README.fr.md : Fix typos

.gitignore

@@ -1,6 +1,6 @@
 data
 */models*
-venv
+.venv
 */out*
 python/__pycache__
 cpp/bin

README.fr.md

@@ -1,6 +1,6 @@
 # Viola Jones
 
-*Lisez ceci dans d'autres langues: [English](README.md)*
+*Lisez ceci dans d'autres langues : [English](README.md)*
 
 ## Description
 
@@ -23,7 +23,7 @@ Implémentation de l'algorithme "Viola Jones" en Python et C++.
 
 Vous pouvez configurer l'algorithme avec les variables globales définies au début du fichier *ViolaJones.cpp* puis lancer 'make start'.
 
-Il y a également la commande 'make clean' qui permet de supprimer tout fichiers compilées.
+Il y a également la commande 'make clean' qui permet de supprimer tous fichiers compilés.
 
 ### Python
 
@@ -34,7 +34,7 @@ Vous pouvez configurer l'algorithme dans le fichier *config.py* puis lancer l'al
 
 ## Entraînement
 
-L'algorithme à été entraîné avec un processeur Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz et un GPU NVIDIA GeForce RTX 2080 Ti.
+L'algorithme a été entraîné avec un processeur Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz et un GPU NVIDIA GeForce RTX 2080 Ti.
 
 ### Tableau de comparaison des temps d'exécution
 
@@ -66,7 +66,7 @@ Il se trouve que le GPU bat systématiquement le CPU en matière de temps d'exé
 
 L'algorithme de ViolaJones étant déterministe, tous les modèles entraînés avec un T donnée, peu importe le moyen (CPU, NJIT ou GPU), seront les mêmes modèles avec les mêmes paramètres.
 
-Rappel: ACC (Accuracy i.e. Précision), F1 (Score F1), FN (Faux Négatif) et FP (Faux Positif).
+Rappel : ACC (Accuracy i.e. Précision), F1 (Score F1), FN (Faux Négatif) et FP (Faux Positif).
 
 | Evaluating         | ACC (E) | F1 (E) | FN (E) | FP (E) | ACC (T) | F1 (T) | FN (T) | FP (T) |
 | ------------------ | ------- | ------ | ------ | ------ | ------- | ------ | ------ | ------ |
@@ -202,7 +202,7 @@ L'algorithme de ViolaJones étant déterministe, les fichiers devraient être é
 | ViolaJones T = 200 (NJIT) | 3,989,600           | 3ms 989µs 600ns          | 15,957,700          | 15ms 957µs 700ns         |
 | ViolaJones T = 300 (NJIT) | 5,983,900           | 5ms 983µs 900ns          | 23,935,500          | 23ms 935µs 500ns         |
 
-## Resources additionnels
+## Ressources additionnelles
 
 - [Rapid Object Detection using a Boosted Cascade of Simple Features](https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/viola-cvpr-01.pdf)
 - [Chapter 39. Parallel Prefix Sum (Scan) with CUDA](https://developer.nvidia.com/gpugems/gpugems3/part-vi-gpu-computing/chapter-39-parallel-prefix-sum-scan-cuda)

cpp/Dockerfile

@@ -1,15 +1,15 @@
-FROM nvidia/cuda:12.4.1-devel-ubi9 as builder
+FROM nvidia/cuda:12.6.2-devel-ubi9 AS builder
 
 WORKDIR /home/ViolaJones/cpp
 
 COPY *.cu *.cpp *.hpp Makefile ./
-RUN make -j "$(nproc)"
+RUN make -j "$(nproc)" && make -j "$(nproc)" ./bin/ViolaJonesTest
 
-FROM nvidia/cuda:12.4.1-base-ubi9
+FROM nvidia/cuda:12.6.2-base-ubi9
 
 WORKDIR /home/ViolaJones/cpp
 
-RUN dnf install -y make-1:4.3-7.el9 && dnf clean all
+RUN dnf install -y make-1:4.3-8.el9 && dnf clean all
 COPY --from=builder /home/ViolaJones/cpp/bin ./bin
 COPY --from=builder /home/ViolaJones/cpp/Makefile .
 

cpp/Makefile

@@ -8,10 +8,12 @@ DATA_PATH := ../data
 #CFLAGS := -O0 -g -G -pg -Xptxas=-w -Xcompiler -O0,-rdynamic,-g
 CFLAGS := -dlto -O2 -Xcompiler -O2
 #CFLAGS := -dlto -O2 -g -Xcompiler -O2,-g,-ggdb
-CFLAGS := $(CFLAGS) -MMD -MP -Werror=all-warnings -Xcompiler -Wall,-Werror,-Werror=implicit-fallthrough=0,-Wextra
+CFLAGS := $(CFLAGS) -MMD -MP -Werror=all-warnings -Xcompiler -Wall,-Werror,-Wextra
 EXEC := $(OBJ_DIR)/ViolaJones
+EXEC_TEST := $(OBJ_DIR)/ViolaJonesTest
 DATA := $(DATA_PATH)/X_train.bin $(DATA_PATH)/X_test.bin $(DATA_PATH)/y_train.bin $(DATA_PATH)/y_test.bin
-SRC := $(shell find $(SRC_DIR) -name '*.cpp' -o -name '*.cu')
+SRC := $(shell find $(SRC_DIR) \( -name '*.cpp' -o -name '*.cu' \) -and -not -name projet_test.cpp)
+SRC_TEST := $(shell find $(SRC_DIR) \( -name '*.cpp' -o -name '*.cu' \) -and -not -name projet.cpp)
 OBJ_EXT := o
 ifeq ($(OS), Windows_NT)
 	EXEC := $(EXEC).exe
@@ -19,6 +21,8 @@ ifeq ($(OS), Windows_NT)
 endif
 OBJ := $(SRC:$(SRC_DIR)/%.cpp=$(OBJ_DIR)/%.$(OBJ_EXT))
 OBJ := $(OBJ:$(SRC_DIR)/%.cu=$(OBJ_DIR)/%.$(OBJ_EXT))
+OBJ_TEST := $(SRC_TEST:$(SRC_DIR)/%.cpp=$(OBJ_DIR)/%.$(OBJ_EXT))
+OBJ_TEST := $(OBJ_TEST:$(SRC_DIR)/%.cu=$(OBJ_DIR)/%.$(OBJ_EXT))
 
