1610 lines
57 KiB
Python
1610 lines
57 KiB
Python
"""
|
||
Carmignac Data Challenge — Pipeline Results Analysis
|
||
=====================================================
|
||
Analyses the CSV outputs produced by carmignac_repair.py:
|
||
- carmignac_scores.csv (post-surgery score history)
|
||
- carmignac_mapping.csv (reg_id mapping history)
|
||
- carmignac_surgery_log.csv (surgery operations)
|
||
|
||
Produces a self-contained HTML report with interactive charts.
|
||
|
||
Usage:
|
||
python carmignac_analysis.py
|
||
python carmignac_analysis.py --scores path/to/scores.csv \
|
||
--mapping path/to/mapping.csv \
|
||
--surgery path/to/surgery_log.csv \
|
||
--out report.html
|
||
"""
|
||
|
||
import argparse
|
||
import json
|
||
import os
|
||
import sys
|
||
import numpy as np
|
||
import pandas as pd
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 1. LOAD & VALIDATE
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def load_outputs(scores_path, mapping_path, surgery_path,
|
||
err_isin_path=None, err_agg_path=None):
|
||
scores = pd.read_csv(scores_path, parse_dates=["date"])
|
||
mapping = pd.read_csv(mapping_path, parse_dates=["date"])
|
||
surgery = pd.read_csv(surgery_path, parse_dates=["date"])
|
||
|
||
# Normalise dtypes
|
||
scores["reg_id"] = scores["reg_id"].astype(str)
|
||
mapping["reg_orig"] = mapping["reg_orig"].astype(str)
|
||
mapping["reg_used"] = mapping["reg_used"].astype(str)
|
||
mapping["changed"] = mapping["changed"].astype(bool)
|
||
surgery["reg_orig"] = surgery["reg_orig"].astype(str)
|
||
surgery["reg_from"] = surgery["reg_from"].astype(str)
|
||
surgery["reg_to"] = surgery["reg_to"].astype(str)
|
||
if "lookback_months" not in surgery.columns:
|
||
surgery["lookback_months"] = 1 # backwards compat
|
||
|
||
# Error account (optional)
|
||
err_isin = None
|
||
err_agg = None
|
||
if err_isin_path and os.path.exists(err_isin_path):
|
||
err_isin = pd.read_csv(err_isin_path, parse_dates=["date"])
|
||
err_isin["isin"] = err_isin["isin"].astype(str)
|
||
if err_agg_path and os.path.exists(err_agg_path):
|
||
err_agg = pd.read_csv(err_agg_path, parse_dates=["date"])
|
||
|
||
return scores, mapping, surgery, err_isin, err_agg
|
||
|
||
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 1b. LOAD ERROR ACCOUNT (optional)
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def load_error_account(isin_path, agg_path):
|
||
"""
|
||
Loads the error account CSVs produced by carmignac_diagnostics.py.
|
||
Returns (df_err_isin, df_err_agg) or (None, None) if files not found.
|
||
"""
|
||
if not isin_path or not agg_path:
|
||
return None, None
|
||
try:
|
||
ei = pd.read_csv(isin_path, parse_dates=["date"])
|
||
ea = pd.read_csv(agg_path, parse_dates=["date"])
|
||
ei["isin"] = ei["isin"].astype(str)
|
||
print(f"[Load] error account (ISIN) : {len(ei)} rows, "
|
||
f"{ei['isin'].nunique()} ISINs")
|
||
print(f"[Load] error account (agg) : {len(ea)} rows")
|
||
return ei, ea
|
||
except Exception as e:
|
||
print(f"[WARN] Could not load error account: {e}")
|
||
return None, None
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 2. COMPUTE ANALYTICS
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def compute_analytics(scores, mapping, surgery):
|
||
dates = sorted(scores["date"].unique())
|
||
|
||
# ── 2.1 Sum of scores per date (post-surgery) ──────────────
|
||
sum_post = (scores.groupby("date")["score"]
|
||
.sum()
|
||
.reindex(dates)
|
||
.rename("sum_post"))
