Reproducible Analysis, Metadata, and Audit Trails

/**
 * Fintech Math Bootcamp · Lesson 120 of 120
 * Reproducible Analysis, Metadata, and Audit Trails
 * Module 12: Statistical Computing and Reproducibility
 *
 * Scenario: Making a result reproducible without confusing metadata with truth
 * Rule:     result + data identity + code version + parameters + information cutoff
 *
 * Try it:   Does a matching teaching checksum prove the financial analysis is correct?
 *
 * Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
 * Free course:    https://courses.thefintechbuilder.com
 * Synthetic teaching example, not financial advice or a production library.
 */

export function lesson120() {
  const record={dataset:"synthetic-five-values",version:"course-1",
    unit:"hours",cutoff:"2026-01-01T00:00:00Z",method:"sample-variance"};
  const keys=["dataset","version","unit","cutoff","method"];
  const canonical=JSON.stringify(Object.fromEntries(Object.entries(record)
    .sort(([a],[b])=>a<b?-1:a>b?1:0))); // locale-independent key order
  let hash=2166136261;
  // Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
  for(let k=0;k<canonical.length;k++){hash=Math.imul(hash^canonical.charCodeAt(k),16777619)>>>0;}
  const result={complete:keys.every(k=>k in record),
    checksum:hash.toString(16).padStart(8,"0"),canonical};
  return result;
}

export const checkedResult = {"complete":true,"checksum":"391bbb44","canonical":"{\"cutoff\":\"2026-01-01T00:00:00Z\",\"dataset\":\"synthetic-five-values\",\"method\":\"sample-variance\",\"unit\":\"hours\",\"version\":\"course-1\"}"};

// Run this file directly: npx tsx lessons/12-statistical-computing-and-reproducibility/120-reproducible-analysis-metadata-and-audit-trails.ts
if (process.argv[1] && import.meta.url.endsWith(process.argv[1].replace(/\\/g, "/").split("/").pop()!)) {
  console.log(JSON.stringify(lesson120(), null, 2));
}

# Fintech Math Bootcamp · Lesson 120 of 120
# Reproducible Analysis, Metadata, and Audit Trails
# Module 12: Statistical Computing and Reproducibility
#
# Scenario: Making a result reproducible without confusing metadata with truth
# Rule:     result + data identity + code version + parameters + information cutoff
#
# Try it:   Does a matching teaching checksum prove the financial analysis is correct?
#
# Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
# Free course:    https://courses.thefintechbuilder.com
# Synthetic teaching example, not financial advice or a production library.
#
# Run: python main.py

import json


def lesson_120():
    record = {
        "dataset": "synthetic-five-values",
        "version": "course-1",
        "unit": "hours",
        "cutoff": "2026-01-01T00:00:00Z",
        "method": "sample-variance",
    }
    keys = ["dataset", "version", "unit", "cutoff", "method"]
    # Sorted keys and compact separators reproduce JSON.stringify of the sorted record.
    canonical = json.dumps(dict(sorted(record.items())), separators=(",", ":"))
    hash_value = 2166136261
    # Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
    for ch in canonical:
        hash_value = ((hash_value ^ ord(ch)) * 16777619) & 0xFFFFFFFF
    return {
        "complete": all(k in record for k in keys),
        "checksum": format(hash_value, "08x"),
        "canonical": canonical,
    }


if __name__ == "__main__":
    print(json.dumps(lesson_120(), indent=2))

/*
 * Fintech Math Bootcamp - Lesson 120 of 120
 * Reproducible Analysis, Metadata, and Audit Trails
 * Module 12: Statistical Computing and Reproducibility
 *
 * Scenario: Making a result reproducible without confusing metadata with truth
 * Rule:     result + data identity + code version + parameters + information cutoff
 *
 * Try it:   Does a matching teaching checksum prove the financial analysis is correct?
 *
 * Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
 * Free course:    https://courses.thefintechbuilder.com
 * Synthetic teaching example, not financial advice or a production library.
 *
 * Run: javac Main.java && java Main
 */

import java.util.*;

