Repository Public
1#!/usr/bin/env python32# =============================================================================3# SP BOUCHER | SOFTWARE & RESEARCH4# ARTIFICIAL INTELLIGENCE • FINANCE • ENGINEERING5# =============================================================================6#7# PROJECT METADATA8# -----------------------------------------------------------------------------9# Project : ORIX Sheet10# File : Packages/SheetCharts/Tests/SheetChartsTests/Generators/gen_fixtures.py11# Description : Reference values for the SheetCharts numeric tests,12# computed with numpy / scipy / matplotlib.13# Module : SheetChartsTests14# Repository : https://git.spboucher.ai/orix-sheet15# Created : 2026-11-2116# Last Modified : 2026-11-2117#18# =============================================================================19# AUTHOR & PROFESSIONAL AFFILIATION20# =============================================================================21#22# Author : Simon-Pierre Boucher23# Position : Professor of Finance24# Institution : Université du Québec en Outaouais (UQO)25# Department : Département des sciences administratives26# Organization : SP Boucher27#28# Website : https://spboucher.ai29# Git : https://git.spboucher.ai30#31# =============================================================================32# OFFICIAL CONTACT DIRECTORY33# =============================================================================34#35# General : info@spboucher.ai36# Professional : contact@spboucher.ai37# Direct : simon@spboucher.ai38# Research : research@spboucher.ai39# Development : dev@spboucher.ai40# Support : support@spboucher.ai41# Security/Admin : admin@spboucher.ai42# Notifications : notifications@spboucher.ai43#44# Preferred Contact: support@spboucher.ai45#46# =============================================================================47# COPYRIGHT & INTELLECTUAL PROPERTY48# =============================================================================49#50# Copyright (c) 202651# Simon-Pierre Boucher52#53# All rights reserved where applicable.54#55# This file is governed by the applicable project license,56# copyright notices, institutional agreements and relevant law.57#58# Unless expressly authorized by the applicable license or59# rights holder, copying, redistribution, sublicensing,60# publication and commercial exploitation are not permitted.61#62# Existing third-party rights and notices remain unaffected.63#64# =============================================================================65# CONFIDENTIALITY & SECURITY66# =============================================================================67#68# Classification : Public69# Distribution : Public repository; use is governed by the project license70# Security Contact : admin@spboucher.ai71#72# Access to this source does not independently grant permission73# to redistribute or disclose confidential materials.74#75# Do not embed credentials, private keys, access tokens,76# certificates or confidential personal information.77#78# =============================================================================79# LICENSE & MAINTENANCE80# =============================================================================81#82# License : None specified (no license file in this repository)83# Maintainer : Simon-Pierre Boucher84# Technical Contact: dev@spboucher.ai85#86# =============================================================================87# END OF SP BOUCHER