|
||
|
||
# ── 2.2 Reconstruct pre-surgery (counterfactual) ───────────
|
||
# Without surgery, every reg_id that had a hard break would score 0
|
||
# from that date backwards. We propagate the surgery "gain" as a
|
||
# cumulative deficit going back in time.
|
||
gain_by_date = surgery.groupby("date")["gain_vs_no_surgery"].sum()
|
||
# cumulative deficit = sum of gains for all surgeries at or after date t
|
||
cumulative_deficit = pd.Series(0.0, index=dates)
|
||
for d in dates:
|
||
cumulative_deficit[d] = gain_by_date[gain_by_date.index >= d].sum()
|
||
sum_pre = (sum_post - cumulative_deficit).clip(lower=0).rename("sum_pre")
|
||
|
||
timeline = pd.DataFrame({"sum_post": sum_post, "sum_pre": sum_pre})
|
||
timeline.index = pd.to_datetime(timeline.index)
|
||
timeline["recovery_pct"] = np.where(
|
||
sum_pre < sum_post,
|
||
(sum_post - sum_pre) / sum_post.clip(lower=1e-9) * 100,
|
||
0.0,
|
||
)
|
||
|
||
# ── 2.3 Per-date surgery stats ─────────────────────────────
|
||
surgery_stats = (
|
||
surgery.groupby("date")
|
||
.agg(
|
||
n_surgeries = ("reg_orig", "count"),
|
||
total_gain = ("gain_vs_no_surgery", "sum"),
|
||
avg_gain = ("gain_vs_no_surgery", "mean"),
|
||
avg_jaccard = ("jaccard_composite", "mean"),
|
||
avg_score_before = ("score_before", "mean"),
|
||
avg_score_after = ("score_after", "mean"),
|
||
)
|
||
.reindex(dates, fill_value=0)
|
||
)
|
||
|
||
# ── 2.4 Score distribution over time ───────────────────────
|
||
# Wide format: rows=dates, cols=reg_ids
|
||
pivot = scores.pivot_table(index="date", columns="reg_id",
|
||
values="score", aggfunc="last")
|
||
pivot = pivot.reindex(dates)
|
||
pivot.index = pd.to_datetime(pivot.index)
|
||
|
||
# ── 2.5 Mapping churn ──────────────────────────────────────
|
||
# For each date, how many reg_ids are remapped (not using their original code)?
|
||
churn = (mapping.groupby("date")["changed"]
|
||
.sum()
|
||
.reindex(dates, fill_value=0)
|
||
.rename("n_remapped"))
|
||
|
||
# ── 2.6 Score entropy (distribution spread) ────────────────
|
||
def entropy(row):
|
||
p = row.dropna()
|
||
p = p[p > 0]
|
||
if len(p) == 0:
|
||
return np.nan
|
||
p = p / p.sum()
|
||
return -(p * np.log(p)).sum()
|
||
|
||
timeline["entropy"] = pivot.apply(entropy, axis=1).values
|
||
|
||
# ── 2.7 Individual score trajectories ──────────────────────
|
||
# Identify which reg_ids were ever remapped
|
||
ever_remapped = set(mapping.loc[mapping["changed"], "reg_orig"].unique())
|
||
|
||
# ── 2.8 Surgery detail table ───────────────────────────────
|
||
surgery_detail = surgery.copy()
|
||
surgery_detail["gain_pct_of_score"] = (
|
||
surgery_detail["gain_vs_no_surgery"]
|
||
/ surgery_detail["score_before"].clip(lower=1e-9) * 100
|
||
).round(2)
|
||
|
||
return {
|
||
"timeline": timeline,
|
||
"surgery_stats": surgery_stats,
|
||
"pivot": pivot,
|
||
"churn": churn,
|
||
"ever_remapped": ever_remapped,
|
||
"surgery_detail": surgery_detail,
|
||
"dates": [d.strftime("%Y-%m-%d") for d in dates],
|
||
}
|
||
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 3. PRINT CONSOLE SUMMARY
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def print_summary(analytics, surgery):
|
||
tl = analytics["timeline"]
|
||
ss = analytics["surgery_stats"]
|
||
|
||
print("\n" + "=" * 65)
|
||
print(" CARMIGNAC PIPELINE — RESULTS SUMMARY")
|
||
print("=" * 65)
|
||
|
||
print(f"\n Date range : {tl.index.min().date()} → {tl.index.max().date()}")
|
||
print(f" Total months : {len(tl)}")
|
||
print(f" Reg IDs : {analytics['pivot'].shape[1]}")
|
||
|
||
print(f"\n ── Score (Σ) ──────────────────────────────────────────")
|
||
print(f" At t_ref (latest) : {tl['sum_post'].iloc[-1]:.6f}")
|
||
print(f" At t_min (earliest): {tl['sum_post'].iloc[0]:.6f}")
|
||
print(f" Min (post-surgery) : {tl['sum_post'].min():.6f} "
|
||
f"({tl['sum_post'].idxmin().date()})")
|
||
print(f" Min (pre-surgery) : {tl['sum_pre'].min():.6f} "
|
||
f"({tl['sum_pre'].idxmin().date()})")
|
||
print(f" Max recovery (pct) : {tl['recovery_pct'].max():.2f}%")
|
||
|
||
print(f"\n ── Surgeries ─────────────────────────────────────────")
|
||
if len(surgery) == 0:
|
||
print(" No surgeries performed.")