 .PHONY: all
 all: $(EXEC)
@@ -42,6 +46,12 @@ $(EXEC): $(OBJ)
 	@echo Linking objects files to $@
 	@$(CC) $(CFLAGS) $^ -o $@
 
+# FIXME When using the docker image, Make check prequisites even when the target already exists
+#$(EXEC_TEST): $(OBJ_TEST) | check-nvcc-works
+$(EXEC_TEST): $(OBJ_TEST)
+	@echo Linking objects files to $@
+	@$(CC) $(CFLAGS) $^ -o $@
+
 $(DATA):
 	@echo 'Missing $(DATA) files, use downloader first' && exit 1
 
@@ -49,6 +59,10 @@ $(DATA):
 start: $(EXEC) $(DATA)
 	@./$(EXEC)
 
+.PHONY: test
+test: $(EXEC_TEST)
+	@./$(EXEC_TEST)
+
 .PHONY: debug
 debug: $(EXEC) $(DATA)
 	#@cuda-gdb -q $(EXEC)
@@ -63,7 +77,7 @@ check: $(EXEC) $(DATA) | check-valgrind-works
 	@valgrind -q -s --leak-check=full --show-leak-kinds=all $(EXEC)
 
 .PHONY: cudacheck
-cudacheck: $(EXEC) $(DATA) | check-computer-sanitizer-works
+cudacheck: $(EXEC) $(DATA) | check-compute-sanitizer-works
 	@compute-sanitizer --destroy-on-device-error kernel --tool memcheck --leak-check full --report-api-errors all --track-stream-ordered-races all --target-processes all $(EXEC)
 	#@compute-sanitizer --destroy-on-device-error kernel --tool racecheck --racecheck-detect-level info --racecheck-report all $(EXEC)
 	#@compute-sanitizer --destroy-on-device-error kernel --tool initcheck --track-unused-memory yes $(EXEC)
@@ -88,9 +102,7 @@ log: $(DATA) reset
 .PHONY: reset
 reset:
 	@echo 'Deleting generated states and models'
-	@rm -frv $(OUT_DIR)/* $(MODELS_DIR)/*
-#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/models .
-#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/out .
+	@rm -frv $(OUT_DIR) $(MODELS_DIR)
 
 .PHONY: clean
 clean:
@@ -130,8 +142,8 @@ check-dot-works:
 check-valgrind-works:
 	@valgrind --version >/dev/null 2>&1 || (echo 'Please install valgrind.' && exit 1)
 
-.PHONY: check-computer-sanitizer-works
-check-computer-sanitizer-works:
-	@computer-sanitizer --version >/dev/null 2>&1 || (echo 'Please install Compute Sanitizer from Cuda toolkit.' && exit 1)
+.PHONY: check-compute-sanitizer-works
+check-compute-sanitizer-works:
+	@compute-sanitizer --version >/dev/null 2>&1 || (echo 'Please install Compute Sanitizer from Cuda toolkit.' && exit 1)
 
 -include $(OBJ:.o=.d)

cpp/ViolaJones.hpp

@@ -9,7 +9,7 @@
  * @tparam T Inner type of the arrays to test
  * @param cpu CPU Array
  * @param gpu GPU Array
- * @return Whether the test was succesful
+ * @return Whether the test was successful
  */
 template <typename T>
 bool unit_test_cpu_vs_gpu(const np::Array<T>& cpu, const np::Array<T>& gpu) noexcept {
@@ -249,7 +249,7 @@ np::Array<uint8_t> classify_viola_jones(const np::Array<float64_t>&, const np::A
 np::Array<float64_t> init_weights(const np::Array<uint8_t>&) noexcept;
 
 /**
- * @brief Select the best classifer given their predictions.
+ * @brief Select the best classifier given their predictions.
  *
  * @param classifiers The weak classifiers
  * @param weights Trained weights of each classifiers
@@ -261,7 +261,7 @@ std::tuple<int32_t, float64_t, np::Array<float64_t>> select_best(const np::Array
 								const np::Array<uint8_t>&) noexcept;
 
 /**
- * @brief Train the weak calssifiers.
+ * @brief Train the weak classifiers.
  *
  * @param T Number of weak classifiers
  * @param X_feat Integrated features

cpp/docker-compose.yaml

@@ -1,6 +1,7 @@
 services:
   violajones-cpp:
     image: saundersp/violajones-cpp
+    pull_policy: never
     build: .
     volumes:
       - ./models:/home/ViolaJones/cpp/models
@@ -11,5 +12,4 @@ services:
         reservations:
           devices:
             - driver: nvidia
-              count: 1
               capabilities: [gpu]

cpp/projet_test.cpp

@@ -0,0 +1,31 @@
+#include "toolbox.hpp"
+#include "config.hpp"
+#include "toolbox_unit_test.hpp"
+#include "ViolaJones.hpp"
+
+#if GPU_BOOSTED
+#include "gpu_unit_test.hpp"
+#endif
+
+int32_t main(void){
+	setlocale(LC_NUMERIC, ""); // Allow proper number display
+
+	const std::chrono::system_clock::time_point unit_timestamp = perf_counter_ns();
+	const std::array<int32_t, 3> unit_gaps = { 27, -18, 29 };
+	header(unit_gaps, { "Unit testing", "Time spent (ns)", "Formatted time spent" });
+#if GPU_BOOSTED
+	benchmark_function_void("Testing GPU capabilities 1D", unit_gaps[0], test_working, 50000);
+	benchmark_function_void("Testing GPU capabilities 2D", unit_gaps[0], test_working_2d, 200, 500);
+	benchmark_function_void("Testing GPU capabilities 3D", unit_gaps[0], test_working_3d, 30, 40, 500);
+#endif
+	benchmark_function_void("Testing format_time", unit_gaps[0], format_time_test);
+	benchmark_function_void("Testing format_time_ns", unit_gaps[0], format_time_ns_test);
+	benchmark_function_void("Testing format_byte_size", unit_gaps[0], format_byte_size_test);
+	benchmark_function_void("Testing thousand_sep", unit_gaps[0], thousand_sep_test);
+	const long long time_spent = duration_ns(perf_counter_ns() - unit_timestamp);
+	formatted_line(unit_gaps, "├", "┼", "─", "┤");
+	formatted_row(unit_gaps, { "Unit testing summary", thousand_sep(time_spent).c_str(), format_time_ns(time_spent).c_str() });
+	footer(unit_gaps);
+
+	return EXIT_SUCCESS;
+}

