| | import os |
| | import sys |
| | import json |
| | import datetime |
| | import math |
| | try: |
| | import scipy.io |
| | except ImportError: |
| | scipy = None |
| | try: |
| | import numpy as np |
| | except ImportError: |
| | np = None |
| | try: |
| | import pandas as pd |
| | except ImportError: |
| | pd = None |
| | from flask import Flask, jsonify, request, render_template, send_from_directory |
| | from dash import Dash, html, dcc, dash_table, Input, Output, State, callback_context |
| | import dash_mantine_components as dmc |
| | import plotly.graph_objects as go |
| |
|
| | sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))) |
| | from leaderboard import rank_results |
| | try: |
| | from complex_com import algorithms as ALGO_COMPLEXITY |
| | except ImportError: |
| | ALGO_COMPLEXITY = {} |
| |
|
| | base_dir = os.getcwd() |
| | if not os.path.isdir(os.path.join(base_dir, "results")): |
| | base_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..")) |
| | PROJECT_ROOT = base_dir |
| | RESULT_DIR = os.path.join(PROJECT_ROOT, "results") |
| | DATA_DIR = os.path.join(PROJECT_ROOT, "data") |
| | PDF_DIR = os.path.join(PROJECT_ROOT, "pdf") |
| |
|
| | os.makedirs(RESULT_DIR, exist_ok=True) |
| |
|
| | server = Flask(__name__) |
| |
|
| | RESULT_CACHE = {} |
| |
|
| |
|
| | def save_result_json(dataset, results): |
| | path = os.path.join(RESULT_DIR, f"{dataset}.json") |
| | with open(path, "w", encoding="utf-8") as f: |
| | json.dump(results, f, indent=4) |
| |
|
| |
|
| | def load_result_json(dataset): |
| | path = os.path.join(RESULT_DIR, f"{dataset}.json") |
| | if not os.path.exists(path): |
| | return None |
| | with open(path, "r", encoding="utf-8") as f: |
| | return json.load(f) |
| |
|
| |
|
| | def list_available_datasets(): |
| | datasets = set() |
| | for f in os.listdir(RESULT_DIR): |
| | if f.endswith(".json"): |
| | datasets.add(f.replace(".json", "")) |
| | datasets.add("Authorship") |
| | return sorted(datasets) |
| |
|
| |
|
| | def run_agent_for_dataset(dataset): |
| | return [] |
| |
|
| |
|
| | def build_dataset_metadata(): |
| | datasets = {} |
| | for name in list_available_datasets(): |
| | last_updated = datetime.datetime.fromtimestamp(1707382400).strftime("%Y-%m-%d") |
| | num_samples = None |
| | total_features = None |
| | if scipy: |
| | mat_path = os.path.join(DATA_DIR, f"{name}.mat") |
| | if os.path.exists(mat_path): |
| | try: |
| | mat = scipy.io.loadmat(mat_path) |
| | if "X" in mat: |
| | X = mat["X"] |
| | num_samples, total_features = X.shape |
| | except Exception: |
| | num_samples = None |
| | total_features = None |
| | datasets[name] = { |
| | "name": name, |
| | "last_updated": last_updated, |
| | "num_samples": num_samples, |
| | "total_features": total_features, |
| | } |
| | return datasets |
| |
|
| |
|
| | DATASET_METADATA = build_dataset_metadata() |
| |
|
| |
|
| | def build_complexity_display(): |
| | display_complexity = {} |
| | for algo, comp in ALGO_COMPLEXITY.items(): |
| | t = comp.get("time", "") |
| | s = comp.get("space", "") |
| | t_disp = t.replace("**", "^").replace(" * ", "") |
| | if "O(" not in t_disp: |
| | t_disp = f"O({t_disp})" if t_disp else "" |
| | s_disp = s.replace("**", "^").replace(" * ", "") |
| | if "O(" not in s_disp: |
| | s_disp = f"O({s_disp})" if s_disp else "" |
| | display_complexity[algo] = {"time": t_disp, "space": s_disp} |
| | return display_complexity |
| |
|
| |
|
| | DISPLAY_COMPLEXITY = build_complexity_display() |
| |
|
| | VIEW_CONFIG = { |
| | "overall": [ |
| | {"key": "mean_f1", "label": "Mean F1"}, |
| | {"key": "mean_auc", "label": "Mean AUC"}, |
| | ], |
| | "classifiers-f1": [ |
| | {"key": "metrics.nb.f1", "label": "NB F1"}, |
| | {"key": "metrics.svm.f1", "label": "SVM F1"}, |
| | {"key": "metrics.rf.f1", "label": "RF F1"}, |
| | ], |
| | "classifiers-auc": [ |
| | {"key": "metrics.nb.auc", "label": "NB AUC"}, |
| | {"key": "metrics.svm.auc", "label": "SVM AUC"}, |
| | {"key": "metrics.rf.auc", "label": "RF AUC"}, |
| | ], |
| | } |
| |
|
| |
|
| | def get_results_for_dataset(dataset): |
| | if dataset in RESULT_CACHE: |
| | leaderboard = rank_results(RESULT_CACHE[dataset]) |
| | else: |
| | results = load_result_json(dataset) |
| | if results is None: |
| | results = run_agent_for_dataset(dataset) |
