Creating k-NN with C++ (from Scratch)

This page summarizes the projects mentioned and recommended in the original post on dev.to

Our great sponsors
  • WorkOS - The modern identity platform for B2B SaaS
  • InfluxDB - Power Real-Time Data Analytics at Scale
  • SaaSHub - Software Alternatives and Reviews
  • knn_cpp

  • Full Source code

  • matplotplusplus

    Matplot++: A C++ Graphics Library for Data Visualization 📊🗾

  • cmake_minimum_required(VERSION 3.5) project(knn_cpp CXX) # Set up C++ version and properties include(CheckIncludeFileCXX) check_include_file_cxx(any HAS_ANY) check_include_file_cxx(string_view HAS_STRING_VIEW) check_include_file_cxx(coroutine HAS_COROUTINE) set(CMAKE_CXX_STANDARD 20) set(CMAKE_BUILD_TYPE Debug) set(CMAKE_CXX_STANDARD_REQUIRED ON) set(CMAKE_CXX_EXTENSIONS OFF) # Copy data file to build directory file(COPY ${CMAKE_CURRENT_SOURCE_DIR}/iris.data DESTINATION ${CMAKE_CURRENT_BINARY_DIR}) # Download library usinng FetchContent include(FetchContent) FetchContent_Declare(matplotplusplus GIT_REPOSITORY https://github.com/alandefreitas/matplotplusplus GIT_TAG origin/master) FetchContent_GetProperties(matplotplusplus) if(NOT matplotplusplus_POPULATED) FetchContent_Populate(matplotplusplus) add_subdirectory(${matplotplusplus_SOURCE_DIR} ${matplotplusplus_BINARY_DIR} EXCLUDE_FROM_ALL) endif() FetchContent_Declare( fmt GIT_REPOSITORY https://github.com/fmtlib/fmt.git GIT_TAG 7.1.3 # Adjust the version as needed ) FetchContent_MakeAvailable(fmt) # Add executable and link project libraries and folders add_executable(${PROJECT_NAME} main.cc) target_link_libraries(${PROJECT_NAME} PUBLIC matplot fmt::fmt) aux_source_directory(lib LIB_SRC) target_include_directories(${PROJECT_NAME} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}) target_sources(${PROJECT_NAME} PRIVATE ${LIB_SRC}) add_subdirectory(tests)

  • WorkOS

    The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

    WorkOS logo
  • C++ Format

    A modern formatting library

  • cmake_minimum_required(VERSION 3.5) project(knn_cpp CXX) # Set up C++ version and properties include(CheckIncludeFileCXX) check_include_file_cxx(any HAS_ANY) check_include_file_cxx(string_view HAS_STRING_VIEW) check_include_file_cxx(coroutine HAS_COROUTINE) set(CMAKE_CXX_STANDARD 20) set(CMAKE_BUILD_TYPE Debug) set(CMAKE_CXX_STANDARD_REQUIRED ON) set(CMAKE_CXX_EXTENSIONS OFF) # Copy data file to build directory file(COPY ${CMAKE_CURRENT_SOURCE_DIR}/iris.data DESTINATION ${CMAKE_CURRENT_BINARY_DIR}) # Download library usinng FetchContent include(FetchContent) FetchContent_Declare(matplotplusplus GIT_REPOSITORY https://github.com/alandefreitas/matplotplusplus GIT_TAG origin/master) FetchContent_GetProperties(matplotplusplus) if(NOT matplotplusplus_POPULATED) FetchContent_Populate(matplotplusplus) add_subdirectory(${matplotplusplus_SOURCE_DIR} ${matplotplusplus_BINARY_DIR} EXCLUDE_FROM_ALL) endif() FetchContent_Declare( fmt GIT_REPOSITORY https://github.com/fmtlib/fmt.git GIT_TAG 7.1.3 # Adjust the version as needed ) FetchContent_MakeAvailable(fmt) # Add executable and link project libraries and folders add_executable(${PROJECT_NAME} main.cc) target_link_libraries(${PROJECT_NAME} PUBLIC matplot fmt::fmt) aux_source_directory(lib LIB_SRC) target_include_directories(${PROJECT_NAME} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}) target_sources(${PROJECT_NAME} PRIVATE ${LIB_SRC}) add_subdirectory(tests)

  • Google Test

    GoogleTest - Google Testing and Mocking Framework

  • cmake_minimum_required(VERSION 3.5) project(knn_cpp CXX) include(FetchContent) FetchContent_Declare( googletest GIT_REPOSITORY https://github.com/google/googletest.git GIT_TAG release-1.11.0 ) FetchContent_MakeAvailable(googletest) FetchContent_Declare(matplotplusplus GIT_REPOSITORY https://github.com/alandefreitas/matplotplusplus GIT_TAG origin/master) FetchContent_GetProperties(matplotplusplus) if(NOT matplotplusplus_POPULATED) FetchContent_Populate(matplotplusplus) add_subdirectory(${matplotplusplus_SOURCE_DIR} ${matplotplusplus_BINARY_DIR} EXCLUDE_FROM_ALL) endif() function(knn_cpp_test TEST_NAME TEST_SOURCE) add_executable(${TEST_NAME} ${TEST_SOURCE}) target_link_libraries(${TEST_NAME} PUBLIC matplot) aux_source_directory(${CMAKE_CURRENT_SOURCE_DIR}/../lib LIB_SOURCES) target_link_libraries(${TEST_NAME} PRIVATE gtest gtest_main gmock gmock_main) target_include_directories(${TEST_NAME} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_SOURCE_DIR}/../) target_sources(${TEST_NAME} PRIVATE ${LIB_SOURCES} ) include(GoogleTest) gtest_discover_tests(${TEST_NAME}) endfunction() knn_cpp_test(LinearAlgebraTest la_test.cc) knn_cpp_test(KnnTest knn_test.cc) knn_cpp_test(UtilsTest utils_test.cc)

  • cmake-tools.nvim: You can find it here

  • data-science-from-scratch

    code for Data Science From Scratch book

  • # This is python code from https://github.com/joelgrus/data-science-from-scratch/blob/master/scratch/machine_learning.py def split_data(data: List[X], prob: float) -> Tuple[List[X], List[X]]: """Split data into fractions [prob, 1 - prob]""" data = data[:] # Make a shallow copy random.shuffle(data) # because shuffle modifies the list. cut = int(len(data) * prob) # Use prob to find a cutoff return data[:cut], data[cut:] # and split the shuffled list there.

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a more popular project.

Suggest a related project

Related posts