SOURCE HEADER88# =============================================================================8990"""Reference values for the SheetCharts numeric tests, computed with numpy / scipy / matplotlib.9192Usage: /opt/homebrew/bin/python3 gen_fixtures.py <Fixtures directory>93Writes reference.json. The script is deterministic (fixed seeds). Re-run it only to extend the fixtures;94the Swift tests compare the engine against the stored numbers.95"""96import json, sys, os, datetime97import numpy as np98import scipy99from scipy import stats100import matplotlib101matplotlib.use("Agg")102from matplotlib import ticker, cbook103import matplotlib.pyplot as plt104105out_dir = sys.argv[1]106rng = np.random.default_rng(20261121)107ref = {"versions": {"numpy": np.__version__, "scipy": scipy.__version__, "matplotlib": matplotlib.__version__}}108109datasets = {110 "normal500": rng.normal(50, 12, 500),111 "lognormal200": rng.lognormal(1.0, 0.8, 200),112 "small7": np.array([2.0, 4.0, 4.0, 5.0, 7.0, 9.0, 21.0]),113 "integers60": rng.integers(0, 12, 60).astype(float),114 "uniform33": rng.uniform(-3, 8, 33),115 "pair": np.array([1.5, 4.0]),116 "tiny": rng.normal(0, 1e-9, 40),117 "huge": rng.normal(0, 1e9, 64),118}119ref["datasets"] = {k: [float(x) for x in v] for k, v in datasets.items()}120121# --- ticks: matplotlib MaxNLocator with steps 1-2-5-10 ------------------------------------------------------122tick_cases = [(0, 1, 5), (0, 100, 6), (-11.8, 18.9, 7), (3.2, 97.5, 5), (0.0012, 0.0087, 6), (-1e-12, 1e-12, 4),123 (1e-12, 1e12, 6), (123456, 987654, 8), (-0.5, 0.5, 10), (20, 80, 6), (0, 7, 7), (0.1, 0.9, 4),124 (-273.15, 1064.18, 5), (5.5, 5.9, 3), (0, 250000, 5), (17, 23, 2), (-8.1, 6.5, 12), (0, 0.3, 3)]125ticks = []126for lo, hi, n in tick_cases:127 loc = ticker.MaxNLocator(nbins=n, steps=[1, 2, 5, 10])128 ticks.append({"min": lo, "max": hi, "intervals": n, "ticks": [float(t) for t in loc.tick_values(lo, hi)]})129ref["ticks"] = ticks130131# --- log ticks: integer powers inside the range -------------------------------------------------------------132logs = []133for lo, hi, base in [(0.03, 4800, 10), (1, 1e6, 10), (1e-12, 1e12, 10), (3, 900, 2), (0.5, 64, 2), (120, 80000, 10)]:134 e0 = int(np.ceil(np.log(lo) / np.log(base) - 1e-9)); e1 = int(np.floor(np.log(hi) / np.log(base) + 1e-9))135 logs.append({"min": lo, "max": hi, "base": base, "powers": [float(base) ** e for e in range(e0, e1 + 1)]})136ref["logTicks"] = logs137138# --- calendar ticks: serial numbers (1900 system; valid after 1900-03-01) ------------------------------------139epoch = datetime.date(1899, 12, 30)140def serial(d): return (d - epoch).days141dates = []142for (a, b, unit, step) in [((2024, 1, 15), (2025, 3, 2), "month", 1), ((2019, 11, 3), (2031, 2, 1), "year", 1),143 ((2023, 12, 20), (2024, 3, 10), "week", 1), ((2000, 2, 20), (2000, 3, 4), "day", 1),144 ((1995, 6, 1), (2026, 6, 1), "year", 5), ((2024, 2, 1), (2026, 1, 31), "month", 3)]:145 da, db = datetime.date(*a), datetime.date(*b)146 vals = []147 d = da148 while d <= db:149 if unit == "day": ok = True150 elif unit == "week": ok = d.weekday() == 0151 elif unit == "month": ok = d.day == 1 and (d.month - 1) % step == 0152 else: ok = d.day == 1 and d.month == 1 and d.year % step == 0153 if ok: vals.append(serial(d))154 d += datetime.timedelta(days=1)155 dates.append({"min": serial(da), "max": serial(db), "unit": unit, "step": step, "ticks": vals,156 "labels": [datetime.date.fromordinal(epoch.toordinal() + v).isoformat() for