| | if results: |
| | save_result_json(dataset, results) |
| | RESULT_CACHE[dataset] = results or [] |
| | leaderboard = rank_results(results or []) |
| | if not isinstance(leaderboard, list): |
| | if hasattr(leaderboard, "to_dict"): |
| | leaderboard = leaderboard.to_dict(orient="records") |
| | else: |
| | leaderboard = list(leaderboard) |
| | return leaderboard |
| |
|
| |
|
| | def get_metric_value(row, key): |
| | value = row |
| | for part in key.split("."): |
| | if isinstance(value, dict): |
| | value = value.get(part) |
| | else: |
| | return None |
| | return value |
| |
|
| |
|
| | def get_feature_count(row): |
| | num_features = row.get("num_features") |
| | if isinstance(num_features, (int, float)): |
| | return int(num_features) |
| | selected = row.get("selected_features") |
| | if isinstance(selected, list): |
| | return len(selected) |
| | return 0 |
| |
|
| |
|
| | def apply_filters(results, dataset_meta, min_f1, max_features, del_range, complexity, selected_algos): |
| | total_features = dataset_meta.get("total_features") if dataset_meta else None |
| | filtered = [] |
| | min_del = (del_range[0] if del_range else 0) / 100 |
| | max_del = (del_range[1] if del_range else 100) / 100 |
| | min_f1 = min_f1 if min_f1 is not None else 0 |
| | max_features = max_features if max_features is not None else float("inf") |
| | selected_algos = selected_algos if selected_algos else None |
| | for r in results: |
| | algo = r.get("algorithm") |
| | if selected_algos and algo not in selected_algos: |
| | continue |
| | raw_f1 = r.get("mean_f1") |
| | try: |
| | f1 = float(raw_f1) if raw_f1 is not None else 0 |
| | except (TypeError, ValueError): |
| | f1 = 0 |
| | if f1 < min_f1: |
| | continue |
| | feats = get_feature_count(r) |
| | if feats > max_features: |
| | continue |
| | if isinstance(total_features, (int, float)) and total_features > 0: |
| | del_rate = 1 - (feats / total_features) |
| | if del_rate < min_del or del_rate > max_del: |
| | continue |
| | if complexity and complexity != "all": |
| | comp = DISPLAY_COMPLEXITY.get(algo, {}).get("time") |
| | if comp != complexity: |
| | continue |
| | filtered.append(r) |
| | return filtered |
| |
|
| |
|
| | def build_score_figure(results, view_mode): |
| | if not results: |
| | fig = go.Figure() |
| | fig.add_annotation( |
| | text="No Data Available", |
| | x=0.5, |
| | y=0.5, |
| | xref="paper", |
| | yref="paper", |
| | showarrow=False, |
| | font=dict(size=16, color="#999"), |
| | ) |
| | fig.update_layout( |
| | xaxis=dict(visible=False), |
| | yaxis=dict(visible=False), |
| | margin=dict(l=20, r=20, t=20, b=20), |
| | ) |
| | return fig |
| | top = results[:20] |
| | labels = [r.get("algorithm") for r in top] |
| | fig = go.Figure() |
| | if view_mode == "overall": |
| | fig.add_trace(go.Bar( |
| | name="Mean F1", |
| | y=labels, |
| | x=[r.get("mean_f1") for r in top], |
| | orientation="h", |
| | marker_color="rgba(52, 152, 219, 0.7)", |
| | )) |
| | fig.add_trace(go.Bar( |
| | name="Mean AUC", |
| | y=labels, |
| | x=[r.get("mean_auc") for r in top], |
| | orientation="h", |
| | marker_color="rgba(46, 204, 113, 0.7)", |
| | )) |
| | elif view_mode == "classifiers-f1": |
| | for idx, clf in enumerate(["nb", "svm", "rf"]): |
| | fig.add_trace(go.Bar( |
| | name=clf.upper(), |
| | y=labels, |
| | x=[get_metric_value(r, f"metrics.{clf}.f1") for r in top], |
| | orientation="h", |
| | marker_color=f"hsla({200 + idx * 40}, 70%, 60%, 0.7)", |
| | )) |
| | else: |
| | for idx, clf in enumerate(["nb", "svm", "rf"]): |
| | fig.add_trace(go.Bar( |
| | name=clf.upper(), |
| | y=labels, |
| | x=[get_metric_value(r, f"metrics.{clf}.auc") for r in top], |
| | orientation="h", |
| | marker_color=f"hsla({100 + idx * 40}, 70%, 60%, 0.7)", |
| | )) |
| | fig.update_layout( |
| | barmode="group", |
| | margin=dict(l=20, r=20, t=20, b=20), |
| | legend=dict(orientation="h"), |
| | yaxis=dict(autorange="reversed"), |
| | ) |
| | return fig |
| |
|
| |
|
| | def build_pareto_figure(results): |
| | x_vals = [get_feature_count(r) for r in results] |
| | y_vals = [r.get("mean_f1") for r in results] |
| | labels = [r.get("algorithm") for r in results] |
| | fig = go.Figure() |
| | fig.add_trace(go.Scatter( |
| | x=x_vals, |
| | y=y_vals, |
| | mode="markers", |