|
||
else:
|
||
print(f" Total operations : {len(surgery)}")
|
||
print(f" Total score gained : {surgery['gain_vs_no_surgery'].sum():.6f}")
|
||
print(f" Avg Jaccard : {surgery['jaccard_composite'].mean():.4f}")
|
||
print(f" Avg gain / surgery : {surgery['gain_vs_no_surgery'].mean():.6f}")
|
||
print()
|
||
print(f" {'Date':12s} {'Reg orig':12s} {'From':15s} {'To':15s} "
|
||
f"{'Jaccard':>8s} {'Gain':>10s}")
|
||
print(" " + "-" * 78)
|
||
for _, row in surgery.sort_values("date").iterrows():
|
||
print(f" {str(row['date'].date()):12s} {row['reg_orig']:12s} "
|
||
f"{row['reg_from']:15s} {row['reg_to']:15s} "
|
||
f"{row['jaccard_composite']:8.4f} {row['gain_vs_no_surgery']:10.6f}")
|
||
|
||
print(f"\n ── Mapping churn ─────────────────────────────────────")
|
||
ch = analytics["churn"]
|
||
print(f" Max remapped at one date : {int(ch.max())} ({ch.idxmax().date() if ch.max()>0 else 'N/A'})")
|
||
print(f" Reg IDs ever remapped : {len(analytics['ever_remapped'])}")
|
||
|
||
print(f"\n ── Score entropy (distribution spread) ───────────────")
|
||
ent = analytics["timeline"]["entropy"]
|
||
print(f" Mean entropy : {ent.mean():.4f}")
|
||
print(f" Std entropy : {ent.std():.4f}")
|
||
print()
|
||
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 4. BUILD HTML REPORT
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def build_html(analytics, surgery, scores, mapping, df_err_isin=None, df_err_agg=None):
|
||
tl = analytics["timeline"]
|
||
ss = analytics["surgery_stats"]
|
||
piv = analytics["pivot"]
|
||
ch = analytics["churn"]
|
||
dates_str = analytics["dates"]
|
||
|
||
# ── helpers to serialise for JS ─────────────────────────────
|
||
def jf(arr, decimals=6):
|
||
return json.dumps([round(float(v), decimals) if not np.isnan(v) else None
|
||
for v in arr])
|
||
|
||
def js(arr):
|
||
return json.dumps(list(arr))
|
||
|
||
# ── colour palette ───────────────────────────────────────────
|
||
REG_COLORS = [
|
||
"#2563eb","#16a34a","#dc2626","#d97706","#7c3aed",
|
||
"#0891b2","#db2777","#65a30d","#ea580c","#6366f1",
|
||
"#059669","#b45309","#9333ea","#0284c7","#e11d48",
|
||
]
|
||
|
||
# ── 4.1 Surgery sparkline data ──────────────────────────────
|
||
surg_dates = [d.strftime("%Y-%m-%d") for d in ss.index]
|
||
n_surg = jf(ss["n_surgeries"].values, 0)
|
||
total_gain = jf(ss["total_gain"].values)
|
||
avg_gain = jf(ss["avg_gain"].values)
|
||
avg_jaccard = jf(ss["avg_jaccard"].values)
|
||
|
||
# ── 4.2 Individual trajectories ────────────────────────────
|
||
reg_ids = list(piv.columns)
|
||
traj_datasets = []
|
||
# Surgery lookup: reg_orig -> list of {date, from, to, composite}
|
||
surg_by_reg = {}
|
||
for _, row in surgery.iterrows():
|
||
surg_by_reg.setdefault(row["reg_orig"], []).append({
|
||
"date": row["date"].strftime("%Y-%m-%d"),
|
||
"reg_from": str(row["reg_from"]),
|
||
"reg_to": str(row["reg_to"]),
|
||
"composite": round(float(row["jaccard_composite"]), 4),
|
||
"gain": round(float(row["gain_vs_no_surgery"]), 6),
|
||
})
|
||
|
||
for idx, rid in enumerate(reg_ids):
|
||
remapped = rid in analytics["ever_remapped"]
|
||
traj_datasets.append({
|
||
"label": rid,
|
||
"data": [round(float(v), 6) if not np.isnan(v) else None
|
||
for v in piv[rid].values],
|
||
"borderColor": REG_COLORS[idx % len(REG_COLORS)],
|
||
"backgroundColor": REG_COLORS[idx % len(REG_COLORS)] + "22",
|
||
"borderWidth": 2,
|
||
"borderDash": [6, 3] if remapped else [],
|
||
"pointRadius": 0,
|
||
"tension": 0.3,
|
||
"fill": False,
|
||
"remapped": remapped,
|
||
"surgeries": surg_by_reg.get(rid, []),
|
||
})
|
||
|
||
traj_json = json.dumps(traj_datasets)
|
||
|
||
# ── 4.2b Error account data (optional) ────────────────────
|
||
