feat(SAC_LSTM_Bot): progress graph tooling + first graphs
This commit is contained in:
@@ -0,0 +1,325 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Plot SAC training progress from live campaign logs.
|
||||
|
||||
Pure-stdlib SVG output (matplotlib not available on this box).
|
||||
Generates:
|
||||
docs/graph_eval_winrates.svg - eval win rate per opponent (+ rolling-20 mean, v1 overlay)
|
||||
docs/graph_losses.svg - critic/actor/alpha loss curves from training_metrics.jsonl
|
||||
|
||||
Usage:
|
||||
python3 tools/plot_progress.py [campaign_log] [metrics_jsonl] [v1_log] [outdir]
|
||||
All args optional; defaults relative to the SAC_LSTM_Bot/ root (parent of tools/).
|
||||
python3 tools/plot_progress.py --selftest # tiny built-in sanity check
|
||||
"""
|
||||
import json
|
||||
import math
|
||||
import re
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
EVAL_RE = re.compile(r">>> \[eval\] win rate: (\d+)/(\d+) \(([\d.]+)%\) vs (\S+)")
|
||||
ROLL_WINDOW = 20
|
||||
COLORS = {"Corners": "#1f77b4", "Crazy": "#2ca02c", "Target": "#d62728"}
|
||||
V1_COLOR = "#888888"
|
||||
W, M_L, M_R, M_T, M_B = 1000, 70, 20, 40, 45
|
||||
|
||||
|
||||
def parse_eval_series(path):
|
||||
"""Return {opponent: [win% per eval, in file order]}."""
|
||||
series = {}
|
||||
if not path.is_file():
|
||||
print(f"[skip] eval log not found: {path}")
|
||||
return series
|
||||
for line in path.read_text(errors="replace").splitlines():
|
||||
m = EVAL_RE.search(line)
|
||||
if not m:
|
||||
continue
|
||||
try:
|
||||
pct = float(m.group(3))
|
||||
except ValueError:
|
||||
continue
|
||||
series.setdefault(m.group(4), []).append(pct)
|
||||
return series
|
||||
|
||||
|
||||
def parse_metrics(path):
|
||||
"""Return list of metric dicts, skipping malformed lines."""
|
||||
rows = []
|
||||
if not path.is_file():
|
||||
print(f"[skip] metrics file not found: {path}")
|
||||
return rows
|
||||
for line in path.read_text(errors="replace").splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
rows.append(json.loads(line))
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
return rows
|
||||
|
||||
|
||||
def rolling(vals, w=ROLL_WINDOW):
|
||||
out, s = [], 0.0
|
||||
for i, v in enumerate(vals):
|
||||
s += v
|
||||
if i >= w:
|
||||
s -= vals[i - w]
|
||||
out.append(s / min(i + 1, w))
|
||||
return out
|
||||
|
||||
|
||||
# ---------- tiny SVG helpers ----------
|
||||
|
||||
def esc(s):
|
||||
return str(s).replace("&", "&").replace("<", "<").replace(">", ">")
|
||||
|
||||
|
||||
def svg_open(w, h, title):
|
||||
return (f'<svg xmlns="http://www.w3.org/2000/svg" width="{w}" height="{h}" '
|
||||
f'viewBox="0 0 {w} {h}" font-family="sans-serif">\n'
|
||||
f'<rect width="{w}" height="{h}" fill="white"/>\n'
|
||||
f'<text x="{w // 2}" y="22" text-anchor="middle" font-size="17" font-weight="bold">'
|
||||
f"{esc(title)}</text>\n")
|
||||
|
||||
|
||||
def polyline(pts, color, width=1.5, dash=None, opacity=1.0):
|
||||
if len(pts) < 2:
|
||||
return ""
|
||||
d = f' stroke-dasharray="{dash}"' if dash else ""
|
||||
p = " ".join(f"{x:.1f},{y:.1f}" for x, y in pts)
|
||||
return (f'<polyline points="{p}" fill="none" stroke="{color}" '
|
||||
f'stroke-width="{width}" opacity="{opacity}"{d}/>\n')
|
||||
|
||||
|
||||
def axis(x0, y0, x1, y1, xt, yt, xlabel, ylabel, ylog=False):
|
||||
"""Draw axes + ticks + labels. xt/yt are (value, px) tick lists."""