| | text=labels, |
| | marker=dict(color="rgba(230, 126, 34, 0.7)", size=10), |
| | )) |
| | fig.update_layout( |
| | margin=dict(l=20, r=20, t=20, b=20), |
| | xaxis_title="Num Features", |
| | yaxis_title="Mean F1", |
| | ) |
| | return fig |
| |
|
| |
|
| | def build_table(results, view_mode): |
| | config = VIEW_CONFIG[view_mode] |
| | headers = ["Rank", "Algorithm"] + [c["label"] for c in config] + ["Selected Features"] |
| | col_keys = [c["key"] for c in config] |
| | max_map = {} |
| | for key in col_keys: |
| | vals = [] |
| | for r in results: |
| | v = get_metric_value(r, key) |
| | try: |
| | v = float(v) if v is not None else None |
| | except Exception: |
| | v = None |
| | if v is not None: |
| | vals.append(v) |
| | max_map[key] = max(vals) if vals else 0 |
| | thead = html.Thead( |
| | html.Tr([html.Th(h, className="cth") for h in headers], className="chead") |
| | ) |
| | rows = [] |
| | if not results: |
| | empty_cells = [html.Td("", className="ctd")] * (len(headers) - 2) |
| | rows.append( |
| | html.Tr( |
| | [html.Td("", className="ctd"), html.Td("No Data Available", className="ctd")]+empty_cells, |
| | className="crow" |
| | ) |
| | ) |
| | else: |
| | for idx, r in enumerate(results): |
| | rank = idx + 1 |
| | medal = {1: "🥇", 2: "🥈", 3: "🥉"}.get(rank, str(rank)) |
| | row_class = ( |
| | "crow crow-gold" if rank == 1 else |
| | "crow crow-silver" if rank == 2 else |
| | "crow crow-bronze" if rank == 3 else |
| | "crow" |
| | ) |
| | algo = r.get("algorithm") or "Unknown" |
| | metric_tds = [] |
| | for c in config: |
| | key = c["key"] |
| | raw = get_metric_value(r, key) |
| | try: |
| | val = float(raw) if raw is not None else 0.0 |
| | except Exception: |
| | val = 0.0 |
| | m = max_map.get(key) or 0.0 |
| | pct = (val / m * 100.0) if m > 0 else 0 |
| | is_max = (m > 0 and abs(val - m) < 1e-12) |
| | bar = html.Div( |
| | [ |
| | html.Div(className="bar-track", children=html.Div(className="bar-fill", style={"width": f"{pct:.2f}%"})), |
| | html.Span(f"{val:.4f}", className=("bar-text is-max" if is_max else "bar-text")), |
| | ], |
| | className="bar-cell", |
| | title=f"max={m:.4f}" if is_max else None, |
| | ) |
| | cell = html.Td(bar, className="ctd cnum") |
| | metric_tds.append(cell) |
| | selected = r.get("selected_features") |
| | feat_count = get_feature_count(r) |
| | if isinstance(selected, list): |
| | features_title = ", ".join(str(s) for s in selected) |
| | else: |
| | features_title = "N/A" |
| | feature_td = html.Td( |
| | f"{feat_count} features", |
| | className="ctd cfeat", |
| | title=features_title, |
| | style={"whiteSpace": "nowrap"}, |
| | ) |
| | row = html.Tr( |
| | [html.Td(medal, className="ctd crank"), html.Td(algo, className="ctd calgo")] + metric_tds + [feature_td], |
| | className=row_class, |
| | ) |
| | rows.append(row) |
| | tbody = html.Tbody(rows) |
| | table = html.Table([thead, tbody], className="custom-table") |
| | return html.Div(className="table-container", children=table) |
| |
|
| |
|
| | dataset_options = [{"label": name, "value": name} for name in sorted(DATASET_METADATA.keys())] |
| | default_dataset = "Authorship" if "Authorship" in DATASET_METADATA else (dataset_options[0]["value"] if dataset_options else "Authorship") |
| |
|
| | complexity_options = sorted({v.get("time") for v in DISPLAY_COMPLEXITY.values() if v.get("time")}) |
| | complexity_data = [{"label": "All Complexities", "value": "all"}] + [ |
| | {"label": c, "value": c} for c in complexity_options |
| | ] |
| |
|
| | dash_app = Dash(__name__, server=server, url_base_pathname="/") |
| | app = dash_app |
| |
|
| | css = """ |
| | :root { |
| | --primary-color: #3498db; |
| | --secondary-color: #2c3e50; |
| | --background-color: #f8f9fa; |
| | --text-color: #333; |
| | --border-color: #dee2e6; |
| | --hover-color: #f1f1f1; |
| | --accent-color: #e67e22; |
| | --sidebar-width: 280px; |
| | } |
| | body { |
| | font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; |
| | margin: 0; |
| | padding: 0; |
| | background-color: var(--background-color); |
| | color: var(--text-color); |
| | } |
| | .app-shell { |
| | display: flex; |
| | min-height: 100vh; |
| | } |
| | .sidebar { |
| | width: var(--sidebar-width); |
| | background-color: var(--secondary-color); |
| | color: white; |