cpp/test.cpp

@@ -1,62 +0,0 @@
-#include <iostream>
-#include <iomanip>
-#include "data.hpp"
-#include "toolbox.hpp"
-
-#define PBSTR "||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||"
-#define PBWIDTH 60
-
-void printProgress(const float64_t& percentage) noexcept {
-	const uint64_t val = static_cast<uint64_t>(percentage * 100);
-	const int32_t lpad = static_cast<int32_t>(percentage * PBWIDTH);
-	const int32_t rpad = PBWIDTH - lpad;
-	fprintf(stderr, "%3lu%% [%.*s%*s]\r", val, lpad, PBSTR, rpad, "");
-	fflush(stderr);
-}
-
-void clearProgress(void) noexcept {
-	// Progress bar width + space before + num space + space after
-	fprintf(stderr, "%*c\r", PBWIDTH + 1 + 3 + 3, ' ');
-}
-
-template<typename T>
-void test(const uint64_t& N) noexcept {
-#if __DEBUG
-	printf("DETERMINISTIC for N=%s of %s sized %s\n", thousand_sep(N).c_str(), typeid(T).name(), format_byte_size(sizeof(T)).c_str());
-	printf("Estimating memory footprint at : %s\n", format_byte_size(3 * N * sizeof(T)).c_str());
-#endif
-
-	T *a = new T[N], *b = new T[N], *c = new T[N];
-
-	T mean = static_cast<T>(0.0);
-	const size_t percent = N / 100;
-	for(size_t i = 0; i < N; ++i){
-		if (i % percent == 0) printProgress(static_cast<float64_t>(i) / N);
-		a[i] = static_cast<T>(i < N>>1 ? 0.1 : 1.0);
-		b[i] = static_cast<T>(1.0);
-		c[i] = a[i] * b[i];
-		mean += c[i];
-	}
-	mean /= static_cast<T>(N);
-
-	clearProgress();
-	std::cout << mean << std::endl;
-
-	delete[] a, delete[] b, delete[] c;
-}
-
-void test_float(void) noexcept {
-	std::cout << std::setprecision(1<<8);
-	const uint64_t N = static_cast<uint64_t>(1)<<28;
-	test<float128_t>(N);
-	test<float64_t>(N);
-	test<float32_t>(N);
-
-	//printf("%.128af\n", static_cast<float64_t>(1) / 3);
-	//std::cout << static_cast<float64_t>(1) / 3 << std::endl;
-	//std::cout << std::hexfloat << static_cast<float64_t>(1) / 3 << std::endl;
-
-	//printf("%.128Lf\n", static_cast<long float64_t>(1) / 3);
-	//printf("%.128lf\n", static_cast<float64_t>(1) / 3);
-	//printf("%.128f\n", static_cast<float>(1) / 3);
-}

downloader/Dockerfile

@@ -1,6 +1,6 @@
-FROM alpine:3.19.1
+FROM alpine:3.20.3
 
-RUN apk add --no-cache curl=8.5.0-r0 python3=3.11.9-r0 && rm -rf /var/cache/apk*
+RUN apk add --no-cache curl=8.11.0-r1 python3=3.12.7-r0 && rm -rf /var/cache/apk*
 
 WORKDIR /home/ViolaJones/downloader
 COPY requirements.txt activate.sh ./

downloader/activate.sh

@@ -4,16 +4,14 @@
 set -e
 
 test -z "$EXEC_DIR" && EXEC_DIR=.
-test -z "$VENV_PATH" && VENV_PATH="$EXEC_DIR/venv"
+test -z "$VENV_PATH" && VENV_PATH="$EXEC_DIR/.venv"
 
 activate(){
 	if [ ! -d "$VENV_PATH" ]; then
 		echo 'Creating python virtual environnement'
-		python -m venv "$VENV_PATH"
+		python -m venv --upgrade-deps "$VENV_PATH"
 		echo 'Activating virtual environnement'
 		activate
-		echo 'Updating base pip packages'
-		python -m pip install -U setuptools pip
 		echo 'Installing requirements'
 		pip install -r requirements.txt
 	elif [ -f "$VENV_PATH"/Scripts/activate ]; then . "$VENV_PATH"/Scripts/activate

downloader/convert_dataset.py

@@ -3,29 +3,31 @@ from tqdm import tqdm
 from functools import partial
 from sys import argv
 import numpy as np
+from numpy.typing import NDArray
+from typing import Final, Callable
 from os import path, listdir
 
 # Induce determinism
-np.random.seed(133742)
+np.random.seed(196_863)
 
-# Makes the "leave" argument default to False
-tqdm = partial(tqdm, leave = False)
+# Makes the 'leave' argument default to False
+tqdm: Callable = partial(tqdm, leave = False)
 
-def read_pgm(pgm_file: BufferedReader) -> np.ndarray:
+def read_pgm(pgm_file: BufferedReader) -> NDArray[np.uint8]:
 	"""Read the data of a PGM file
 
 	Args:
 		pgm_file (BufferedReader): PGM File
 
 	Returns:
-		np.ndarray: PGM data
+		NDArray[np.uint8]: PGM data
 	"""
-	assert (f := pgm_file.readline()) == b'P5\n', f"Incorrect file format: {f}"
-	(width, height) = [int(i) for i in pgm_file.readline().split()]
-	assert width > 0 and height > 0, f"Incorrect dimensions: {width}x{height}"
-	assert (depth := int(pgm_file.readline())) < 256, f"Incorrect depth: {depth}"
+	assert (f := pgm_file.readline()) == b'P5\n', f'Incorrect file format: {f}'
+	(width, height) = (int(i) for i in pgm_file.readline().split())
+	assert width > 0 and height > 0, f'Incorrect dimensions: {width}x{height}'
+	assert (depth := int(pgm_file.readline())) < 256, f'Incorrect depth: {depth}'
 