|
||||
s = (f'<line x1="{x0}" y1="{y0}" x2="{x1}" y2="{y0}" stroke="black"/>\n'
|
||||
f'<line x1="{x0}" y1="{y0}" x2="{x0}" y2="{y1}" stroke="black"/>\n')
|
||||
for v, px in xt:
|
||||
s += (f'<line x1="{px:.1f}" y1="{y0}" x2="{px:.1f}" y2="{y0 + 4}" stroke="black"/>\n'
|
||||
f'<text x="{px:.1f}" y="{y0 + 17}" text-anchor="middle" font-size="11">'
|
||||
f"{esc(v)}</text>\n")
|
||||
for v, py in yt:
|
||||
s += (f'<line x1="{x0 - 4}" y1="{py:.1f}" x2="{x0}" y2="{py:.1f}" stroke="black"/>\n'
|
||||
f'<text x="{x0 - 7}" y="{py + 4:.1f}" text-anchor="end" font-size="11">'
|
||||
f"{esc(v)}</text>\n")
|
||||
s += (f'<text x="{(x0 + x1) // 2}" y="{y0 + 33}" text-anchor="middle" font-size="12">'
|
||||
f"{esc(xlabel)}</text>\n"
|
||||
f'<text x="16" y="{(y0 + y1) // 2}" text-anchor="middle" font-size="12" '
|
||||
f'transform="rotate(-90 16 {(y0 + y1) // 2})">{esc(ylabel)}</text>\n')
|
||||
return s
|
||||
|
||||
|
||||
def ticks_linear(vmin, vmax, p0, p1, n=5, fmt="{:.0f}"):
|
||||
return [(fmt.format(vmin + (vmax - vmin) * i / (n - 1)),
|
||||
p0 + (p1 - p0) * i / (n - 1)) for i in range(n)]
|
||||
|
||||
|
||||
def ticks_log(vmin, vmax, p0, p1, n=5):
|
||||
vals = [10 ** (vmin + (vmax - vmin) * i / (n - 1)) for i in range(n)]
|
||||
return [("{:.3g}".format(v), p0 + (p1 - p0) * i / (n - 1)) for i, v in enumerate(vals)]
|
||||
|
||||
|
||||
def legend(items, x, y):
|
||||
"""items: [(color, dash, label)]"""
|
||||
s = ""
|
||||
for i, (color, dash, label) in enumerate(items):
|
||||
yy = y + i * 18
|
||||
d = f' stroke-dasharray="{dash}"' if dash else ""
|
||||
s += (f'<line x1="{x}" y1="{yy}" x2="{x + 28}" y2="{yy}" stroke="{color}" '
|
||||
f'stroke-width="3"{d}/>\n'
|
||||
f'<text x="{x + 34}" y="{yy + 4}" font-size="12">{esc(label)}</text>\n')
|
||||
return s
|
||||
|
||||
|
||||
def map_fn(p0, p1, vmin, vmax, log=False):
|
||||
def f(v):
|
||||
t = (math.log10(v) - vmin) / (vmax - vmin) if log else (v - vmin) / (vmax - vmin)
|
||||
return p1 - max(0.0, min(1.0, t)) * (p1 - p0)
|
||||
return f
|
||||
|
||||
|
||||
# ---------- graph 1: eval win rates ----------
|
||||
|
||||
def graph_eval(series_v2, series_v1, out):
|
||||
if not series_v2 and not series_v1:
|
||||
print("[skip] no eval data at all -> no win-rate graph")
|
||||
return 0
|
||||
H = 560
|
||||
x0, y0, x1, y1 = M_L, H - M_B, W - M_R, M_T
|
||||
xmax = max(max((len(v) for v in s.values()), default=1) for s in (series_v2, series_v1))
|
||||
xmax = max(xmax, 2)
|
||||
xm = map_fn(x0, x1, 1, xmax)
|
||||
ym = map_fn(y0, y1, 0, 100)
|
||||
s = svg_open(W, H, "SAC-LSTM campaign: eval win rate vs opponents (v2 live, v1 archived)")
|
||||
s += axis(x0, y0, x1, y1, ticks_linear(1, xmax, x0, x1),
|
||||
ticks_linear(0, 100, y0, y1), f"eval number (per opponent)",
|
||||
"win rate (%)")
|
||||
counts = []
|
||||
items = []
|
||||
for name in ("Corners", "Crazy", "Target"):
|
||||
vals = series_v2.get(name, [])
|
||||
if not vals:
|
||||
continue
|
||||
c = COLORS[name]
|
||||
s += polyline([(xm(i + 1), ym(v)) for i, v in enumerate(vals)], c, 1, opacity=0.30)
|
||||