| | position: fixed; |
| | height: 100vh; |
| | overflow-y: auto; |
| | padding: 20px; |
| | box-sizing: border-box; |
| | left: 0; |
| | top: 0; |
| | z-index: 100; |
| | display: flex; |
| | flex-direction: column; |
| | gap: 20px; |
| | } |
| | .sidebar h2 { |
| | font-size: 1.1em; |
| | margin-bottom: 10px; |
| | color: #ecf0f1; |
| | border-bottom: 1px solid #34495e; |
| | padding-bottom: 5px; |
| | } |
| | .main-content { |
| | margin-left: var(--sidebar-width); |
| | padding: 24px; |
| | width: calc(100% - var(--sidebar-width)); |
| | box-sizing: border-box; |
| | } |
| | .stats-grid { |
| | display: grid; |
| | grid-template-columns: 1fr; |
| | gap: 10px; |
| | } |
| | .stat-card { |
| | background: rgba(255,255,255,0.1); |
| | padding: 10px; |
| | border-radius: 6px; |
| | text-align: center; |
| | } |
| | .stat-value { |
| | font-size: 1.2em; |
| | font-weight: 600; |
| | color: var(--accent-color); |
| | } |
| | .stat-label { |
| | font-size: 0.8em; |
| | color: #bdc3c7; |
| | } |
| | .card { |
| | background: white; |
| | padding: 16px; |
| | border-radius: 8px; |
| | box-shadow: 0 1px 3px rgba(0,0,0,0.1); |
| | } |
| | .chart-card { |
| | background: white; |
| | padding: 16px; |
| | border-radius: 8px; |
| | box-shadow: 0 1px 3px rgba(0,0,0,0.1); |
| | height: 420px; |
| | display: flex; |
| | flex-direction: column; |
| | } |
| | .chart-card .dash-graph { |
| | flex: 1; |
| | } |
| | .table-container { |
| | background: white; |
| | padding: 12px; |
| | border-radius: 8px; |
| | box-shadow: 0 1px 3px rgba(0,0,0,0.1); |
| | } |
| | .nav-links { |
| | list-style: none; |
| | padding: 0; |
| | margin: 0; |
| | } |
| | .nav-links li a { |
| | display: block; |
| | padding: 8px; |
| | color: #bdc3c7; |
| | text-decoration: none; |
| | border-radius: 4px; |
| | } |
| | .nav-links li a:hover { |
| | background: rgba(255,255,255,0.1); |
| | color: white; |
| | } |
| | |
| | /* Custom Table Styles */ |
| | .custom-table-wrapper { |
| | overflow-x: auto; |
| | overflow-y: auto; |
| | max-height: 520px; |
| | background: #fff; |
| | border: 1px solid #eee; |
| | border-radius: 8px; |
| | box-shadow: 0 1px 3px rgba(0,0,0,0.06); |
| | } |
| | .custom-table { |
| | width: 100%; |
| | border-collapse: separate; |
| | border-spacing: 0; |
| | table-layout: fixed; |
| | } |
| | .custom-table thead th { |
| | text-align: left; |
| | border-bottom: 2px solid var(--border-color); |
| | padding: 10px; |
| | } |
| | .custom-table tbody td { |
| | padding: 8px 10px; |
| | border-bottom: 1px solid #eee; |
| | vertical-align: middle; |
| | } |
| | .custom-table tbody tr:hover { |
| | background: #fafafa; |
| | transition: background 0.2s ease; |
| | } |
| | .custom-table tbody tr:nth-child(even) { background: #fcfcfc; } |
| | .custom-table thead th { |
| | position: sticky; |
| | top: 0; |
| | background: #fff; |
| | z-index: 1; |
| | } |
| | .cnum { font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", monospace; text-align: right; } |
| | .is-max { font-weight: 600; color: var(--accent-color); } |
| | .crow-gold { background: rgba(255,215,0,0.12); } |
| | .crow-silver { background: rgba(192,192,192,0.12); } |
| | .crow-bronze { background: rgba(205,127,50,0.12); } |
| | .crank { width: 56px; text-align: center; } |
| | .calgo { font-weight: 500; } |
| | .cth { background: var(--background-color); } |
| | .cfeat { white-space: nowrap; overflow: hidden; text-overflow: ellipsis; } |
| | |
| | /* In-cell Data Bars */ |
| | .bar-cell { |
| | position: relative; |
| | height: 26px; |
| | display: flex; |
| | align-items: center; |
| | justify-content: flex-end; |
| | } |
| | .bar-track { |
| | position: absolute; |
| | left: 6px; |
| | right: 6px; |
| | height: 60%; |
| | background: #f4f7fb; |
| | border: 1px solid #e6eef7; |
| | border-radius: 6px; |
| | overflow: hidden; |
| | } |
| | .bar-fill { |
| | height: 100%; |
| | background: linear-gradient(90deg, #7db9e8 0%, #3498db 100%); |
| | opacity: 0.35; |
| | transition: width 200ms ease; |
| | } |
| | .bar-text { |
| | position: relative; |
| | z-index: 1; |
| | font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", monospace; |
| | padding: 0 6px; |
| | line-height: 1; |
| | } |
| | """ |
| |
|
| | dash_app.index_string = f""" |
| | <!DOCTYPE html> |
| | <html> |
