Step 1 of moving the repo to Python with declarative rules. - core/spec/form.yaml: every question (how it is found in an export), every answer and what it is coded as, missing answers, email redaction, burn order, first-dragon pools. - core/atlas/coding.py reads it and replaces core/python/clean.py (python -m atlas.coding). - tests/core/test_coding.py: 16 rule tests, one hand-written row per rule, checking the rules are right rather than only that JS and Python agree. - analysis/stats/analyze.py takes the colours and missing answers from the spec instead of its own copy; the daily update job codes rows through the package. - pyproject.toml for the package; pyyaml and pytest added to requirements. The coded runs are byte-identical to before (5,988 runs); all parity checks still match. Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
140 lines
5.5 KiB
Python
140 lines
5.5 KiB
Python
"""
|
||
analyze.py — Python reference implementation of the statistics shown on the route-map page.
|
||
|
||
python analyze.py ../../data/derived/runs_clean.csv ../../tests/out/results_py.json
|
||
|
||
It mirrors analyse() in core/engine.js (same denominators, same tests, same model); tests/parity/compare_results.py
|
||
checks that both produce the same numbers. Edit either, then re-run the comparison.
|
||
"""
|
||
import json
|
||
import sys
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
|
||
from stats_core import Z95, bh, logistic_ridge, odds_ratio, p_from_z, wilson
|
||
|
||
# colours and the answers that count as missing come from core/spec/form.yaml, like everything else
|
||
from atlas.coding import COLORS, MISSING, is_missing # noqa: E402
|
||
FACTORS = ["company", "direction", "first_sighting", "scream", "resolution", "combat_first",
|
||
"post_path", "hour", "wing", "squad", "attempt_group", "source", "goal", "sighting_action", "combat_second", "malek_intent"]
|
||
|
||
|
||
def W(k, n):
|
||
p, lo, hi = wilson(k, n)
|
||
return {"k": int(k), "n": int(n), "p": p, "lo": lo, "hi": hi}
|
||
|
||
|
||
def outcomes():
|
||
o = {
|
||
"blue_meadow": (lambda d: d.branch == "Passed the Red: meadow", lambda d: d.saw_blue_meadow),
|
||
"shadow": (lambda d: (d.hour == "Tree") & d.branch.notna(), lambda d: d.saw_shadow),
|
||
"bond_blue_meadow": (lambda d: (d.branch == "Passed the Red: meadow") & d.enc_Blue.isin(["Bonded!", "Incinerated"]),
|
||
lambda d: d.enc_Blue == "Bonded!"),
|
||
"reach_hour": (lambda d: pd.Series(True, index=d.index), lambda d: d.hour.isin(["Tree", "Valley"])),
|
||
}
|
||
for c in COLORS:
|
||
o["bonded_" + c] = (lambda d: d.hour.isin(["Tree", "Valley"]),
|
||
(lambda c: lambda d: (d.outcome == "Bonded") & (d.outcome_color == c))(c))
|
||
return o
|
||
|
||
|
||
OUT = outcomes()
|
||
|
||
|
||
def factor_table(d, key, min_n=5):
|
||
den, ev = OUT[key]
|
||
D = d[den(d)].copy()
|
||
D["_e"] = ev(D).astype(bool)
|
||
rows = []
|
||
for f in FACTORS:
|
||
sub = D[D[f].notna() & ~D[f].isin(MISSING)]
|
||
nf, ef = len(sub), int(sub._e.sum())
|
||
for lv in sorted(sub[f].astype(str).unique()):
|
||
g = sub[sub[f].astype(str) == lv]
|
||
k, n = int(g._e.sum()), len(g)
|
||
row = {"factor": f, "level": lv, **W(k, n)}
|
||
rk, rn = ef - k, nf - n
|
||
if n >= min_n and rn >= min_n and 0 < ef < nf:
|
||
or_, lo, hi, p, corr = odds_ratio(k, n - k, rk, rn - rk)