has_error = df_err_isin is not None and df_err_agg is not None
|
||
|
||
if has_error:
|
||
err_dates = [d.strftime("%Y-%m-%d") for d in pd.to_datetime(df_err_agg["date"])]
|
||
err_agg_stock = [round(float(v), 3) if not pd.isna(v) else None
|
||
for v in df_err_agg["stock_error_agg"].values]
|
||
err_agg_res = [round(float(v), 3) if not pd.isna(v) else None
|
||
for v in df_err_agg["residual_agg"].values]
|
||
err_agg_pct = [round(float(v), 4) if not pd.isna(v) else None
|
||
for v in df_err_agg["stock_error_agg_pct"].values]
|
||
|
||
# Top 5 ISINs by max |stock error|
|
||
top_err = (df_err_isin.groupby("isin")["stock_error"]
|
||
.apply(lambda x: x.abs().max())
|
||
.nlargest(5).index.tolist())
|
||
all_err_dates = sorted(df_err_isin["date"].unique())
|
||
ERR_COLORS = ["#ef4444","#f59e0b","#8b5cf6","#06b6d4","#10b981"]
|
||
err_isin_ds = []
|
||
for idx, isin in enumerate(top_err):
|
||
sub = (df_err_isin[df_err_isin["isin"] == isin]
|
||
.set_index("date")["stock_error"]
|
||
.reindex(all_err_dates))
|
||
err_isin_ds.append({
|
||
"label": isin,
|
||
"data": [round(float(v), 3) if not pd.isna(v) else None for v in sub.values],
|
||
"borderColor": ERR_COLORS[idx % len(ERR_COLORS)],
|
||
"backgroundColor": ERR_COLORS[idx % len(ERR_COLORS)] + "22",
|
||
"borderWidth": 1.5, "pointRadius": 0, "tension": 0.3, "fill": False,
|
||
})
|
||
|
||
max_err_stock = float(df_err_agg["stock_error_agg"].abs().max())
|
||
max_err_pct = float(df_err_agg["stock_error_agg_pct"].max())
|
||
agg_std = float(df_err_agg["stock_error_agg"].std())
|
||
agg_mean = float(df_err_agg["stock_error_agg"].abs().mean())
|
||
stationarity = round(agg_std / max(agg_mean, 1e-9), 3)
|
||
|
||
err_dates_js = json.dumps(err_dates)
|
||
err_agg_stock_js = json.dumps(err_agg_stock)
|
||
err_agg_res_js = json.dumps(err_agg_res)
|
||
err_agg_pct_js = json.dumps(err_agg_pct)
|
||
err_isin_ds_js = json.dumps(err_isin_ds)
|
||
err_isin_dates_js = json.dumps([d.strftime("%Y-%m-%d") if hasattr(d, "strftime")
|
||
else str(d)[:10] for d in all_err_dates])
|
||
|
||
# ISIN detail table (top 100 worst)
|
||
err_rows = []
|
||
for _, r in (df_err_isin.assign(abs_s=df_err_isin["stock_error"].abs())
|
||
.sort_values("abs_s", ascending=False)
|
||
.head(100).iterrows()):
|
||
ds = r["date"].strftime("%Y-%m-%d") if hasattr(r["date"], "strftime") else str(r["date"])[:10]
|
||
sc = "color:var(--danger)" if r["stock_error"] < 0 else "color:var(--warn)"
|
||
rc = "color:var(--danger)" if r["residual"] < 0 else "color:var(--warn)"
|
||
pch = "color:var(--danger);font-weight:600" if r["stock_error_pct"] > 5 else ("color:var(--warn)" if r["stock_error_pct"] > 1 else "")
|
||
err_rows.append(
|
||
f'<tr><td>{ds}</td>'
|
||
f'<td style="font-family:var(--mono)">{r["isin"]}</td>'
|
||
f'<td style="text-align:right;font-family:var(--mono);{rc}">{r["residual"]:+,.2f}</td>'
|
||
f'<td style="text-align:right;font-family:var(--mono);{sc}">{r["stock_error"]:+,.2f}</td>'
|
||
f'<td style="text-align:right;font-family:var(--mono);{pch}">{r["stock_error_pct"]:.3f}%</td>'
|
||
f'</tr>'
|
||
)
|
||
err_isin_detail = "".join(err_rows) if err_rows else (
|
||
'<tr><td colspan="5" style="padding:24px;text-align:center;color:var(--accent2)'
|
||
';font-family:var(--mono)">✓ Error account is flat</td></tr>'
|
||
)
|
||
|
||
# HTML block for error account section
|
||
err_section_html = f"""
|
||
<div class="section-label">06 · Error Account</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Aggregate error account stock</span>
|
||
<span class="card-desc">
|
||
Stock_error(t_ref) = 0. The stock absorbs unreconciled residuals going backwards.
|
||
A flat signal near zero = clean data. A drift = structural gap.