| | <head> |
| | {{%metas%}} |
| | <title>AutoFS Leaderboard</title> |
| | {{%favicon%}} |
| | {{%css%}} |
| | <style>{css}</style> |
| | </head> |
| | <body> |
| | {{%app_entry%}} |
| | <footer> |
| | {{%config%}} |
| | {{%scripts%}} |
| | {{%renderer%}} |
| | </footer> |
| | </body> |
| | </html> |
| | """ |
| |
|
| | dash_app.layout = dmc.MantineProvider( |
| | children=html.Div( |
| | className="app-shell", |
| | children=[ |
| | html.Aside( |
| | className="sidebar", |
| | children=[ |
| | html.Div( |
| | [ |
| | html.H1("AutoFS", style={"fontSize": "1.5em", "margin": 0, "color": "white"}), |
| | html.Div("Feature Selection Leaderboard", style={"fontSize": "0.8em", "color": "#bdc3c7"}), |
| | ], |
| | style={"textAlign": "center", "marginBottom": "10px"}, |
| | ), |
| | html.Div( |
| | className="stats-grid", |
| | children=[ |
| | html.Div([html.Div("-", id="stat-count", className="stat-value"), html.Div("Methods", className="stat-label")], className="stat-card"), |
| | html.Div([html.Div("-", id="stat-best", className="stat-value"), html.Div("Best F1", className="stat-label")], className="stat-card"), |
| | html.Div([html.Div("-", id="stat-updated", className="stat-value"), html.Div("Updated", className="stat-label")], className="stat-card"), |
| | ], |
| | ), |
| | html.Div( |
| | [ |
| | html.H2("Navigation"), |
| | html.Ul( |
| | className="nav-links", |
| | children=[ |
| | html.Li(html.A("📊 Overview", href="#overview")), |
| | html.Li(html.A("🏆 Leaderboard", href="#main-table")), |
| | html.Li(html.A("📈 Charts", href="#charts")), |
| | html.Li(html.A("ℹ️ Details", href="#details")), |
| | html.Li(html.A("🌍 Global Rankings", href="/global")), |
| | html.Li(html.A("📤 Submit Data/Method", href="/submit")), |
| | ], |
| | ), |
| | ] |
| | ), |
| | html.Div( |
| | [ |
| | html.H2("Global Controls"), |
| | dmc.Select( |
| | id="view-mode", |
| | data=[ |
| | {"label": "Overall (Mean)", "value": "overall"}, |
| | {"label": "F1 by Classifier", "value": "classifiers-f1"}, |
| | {"label": "AUC by Classifier", "value": "classifiers-auc"}, |
| | ], |
| | value="overall", |
| | clearable=False, |
| | style={"marginBottom": "10px"}, |
| | ), |
| | ] |
| | ), |
| | html.Div( |
| | [ |
| | html.H2("Filters"), |
| | dmc.Select( |
| | id="dataset-select", |
| | data=dataset_options, |
| | value="Authorship", |
| | clearable=False, |
| | style={"marginBottom": "10px"}, |
| | ), |
| | html.Div( |
| | [ |
| | html.Div( |
| | [ |
| | html.Span("Min F1 Score: "), |
| | html.Span("0.0000", id="val-f1", style={"color": "var(--accent-color)"}), |
| | ], |
| | style={"marginBottom": "6px", "color": "#bdc3c7"}, |
| | ), |
| | dmc.Slider(id="filter-f1", min=0, max=1, step=0.0001, value=0), |
| | ], |
| | style={"marginBottom": "12px"}, |
| | ), |
| | html.Div( |
| | [ |
| | html.Div( |
| | [ |
| | html.Span("Del. Rate: "), |
| | html.Span("0% - 100%", id="val-del-rate", style={"color": "var(--accent-color)"}), |
| | ], |
| | style={"marginBottom": "6px", "color": "#bdc3c7"}, |
| | ), |
| | dmc.RangeSlider(id="filter-del-rate", min=0, max=100, value=[0, 100], step=1), |
| | ], |
| | style={"marginBottom": "12px"}, |
| | ), |
| | html.Div( |
| | [ |
| | html.Div( |
| | [ |
| | html.Span("Max Features: "), |
| | html.Span("All", id="val-feats", style={"color": "var(--accent-color)"}), |
| | ], |
| | style={"marginBottom": "6px", "color": "#bdc3c7"}, |
| | ), |
| | dmc.Slider(id="filter-feats", min=1, max=100, step=1, value=100), |
| | ], |
| | style={"marginBottom": "12px"}, |
| | ), |
| | dmc.Select( |
| | id="filter-complexity", |
| | data=complexity_data, |
| | value="all", |
| | clearable=False, |
| | style={"marginBottom": "12px"}, |
| | ), |
| | dmc.CheckboxGroup(id="filter-algos", children=[], value=[], orientation="vertical"), |
| | ] |
| | ), |
| | ], |
| | ), |
| | html.Main( |
| | className="main-content", |
| | children=[ |
| | html.Header( |
| | [ |
| | html.H1("🏆 Leaderboard Dashboard", style={"color": "var(--secondary-color)", "margin": 0}), |
| | html.Div("Comprehensive benchmark of feature selection algorithms across diverse datasets.", className="subtitle"), |
| | ] |
| | ), |
| | html.Div( |
| | className="card", |
| | children=[ |
| | html.P([ |
| | "Feature selection is a critical step in machine learning and data analysis, aimed at ", |
