fedex/mt
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip

Browse Source
This commit is contained in:
Jan Kowalczyk
2025-09-22 08:15:54 +02:00
parent a20a4a0832
commit 8e7c210872
5 changed files with 454 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files

204
tools/plot_scripts/results_latent_space_tables.py
View File

@@ -5,6 +5,7 @@ from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
import numpy as np
import polars as pl
# CHANGE THIS IMPORT IF YOUR LOADER MODULE IS NAMED DIFFERENTLY
@@ -41,6 +42,17 @@ DECIMALS = 3 # cells look like 1.000 or 0.928 (3 decimals)
# ----------------------------
# Helpers
# ----------------------------
def _fmt_mean_std(mean: float | None, std: float | None) -> str:
"""Format mean ± std with 3 decimals (leading zero), or '--' if missing."""
if mean is None or not (mean == mean): # NaN check
return "--"
if std is None or not (std == std):
return f"{mean:.3f}"
return f"{mean:.3f}$\\,\\pm\\,{std:.3f}$"
def _with_net_label(df: pl.DataFrame) -> pl.DataFrame:
"""Add a canonical 'net_label' column like the plotting script (LeNet/Efficient/fallback)."""
return df.with_columns(
@@ -68,7 +80,7 @@ def _filter_base(df: pl.DataFrame) -> pl.DataFrame:
"net_label",
"latent_dim",
"fold",
"auc",
"ap",
"eval",
"semi_normals",
"semi_anomalous",
@@ -84,7 +96,7 @@ class Cell:
def _compute_cells(df: pl.DataFrame) -> dict[tuple[str, int, str, str, int, int], Cell]:
"""
Compute per-(eval, latent_dim, model, net_label, semi_normals, semi_anomalous)
mean/std for AUC across folds.
mean/std for AP across folds.
"""
if df.is_empty():
return {}
@@ -107,9 +119,7 @@ def _compute_cells(df: pl.DataFrame) -> dict[tuple[str, int, str, str, int, int]
"semi_anomalous",
]
)
.agg(
pl.col("auc").mean().alias("mean_auc"), pl.col("auc").std().alias("std_auc")
)
.agg(pl.col("ap").mean().alias("mean_ap"), pl.col("ap").std().alias("std_ap"))
.to_dicts()
)
@@ -123,10 +133,96 @@ def _compute_cells(df: pl.DataFrame) -> dict[tuple[str, int, str, str, int, int]
int(row["semi_normals"]),
int(row["semi_anomalous"]),
)
out[key] = Cell(mean=row.get("mean_auc"), std=row.get("std_auc"))
out[key] = Cell(mean=row.get("mean_ap"), std=row.get("std_ap"))
return out
def method_label(model: str, net_label: str) -> str:
"""Map (model, net_label) to the four method names used in headers/caption."""
if model == "deepsad" and net_label == "LeNet":
return "DeepSAD (LeNet)"
if model == "deepsad" and net_label == "Efficient":
return "DeepSAD (Efficient)"
if model == "isoforest":
return "IsoForest"
if model == "ocsvm":
return "OC-SVM"
# ignore anything else (e.g., other backbones)
return ""
def per_method_median_std_from_cells(
cells: dict[tuple[str, int, str, str, int, int], Cell],
) -> dict[str, float]:
"""Compute the median std across all cells, per method."""
stds_by_method: dict[str, list[float]] = {
"DeepSAD (LeNet)": [],
"DeepSAD (Efficient)": [],
"IsoForest": [],
"OC-SVM": [],
}
for key, cell in cells.items():
(ev, dim, model, net, semi_n, semi_a) = key
name = method_label(model, net)
if name and (cell.std is not None) and (cell.std == cell.std): # not NaN
stds_by_method[name].append(cell.std)
return {
name: float(np.median(vals)) if vals else float("nan")
for name, vals in stds_by_method.items()
}
def per_method_max_std_from_cells(
cells: dict[tuple[str, int, str, str, int, int], Cell],
) -> tuple[dict[str, float], dict[str, tuple]]:
"""
Scan the aggregated 'cells' and return:
- max_std_by_method: dict {"DeepSAD (LeNet)": 0.037, ...}
- argmax_key_by_method: which cell (eval, dim, model, net, semi_n, semi_a) produced that max
Only considers the four methods shown in the table.
"""
max_std_by_method: dict[str, float] = {
"DeepSAD (LeNet)": float("nan"),
"DeepSAD (Efficient)": float("nan"),
"IsoForest": float("nan"),
"OC-SVM": float("nan"),
}
argmax_key_by_method: dict[str, tuple] = {}
for key, cell in cells.items():
(ev, dim, model, net, semi_n, semi_a) = key
name = method_label(model, net)
if name == "" or cell.std is None or not (cell.std == cell.std): # empty/NaN
continue
cur = max_std_by_method.get(name, float("nan"))
if (cur != cur) or (cell.std > cur): # handle NaN initial
max_std_by_method[name] = cell.std
argmax_key_by_method[name] = key
# Replace remaining NaNs with 0.0 for nice formatting
for k, v in list(max_std_by_method.items()):
if not (v == v): # NaN
max_std_by_method[k] = 0.0
return max_std_by_method, argmax_key_by_method
def _fmt_val(val: float | None) -> str:
"""
Format value as:
- '--' if None/NaN
- '1.0' if exactly 1 (within 1e-9)
- '.xx' otherwise (2 decimals, no leading 0)
"""
if val is None or not (val == val): # None or NaN