|
||
</span>
|
||
</div>
|
||
<div class="card-body" style="padding-bottom:8px">
|
||
<div style="display:grid;grid-template-columns:repeat(3,1fr);gap:1px;background:var(--border);margin-bottom:20px">
|
||
<div style="background:var(--surface);padding:14px 20px">
|
||
<div style="font-family:var(--mono);font-size:.68rem;letter-spacing:.1em;text-transform:uppercase;color:var(--muted)">Max |error stock|</div>
|
||
<div style="font-family:var(--mono);font-size:1.35rem;font-weight:700;color:var(--danger)">{max_err_stock:,.1f} shares</div>
|
||
</div>
|
||
<div style="background:var(--surface);padding:14px 20px">
|
||
<div style="font-family:var(--mono);font-size:.68rem;letter-spacing:.1em;text-transform:uppercase;color:var(--muted)">Max % of total AUM</div>
|
||
<div style="font-family:var(--mono);font-size:1.35rem;font-weight:700;color:{'var(--danger)' if max_err_pct > 5 else 'var(--warn)'}">{max_err_pct:.3f}%</div>
|
||
</div>
|
||
<div style="background:var(--surface);padding:14px 20px">
|
||
<div style="font-family:var(--mono);font-size:.68rem;letter-spacing:.1em;text-transform:uppercase;color:var(--muted)">Stationarity σ/μ</div>
|
||
<div style="font-family:var(--mono);font-size:1.35rem;font-weight:700;color:{'var(--accent2)' if stationarity < 1 else 'var(--warn)'}">{stationarity:.3f}</div>
|
||
<div style="font-size:.7rem;color:var(--muted);font-family:var(--mono)">lower = more stationary</div>
|
||
</div>
|
||
</div>
|
||
<div class="chart-wrap-tall"><canvas id="chartErrStock"></canvas></div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="grid-2">
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Monthly aggregate residual</span>
|
||
<span class="card-desc">ΔQ_total − F_total per month</span>
|
||
</div>
|
||
<div class="card-body"><div class="chart-wrap"><canvas id="chartErrRes"></canvas></div></div>
|
||
</div>
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Error stock — top 5 ISINs</span>
|
||
<span class="card-desc">Cumulative error stock per ISIN</span>
|
||
</div>
|
||
<div class="card-body"><div class="chart-wrap"><canvas id="chartErrIsin"></canvas></div></div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Error account detail — worst (ISIN, month) pairs</span>
|
||
</div>
|
||
<div class="card-body" style="padding:0">
|
||
<table>
|
||
<thead><tr>
|
||
<th>Date</th><th>ISIN</th>
|
||
<th style="text-align:right">Monthly residual</th>
|
||
<th style="text-align:right">Cumul. stock</th>
|
||
<th style="text-align:right">% of max AUM</th>
|
||
</tr></thead>
|
||
<tbody>{err_isin_detail}</tbody>
|
||
</table>
|
||
</div>
|
||
</div>"""
|
||
|
||
# JS block for error account charts
|
||
err_js_block = f"""
|
||
// ── 8. Error account charts ──────────────────────────────────
|
||
const ERR_DATES = {err_dates_js};
|
||
const ERR_AGG_STOCK = {err_agg_stock_js};
|
||
const ERR_AGG_RES = {err_agg_res_js};
|
||
const ERR_ISIN_TS = {err_isin_ds_js};
|
||
const ERR_ISIN_DATES = {err_isin_dates_js};
|
||
|
||
new Chart(document.getElementById('chartErrStock'), {{
|
||
type: 'line',
|
||
data: {{ labels: ERR_DATES, datasets: [{{
|
||
label: 'Aggregate error stock', data: ERR_AGG_STOCK,
|
||
borderColor: '#ef4444', backgroundColor: '#ef444415',
|
||
borderWidth: 2, pointRadius: 0, tension: 0.3, fill: true
|
||
}}] }},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
interaction: {{mode:'index', intersect:false}},
|
||
plugins: {{ legend: {{display:false}}, tooltip: tooltip() }},
|
||
scales: {{ x: timeAxis(), y: {{
|
||
...yAxis('Shares'),
|
||
grid: {{ color: ctx => ctx.tick.value === 0 ? '#ffffff55' : '#1a2030',
|
||
lineWidth: ctx => ctx.tick.value === 0 ? 1.5 : 1 }}
|
||
}} }}
|
||
}}
|
||
}});
|
||
|
||
new Chart(document.getElementById('chartErrRes'), {{
|
||
type: 'bar',
|
||
data: {{ labels: ERR_DATES, datasets: [{{
|
||
label: 'Monthly residual', data: ERR_AGG_RES,
|