public class Main {
    static Map<String, Object> lesson120() {
        Map<String, String> record = new LinkedHashMap<String, String>();
        record.put("dataset", "synthetic-five-values");
        record.put("version", "course-1");
        record.put("unit", "hours");
        record.put("cutoff", "2026-01-01T00:00:00Z");
        record.put("method", "sample-variance");
        String[] keys = {"dataset", "version", "unit", "cutoff", "method"};
        // TreeMap orders String keys by UTF-16 code units, the same order as JavaScript's < on strings.
        StringBuilder canonical = new StringBuilder("{");
        for (Map.Entry<String, String> e : new TreeMap<String, String>(record).entrySet()) {
            if (canonical.length() > 1) canonical.append(',');
            canonical.append(quote(e.getKey())).append(':').append(quote(e.getValue()));
        }
        canonical.append('}');
        int hash = 0x811C9DC5; // 2166136261
        // Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
        for (int k = 0; k < canonical.length(); k++) hash = (hash ^ canonical.charAt(k)) * 16777619;
        boolean complete = true;
        for (String k : keys) complete &= record.containsKey(k);
        return obj("complete", complete, "checksum", String.format("%08x", hash), "canonical", canonical.toString());
    }

    public static void main(String[] args) {
        System.out.println(toJson(lesson120(), ""));
    }

    // Minimal JSON writer: insertion-ordered Map, List, Number, Boolean, String and null.
    static String toJson(Object value, String indent) {
        if (value == null) return "null";
        if (value instanceof String) return quote((String) value);
        if (value instanceof Boolean) return value.toString();
        if (value instanceof Double) return formatNumber((Double) value);
        if (value instanceof Number) return value.toString();
        String inner = indent + "  ";
        StringBuilder sb = new StringBuilder();
        if (value instanceof Map) {
            Map<?, ?> map = (Map<?, ?>) value;
            if (map.isEmpty()) return "{}";
            sb.append("{\n");
            int i = 0;
            for (Map.Entry<?, ?> e : map.entrySet()) {
                sb.append(inner).append(quote(e.getKey().toString())).append(": ").append(toJson(e.getValue(), inner));
                sb.append(++i < map.size() ? ",\n" : "\n");
            }
            return sb.append(indent).append("}").toString();
        }
        List<?> list = (List<?>) value;
        if (list.isEmpty()) return "[]";
        sb.append("[\n");
        for (int i = 0; i < list.size(); i++) {
            sb.append(inner).append(toJson(list.get(i), inner)).append(i + 1 < list.size() ? ",\n" : "\n");
        }
        return sb.append(indent).append("]").toString();
    }

    // Integral doubles print without ".0", as JavaScript does; others use Java's round-trip form.
    static String formatNumber(double x) {
        if (x == Math.rint(x) && Math.abs(x) < 1e15) return Long.toString((long) x);
        return Double.toString(x);
    }

    static String quote(String s) {
        StringBuilder sb = new StringBuilder("\"");
        for (char c : s.toCharArray()) {
            if (c == '"' || c == '\\') sb.append('\\').append(c);
            else if (c < 0x20) sb.append(String.format("\\u%04x", (int) c));
            else sb.append(c);
        }
        return sb.append('"').toString();
    }

    // Builds an insertion-ordered object from alternating keys and values.
    static Map<String, Object> obj(Object... keysAndValues) {
        Map<String, Object> map = new LinkedHashMap<String, Object>();
        for (int i = 0; i < keysAndValues.length; i += 2) map.put((String) keysAndValues[i], keysAndValues[i + 1]);
        return map;
    }

    static List<Object> list(double... values) {
        List<Object> out = new ArrayList<Object>();
        for (double v : values) out.add(v);
        return out;
    }
}

// Fintech Math Bootcamp · Lesson 120 of 120
// Reproducible Analysis, Metadata, and Audit Trails
// Module 12: Statistical Computing and Reproducibility
//
// Scenario: Making a result reproducible without confusing metadata with truth
// Rule:     result + data identity + code version + parameters + information cutoff
//
// Try it:   Does a matching teaching checksum prove the financial analysis is correct?
//
// Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
// Free course:    https://courses.thefintechbuilder.com
// Synthetic teaching example, not financial advice or a production library.
//
// Run: go run main.go

package main

import (
	"encoding/json"
	"fmt"
	"sort"
	"unicode/utf16"
)

type Result struct {
	Complete  bool   `json:"complete"`
	Checksum  string `json:"checksum"`
	Canonical string `json:"canonical"`
}