s += polyline([(xm(i + 1), ym(v)) for i, v in enumerate(rolling(vals))], c, 3)
|
||||
counts.append(f"{name}: {len(vals)} evals")
|
||||
items.append((c, None, f"{name} (thick = rolling-{ROLL_WINDOW} mean)"))
|
||||
v1 = series_v1.get("Corners", [])
|
||||
if v1:
|
||||
s += polyline([(xm(i + 1), ym(v)) for i, v in enumerate(v1)], V1_COLOR, 1, dash="6,4")
|
||||
s += polyline([(xm(i + 1), ym(v)) for i, v in enumerate(rolling(v1))], V1_COLOR, 2, dash="6,4")
|
||||
counts.append(f"v1 Corners (old run): {len(v1)} evals")
|
||||
items.append((V1_COLOR, "6,4", "v1 Corners (old run)"))
|
||||
s += legend(items, x1 - 260, y1 + 14)
|
||||
s += (f'<text x="{x0 + 8}" y="{y1 + 14}" font-size="11" fill="#555">'
|
||||
f'{esc("; ".join(counts))}</text>\n</svg>\n')
|
||||
out.write_text(s)
|
||||
return 1
|
||||
|
||||
|
||||
# ---------- graph 2: loss curves ----------
|
||||
|
||||
def graph_losses(rows, out):
|
||||
if not rows:
|
||||
print("[skip] no metric rows -> no loss graph")
|
||||
return 0
|
||||
|
||||
def col(key, log=False):
|
||||
vals = []
|
||||
for r in rows:
|
||||
try:
|
||||
v = abs(float(r[key])) # abs: log panels plot magnitude
|
||||
except (KeyError, TypeError, ValueError):
|
||||
continue
|
||||
if log and v <= 0:
|
||||
continue
|
||||
vals.append(v)
|
||||
return vals
|
||||
|
||||
critic = col("critic_loss", log=True)
|
||||
actor = col("actor_loss", log=True)
|
||||
alpha = col("alpha")
|
||||
if not (critic or actor or alpha):
|
||||
print("[skip] metric rows lack critic_loss/actor_loss/alpha -> no loss graph")
|
||||
return 0
|
||||
|
||||
PH, GAP = 210, 55
|
||||
H = M_T + 3 * PH + 2 * GAP + M_B
|
||||
x0, x1 = M_L, W - M_R
|
||||
n = len(rows)
|
||||
s = svg_open(W, H, "SAC-LSTM training losses (x = metric line number)")
|
||||
|
||||
def panel(top, vals, title, log, ylab, fixed_range=None):
|
||||
nonlocal s
|
||||
y0, y1 = top + PH, top
|
||||
if not vals:
|
||||
s += (f'<text x="{x0 + 10}" y="{top + 20}" font-size="12" fill="#a00">'
|
||||
f"{esc(title)}: no valid points</text>\n")
|
||||
return
|
||||
if log:
|
||||
lo = math.floor(math.log10(min(vals)))
|
||||
hi = math.ceil(math.log10(max(vals)))
|
||||
if lo == hi:
|
||||
hi = lo + 1
|
||||
yt = ticks_log(lo, hi, y0, y1)
|
||||
else:
|
||||
lo, hi = fixed_range or (min(vals), max(vals))
|
||||
if lo == hi:
|
||||
hi = lo + 1
|
||||
yt = ticks_linear(lo, hi, y0, y1, n=5, fmt="{:.3g}")
|
||||
s += (f'<text x="{x0 + 6}" y="{top + 16}" font-size="13" font-weight="bold">'
|
||||
f"{esc(title)}</text>\n")
|
||||
s += axis(x0, y0, x1, y1, ticks_linear(1, n, x0, x1, fmt="{:.0f}"), yt,
|
||||
"", ylab)
|
||||
ym = map_fn(y0, y1, lo, hi, log=log)
|
||||
pts = []
|
||||
for i, r in enumerate(rows):
|
||||
try:
|
||||
v = abs(float(r[title_key(title)]))
|
||||
except (KeyError, TypeError, ValueError):
|
||||
continue
|
||||
if log and v <= 0:
|
||||
continue
|
||||
pts.append((x0 + (x1 - x0) * i / max(n - 1, 1), ym(v)))
|
||||
s += polyline(pts, "#1f77b4", 1.6)
|
||||
|
||||
def title_key(title):
|
||||
return {"critic_loss (log scale)": "critic_loss",
|
||||
"actor_loss |abs| (log scale)": "actor_loss",
|
||||