-	buff = np.empty(height * width, dtype = np.uint8)
+	buff: Final[NDArray[np.uint8]] = np.empty(height * width, dtype = np.uint8)
 	for i in range(buff.shape[0]):
 		buff[i] = ord(pgm_file.read(1))
 	return buff.reshape((height, width))
@@ -36,25 +38,25 @@ def __main__(data_path: str) -> None:
 	Args:
 		data_path (str): Path of the PGM files
 	"""
-	for set_name in tqdm(["train", "test"], desc = "set name"):
+	for set_name in tqdm(['train', 'test'], desc = 'set name'):
 		X, y = [], []
-		for y_i, label in enumerate(tqdm(["non-face", "face"], desc = "label")):
-			for filename in tqdm(listdir(f"{data_path}/{set_name}/{label}"), desc = "Reading pgm file"):
-				with open(f"{data_path}/{set_name}/{label}/{filename}", "rb") as face:
+		for y_i, label in enumerate(tqdm(['non-face', 'face'], desc = 'label')):
+			for filename in tqdm(listdir(f'{data_path}/{set_name}/{label}'), desc = 'Reading pgm file'):
+				with open(f'{data_path}/{set_name}/{label}/{filename}', 'rb') as face:
 					X.append(read_pgm(face))
 					y.append(y_i)
 
 		X, y = np.asarray(X), np.asarray(y)
-		idx = np.random.permutation(y.shape[0])
+		idx: NDArray[np.int64] = np.random.permutation(y.shape[0])
 		X, y = X[idx], y[idx]
 
-		for org, s in tqdm(zip("Xy", [X, y]), desc = f"Writing {set_name}"):
-			with open(f"{data_path}/{org}_{set_name}.bin", "w") as out:
-				out.write(f'{str(s.shape)[1:-1].replace(",", "")}\n')
-				raw = s.ravel()
-				for s_i in tqdm(raw[:-1], desc = f"Writing {org}"):
-					out.write(f"{s_i} ")
+		for org, s in tqdm(zip('Xy', [X, y]), desc = f'Writing {set_name}'):
+			with open(f'{data_path}/{org}_{set_name}.bin', 'w') as out:
+				out.write(f'{str(s.shape)[1:-1].replace(',', '')}\n')
+				raw: NDArray = s.ravel()
+				for s_i in tqdm(raw[:-1], desc = f'Writing {org}'):
+					out.write(f'{s_i} ')
 				out.write(str(raw[-1]))
 
-if __name__ == "__main__":
-	__main__(argv[1]) if len(argv) == 2 else print(f"Usage: python {__file__[__file__.rfind(path.sep) + 1:]} ./data_location")
+if __name__ == '__main__':
+	__main__(argv[1]) if len(argv) == 2 else print(f'Usage: python {__file__[__file__.rfind(path.sep) + 1:]} ./data_location')

downloader/docker-compose.yaml

@@ -1,6 +1,7 @@
 services:
   downloader:
     image: saundersp/violajones-downloader
+    pull_policy: never
     build: .
     volumes:
       - ../data:/home/ViolaJones/data

downloader/requirements.txt

@@ -1,2 +1,2 @@
-numpy==1.26.4
-tqdm==4.66.2
+numpy==2.1.3
+tqdm==4.67.0

python/Dockerfile

@@ -1,7 +1,8 @@
-FROM nvidia/cuda:12.4.1-devel-ubi9 as builder
+FROM nvidia/cuda:12.6.2-devel-ubi9
 
-RUN dnf install -y python3.11-3.11.5-1.el9_3 && dnf clean all
-RUN ln -s /usr/bin/python3 /usr/bin/python
+RUN dnf install -y python3.12-3.12.1-4.el9_4.4 \
+	&& dnf clean all \
+	&& ln -s /usr/bin/python3.12 /usr/bin/python
 
 WORKDIR /home/ViolaJones/python
 COPY Makefile activate.sh requirements.txt ./

python/Makefile

@@ -17,6 +17,10 @@ venv:
 start: $(DATA) | venv check-python-works
 	@sh -c '. ./activate.sh && python projet.py'
 
+.PHONY: test
+test: | venv check-python-works
+	@sh -c '. ./activate.sh && python project_test.py'
+
 .PHONY: debug
 debug: $(DATA) | venv check-python-works check-pudb-works
 	@bash -c 'source activate.sh && pudb projet.py'
@@ -45,9 +49,7 @@ log: $(DATA) reset | venv
 .PHONY: reset
 reset:
 	@echo 'Deleting generated states and models'
-	@rm -frv $(OUT_DIR)/* $(MODELS_DIR)/*
-#@ln -sv /mnt/pierre_stuffs/ViolaJones/python/models .
-#@ln -sv /mnt/pierre_stuffs/ViolaJones/python/out .
+	@rm -frv $(OUT_DIR) $(MODELS_DIR)
 
 .PHONY: clean
 clean:
@@ -55,7 +57,7 @@ clean:
 
 .PHONY: mrproper
 mrproper: clean
-	@rm -rfv __pycache__ venv
+	@rm -rfv __pycache__ .venv
 