func lesson120() Result {
	record := map[string]string{
		"dataset": "synthetic-five-values",
		"version": "course-1",
		"unit":    "hours",
		"cutoff":  "2026-01-01T00:00:00Z",
		"method":  "sample-variance",
	}
	keys := []string{"dataset", "version", "unit", "cutoff", "method"}
	names := make([]string, 0, len(record))
	for k := range record {
		names = append(names, k)
	}
	sort.Strings(names) // byte order equals code-unit order for these ASCII keys
	canonical := "{"
	for i, k := range names {
		if i > 0 {
			canonical += ","
		}
		key, _ := json.Marshal(k)
		value, _ := json.Marshal(record[k])
		canonical += string(key) + ":" + string(value)
	}
	canonical += "}"
	hash := uint32(2166136261)
	// Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
	for _, unit := range utf16.Encode([]rune(canonical)) {
		hash = (hash ^ uint32(unit)) * 16777619
	}
	complete := true
	for _, k := range keys {
		if _, ok := record[k]; !ok {
			complete = false
		}
	}
	return Result{Complete: complete, Checksum: fmt.Sprintf("%08x", hash), Canonical: canonical}
}

func main() {
	out, err := json.MarshalIndent(lesson120(), "", "  ")
	if err != nil {
		panic(err)
	}
	fmt.Println(string(out))
}

// Fintech Math Bootcamp · Lesson 120 of 120
// Reproducible Analysis, Metadata, and Audit Trails
// Module 12: Statistical Computing and Reproducibility
//
// Scenario: Making a result reproducible without confusing metadata with truth
// Rule:     result + data identity + code version + parameters + information cutoff
//
// Try it:   Does a matching teaching checksum prove the financial analysis is correct?
//
// Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
// Free course:    https://courses.thefintechbuilder.com
// Synthetic teaching example, not financial advice or a production library.
//
// Run: g++ -std=c++17 -O1 -o lesson main.cpp && ./lesson

#include <algorithm>
#include <charconv>
#include <cmath>
#include <cstdint>
#include <cstdio>
#include <deque>
#include <iostream>
#include <limits>
#include <map>
#include <optional>
#include <stdexcept>
#include <string>
#include <utility>
#include <variant>
#include <vector>

// Minimal JSON value: objects keep insertion order; numbers print in shortest round-trip form.
struct Json {
    enum class Kind { Null, Bool, Number, String, Array, Object };
    Kind kind = Kind::Null;
    bool flag = false;
    double number = 0.0;
    std::string text;
    std::vector<std::string> keys;  // object keys, parallel to items
    std::vector<Json> items;        // array items, or object values
};

Json jnull() { return Json{}; }
Json jbool(bool value) { Json j; j.kind = Json::Kind::Bool; j.flag = value; return j; }
Json jnum(double value) { Json j; j.kind = Json::Kind::Number; j.number = value; return j; }
Json jstr(const std::string& value) { Json j; j.kind = Json::Kind::String; j.text = value; return j; }
Json jarr(std::vector<Json> items) { Json j; j.kind = Json::Kind::Array; j.items = std::move(items); return j; }

Json jobj(std::vector<std::pair<std::string, Json>> fields) {
    Json j;
    j.kind = Json::Kind::Object;
    for (auto& field : fields) {
        j.keys.push_back(field.first);
        j.items.push_back(std::move(field.second));
    }
    return j;
}

Json jnums(const std::vector<double>& values) {
    std::vector<Json> items;
    for (double v : values) items.push_back(jnum(v));
    return jarr(std::move(items));
}

Json jnums(const std::vector<std::optional<double>>& values) {
    std::vector<Json> items;
    for (const auto& v : values) items.push_back(v ? jnum(*v) : jnull());
    return jarr(std::move(items));
}

std::string formatNumber(double value) {
    char buffer[64];
    auto result = std::to_chars(buffer, buffer + sizeof buffer, value);  // shortest round-trip form
    return std::string(buffer, result.ptr);
}

std::string quote(const std::string& text) {
    std::string out = "\"";
    for (char c : text) {
        if (c == '"' || c == '\\') {
            out += '\\';
            out += c;
        } else if (static_cast<unsigned char>(c) < 0x20) {
            char buffer[8];
            std::snprintf(buffer, sizeof buffer, "\\u%04x", static_cast<unsigned>(c));
            out += buffer;
        } else {
            out += c;
        }
    }
    return out + "\"";
}