"alpha (temperature)": "alpha"}[title]
|
||||
|
||||
panel(M_T, critic, "critic_loss (log scale)", True, "critic_loss")
|
||||
panel(M_T + PH + GAP, actor, "actor_loss |abs| (log scale)", True, "|actor_loss|")
|
||||
panel(M_T + 2 * (PH + GAP), alpha, "alpha (temperature)", False, "alpha",
|
||||
fixed_range=(0, max(1.0, max(alpha))))
|
||||
s += (f'<text x="{x0 + (x1 - x0) // 2}" y="{H - 8}" text-anchor="middle" '
|
||||
f'font-size="12">metric line number ({n} rows)</text>\n</svg>\n')
|
||||
out.write_text(s)
|
||||
return 1
|
||||
|
||||
|
||||
# ---------- selftest ----------
|
||||
|
||||
def selftest():
|
||||
with tempfile.TemporaryDirectory() as td:
|
||||
td = Path(td)
|
||||
(td / "log").write_text(
|
||||
">>> [eval] win rate: 3/10 (30%) vs Corners\n"
|
||||
"garbage line\n"
|
||||
">>> [eval] win rate: 7/10 (70%) vs Crazy\n"
|
||||
">>> [eval] win rate: broken\n"
|
||||
">>> [eval] win rate: 5/10 (50%) vs Corners\n")
|
||||
ser = parse_eval_series(td / "log")
|
||||
assert ser == {"Corners": [30.0, 50.0], "Crazy": [70.0]}, ser
|
||||
assert rolling([10] * 25, 20)[-1] == 10.0
|
||||
assert rolling([1, 2, 3], 20) == [1.0, 1.5, 2.0]
|
||||
(td / "m.jsonl").write_text(
|
||||
'{"critic_loss": 10, "actor_loss": -2, "alpha": 0.5}\n'
|
||||
"not json\n"
|
||||
'{"critic_loss": 100, "actor_loss": -4, "alpha": 0.25}\n')
|
||||
rows = parse_metrics(td / "m.jsonl")
|
||||
assert len(rows) == 2 and rows[1]["critic_loss"] == 100
|
||||
ok = graph_losses(rows, td / "g2.svg") and graph_eval(ser, {"Corners": [0, 10]}, td / "g1.svg")
|
||||
assert ok and (td / "g1.svg").stat().st_size > 500
|
||||
assert graph_eval({}, {}, td / "none.svg") == 0 # missing data handled
|
||||
print("selftest OK")
|
||||
|
||||
|
||||
def main():
|
||||
if "--selftest" in sys.argv:
|
||||
selftest()
|
||||
return
|
||||
args = [a for a in sys.argv[1:] if not a.startswith("-")]
|
||||
campaign = Path(args[0]) if len(args) > 0 else ROOT / "campaign_v2_stdout.log"
|
||||
metrics = Path(args[1]) if len(args) > 1 else ROOT / "training_metrics.jsonl"
|
||||
v1log = Path(args[2]) if len(args) > 2 else ROOT / "weights_v1_archive" / "campaign_stdout.log"
|
||||
outdir = Path(args[3]) if len(args) > 3 else ROOT / "docs"
|
||||
outdir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
made = 0
|
||||
series_v2 = parse_eval_series(campaign)
|
||||
print(f"[info] v2 evals parsed: " +
|
||||
", ".join(f"{k}={len(v)}" for k, v in sorted(series_v2.items())) or "(none)")
|
||||
series_v1 = parse_eval_series(v1log)
|
||||
print(f"[info] v1 evals parsed: " +
|
||||
", ".join(f"{k}={len(v)}" for k, v in sorted(series_v1.items())) or "(none)")
|
||||
made += graph_eval(series_v2, series_v1, outdir / "graph_eval_winrates.svg")
|
||||
|
||||
rows = parse_metrics(metrics)
|
||||
print(f"[info] metric rows parsed: {len(rows)}")
|
||||
made += graph_losses(rows, outdir / "graph_losses.svg")
|
||||
|
||||
if made:
|
||||
print(f"[done] {made} graph(s) written to {outdir}")
|
||||
else:
|
||||
print("[error] nothing plotted - check paths above")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user