| | html.Strong("identifying the most relevant subset of features"), |
| | " from a high-dimensional dataset. By eliminating irrelevant or redundant features, feature selection not only ", |
| | html.Strong("improves model interpretability"), |
| | " but also ", |
| | html.Strong("enhances predictive performance"), |
| | " and ", |
| | html.Strong("reduces computational cost"), |
| | ".", |
| | ]), |
| | html.P([ |
| | "This leaderboard presents a comprehensive comparison of various feature selection algorithms across multiple benchmark datasets. It includes several ", |
| | html.Strong("information-theoretic and mutual information-based methods"), |
| | ", which quantify the statistical dependency between features and the target variable to rank feature relevance. Mutual information approaches are particularly effective in ", |
| | html.Strong("capturing both linear and non-linear relationships"), |
| | ", making them suitable for complex datasets where classical correlation-based methods may fail.", |
| | ]), |
| | html.P([ |
| | "The leaderboard is structured to reflect algorithm performance across different datasets, allowing for an objective assessment of each method’s ability to select informative features. For each method and dataset combination, metrics such as ", |
| | html.Strong("classification accuracy, F1-score, and area under the ROC curve (AUC)"), |
| | " are reported, providing insights into how the selected features contribute to predictive modeling.", |
| | ]), |
| | html.P([ |
| | "By examining this feature selection leaderboard, researchers and practitioners can gain a better understanding of which methods perform consistently well across diverse domains, helping to guide the choice of feature selection strategies in real-world applications. This serves as a valuable resource for both benchmarking and method development in the field of feature selection.", |
| | ]), |
| | ], |
| | style={"marginTop": "16px"}, |
| | ), |
| | dmc.Grid( |
| | id="overview", |
| | gutter="md", |
| | style={"marginTop": "16px"}, |
| | children=[ |
| | dmc.Col( |
| | span=12, |
| | md=6, |
| | children=html.Div( |
| | className="card", |
| | children=[ |
| | html.H3("About This Dataset"), |
| | html.P(["Analyzing performance on ", html.Strong(html.Span("Selected", id="desc-dataset-name")), "."]), |
| | ], |
| | ), |
| | ), |
| | dmc.Col( |
| | span=12, |
| | md=6, |
| | children=html.Div( |
| | className="card", |
| | children=[ |
| | html.H3("Dataset Metadata"), |
| | html.Div(["Name: ", html.Span("-", id="meta-name")]), |
| | html.Div(["Samples: ", html.Span("-", id="meta-samples"), " | Features: ", html.Span("-", id="meta-features")]), |
| | html.Div(["Last Updated: ", html.Span("-", id="meta-updated")]), |
| | ], |
| | ), |
| | ), |
| | ], |
| | ), |
| | html.Div( |
| | id="main-table", |
| | style={"marginTop": "24px"}, |
| | children=[ |
| | html.H3("📋 Detailed Rankings"), |
| | html.Div(id="custom-table-container", className="custom-table-wrapper"), |
| | ], |
| | ), |
| | html.Div( |
| | id="charts", |
| | style={"marginTop": "24px"}, |
| | children=[ |
| | dmc.Grid( |
| | gutter="md", |
| | children=[ |
| | dmc.Col( |
| | span=12, |
| | md=6, |
| | children=html.Div( |
| | className="chart-card", |
| | children=[ |
| | html.H3("📊 Performance Comparison"), |
| | dcc.Graph(id="score-graph", config={"responsive": True}, style={"height": "100%"}), |
| | ], |
| | ), |
| | ), |
| | dmc.Col( |
| | span=12, |
| | md=6, |
| | children=html.Div( |
| | className="chart-card", |
| | children=[ |
| | html.H3("📉 Pareto Frontier (Trade-off)"), |
| | html.Div("X: Selected Features vs Y: F1 Score (Top-Left is better)", style={"fontSize": "0.9em", "color": "#666"}), |
| | dcc.Graph(id="pareto-graph", config={"responsive": True}, style={"height": "100%"}), |
| | ], |
| | ), |
| | ), |
| | ], |
| | ) |
| | ], |
| | ), |
| | html.Div( |
| | id="details", |
| | style={"marginTop": "50px", "color": "#999", "textAlign": "center", "borderTop": "1px solid #eee", "paddingTop": "20px"}, |
| | children="AutoFS Benchmark Platform © 2026", |
| | ), |
| | ], |
| | ), |
| | ], |
| | ) |
| | ) |
| |
|
| |
|
| | @dash_app.callback( |
| | Output("filter-feats", "max"), |
| | Output("filter-feats", "value"), |
| | Output("filter-f1", "min"), |