||
backgroundColor: ERR_AGG_RES.map(v => v != null && v < 0 ? '#ef444488' : '#f59e0b88'),
|
||
borderColor: ERR_AGG_RES.map(v => v != null && v < 0 ? '#ef4444' : '#f59e0b'),
|
||
borderWidth: 1, borderRadius: 2
|
||
}}] }},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
plugins: {{ legend: {{display:false}}, tooltip: tooltip() }},
|
||
scales: {{ x: timeAxis(), y: yAxis('Shares') }}
|
||
}}
|
||
}});
|
||
|
||
new Chart(document.getElementById('chartErrIsin'), {{
|
||
type: 'line',
|
||
data: {{ labels: ERR_ISIN_DATES, datasets: ERR_ISIN_TS }},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
interaction: {{mode:'index', intersect:false}},
|
||
plugins: {{
|
||
legend: {{position:'right', labels:{{boxWidth:10, padding:8, font:{{size:10}}}}}},
|
||
tooltip: tooltip()
|
||
}},
|
||
scales: {{ x: timeAxis(), y: yAxis('Error stock (shares)') }}
|
||
}}
|
||
}});"""
|
||
|
||
else:
|
||
err_section_html = ""
|
||
err_js_block = ""
|
||
|
||
# ── 4.3 Surgery detail table rows ──────────────────────────
|
||
sd = analytics["surgery_detail"].sort_values("date")
|
||
surg_rows_html = ""
|
||
if len(sd) == 0:
|
||
surg_rows_html = "<tr><td colspan='9' style='text-align:center;color:#888'>No surgeries performed</td></tr>"
|
||
else:
|
||
for _, r in sd.iterrows():
|
||
gain_class = "gain-high" if r["gain_vs_no_surgery"] > 0.05 else "gain-low"
|
||
lb = int(r.get("lookback_months", 1))
|
||
lb_cell = (f'<span style="font-family:var(--mono);font-size:.65rem;padding:1px 5px;'
|
||
f'border-radius:3px;background:#7c3aed22;border:1px solid #7c3aed55;'
|
||
f'color:#a78bfa">{lb}m</span>' if lb > 1 else "—")
|
||
surg_rows_html += f"""
|
||
<tr>
|
||
<td>{r['date'].date()}</td>
|
||
<td><span class="reg-badge">{r['reg_orig']}</span></td>
|
||
<td class="code-cell">{r['reg_from']}</td>
|
||
<td>→</td>
|
||
<td class="code-cell">{r['reg_to']}</td>
|
||
<td>{r['jaccard_composite']:.4f}</td>
|
||
<td class="{gain_class}">+{r['gain_vs_no_surgery']:.6f}</td>
|
||
<td>{r['gain_pct_of_score']:.1f}%</td>
|
||
<td>{lb_cell}</td>
|
||
</tr>"""
|
||
|
||
# ── 4.4 Top accounts table ──────────────────────────────────
|
||
last_date = piv.index.max()
|
||
top_accounts = piv.loc[last_date].dropna().sort_values(ascending=False)
|
||
top_rows_html = ""
|
||
for rank, (rid, sc) in enumerate(top_accounts.items(), 1):
|
||
remapped = "✓" if rid in analytics["ever_remapped"] else ""
|
||
bar_w = int(sc / top_accounts.max() * 100)
|
||
color = REG_COLORS[(rank - 1) % len(REG_COLORS)]
|
||
top_rows_html += f"""
|
||
<tr>
|
||
<td class="rank">#{rank}</td>
|
||
<td><span class="reg-badge" style="background:{color}22;border-color:{color}">{rid}</span></td>
|
||
<td class="score-val">{sc:.6f}</td>
|
||
<td class="bar-cell">
|
||
<div class="score-bar" style="width:{bar_w}%;background:{color}"></div>
|
||
</td>
|
||
<td class="center">{remapped}</td>
|
||
</tr>"""
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# HTML TEMPLATE
|
||
# ─────────────────────────────────────────────────────────────
|
||
html = f"""<!DOCTYPE html>
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
<title>Carmignac Pipeline — Analysis Report</title>
|
||
<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.0/dist/chart.umd.min.js"></script>
|
||
<style>
|
||
@import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600&family=IBM+Plex+Sans:wght@300;400;600;700&display=swap');
|
||
|
||
:root {{
|
||
--bg: #0d0f12;
|
||
--surface: #151820;
|
||
--border: #252a35;
|
||
--accent: #3b82f6;
|
||
--accent2: #10b981;
|
||
--warn: #f59e0b;
|
||
--danger: #ef4444;
|
||
--text: #e2e8f0;
|
||
--muted: #64748b;
|
||
--mono: 'IBM Plex Mono', monospace;
|
||
--sans: 'IBM Plex Sans', sans-serif;
|
||
}}
|
||
|
||
*, *::before, *::after {{ box-sizing: border-box; margin: 0; padding: 0; }}
|
||
|
||
body {{
|
||
font-family: var(--sans);
|
||
background: var(--bg);