|
||
row.update({"or": or_, "or_lo": lo, "or_hi": hi, "fisher_p": p, "corrected": corr})
|
||
rows.append(row)
|
||
tested = [r for r in rows if "fisher_p" in r]
|
||
for r, q in zip(tested, bh([r["fisher_p"] for r in tested])):
|
||
r["q"] = q
|
||
return {"outcome": key, "overall": W(int(D._e.sum()), len(D)), "rows": rows}
|
||
|
||
|
||
def model(d, key, factors, lam=1.0):
|
||
den, ev = OUT[key]
|
||
D = d[den(d)].copy()
|
||
y = ev(D).astype(int).values
|
||
F = pd.DataFrame({name: D.apply(fn, axis=1) for name, fn in factors.items()}, index=D.index)
|
||
keep = F.notna().all(axis=1).values
|
||
F, y = F[keep], y[keep]
|
||
cols, names = [np.ones(len(F))], []
|
||
refs = {}
|
||
for f in factors:
|
||
counts = F[f].value_counts()
|
||
levels = sorted(counts.index, key=lambda lv: (-counts[lv], lv))
|
||
refs[f] = levels[0]
|
||
for lv in levels[1:]:
|
||
cols.append((F[f] == lv).astype(float).values)
|
||
names.append((f, lv, int(counts[lv])))
|
||
X = np.column_stack(cols)
|
||
b, se = logistic_ridge(X, y, lam)
|
||
terms = [{"term": f"{f} = {lv}", "factor": f, "level": lv, "n": n, "or": float(np.exp(b[i + 1])),
|
||
"lo": float(np.exp(b[i + 1] - Z95 * se[i + 1])), "hi": float(np.exp(b[i + 1] + Z95 * se[i + 1])),
|
||
"p": float(p_from_z(b[i + 1] / se[i + 1]))} for i, (f, lv, n) in enumerate(names)]
|
||
return {"outcome": key, "n": int(len(y)), "events": int(y.sum()), "refs": refs, "lambda": lam, "terms": terms}
|
||
|
||
|
||
def goal2(r):
|
||
if r.goal in ("Blue", "Black", "Blue or Black"):
|
||
return r.goal
|
||
return "Blank/not asked" if r.goal == "(not asked/blank)" else "Other colour/any"
|
||
|
||
|
||
def src2(r):
|
||
return "Form submission" if r.source == "Form" else "Bulk log (import)"
|
||
|
||
|
||
def first2(r):
|
||
return r.first_sighting if r.first_sighting in ("Red", "Brown", "Orange", "Green") else None
|
||
|
||
|
||
def known(f):
|
||
return lambda r: None if is_missing(r[f]) else r[f]
|
||
|
||
|
||
def period(r):
|
||
if not isinstance(r.date, str):
|
||
return "No date (import)"
|
||
return "Oct 4–10" if r.date < "2026-10-11" else "Oct 11 onward"
|
||
|
||
|
||
def analyse(d):
|
||
res = {"n": len(d), "factors": {k: factor_table(d, k) for k in OUT}}
|
||
res["models"] = {
|
||
"blue_meadow": model(d, "blue_meadow", {
|
||
"source": src2, "goal": goal2, "direction": known("direction"), "first_sighting": first2,
|
||
"resolution": known("resolution"), "company": known("company")}),
|
||
"shadow": model(d, "shadow", {
|
||
"source": src2, "goal": goal2, "attempt": known("attempt_group"),
|
||
"direction": known("direction")}),
|
||
"bond_blue_meadow": model(d, "bond_blue_meadow", {
|
||
"source": src2, "goal": goal2, "direction": known("direction"), "resolution": known("resolution")}),
|
||
}
|
||
return res
|
||
|
||
|
||
if __name__ == "__main__":
|
||
src = sys.argv[1] if len(sys.argv) > 1 else "../../data/derived/runs_clean.csv"
|
||
out = sys.argv[2] if len(sys.argv) > 2 else "../../tests/out/results_py.json"
|
||
d = pd.read_csv(src, keep_default_na=False, na_values=[""])
|
||
for c in ("saw_blue_meadow", "saw_shadow", "rescued"):
|
||
d[c] = d[c].astype(str) == "True"
|
||
res = analyse(d)
|
||
json.dump(res, open(out, "w"), indent=1, default=float)
|
||
print("wrote", out)
|