| | Output("filter-f1", "max"), |
| | Output("filter-f1", "value"), |
| | Output("filter-algos", "children"), |
| | Output("filter-algos", "value"), |
| | Output("meta-name", "children"), |
| | Output("meta-samples", "children"), |
| | Output("meta-features", "children"), |
| | Output("meta-updated", "children"), |
| | Output("desc-dataset-name", "children"), |
| | Output("stat-updated", "children"), |
| | Output("stat-count", "children"), |
| | Output("stat-best", "children"), |
| | Output("score-graph", "figure"), |
| | Output("pareto-graph", "figure"), |
| | Output("custom-table-container", "children"), |
| | Output("val-f1", "children"), |
| | Output("val-feats", "children"), |
| | Output("val-del-rate", "children"), |
| | Input("dataset-select", "value"), |
| | Input("view-mode", "value"), |
| | Input("filter-f1", "value"), |
| | Input("filter-feats", "value"), |
| | Input("filter-del-rate", "value"), |
| | Input("filter-complexity", "value"), |
| | Input("filter-algos", "value"), |
| | State("filter-f1", "min"), |
| | State("filter-f1", "max"), |
| | State("filter-feats", "max"), |
| | State("filter-algos", "children"), |
| | State("filter-algos", "value"), |
| | ) |
| | def update_dashboard_all( |
| | dataset, |
| | view_mode, |
| | min_f1_value, |
| | max_features_value, |
| | del_range, |
| | complexity, |
| | selected_algos, |
| | f1_min_state, |
| | f1_max_state, |
| | feats_max_state, |
| | algo_children_state, |
| | algo_value_state, |
| | ): |
| | triggered_id = callback_context.triggered_id if callback_context.triggered else None |
| | dataset_changed = triggered_id == "dataset-select" or triggered_id is None |
| | selected = dataset or "Authorship" |
| | meta = DATASET_METADATA.get(selected, {"name": selected, "last_updated": "-", "num_samples": None, "total_features": None}) |
| | results = get_results_for_dataset(selected) |
| | algo_list = sorted({r.get("algorithm") for r in results if r.get("algorithm")}) |
| | if dataset_changed: |
| | f1_scores = [r.get("mean_f1") for r in results if r.get("mean_f1") is not None] |
| | if f1_scores: |
| | min_f1 = min(f1_scores) |
| | safe_min = max(0, math.floor((min_f1 - 0.1) * 10) / 10) |
| | else: |
| | safe_min = 0 |
| | max_feats = meta.get("total_features") or 100 |
| | f1_min = safe_min |
| | f1_max = 1 |
| | f1_value = safe_min |
| | feats_max = max_feats |
| | feats_value = max_feats |
| | algo_children = [dmc.Checkbox(label=a, value=a) for a in algo_list] |
| | algo_value = algo_list |
| | else: |
| | f1_min = f1_min_state if f1_min_state is not None else 0 |
| | f1_max = f1_max_state if f1_max_state is not None else 1 |
| | f1_value = min_f1_value if min_f1_value is not None else f1_min |
| | feats_max = feats_max_state if feats_max_state is not None else (meta.get("total_features") or 100) |
| | feats_value = max_features_value if max_features_value is not None else feats_max |
| | if algo_children_state: |
| | algo_children = algo_children_state |
| | else: |
| | algo_children = [dmc.Checkbox(label=a, value=a) for a in algo_list] |
| | if selected_algos is not None: |
| | algo_value = selected_algos |
| | else: |
| | algo_value = algo_value_state if algo_value_state is not None else algo_list |
| | filtered = apply_filters(results, meta, f1_value or 0, feats_value, del_range, complexity, algo_value or []) |
| | count = len(filtered) |
| | if filtered: |
| | best = max(filtered, key=lambda r: r.get("mean_f1") or 0) |
| | best_text = f"{best.get('algorithm')} ({(best.get('mean_f1') or 0):.3f})" |
| | else: |
| | best_text = "-" |
| | score_fig = build_score_figure(filtered, view_mode or "overall") |
| | pareto_fig = build_pareto_figure(filtered) |
| | table_component = build_table(filtered, view_mode or "overall") |
| | val_f1 = f"{(f1_value or 0):.4f}" |
| | val_feats = str(int(feats_value)) if isinstance(feats_value, (int, float)) else "All" |
| | del_min = del_range[0] if del_range else 0 |
| | del_max = del_range[1] if del_range else 100 |
| | val_del = f"{del_min:.0f}% - {del_max:.0f}%" |
| | meta_samples = meta.get("num_samples") if meta.get("num_samples") is not None else "Unavailable" |
| | meta_features = meta.get("total_features") if meta.get("total_features") is not None else "Unavailable" |
| | return ( |
| | feats_max, |