|
||
color: var(--text);
|
||
min-height: 100vh;
|
||
padding: 0 0 60px;
|
||
}}
|
||
|
||
/* ── Header ── */
|
||
.header {{
|
||
background: linear-gradient(135deg, #0d1117 0%, #111827 50%, #0d1f3c 100%);
|
||
border-bottom: 1px solid var(--border);
|
||
padding: 40px 48px 36px;
|
||
position: relative;
|
||
overflow: hidden;
|
||
}}
|
||
.header::before {{
|
||
content: '';
|
||
position: absolute;
|
||
inset: 0;
|
||
background: radial-gradient(ellipse 70% 80% at 80% 50%, #1e40af18, transparent);
|
||
pointer-events: none;
|
||
}}
|
||
.header-eyebrow {{
|
||
font-family: var(--mono);
|
||
font-size: 11px;
|
||
letter-spacing: 0.15em;
|
||
color: var(--accent);
|
||
text-transform: uppercase;
|
||
margin-bottom: 10px;
|
||
}}
|
||
.header h1 {{
|
||
font-size: 2rem;
|
||
font-weight: 700;
|
||
letter-spacing: -0.02em;
|
||
line-height: 1.1;
|
||
margin-bottom: 8px;
|
||
}}
|
||
.header-sub {{
|
||
font-size: 0.85rem;
|
||
color: var(--muted);
|
||
font-family: var(--mono);
|
||
}}
|
||
|
||
/* ── KPI strip ── */
|
||
.kpi-strip {{
|
||
display: grid;
|
||
grid-template-columns: repeat(auto-fit, minmax(160px, 1fr));
|
||
gap: 1px;
|
||
background: var(--border);
|
||
border-bottom: 1px solid var(--border);
|
||
}}
|
||
.kpi {{
|
||
background: var(--surface);
|
||
padding: 22px 28px;
|
||
display: flex;
|
||
flex-direction: column;
|
||
gap: 4px;
|
||
}}
|
||
.kpi-label {{
|
||
font-size: 0.7rem;
|
||
letter-spacing: 0.1em;
|
||
text-transform: uppercase;
|
||
color: var(--muted);
|
||
font-family: var(--mono);
|
||
}}
|
||
.kpi-value {{
|
||
font-size: 1.6rem;
|
||
font-weight: 700;
|
||
font-family: var(--mono);
|
||
color: var(--text);
|
||
line-height: 1;
|
||
}}
|
||
.kpi-value.accent {{ color: var(--accent); }}
|
||
.kpi-value.success {{ color: var(--accent2); }}
|
||
.kpi-value.warn {{ color: var(--warn); }}
|
||
.kpi-sub {{
|
||
font-size: 0.7rem;
|
||
color: var(--muted);
|
||
font-family: var(--mono);
|
||
}}
|
||
|
||
/* ── Main layout ── */
|
||
.main {{
|
||
max-width: 1400px;
|
||
margin: 0 auto;
|
||
padding: 36px 48px;
|
||
display: flex;
|
||
flex-direction: column;
|
||
gap: 32px;
|
||
}}
|
||
|
||
/* ── Cards ── */
|
||
.card {{
|
||
background: var(--surface);
|
||
border: 1px solid var(--border);
|
||
border-radius: 8px;
|
||
overflow: hidden;
|
||
}}
|
||
.card-header {{
|
||
padding: 18px 24px 14px;
|
||
border-bottom: 1px solid var(--border);
|
||
display: flex;
|
||
align-items: baseline;
|
||
gap: 12px;
|
||
}}
|
||
.card-title {{
|
||
font-size: 0.8rem;
|
||
font-weight: 600;
|
||
letter-spacing: 0.1em;
|
||
text-transform: uppercase;
|
||
color: var(--muted);
|
||
font-family: var(--mono);
|
||
}}
|
||
.card-desc {{
|
||
font-size: 0.78rem;
|
||
color: #475569;
|
||
}}
|
||
.card-body {{
|
||
padding: 24px;
|
||
}}
|
||
.chart-wrap {{
|
||
position: relative;
|
||
height: 280px;
|
||
}}
|
||
.chart-wrap-tall {{
|
||
position: relative;
|
||
height: 340px;
|
||
}}
|
||
|
||
/* ── Two-column grid ── */
|
||
.grid-2 {{
|
||
display: grid;
|
||
grid-template-columns: 1fr 1fr;
|
||
gap: 24px;
|
||
}}
|
||
@media (max-width: 900px) {{
|
||
.grid-2 {{ grid-template-columns: 1fr; }}
|
||
.main {{ padding: 24px 20px; }}
|
||
}}
|
||
|
||
/* ── Section label ── */
|
||
.section-label {{
|
||
font-family: var(--mono);
|
||
font-size: 0.68rem;
|
||
letter-spacing: 0.15em;
|
||
text-transform: uppercase;
|
||
color: var(--muted);
|
||
padding: 0 4px;
|
||
border-left: 3px solid var(--accent);
|
||
padding-left: 10px;
|
||
margin-bottom: -8px;
|
||
}}
|
||
|
||
/* ── Tables ── */
|
||
table {{
|
||
width: 100%;
|
||
border-collapse: collapse;
|
||
font-size: 0.82rem;
|
||
}}
|
||
th {{
|
||
font-family: var(--mono);
|
||
font-size: 0.68rem;
|
||
letter-spacing: 0.08em;
|
||
text-transform: uppercase;
|
||
color: var(--muted);
|
||
padding: 10px 14px;
|
||
text-align: left;
|