 .PHONY: help
 help:

python/activate.sh

@@ -4,16 +4,14 @@
 set -e
 
 test -z "$EXEC_DIR" && EXEC_DIR=.
-test -z "$VENV_PATH" && VENV_PATH="$EXEC_DIR/venv"
+test -z "$VENV_PATH" && VENV_PATH="$EXEC_DIR/.venv"
 
 activate(){
 	if [ ! -d "$VENV_PATH" ]; then
 		echo 'Creating python virtual environnement'
-		python -m venv "$VENV_PATH"
+		python -m venv --upgrade-deps "$VENV_PATH"
 		echo 'Activating virtual environnement'
 		activate
-		echo 'Updating base pip packages'
-		python -m pip install -U setuptools pip
 		echo 'Installing requirements'
 		pip install -r requirements.txt
 	elif [ -f "$VENV_PATH"/Scripts/activate ]; then . "$VENV_PATH"/Scripts/activate

python/docker-compose.yaml

@@ -1,6 +1,7 @@
 services:
   violajones-python:
     image: saundersp/violajones-python
+    pull_policy: never
     build: .
     volumes:
       - ./models:/home/ViolaJones/python/models
@@ -11,5 +12,4 @@ services:
         reservations:
           devices:
             - driver: nvidia
-              count: 1
               capabilities: [gpu]

python/project_test.py

@@ -0,0 +1,15 @@
+from toolbox_unit_test import format_time_test, format_time_ns_test
+from toolbox import header, footer, formatted_row, formatted_line
+from toolbox import format_time_ns, benchmark_function
+from time import perf_counter_ns
+
+if __name__ == '__main__':
+	unit_timestamp = perf_counter_ns()
+	unit_gaps = [27, -18, 29]
+	header(unit_gaps, ['Unit testing', 'Time spent (ns)', 'Formatted time spent'])
+	benchmark_function('testing format_time', unit_gaps[0], format_time_test)
+	benchmark_function('testing format_time_ns', unit_gaps[0], format_time_ns_test)
+	time_spent = perf_counter_ns() - unit_timestamp
+	formatted_line(unit_gaps, '├', '┼', '─', '┤')
+	formatted_row(unit_gaps, ['Unit testing summary', f'{time_spent:,}', format_time_ns(time_spent)])
+	footer(unit_gaps)

python/requirements.txt

@@ -1,3 +1,5 @@
-numba==0.59.1
-scikit-learn==1.4.1.post1
-tqdm==4.66.2
+numba==0.60.0
+scikit-learn==1.5.2
+tqdm==4.67.0
+
+#pudb==2024.1.3

python/toolbox_unit_test.py

@@ -1,5 +1,5 @@
-from typing import Any
 from toolbox import format_time, format_time_ns
+from typing import Any
 
 def Assert(name: str, expected: Any, result: Any):
 	"""Test if a given result is equal of the expected one and log result
@@ -18,115 +18,116 @@ def format_time_test() -> None:
 