void writeJson(std::ostream& out, const Json& value, const std::string& indent = "") {
    const std::string inner = indent + "  ";
    switch (value.kind) {
        case Json::Kind::Null: out << "null"; return;
        case Json::Kind::Bool: out << (value.flag ? "true" : "false"); return;
        case Json::Kind::Number: out << formatNumber(value.number); return;
        case Json::Kind::String: out << quote(value.text); return;
        case Json::Kind::Array:
        case Json::Kind::Object: {
            const bool isObject = value.kind == Json::Kind::Object;
            if (value.items.empty()) {
                out << (isObject ? "{}" : "[]");
                return;
            }
            out << (isObject ? "{\n" : "[\n");
            for (std::size_t i = 0; i < value.items.size(); ++i) {
                out << inner;
                if (isObject) out << quote(value.keys[i]) << ": ";
                writeJson(out, value.items[i], inner);
                out << (i + 1 < value.items.size() ? ",\n" : "\n");
            }
            out << indent << (isObject ? "}" : "]");
        }
    }
}

Json lesson120() {
    const std::map<std::string, std::string> record{  // std::map keeps keys sorted
        {"dataset", "synthetic-five-values"},
        {"version", "course-1"},
        {"unit", "hours"},
        {"cutoff", "2026-01-01T00:00:00Z"},
        {"method", "sample-variance"}};
    const std::vector<std::string> keys{"dataset", "version", "unit", "cutoff", "method"};
    std::string canonical = "{";
    for (const auto& [key, value] : record) {
        if (canonical.size() > 1) canonical += ",";
        canonical += quote(key) + ":" + quote(value);
    }
    canonical += "}";
    std::uint32_t hash = 2166136261u;
    // Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for this ASCII input)
    for (unsigned char c : canonical) hash = static_cast<std::uint32_t>((hash ^ c) * 16777619u);
    const bool complete = std::all_of(keys.begin(), keys.end(), [&](const std::string& k) { return record.count(k) > 0; });
    char checksum[9];
    std::snprintf(checksum, sizeof checksum, "%08x", static_cast<unsigned>(hash));
    return jobj({{"complete", jbool(complete)}, {"checksum", jstr(checksum)}, {"canonical", jstr(canonical)}});
}

int main() {
    writeJson(std::cout, lesson120());
    std::cout << "\n";
    return 0;
}

// Fintech Math Bootcamp · Lesson 120 of 120
// Reproducible Analysis, Metadata, and Audit Trails
// Module 12: Statistical Computing and Reproducibility
//
// Scenario: Making a result reproducible without confusing metadata with truth
// Rule:     result + data identity + code version + parameters + information cutoff
//
// Try it:   Does a matching teaching checksum prove the financial analysis is correct?
//
// Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
// Free course:    https://courses.thefintechbuilder.com
// Synthetic teaching example, not financial advice or a production library.
//
// Run: rustc -O main.rs && ./main

#![allow(dead_code)]

use std::collections::BTreeMap;

/// Minimal JSON value; objects keep insertion order.
enum Json {
    Null,
    Bool(bool),
    Num(f64),
    Str(String),
    Arr(Vec<Json>),
    Obj(Vec<(String, Json)>),
}

fn obj(fields: Vec<(&str, Json)>) -> Json {
    Json::Obj(fields.into_iter().map(|(k, v)| (k.to_string(), v)).collect())
}

fn nums(values: &[f64]) -> Json {
    Json::Arr(values.iter().map(|&v| Json::Num(v)).collect())
}

fn optional_nums(values: &[Option<f64>]) -> Json {
    Json::Arr(values.iter().map(|v| v.map_or(Json::Null, Json::Num)).collect())
}

fn quote(text: &str) -> String {
    let mut out = String::from("\"");
    for c in text.chars() {
        match c {
            '"' => out.push_str("\\\""),
            '\\' => out.push_str("\\\\"),
            c if (c as u32) < 0x20 => out.push_str(&format!("\\u{:04x}", c as u32)),
            c => out.push(c),
        }
    }
    out.push('"');
    out
}

