plotting scratchpad

examples/15_plotting-scratchpad/notes.md

@@ -0,0 +1,12 @@
+options:
+- use gnuplot
+  - requires aggregation
+    - do aggregation in its own gnuplot language
+    - use something like awk
+    - use some other language, like python or R, specifically to do the aggregation
+    - do the aggregation in C
+- use ggplot
+  - requires setting up bins correctly
+  - also can't pipe to an r script directly, sadly enough.
+- use python for plotting?
+- just present the confidence intervals in C?

examples/15_plotting-scratchpad/r/plot.R

@@ -0,0 +1,7 @@
+library(ggplot2)
+
+data <- read.csv("samples.txt", header = FALSE)
+data <- as.data.frame(data)
+
+ggplot(data = data, aes(x = V1)) +
+  geom_freqpoly()

examples/15_plotting-scratchpad/src/example.c

@@ -0,0 +1,50 @@
+#include "../../squiggle.h"
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+// Estimate functions
+double sample_0(uint64_t* seed)
+{
+    return 0;
+}
+
+double sample_1(uint64_t* seed)
+{
+    return 1;
+}
+
+double sample_few(uint64_t* seed)
+{
+    return sample_to(1, 3, seed);
+}
+
+double sample_many(uint64_t* seed)
+{
+    return sample_to(2, 10, seed);
+}
+
+int main()
+{
+    // set randomness seed
+    uint64_t* seed = malloc(sizeof(uint64_t));
+    *seed = 1000; // xorshift can't start with 0
+
+    double p_a = 0.8;
+    double p_b = 0.5;
+    double p_c = p_a * p_b;
+
+    int n_dists = 4;
+    double weights[] = { 1 - p_c, p_c / 2, p_c / 4, p_c / 4 };
+    double (*samplers[])(uint64_t*) = { sample_0, sample_1, sample_few, sample_many };
+
+    int n_samples = 1000000;
+    double* result_many = (double*)malloc(n_samples * sizeof(double));
+    for (int i = 0; i < n_samples; i++) {
+        result_many[i] = sample_mixture(samplers, weights, n_dists, seed);
+        printf("%f\n", result_many[i]);
+    }
+    // printf("Mean: %f\n", array_mean(result_many, n_samples));
+
+    free(seed);
+}

examples/15_plotting-scratchpad/src/makefile

@@ -0,0 +1,53 @@
+# Interface: 
+#   make
+#   make build
+#   make format
+#   make run
+
+# Compiler
+CC=gcc
+# CC=tcc # <= faster compilation
+
+# Main file
+SRC=example.c ../../squiggle.c
+OUTPUT=example
+
+## Dependencies
+MATH=-lm
+
+## Flags
+DEBUG= #'-g'
+STANDARD=-std=c99
+WARNINGS=-Wall
+OPTIMIZED=-O3  #-Ofast
+# OPENMP=-fopenmp
+
+## Formatter
+STYLE_BLUEPRINT=webkit
+FORMATTER=clang-format -i -style=$(STYLE_BLUEPRINT)
+
+## make build
+build: $(SRC)
+	$(CC) $(OPTIMIZED) $(DEBUG) $(SRC) $(MATH) -o $(OUTPUT)
+
+format: $(SRC)
+	$(FORMATTER) $(SRC)
+
+run: $(SRC) $(OUTPUT)
+	./$(OUTPUT) && echo
+
+time-linux: 
+	@echo "Requires /bin/time, found on GNU/Linux systems" && echo
+	
+	@echo "Running 100x and taking avg time $(OUTPUT)"
+	@t=$$(/usr/bin/time -f "%e" -p bash -c 'for i in {1..100}; do ./$(OUTPUT); done' 2>&1 >/dev/null | grep real | awk '{print $$2}' ); echo "scale=2; 1000 * $$t / 100" | bc | sed "s|^|Time using 1 thread: |" | sed 's|$$|ms|' && echo
+
+## Profiling
+
+profile-linux: 
+	echo "Requires perf, which depends on the kernel version, and might be in linux-tools package or similar"
+	echo "Must be run as sudo"
+	$(CC) $(SRC) $(MATH) -o $(OUTPUT)
+	sudo perf record ./$(OUTPUT)
+	sudo perf report
+	rm perf.data