 	See https://en.wikipedia.org/wiki/Unit_of_time for details
 	"""
-	Assert("format_time null",                      "0s",                               format_time(0))
-	Assert("format_time second",                    "1s",                               format_time(1))
-	Assert("format_time decasecond",                "10s",                              format_time(10))
-	Assert("format_time minute",                    "1m",                               format_time(60))
-	Assert("format_time milliday",                  "1m 26s",                           format_time(86)) # missing 0.4s due to precision
-	Assert("format_time hectosecond",               "1m 40s",                           format_time(100))
-	Assert("format_time kilosecond",                "16m 40s",                          format_time(int(1e3)))
-	Assert("format_time hour",                      "1h",                               format_time(3600))
-	Assert("format_time day",                       "1j",                               format_time(86400))
-	Assert("format_time week/sennight",             "1w",                               format_time(604800))
-	Assert("format_time megasecond",                "1w 4j 13h 46m 40s",                format_time(int(1e6)))
-	Assert("format_time fortnight",                 "2w",                               format_time(1209600))
-	Assert("format_time lunar month (draconitic)",  "3w 6j 5h 5m 35s",                  format_time(2351135)) # missing 0.8 due to precision
-	Assert("format_time lunar month (tropical)",    "3w 6j 7h 43m 4s",                  format_time(2360584)) # missing 0.7 due to precision
-	Assert("format_time lunar month (sidereal)",    "3w 6j 7h 43m 11s",                 format_time(2360591)) # missing 0.6 to precision
-	Assert("format_time lunar month (anomalistic)", "3w 6j 13h 18m 33s",                format_time(2380713)) # missing 0.2 due to precision
-	Assert("format_time lunar month (synodic)",     "4w 1j 12h 44m 2s",                 format_time(2551442)) # missing 0.9 due to precision
-	Assert("format_time month",                     "1M",                               format_time(2678400))
-	Assert("format_time quarantine",                "1M 1w 2j",                         format_time(int(3456e3)))
-	Assert("format_time semester",                  "4M 2j",                            format_time(10886400))
-	Assert("format_time lunar year",                "11M 1w 6j 8h 52m 48s",             format_time(30617568))
-	Assert("format_time year",                      "1y",                               format_time(int(31536e3)))
-	Assert("format_time tropical year",             "1y 5h 48m 45s",                    format_time(31556925)) # missing 0.216 due to precision
-	Assert("format_time gregorian year",            "1y 5h 49m 12s",                    format_time(31556952))
-	Assert("format_time sidereal year",             "1y 6h 9m 9s",                      format_time(31558149)) # missing 0.7635456 due to precision
-	Assert("format_time leap year",                 "1y 1j",                            format_time(31622400))
-	Assert("format_time olympiad",                  "4y",                               format_time(int(126144e3)))
-	Assert("format_time lusturm",                   "5y",                               format_time(int(15768e4)))
-	Assert("format_time decade",                    "10y",                              format_time(int(31536e4)))
-	Assert("format_time indiction",                 "15y",                              format_time(int(47304e4)))
-	Assert("format_time score",                     "20y",                              format_time(int(63072e4)))
-	Assert("format_time gigasecond",                "31y 8M 1w 4j 1h 46m 40s",          format_time(int(1e9)))
-	Assert("format_time jubilee",                   "50y",                              format_time(int(15768e5)))
-	Assert("format_time century",                   "1c",                               format_time(int(31536e5)))
-	Assert("format_time millennium",                "10c",                              format_time(int(31536e6)))
-	Assert("format_time age",                       "257c 72y",                         format_time(int(812745792e3)))
-	Assert("format_time terasecond",                "3170c 97y 10M 3w 4j 17h 46m 40s",  format_time(int(1e13)))
-	Assert("format_time megaannum",                 "10000c",                           format_time(int(31536e9)))
-	Assert("format_time petasecond",                "317097c 91y 11M 2w 4j 1h 46m 40s", format_time(int(1e15)))
-	Assert("format_time galactic year",             "2300000c",                         format_time(int(725328e10)))
-	Assert("format_time eon",                       "10000000c",                        format_time(int(31536e12)))
-	Assert("format_time kalpa",                     "43200000c",                        format_time(int(13623552e10)))
-	Assert("format_time exasecond",                 "317097919c 83y 9M 1h 46m 40s",     format_time(int(1e18)))
+	Assert('format_time null',                      '0s',                               format_time(0))
+	Assert('format_time second',                    '1s',                               format_time(1))
+	Assert('format_time decasecond',                '10s',                              format_time(10))
+	Assert('format_time minute',                    '1m',                               format_time(60))
+	Assert('format_time milliday',                  '1m 26s',                           format_time(86))  # missing 0.4s due to precision
+	Assert('format_time hectosecond',               '1m 40s',                           format_time(100))
+	Assert('format_time kilosecond',                '16m 40s',                          format_time(int(1e3)))
+	Assert('format_time hour',                      '1h',                               format_time(3600))
+	Assert('format_time day',                       '1j',                               format_time(86400))
+	Assert('format_time week/sennight',             '1w',                               format_time(604800))
+	Assert('format_time megasecond',                '1w 4j 13h 46m 40s',                format_time(int(1e6)))
+	Assert('format_time fortnight',                 '2w',                               format_time(1209600))
+	Assert('format_time lunar month (draconitic)',  '3w 6j 5h 5m 35s',                  format_time(2351135))  # missing 0.8 due to precision
+	Assert('format_time lunar month (tropical)',    '3w 6j 7h 43m 4s',                  format_time(2360584))  # missing 0.7 due to precision
+	Assert('format_time lunar month (sidereal)',    '3w 6j 7h 43m 11s',                 format_time(2360591))  # missing 0.6 to precision
+	Assert('format_time lunar month (anomalistic)', '3w 6j 13h 18m 33s',                format_time(2380713))  # missing 0.2 due to precision
+	Assert('format_time lunar month (synodic)',     '4w 1j 12h 44m 2s',                 format_time(2551442))  # missing 0.9 due to precision
+	Assert('format_time month',                     '1M',                               format_time(2678400))
+	Assert('format_time quarantine',                '1M 1w 2j',                         format_time(int(3456e3)))
+	Assert('format_time semester',                  '4M 2j',                            format_time(10886400))
+	Assert('format_time lunar year',                '11M 1w 6j 8h 52m 48s',             format_time(30617568))
+	Assert('format_time year',                      '1y',                               format_time(int(31536e3)))
+	Assert('format_time tropical year',             '1y 5h 48m 45s',                    format_time(31556925))  # missing 0.216 due to precision
+	Assert('format_time gregorian year',            '1y 5h 49m 12s',                    format_time(31556952))
+	Assert('format_time sidereal year',             '1y 6h 9m 9s',                      format_time(31558149))  # missing 0.7635456 due to precision
+	Assert('format_time leap year',                 '1y 1j',                            format_time(31622400))
+	Assert('format_time olympiad',                  '4y',                               format_time(int(126144e3)))
+	Assert('format_time lusturm',                   '5y',                               format_time(int(15768e4)))
+	Assert('format_time decade',                    '10y',                              format_time(int(31536e4)))
+	Assert('format_time indiction',                 '15y',                              format_time(int(47304e4)))
+	Assert('format_time score',                     '20y',                              format_time(int(63072e4)))
+	Assert('format_time gigasecond',                '31y 8M 1w 4j 1h 46m 40s',          format_time(int(1e9)))
+	Assert('format_time jubilee',                   '50y',                              format_time(int(15768e5)))
+	Assert('format_time century',                   '1c',                               format_time(int(31536e5)))
+	Assert('format_time millennium',                '10c',                              format_time(int(31536e6)))
+	Assert('format_time age',                       '257c 72y',                         format_time(int(812745792e3)))
+	Assert('format_time terasecond',                '3170c 97y 10M 3w 4j 17h 46m 40s',  format_time(int(1e13)))
+	Assert('format_time megaannum',                 '10000c',                           format_time(int(31536e9)))
+	Assert('format_time petasecond',                '317097c 91y 11M 2w 4j 1h 46m 40s', format_time(int(1e15)))
+	Assert('format_time galactic year',             '2300000c',                         format_time(int(725328e10)))
+	Assert('format_time eon',                       '10000000c',                        format_time(int(31536e12)))
+	Assert('format_time kalpa',                     '43200000c',                        format_time(int(13623552e10)))
+	Assert('format_time exasecond',                 '317097919c 83y 9M 1h 46m 40s',     format_time(int(1e18)))
 	# Cannot use number bigger than currently supported ISO Python
-	#Assert("format_time zettasecond",               "",                                 format_time(1e21))
-	#Assert("format_time yottasecond",               "",                                 format_time(1e24))
-	#Assert("format_time ronnasecond",               "",                                 format_time(1e27))
-	#Assert("format_time quettasecond",              "",                                 format_time(1e30))
+	# Assert('format_time zettasecond',               '',                                 format_time(1e21))
+	# Assert('format_time yottasecond',               '',                                 format_time(1e24))
+	# Assert('format_time ronnasecond',               '',                                 format_time(1e27))
+	# Assert('format_time quettasecond',              '',                                 format_time(1e30))
 	# uint64_t_MAX == 2**64 == 18446744073709551615 == -1
-	Assert("format_time max",                       "5849424173c 55y 3w 5j 7h 16s",     format_time(int(2**64 - 1)))
+	Assert('format_time max',                       '5849424173c 55y 3w 5j 7h 16s',     format_time(int(2**64 - 1)))
 