// Display for f64 prints the shortest string that round-trips, as JavaScript does.
fn write_json(value: &Json, indent: &str, out: &mut String) {
    let inner = format!("{}  ", indent);
    match value {
        Json::Null => out.push_str("null"),
        Json::Bool(b) => out.push_str(if *b { "true" } else { "false" }),
        Json::Num(n) => out.push_str(&format!("{}", n)),
        Json::Str(s) => out.push_str(&quote(s)),
        Json::Arr(items) if items.is_empty() => out.push_str("[]"),
        Json::Obj(fields) if fields.is_empty() => out.push_str("{}"),
        Json::Arr(items) => {
            out.push_str("[\n");
            for (i, item) in items.iter().enumerate() {
                out.push_str(&inner);
                write_json(item, &inner, out);
                out.push_str(if i + 1 < items.len() { ",\n" } else { "\n" });
            }
            out.push_str(indent);
            out.push(']');
        }
        Json::Obj(fields) => {
            out.push_str("{\n");
            for (i, (key, item)) in fields.iter().enumerate() {
                out.push_str(&inner);
                out.push_str(&quote(key));
                out.push_str(": ");
                write_json(item, &inner, out);
                out.push_str(if i + 1 < fields.len() { ",\n" } else { "\n" });
            }
            out.push_str(indent);
            out.push('}');
        }
    }
}

fn lesson_120() -> Json {
    // BTreeMap keeps keys sorted; byte order equals code-unit order for these ASCII keys.
    let record: BTreeMap<&str, &str> = [
        ("dataset", "synthetic-five-values"),
        ("version", "course-1"),
        ("unit", "hours"),
        ("cutoff", "2026-01-01T00:00:00Z"),
        ("method", "sample-variance"),
    ]
    .into_iter()
    .collect();
    let keys = ["dataset", "version", "unit", "cutoff", "method"];
    let fields: Vec<String> = record.iter().map(|(k, v)| format!("{}:{}", quote(k), quote(v))).collect();
    let canonical = format!("{{{}}}", fields.join(","));
    let mut hash: u32 = 2166136261;
    // Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
    for unit in canonical.encode_utf16() {
        hash = (hash ^ unit as u32).wrapping_mul(16777619);
    }
    obj(vec![
        ("complete", Json::Bool(keys.iter().all(|k| record.contains_key(k)))),
        ("checksum", Json::Str(format!("{:08x}", hash))),
        ("canonical", Json::Str(canonical)),
    ])
}

fn main() {
    let mut out = String::new();
    write_json(&lesson_120(), "", &mut out);
    println!("{}", out);
}

// Fintech Math Bootcamp · Lesson 120 of 120
// Reproducible Analysis, Metadata, and Audit Trails
// Module 12: Statistical Computing and Reproducibility
//
// Scenario: Making a result reproducible without confusing metadata with truth
// Rule:     result + data identity + code version + parameters + information cutoff
//
// Try it:   Does a matching teaching checksum prove the financial analysis is correct?
//
// Lesson article: https://thefintechbuilder.com/financial-mathematics-statistics-and-data-foundations/statistical-computing-and-reproducibility/reproducible-analysis-metadata-and-audit-trails/
// Free course:    https://courses.thefintechbuilder.com
// Synthetic teaching example, not financial advice or a production library.
//
// Run: dotnet run

using System;
using System.Collections.Generic;
using System.Globalization;
using System.Linq;
using System.Text.Encodings.Web;
using System.Text.Json;

var options = new JsonSerializerOptions { WriteIndented = true, Encoder = JavaScriptEncoder.UnsafeRelaxedJsonEscaping };
Console.WriteLine(JsonSerializer.Serialize(Lesson120(), options));

static object Lesson120()
{
    var record = new Dictionary<string, string>
    {
        ["dataset"] = "synthetic-five-values",
        ["version"] = "course-1",
        ["unit"] = "hours",
        ["cutoff"] = "2026-01-01T00:00:00Z",
        ["method"] = "sample-variance",
    };
    string[] keys = { "dataset", "version", "unit", "cutoff", "method" };
    static string Quote(string s) => "\"" + s.Replace("\\", "\\\\").Replace("\"", "\\\"") + "\"";
    // Ordinal comparison sorts by UTF-16 code units, like JavaScript's < on strings.
    string canonical = "{" + string.Join(",", record.OrderBy(p => p.Key, StringComparer.Ordinal)
        .Select(p => Quote(p.Key) + ":" + Quote(p.Value))) + "}";
    uint hash = 2166136261;
    // Teaching FNV-1a over UTF-16 code units (equals byte-wise FNV-1a for ASCII input)
    foreach (char c in canonical) hash = unchecked((hash ^ c) * 16777619u);
    return new { complete = keys.All(record.ContainsKey), checksum = hash.ToString("x8"), canonical };
}