ======================";

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

            // Expanding median: 1, 1.5, 2, 2.5, 3
            bool passed = std::abs(result[0] - 1.0) < 0.001 &&
                          std::abs(result[1] - 1.5) < 0.001 &&
                          std::abs(result[2] - 2.0) < 0.001 &&
                          std::abs(result[3] - 2.5) < 0.001 &&
                          std::abs(result[4] - 3.0) < 0.001;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_expanding_median() : expanding median values incorrect" << std::endl;
                throw std::runtime_error("pd_test_expanding_median failed: expanding median values incorrect");

min (pd_test_1_all.cpp:764)

    }

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

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

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

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

prod (pd_test_1_all.cpp:26082)

        std::cout << "====================================== [OK] pd_test_pivot_table test suite ========================== " << std::endl;
        return 0;
    }

} // namespace dataframe_tests
// ------------------- pd_test_pivot_table.cpp (end) -----------------------------

// ------------------- pd_test_prod.cpp (start) -----------------------------
// dataframe_tests/pd_test_prod.cpp
// Tests for DataFrame.prod() and DataFrame.prod_cols() methods

#include <iostream>
#include <stdexcept>
#include <cmath>
#include <limits>
#include "../pandas/pd_dataframe.h"

// CRITICAL: No using namespace directives

namespace dataframe_tests {

std_ (pd_test_1_all.cpp:20752)

                throw std::runtime_error("pd_test_rolling_min_periods failed: with min_periods=1, idx 1 should be 3.0");
            }

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

        void pd_test_rolling_std() {
            std::cout << "========= Rolling std ===========================";

            pandas::Series<double> s({1.0, 2.0, 3.0, 4.0, 5.0});
            auto result = s.rolling(3).std_();

            // std([1,2,3]) = 1.0 (ddof=1)
            // std([2,3,4]) = 1.0
            // std([3,4,5]) = 1.0
            bool passed = std::abs(result[2] - 1.0) < 0.001;
            if (!passed) {
                std::cout << "  [FAIL] : in pd_test_rolling_std() : rolling std should be 1.0" << std::endl;
                throw std::runtime_error("pd_test_rolling_std failed: rolling std should be 1.0");
            }

sum (pd_test_1_all.cpp:276)

        }

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

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

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

var (pd_test_1_all.cpp:20890)

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

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

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

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

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

agg (pd_test_1_all.cpp:11100)

        }

        void pd_test_func_apply_series_agg() {
            std::cout << "========= Series agg ==================================";

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

            bool passed = true;

            // Test string-based aggregation
            auto sum_result = s.agg("sum");
            if (!sum_result.has_value() || !approx_equal(sum_result.value(), 15.0)) {
                passed = false;
                std::cout << "  [FAIL] : in pd_test_func_apply_series_agg() : sum failed" << std::endl;
                throw std::runtime_error("pd_test_func_apply_series_agg failed: sum failed");
            }

            auto mean_result = s.agg("mean");
            if (!mean_result.has_value() || !approx_equal(mean_result.value(), 3.0)) {
                passed = false;
                std::cout << "  [FAIL] : in pd_test_func_apply_series_agg() : mean failed" << std::endl;

apply (pd_test_1_all.cpp:11244)

        void pd_test_func_apply_dataframe_apply_axis0() {
            std::cout << "========= DataFrame apply axis=0 ======================";

            std::map<std::string, std::vector<double>> data = {
                {"A", {1.0, 2.0, 3.0}},
                {"B", {4.0, 5.0, 6.0}}
            };
            pandas::DataFrame df(data);

            // apply axis=0 applies function to each column
            auto result = df.apply([](const std::vector<double>& col) {
                return std::accumulate(col.begin(), col.end(), 0.0);
            }, 0);

            bool passed = true;

            // Plan F·dtype: axis=0 reduce now returns a single "result" column
            // with the original column names ("A", "B") as the row index.
            // Sum of A: 1+2+3=6, Sum of B: 4+5+6=15
            const auto& result_col = result["result"];
            double sum_a = std::stod(result_col.get_value_str(0));

asfreq (pd_test_1_all.cpp:2869)

        std::cout << "========= PeriodArray: asfreq ======================= ";

        // Monthly to quarterly
        pandas::PeriodArray arr_m(std::vector<std::string>{
            "2024-01",
            "2024-04",
            "2024-07",
            "NaT"
        }, "M");

        auto arr_q = arr_m.asfreq("Q");
        if (arr_q.size() != 4) {
            std::cout << "  [FAIL] : asfreq size should be 4" << std::endl;
            throw std::runtime_error("pd_test_period_array_asfreq failed: size");
        }
        if (arr_q.freqstr() != "Q") {
            std::cout << "  [FAIL] : asfreq freqstr should be 'Q'" << std::endl;
            throw std::runtime_error("pd_test_period_array_asfreq failed: freqstr");
        }

        // Check NaT is preserved

groups (pd_test_2_all.cpp:20864)

// =====================================================================
// Per-group expanding tests
// =====================================================================

void test_series_groupby_expanding_sum() {
    std::cout << "  -- test_series_groupby_expanding_sum --" << std::endl;

    // Two groups: A=[1,2,3], B=[10,20]
    std::vector<numpy::float64> vals = {1.0, 10.0, 2.0, 20.0, 3.0};
    pandas::Series<numpy::float64> data(vals);
    pandas::Series<std::string> groups({"A", "B", "A", "B", "A"});

    auto sgb = data.groupby(groups);
    pandas::SeriesGroupByExpandingWindow ew(sgb, 1);
    auto result = ew.sum();

    check(result.size() == 5, "size_5");
    // A group: expanding sum = 1, 3, 6
    // B group: expanding sum = 10, 30
    // Original order: [A:1, B:10, A:3, B:30, A:6]
    check(approx_eq(result[0], 1.0), "A_exp_sum_0");

ngroups (pd_test_1_all.cpp:11497)

            // Create DataFrame with category column
            std::map<std::string, std::vector<double>> 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;
        }

        void pd_test_groupby_multiple_columns() {
            std::cout << "========= GroupBy multiple columns ==============";

series (pd_test_2_all.cpp:2307)

            std::vector<std::string> index = {"a", "b", "c", "d", "e"};

            std::map<std::string, std::vector<numpy::float64>> data1;
            data1["col1"] = {1.0, 2.0, 3.0, 4.0, 5.0};
            data1["col2"] = {2.0, 4.0, 6.0, 8.0, 10.0};  // Perfectly correlated with col1

            pandas::DataFrame df1(data1, std::make_unique<pandas::Index<std::string>>(index));

            // Series with same index and values that correlate with df columns
            pandas::Series<numpy::float64> series({1.0, 2.0, 3.0, 4.0, 5.0});
            series.set_index(pandas::Index<std::string>(index));

            pandas::Series<numpy::float64> result = df1.corrwith(series);

            bool passed = true;
            // col1 should have correlation 1.0 with series
            if (!approx_equal(result[0], 1.0)) {
                std::cout << "\n  [FAIL] : Expected correlation 1.0 for col1, got " << result[0] << std::endl;
                passed = false;
            }