 def format_time_ns_test() -> None:
 	"""Test suite for the format_time_ns output
 
 	See https://en.wikipedia.org/wiki/Unit_of_time for details
 	"""
-	Assert("format_time_ns null",                      "0ns",                                         format_time_ns(0))
-	Assert("format_time_ns nanosecond",                "1ns",                                         format_time_ns(1))
-	Assert("format_time_ns shake",                     "10ns",                                        format_time_ns(10))
-	Assert("format_time_ns microsecond",               "1µs",                                         format_time_ns(int(1e3)))
-	Assert("format_time_ns millisecond",               "1ms",                                         format_time_ns(int(1e6)))
-	Assert("format_time_ns centisecond",               "10ms",                                        format_time_ns(int(1e7)))
-	Assert("format_time_ns decisecond",                "100ms",                                       format_time_ns(int(1e8)))
-	Assert("format_time_ns second",                    "1s",                                          format_time_ns(int(1e9)))
-	Assert("format_time_ns decasecond",                "10s",                                         format_time_ns(int(1e10)))
-	Assert("format_time_ns minute",                    "1m",                                          format_time_ns(int(6e10)))
-	Assert("format_time_ns milliday",                  "1m 26s 400ms",                                format_time_ns(int(864e8)))
-	Assert("format_time_ns hectosecond",               "1m 40s",                                      format_time_ns(int(1e11)))
-	Assert("format_time_ns kilosecond",                "16m 40s",                                     format_time_ns(int(1e12)))
-	Assert("format_time_ns hour",                      "1h",                                          format_time_ns(int(36e11)))
-	Assert("format_time_ns day",                       "1j",                                          format_time_ns(int(864e11)))
-	Assert("format_time_ns week/sennight",             "1w",                                          format_time_ns(int(6048e11)))
-	Assert("format_time_ns megasecond",                "1w 4j 13h 46m 40s",                           format_time_ns(int(1e15)))
-	Assert("format_time_ns fortnight",                 "2w",                                          format_time_ns(int(12096e11)))
-	Assert("format_time_ns lunar month (draconitic)",  "3w 6j 5h 5m 35s 800ms",                       format_time_ns(int(23511358e8)))
-	Assert("format_time_ns lunar month (tropical)",    "3w 6j 7h 43m 4s 700ms",                       format_time_ns(int(23605847e8)))
-	Assert("format_time_ns lunar month (sidereal)",    "3w 6j 7h 43m 11s 600ms",                      format_time_ns(int(23605916e8)))
-	Assert("format_time_ns lunar month (anomalistic)", "3w 6j 13h 18m 33s 200ms",                     format_time_ns(int(23807132e8)))
-	Assert("format_time_ns lunar month (synodic)",     "4w 1j 12h 44m 2s 900ms",                      format_time_ns(int(25514429e8)))
-	Assert("format_time_ns month",                     "1M",                                          format_time_ns(int(26784e11)))
-	Assert("format_time_ns quarantine",                "1M 1w 2j",                                    format_time_ns(int(3456e12)))
-	Assert("format_time_ns semester",                  "4M 2j",                                       format_time_ns(int(108864e11)))
-	Assert("format_time_ns lunar year",                "11M 1w 6j 8h 52m 48s",                        format_time_ns(int(30617568e9)))
-	Assert("format_time_ns year",                      "1y",                                          format_time_ns(int(31536e12)))
-	Assert("format_time_ns tropical year",             "1y 5h 48m 45s 216ms",                         format_time_ns(int(31556925216e6)))
-	Assert("format_time_ns gregorian year",            "1y 5h 49m 12s",                               format_time_ns(int(31556952e9)))
-	Assert("format_time_ns sidereal year",             "1y 6h 9m 9s 763ms 545µs 600ns",               format_time_ns(int(315581497635456e2)))
-	Assert("format_time_ns leap year",                 "1y 1j",                                       format_time_ns(int(316224e11)))
-	Assert("format_time_ns olympiad",                  "4y",                                          format_time_ns(int(126144e12)))
-	Assert("format_time_ns lusturm",                   "5y",                                          format_time_ns(int(15768e13)))
-	Assert("format_time_ns decade",                    "10y",                                         format_time_ns(int(31536e13)))
-	Assert("format_time_ns indiction",                 "15y",                                         format_time_ns(int(47304e13)))
-	Assert("format_time_ns score",                     "20y",                                         format_time_ns(int(63072e13)))
-	Assert("format_time_ns gigasecond",                "31y 8M 1w 4j 1h 46m 40s",                     format_time_ns(int(1e18)))
-	Assert("format_time_ns jubilee",                   "50y",                                         format_time_ns(int(15768e14)))
-	Assert("format_time_ns century",                   "1c",                                          format_time_ns(int(31536e14)))
-	Assert("format_time_ns millennium",                "10c",                                         format_time_ns(int(31536e15)))
-	Assert("format_time_ns age",                       "257c 72y",                                    format_time_ns(int(812745792e12)))
-	Assert("format_time_ns terasecond",                "3170c 97y 10M 3w 4j 17h 46m 40s",             format_time_ns(int(1e22)))
-	Assert("format_time_ns megaannum",                 "10000c",                                      format_time_ns(int(31536e18)))
+	Assert('format_time_ns null',                      '0ns',                                         format_time_ns(0))
+	Assert('format_time_ns nanosecond',                '1ns',                                         format_time_ns(1))
+	Assert('format_time_ns shake',                     '10ns',                                        format_time_ns(10))
+	Assert('format_time_ns microsecond',               '1µs',                                         format_time_ns(int(1e3)))
+	Assert('format_time_ns millisecond',               '1ms',                                         format_time_ns(int(1e6)))
+	Assert('format_time_ns centisecond',               '10ms',                                        format_time_ns(int(1e7)))
+	Assert('format_time_ns decisecond',                '100ms',                                       format_time_ns(int(1e8)))
+	Assert('format_time_ns second',                    '1s',                                          format_time_ns(int(1e9)))
+	Assert('format_time_ns decasecond',                '10s',                                         format_time_ns(int(1e10)))
+	Assert('format_time_ns minute',                    '1m',                                          format_time_ns(int(6e10)))
+	Assert('format_time_ns milliday',                  '1m 26s 400ms',                                format_time_ns(int(864e8)))