v in vals]})157ref["dateTicks"] = dates158ref["dateSerials"] = [{"iso": d.isoformat(), "serial": serial(d)} for d in159 [datetime.date(1900, 3, 1), datetime.date(1999, 12, 31), datetime.date(2000, 2, 29), datetime.date(2024, 2, 29), datetime.date(2030, 1, 1)]]160161# --- histogram bins -----------------------------------------------------------------------------------------162bins = []163for name, x in datasets.items():164 for rule, np_rule in [("auto", "auto"), ("freedmanDiaconis", "fd"), ("sturges", "sturges"), ("scott", "scott"), ("fixedCount", 13)]:165 edges = np.histogram_bin_edges(x, bins=np_rule)166 counts, _ = np.histogram(x, bins=edges)167 dens, _ = np.histogram(x, bins=edges, density=True)168 bins.append({"data": name, "rule": rule, "edges": [float(e) for e in edges], "counts": [int(c) for c in counts], "density": [float(d) for d in dens]})169const = np.full(9, 3.25)170edges = np.histogram_bin_edges(const, bins="auto")171bins.append({"data": "const", "rule": "auto", "edges": [float(e) for e in edges], "counts": [int(c) for c in np.histogram(const, bins=edges)[0]], "density": []})172ref["datasets"]["const"] = [float(v) for v in const]173ref["bins"] = bins174175# --- quantiles ----------------------------------------------------------------------------------------------176methods = {"inclusive": "linear", "exclusive": "weibull", "averaged": "averaged_inverted_cdf", "medianUnbiased": "median_unbiased"}177probs = [0, 0.05, 0.1, 0.25, 1 / 3, 0.5, 0.6, 0.75, 0.9, 0.99, 1]178quant = []179qsets = dict(datasets)180for n in [1, 2, 3, 4, 5, 8, 11]:181 qsets["n%d" % n] = np.round(rng.normal(10, 4, n), 3)182for name, x in qsets.items():183 ref["datasets"][name] = [float(v) for v in x]184 for m, npm in methods.items():185 quant.append({"data": name, "method": m, "p": probs, "q": [float(np.quantile(x, p, method=npm)) for p in probs]})186ref["quantiles"] = quant187188# --- box plot statistics (matplotlib, Tukey whiskers, linear quartiles) ---------------------------------------189box = []190for name in ["normal500", "lognormal200", "small7", "integers60", "uniform33", "pair"]:191 s = cbook.boxplot_stats(datasets[name], whis=1.5)[0]192 box.append({"data": name, "q1": float(s["q1"]), "median": float(s["med"]), "q3": float(s["q3"]), "whiskerLow": float(s["whislo"]),193 "whiskerHigh": float(s["whishi"]), "outliers": sorted(float(f) for f in s["fliers"]), "mean": float(s["mean"])})194ref["box"] = box195196# --- Gaussian KDE -------------------------------------------------------------------------------------------197kde = []198for name in ["normal500", "lognormal200", "small7", "uniform33", "tiny", "huge"]:199 x = datasets[name]200 n = len(x); s = np.std(x, ddof=1)201 iqr = np.percentile(x, 75) - np.percentile(x, 25)202 h_scott = s * n ** (-0.2)203 h_silverman = 0.9 * min(s, iqr / 1.34) * n ** (-0.2)204 grid = np.linspace(x.min() - 3 * h_scott, x.max() + 3 * h_scott, 41)205 for rule, h in [("scott", h_scott), ("silverman", h_silverman), ("fixed", 0.5 * h_scott)]:206 # scipy's default bandwidth IS Scott's rule; other bandwidths are passed as a factor of the sample std207 k = stats.gaussian_kde(x) if rule == "scott" else stats.gaussian_kde(x, bw_method=h / s)208 kde.append({"data": name, "rule": rule, "bandwidth": float(h), "grid": [float(g) for g in grid], "density": [float(v) for v in k(grid)]})209ref["kde"] = kde210211# --- trendlines ---------------------------------------------------------------------------------------------212def r2(y, yhat): return float(1 - np.sum((y - yhat) ** 2) / np.sum((y - np.mean(y)) ** 2))213trend = []214x = np.sort(rng.uniform(0.5, 40, 60)); noise = rng.normal(0, 1, 60)215series = {216 "linear": (x, 3.2 * x - 7 + 4 * noise),217 "curved": (x, 0.04 * x ** 3 - 1.5 * x ** 2 + 9 * x + 20 + 12 * noise),218 "growth": (x, 2.5 * np.exp(0.09 * x) * np.exp(0.1 * noise)),219 "power": (x, 4.1 * x ** 0.63 * np.exp(0.07 * noise)),220 "logish": (x, 6.0 * np.log(x) + 2 + 0.5 * noise),221 "years": (np.arange(1990, 2026, dtype=float), 100 + 2.3 * (np.arange(36)) + rng.normal(0, 3, 36)),222 "bigx": (1e6 + np.arange(30, dtype=float) * 250, rng.normal(5, 1, 30) + 0.002 * np.arange(30) * 250),223}224for name, (xs, ys) in series.items():225 entry = {"name": name, "x": [float(v) for v in xs], "y": [float(v) for v in ys], "fits": []}226 for deg in [1, 2, 3, 5]:227 c = np.polyfit(xs, ys, deg) # descending powers228 entry["fits"].append({"kind": "linear" if deg == 1 else "polynomial", "order": deg, "coefficients": [float(v) for v in c[::-1]],229 "r2": r2(ys, np.polyval(c, xs)), "probe": [float(np.polyval(c, v)) for v in (xs[0], xs[len(xs) // 2], xs[-1])]})230 if np.all(ys > 0):231 b, a = np.polyfit(xs, np.log(ys), 1)232 entry["fits"].append({"kind": "exponential", "order": 0, "coefficients": [float(np.exp(a)), float(b)], "r2": r2(np.log(ys), a + b * xs), "probe": []})233 b, a = np.polyfit(np.log(xs), np.log(ys), 1)234 entry["fits"].append({"kind": "power", "order": 0, "coefficients": [float(np.exp(a)), float(b)], "r2": r2(np.log(ys), a + b * np.log(xs)), "probe": []})235 a, b = np.polyfit(np.log(xs), ys, 1)236 entry["fits"].append({"kind": "logarithmic", "order": 0, "coefficients": [float(a), float(b)], "r2": r2(ys, a * np.log(xs) + b), "probe": []})237 entry["movingAverage5"] = [float(v) for v in np.convolve(ys, np.ones(5) / 5, mode="valid")]238 trend.append(entry)239ref["trend"] = trend240241# --- stacking -----------------------------------------------------------------------------------------------242m = np.round(rng.normal(2, 6, (4, 7)), 2)243pos = np.where(m > 0, m, 0).cumsum(axis=0); neg = np.where(m < 0, m, 0).cumsum(axis=0)244top = np.where(m >= 0, pos, neg)245pct = m / np.abs(m).sum(axis=0) * 100246ppos = np.where(pct > 0, pct, 0).cumsum(axis=0); pneg = np.where(pct < 0, pct, 0).cumsum(axis=0)247ref["stack"] = {"values": m.tolist(), "top": top.tolist(), "base": (top - m).tolist(),248 "percentTop": np.where(pct >= 0, ppos, pneg).tolist(), "percentBase": (np.where(pct >= 0, ppos, pneg) - pct).tolist()}249250# --- contours: total iso-line length from matplotlib (contourpy) --------------------------------------------251g = np.linspace(-3, 3, 41)252X, Y = np.meshgrid(g, g)253Z = 3 * (1 - X) ** 2 * np.exp(-X ** 2 - (Y + 1) ** 2) - 10 * (X / 5 - X ** 3 - Y ** 5) * np.exp(-X ** 2 - Y ** 2) - 1 / 3 * np.exp(-(X + 1) ** 2 - Y ** 2)254levels = [-4.0, -1.5, 0.5, 2.0, 5.0]255cs = plt.contour(Z, levels=levels) # coordinates are grid indices, like the engine's256lengths = []257for segs in cs.allsegs:258 lengths.append(float(sum(np.sum(np.hypot(np.diff(s[:, 0]), np.diff(s[:, 1]))) for s in segs)))259ref["contour"] = {"z": Z.tolist(), "levels": levels, "lengths": lengths, "segments": [len(s) for s in cs.allsegs]}260261json.dump(ref, open(os.path.join(out_dir, "reference.json"), "w"))262print("wrote reference.json with", ", ".join(k for k in ref))263