return "--"
if abs(val - 1.0) < 1e-9:
return "1.0"
return f"{val:.2f}".lstrip("0")
def _fmt_mean(mean: float | None) -> str:
return "--" if (mean is None or not (mean == mean)) else f"{mean:.{DECIMALS}f}"
@@ -150,6 +246,61 @@ def _bold_best_mask_display(values: list[float | None], decimals: int) -> list[b
return [(v is not None and v == maxv) for v in rounded]
def _build_exp_based_table(
cells: dict[tuple[str, int, str, str, int, int], Cell],
*,
semi_labeling_regimes: list[tuple[int, int]],
) -> str:
"""
Build LaTeX table with mean ± std values for experiment-based evaluation only.
"""
header_cols = [
r"\rotheader{DeepSAD\\(LeNet)}",
r"\rotheader{DeepSAD\\(Efficient)}",
r"\rotheader{IsoForest}",
r"\rotheader{OC-SVM}",
]
lines: list[str] = []
lines.append(r"\begin{table}[t]")
lines.append(r"\centering")
lines.append(r"\setlength{\tabcolsep}{4pt}")
lines.append(r"\renewcommand{\arraystretch}{1.2}")
lines.append(r"\begin{tabularx}{\textwidth}{c*{4}{Y}}")
lines.append(r"\toprule")
lines.append(r"Latent Dim. & " + " & ".join(header_cols) + r" \\")
lines.append(r"\midrule")
for idx, (semi_n, semi_a) in enumerate(semi_labeling_regimes):
# regime label row
lines.append(
rf"\multicolumn{{5}}{{l}}{{\textbf{{Labeling regime: }}\(\mathbf{{{semi_n}/{semi_a}}}\)}} \\"
)
lines.append(r"\addlinespace[2pt]")
for dim in LATENT_DIMS:
row_vals = []
for model, net in METHOD_COLUMNS:
key = ("exp_based", dim, model, net, semi_n, semi_a)
cell = cells.get(key, Cell(None, None))
row_vals.append(_fmt_mean_std(cell.mean, cell.std))
lines.append(f"{dim} & " + " & ".join(row_vals) + r" \\")
if idx < len(semi_labeling_regimes) - 1:
lines.append(r"\midrule")
lines.append(r"\bottomrule")
lines.append(r"\end{tabularx}")
lines.append(
r"\caption{AP means $\pm$ std across 5 folds for experiment-based evaluation only, grouped by labeling regime.}"
)
lines.append(r"\end{table}")
return "\n".join(lines)
def _build_single_table(
cells: dict[tuple[str, int, str, str, int, int], Cell],
*,
@@ -224,6 +375,12 @@ def _build_single_table(
cell = cells.get(key, Cell(None, None))
means_left.append(cell.mean)
cell_strs_left.append(_fmt_mean(cell.mean))
# mean_str = _fmt_val(cell.mean)
# std_str = _fmt_val(cell.std)
# if mean_str == "--":
# cell_strs_left.append("--")
# else:
# cell_strs_left.append(f"{mean_str} $\\textpm$ {std_str}")
push_std(cell.std)
# Right group: manual_based
@@ -233,6 +390,12 @@ def _build_single_table(
cell = cells.get(key, Cell(None, None))
means_right.append(cell.mean)
cell_strs_right.append(_fmt_mean(cell.mean))
# mean_str = _fmt_val(cell.mean)
# std_str = _fmt_val(cell.std)
# if mean_str == "--":
# cell_strs_right.append("--")
# else:
# cell_strs_right.append(f"{mean_str} $\\textpm$ {std_str}")
push_std(cell.std)
# Bolding per group based on displayed precision
@@ -264,11 +427,23 @@ def _build_single_table(
lines.append(r"\bottomrule")
lines.append(r"\end{tabularx}")
# Caption with max std (not shown in table)
max_std_str = "n/a" if max_std is None else f"{max_std:.{DECIMALS}f}"
# Compute per-method max std across everything included in the table
# max_std_by_method, argmax_key = per_method_max_std_from_cells(cells)
median_std_by_method = per_method_median_std_from_cells(cells)
# Optional: print where each max came from (helps verify)
for name, v in median_std_by_method.items():
print(f"[max-std] {name}: {v:.3f}")
cap_parts = []
for name in ["DeepSAD (LeNet)", "DeepSAD (Efficient)", "IsoForest", "OC-SVM"]:
v = median_std_by_method.get(name, 0.0)
cap_parts.append(f"{name} {v:.3f}")
cap_str = "; ".join(cap_parts)
lines.append(
rf"\caption{{AUC means across 5 folds for both evaluations, grouped by labeling regime. "
rf"Maximum observed standard deviation across all cells (not shown in table): {max_std_str}.}}"
rf"\caption{{AP means across 5 folds for both evaluations, grouped by labeling regime. "
rf"Maximum observed standard deviation per method (not shown in table): {cap_str}.}}"
)
lines.append(r"\end{table}")
@@ -296,10 +471,17 @@ def main():
cells, semi_labeling_regimes=SEMI_LABELING_REGIMES
)
out_name = "auc_table_all_evals_all_regimes.tex"
out_name = "ap_table_all_evals_all_regimes.tex"
out_path = ts_dir / out_name
out_path.write_text(tex, encoding="utf-8")
# Build experiment-based table with mean ± std
tex_exp = _build_exp_based_table(cells, semi_labeling_regimes=SEMI_LABELING_REGIMES)
out_name_exp = "ap_table_exp_based_mean_std.tex"
out_path_exp = ts_dir / out_name_exp
out_path_exp.write_text(tex_exp, encoding="utf-8")
# Copy this script to preserve the code used for the outputs
script_path = Path(__file__)
shutil.copy2(script_path, ts_dir / script_path.name)