| | feats_value, |
| | f1_min, |
| | f1_max, |
| | f1_value, |
| | algo_children, |
| | algo_value, |
| | meta.get("name", "-"), |
| | meta_samples, |
| | meta_features, |
| | meta.get("last_updated", "-"), |
| | meta.get("name", "-"), |
| | meta.get("last_updated", "-"), |
| | count, |
| | best_text, |
| | score_fig, |
| | pareto_fig, |
| | table_component, |
| | val_f1, |
| | val_feats, |
| | val_del, |
| | ) |
| |
|
| |
|
| | def sanitize_json(value): |
| | if value is None or isinstance(value, (str, int, float, bool)): |
| | return value |
| | if np and isinstance(value, np.generic): |
| | return value.item() |
| | if np and isinstance(value, np.ndarray): |
| | return value.tolist() |
| | if pd and isinstance(value, (pd.DataFrame, pd.Series)): |
| | if isinstance(value, pd.DataFrame): |
| | return value.to_dict(orient="records") |
| | return value.to_dict() |
| | if isinstance(value, (datetime.datetime, datetime.date)): |
| | return value.isoformat() |
| | if isinstance(value, dict): |
| | return {str(k): sanitize_json(v) for k, v in value.items()} |
| | if isinstance(value, (list, tuple, set)): |
| | return [sanitize_json(v) for v in value] |
| | if hasattr(value, "to_dict"): |
| | return sanitize_json(value.to_dict()) |
| | return str(value) |
| |
|
| |
|
| | @server.route("/global") |
| | def global_view(): |
| | return render_template("global.html") |
| |
|
| |
|
| | @server.route("/submit") |
| | def submit_view(): |
| | return render_template("submit.html") |
| |
|
| |
|
| | @server.route("/api/results") |
| | def get_results_api(): |
| | try: |
| | dataset = request.args.get("dataset") or "Authorship" |
| | leaderboard = get_results_for_dataset(dataset) |
| | return jsonify(sanitize_json(leaderboard)) |
| | except Exception as e: |
| | print(e) |
| | return jsonify({"error": str(e)}) |
| |
|
| |
|
| | @server.route("/api/datasets") |
| | def api_datasets(): |
| | try: |
| | datasets = [] |
| | for name, meta in DATASET_METADATA.items(): |
| | datasets.append({ |
| | "name": name, |
| | "last_updated": meta.get("last_updated"), |
| | "num_samples": meta.get("num_samples") if meta.get("num_samples") is not None else "Unavailable", |
| | "total_features": meta.get("total_features") if meta.get("total_features") is not None else "Unavailable", |
| | }) |
| | return jsonify(sanitize_json(datasets)) |
| | except Exception as e: |
| | print(e) |
| | return jsonify({"error": str(e)}) |
| |
|
| |
|
| | @server.route("/api/global_stats") |
| | def api_global_stats(): |
| | try: |
| | algo_totals = {} |
| | algo_counts = {} |
| | for dataset in DATASET_METADATA.keys(): |
| | results = get_results_for_dataset(dataset) or [] |
| | for row in results: |
| | algo = row.get("algorithm") or "Unknown" |
| | mean_f1 = row.get("mean_f1") |
| | mean_auc = row.get("mean_auc") |
| | if mean_f1 is None and mean_auc is None: |
| | continue |
| | totals = algo_totals.get(algo, {"f1": 0.0, "auc": 0.0}) |
| | counts = algo_counts.get(algo, {"f1": 0, "auc": 0}) |
| | if mean_f1 is not None: |
| | totals["f1"] += float(mean_f1) |
| | counts["f1"] += 1 |
| | if mean_auc is not None: |
| | totals["auc"] += float(mean_auc) |
| | counts["auc"] += 1 |
| | algo_totals[algo] = totals |
| | algo_counts[algo] = counts |
| | global_stats = [] |
| | for algo, totals in algo_totals.items(): |
| | counts = algo_counts.get(algo, {"f1": 0, "auc": 0}) |
| | mean_f1_global = totals["f1"] / counts["f1"] if counts["f1"] else None |
| | mean_auc_global = totals["auc"] / counts["auc"] if counts["auc"] else None |
| | global_stats.append({ |
| | "algorithm": algo, |
| | "mean_f1_global": mean_f1_global, |
| | "mean_auc_global": mean_auc_global, |
| | }) |
| | return jsonify(sanitize_json(global_stats)) |
| | except Exception as e: |
| | print(e) |
| | return jsonify({"error": str(e)}) |
| |
|
| |
|
| | @server.route("/api/algos") |
| | def api_algorithms(): |
| | return jsonify(DISPLAY_COMPLEXITY) |
| |
|
| |
|
| | @server.route("/pdfs/<path:filename>") |
| | def serve_pdf(filename): |
| | return send_from_directory(PDF_DIR, filename) |
| |
|
| |
|
| | if __name__ == "__main__": |
| | port = int(os.environ.get("PORT", 7860)) |
| | print(f"Loaded {len(DATASET_METADATA)} datasets from {RESULT_DIR}") |
| | app.run(host="0.0.0.0", port=port, debug=False) |
| |
|