+	Assert('format_time_ns hectosecond',               '1m 40s',                                      format_time_ns(int(1e11)))
+	Assert('format_time_ns kilosecond',                '16m 40s',                                     format_time_ns(int(1e12)))
+	Assert('format_time_ns hour',                      '1h',                                          format_time_ns(int(36e11)))
+	Assert('format_time_ns day',                       '1j',                                          format_time_ns(int(864e11)))
+	Assert('format_time_ns week/sennight',             '1w',                                          format_time_ns(int(6048e11)))
+	Assert('format_time_ns megasecond',                '1w 4j 13h 46m 40s',                           format_time_ns(int(1e15)))
+	Assert('format_time_ns fortnight',                 '2w',                                          format_time_ns(int(12096e11)))
+	Assert('format_time_ns lunar month (draconitic)',  '3w 6j 5h 5m 35s 800ms',                       format_time_ns(int(23511358e8)))
+	Assert('format_time_ns lunar month (tropical)',    '3w 6j 7h 43m 4s 700ms',                       format_time_ns(int(23605847e8)))
+	Assert('format_time_ns lunar month (sidereal)',    '3w 6j 7h 43m 11s 600ms',                      format_time_ns(int(23605916e8)))
+	Assert('format_time_ns lunar month (anomalistic)', '3w 6j 13h 18m 33s 200ms',                     format_time_ns(int(23807132e8)))
+	Assert('format_time_ns lunar month (synodic)',     '4w 1j 12h 44m 2s 900ms',                      format_time_ns(int(25514429e8)))
+	Assert('format_time_ns month',                     '1M',                                          format_time_ns(int(26784e11)))
+	Assert('format_time_ns quarantine',                '1M 1w 2j',                                    format_time_ns(int(3456e12)))
+	Assert('format_time_ns semester',                  '4M 2j',                                       format_time_ns(int(108864e11)))
+	Assert('format_time_ns lunar year',                '11M 1w 6j 8h 52m 48s',                        format_time_ns(int(30617568e9)))
+	Assert('format_time_ns year',                      '1y',                                          format_time_ns(int(31536e12)))
+	Assert('format_time_ns tropical year',             '1y 5h 48m 45s 216ms',                         format_time_ns(int(31556925216e6)))
+	Assert('format_time_ns gregorian year',            '1y 5h 49m 12s',                               format_time_ns(int(31556952e9)))
+	Assert('format_time_ns sidereal year',             '1y 6h 9m 9s 763ms 545µs 600ns',               format_time_ns(int(315581497635456e2)))
+	Assert('format_time_ns leap year',                 '1y 1j',                                       format_time_ns(int(316224e11)))
+	Assert('format_time_ns olympiad',                  '4y',                                          format_time_ns(int(126144e12)))
+	Assert('format_time_ns lusturm',                   '5y',                                          format_time_ns(int(15768e13)))
+	Assert('format_time_ns decade',                    '10y',                                         format_time_ns(int(31536e13)))
+	Assert('format_time_ns indiction',                 '15y',                                         format_time_ns(int(47304e13)))
+	Assert('format_time_ns score',                     '20y',                                         format_time_ns(int(63072e13)))
+	Assert('format_time_ns gigasecond',                '31y 8M 1w 4j 1h 46m 40s',                     format_time_ns(int(1e18)))
+	Assert('format_time_ns jubilee',                   '50y',                                         format_time_ns(int(15768e14)))
+	Assert('format_time_ns century',                   '1c',                                          format_time_ns(int(31536e14)))
+	# Python int too large to convert to C long
+	# Assert('format_time_ns millennium',                '10c',                                         format_time_ns(int(31536e15)))
+	# Assert('format_time_ns age',                       '257c 72y',                                    format_time_ns(int(812745792e12)))
+	# Assert('format_time_ns terasecond',                '3170c 97y 10M 3w 4j 17h 46m 40s',             format_time_ns(int(1e22)))
+	# Assert('format_time_ns megaannum',                 '10000c',                                      format_time_ns(int(31536e18)))
 	# Cannot use number bigger than currently supported ISO Python
-	# Assert("format_time_ns petasecond",                "317097c 91y 11M 2w 4j 1h 46m 40s",            format_time_ns(int(1e24)))
-	# Assert("format_time_ns galactic year",             "2300000c",                                    format_time_ns(int(725328e19)))
-	# Assert("format_time_ns eon",                       "10000000c",                                   format_time_ns(int(31536e21)))
-	# Assert("format_time_ns kalpa",                     "43200000c",                                   format_time_ns(int(13623552e19)))
-	# Assert("format_time_ns exasecond",                 "317097919c 83y 9M 1h 46m 40s",                format_time_ns(int(1e27)))
-	# Assert("format_time_ns zettasecond",               "",                                            format_time_ns(int(1e30)))
-	# Assert("format_time_ns yottasecond",               "",                                            format_time_ns(int(1e33)))
-	# Assert("format_time_ns ronnasecond",               "",                                            format_time_ns(int(1e36)))
-	# Assert("format_time_ns quettasecond",              "",                                            format_time_ns(int(1e39)))
+	# Assert('format_time_ns petasecond',                '317097c 91y 11M 2w 4j 1h 46m 40s',            format_time_ns(int(1e24)))
+	# Assert('format_time_ns galactic year',             '2300000c',                                    format_time_ns(int(725328e19)))
+	# Assert('format_time_ns eon',                       '10000000c',                                   format_time_ns(int(31536e21)))
+	# Assert('format_time_ns kalpa',                     '43200000c',                                   format_time_ns(int(13623552e19)))
+	# Assert('format_time_ns exasecond',                 '317097919c 83y 9M 1h 46m 40s',                format_time_ns(int(1e27)))
+	# Assert('format_time_ns zettasecond',               '',                                            format_time_ns(int(1e30)))
+	# Assert('format_time_ns yottasecond',               '',                                            format_time_ns(int(1e33)))
+	# Assert('format_time_ns ronnasecond',               '',                                            format_time_ns(int(1e36)))
+	# Assert('format_time_ns quettasecond',              '',                                            format_time_ns(int(1e39)))
 	# uint64_t_MAX == 2**64 == 18446744073709551615 == -1
-	Assert("format_time_ns max",                       "5c 84y 11M 2j 23h 34m 33s 709ms 551µs 615ns", format_time_ns(2**64 - 1))
+	Assert('format_time_ns max',                       '5c 84y 11M 2j 23h 34m 33s 709ms 551µs 615ns', format_time_ns(2**64 - 1))