||
border-bottom: 1px solid var(--border);
|
||
background: #0f1218;
|
||
}}
|
||
td {{
|
||
padding: 10px 14px;
|
||
border-bottom: 1px solid #1a1f2a;
|
||
vertical-align: middle;
|
||
}}
|
||
tr:last-child td {{ border-bottom: none; }}
|
||
tr:hover td {{ background: #181e2b; }}
|
||
|
||
.rank {{ color: var(--muted); font-family: var(--mono); font-size: 0.75rem; }}
|
||
.score-val {{ font-family: var(--mono); color: var(--accent2); }}
|
||
.code-cell {{ font-family: var(--mono); font-size: 0.78rem; color: #94a3b8; }}
|
||
.center {{ text-align: center; color: var(--accent2); }}
|
||
.gain-high {{ font-family: var(--mono); color: var(--accent2); font-weight: 600; }}
|
||
.gain-low {{ font-family: var(--mono); color: var(--warn); }}
|
||
|
||
.bar-cell {{ width: 120px; }}
|
||
.score-bar {{
|
||
height: 6px;
|
||
border-radius: 3px;
|
||
min-width: 2px;
|
||
transition: width 0.3s;
|
||
}}
|
||
|
||
.reg-badge {{
|
||
display: inline-block;
|
||
padding: 2px 8px;
|
||
border-radius: 4px;
|
||
background: #1e2a3a;
|
||
border: 1px solid #2d3f54;
|
||
font-family: var(--mono);
|
||
font-size: 0.75rem;
|
||
color: var(--accent);
|
||
white-space: nowrap;
|
||
}}
|
||
|
||
/* ── Legend patch ── */
|
||
.legend-patch {{
|
||
display: inline-block;
|
||
width: 12px; height: 12px;
|
||
border-radius: 2px;
|
||
margin-right: 4px;
|
||
vertical-align: middle;
|
||
}}
|
||
|
||
/* ── No-surgery notice ── */
|
||
.no-surg {{
|
||
padding: 32px;
|
||
text-align: center;
|
||
color: var(--muted);
|
||
font-family: var(--mono);
|
||
font-size: 0.82rem;
|
||
}}
|
||
|
||
/* ── Trajectory explorer ── */
|
||
.badge-surgery {{
|
||
font-family: var(--mono);
|
||
font-size: 0.68rem;
|
||
color: var(--warn);
|
||
background: #f59e0b18;
|
||
border: 1px solid #f59e0b44;
|
||
border-radius: 3px;
|
||
padding: 1px 6px;
|
||
margin-left: 4px;
|
||
}}
|
||
.traj-selector {{
|
||
display: flex;
|
||
flex-wrap: wrap;
|
||
gap: 6px;
|
||
padding: 16px 20px;
|
||
border-bottom: 1px solid var(--border);
|
||
background: #0f1218;
|
||
}}
|
||
.traj-btn {{
|
||
font-family: var(--mono);
|
||
font-size: 0.72rem;
|
||
padding: 5px 12px;
|
||
border-radius: 4px;
|
||
border: 1px solid var(--border);
|
||
background: var(--surface);
|
||
color: var(--muted);
|
||
cursor: pointer;
|
||
transition: all 0.15s;
|
||
}}
|
||
.traj-btn:hover {{ border-color: var(--acc, var(--accent)); color: var(--text); }}
|
||
.traj-btn.active {{
|
||
background: color-mix(in srgb, var(--acc, var(--accent)) 15%, transparent);
|
||
border-color: var(--acc, var(--accent));
|
||
color: var(--acc, var(--accent));
|
||
}}
|
||
.traj-btn-badge {{
|
||
font-size: 0.6rem;
|
||
background: #f59e0b33;
|
||
color: var(--warn);
|
||
border-radius: 3px;
|
||
padding: 0 4px;
|
||
margin-left: 4px;
|
||
}}
|
||
.traj-focus-wrap {{ padding: 16px 24px 8px; }}
|
||
.traj-account-meta {{
|
||
display: flex;
|
||
align-items: center;
|
||
flex-wrap: wrap;
|
||
gap: 8px;
|
||
margin-bottom: 12px;
|
||
min-height: 28px;
|
||
}}
|
||
.meta-id {{
|
||
font-family: var(--mono);
|
||
font-size: 0.85rem;
|
||
font-weight: 600;
|
||
padding: 3px 10px;
|
||
border-radius: 4px;
|
||
border: 1.5px solid;
|
||
}}
|
||
.meta-surgs {{ display: flex; flex-wrap: wrap; gap: 6px; }}
|
||
.surg-chip {{
|
||
font-family: var(--mono);
|
||
font-size: 0.7rem;
|
||
color: var(--warn);
|
||
background: #f59e0b18;
|
||
border: 1px solid #f59e0b44;
|
||
border-radius: 4px;
|
||
padding: 2px 8px;
|
||
}}
|
||
.spark-section-label {{
|
||
font-family: var(--mono);
|
||
font-size: 0.65rem;
|
||
letter-spacing: 0.12em;
|
||
text-transform: uppercase;
|
||
color: var(--muted);
|
||
padding: 14px 24px 6px;
|
||
border-top: 1px solid var(--border);
|
||
margin-top: 8px;
|
||
}}
|
||
.spark-grid {{
|
||
display: grid;
|
||
grid-template-columns: repeat(auto-fill, minmax(140px, 1fr));
|
||
gap: 1px;
|
||
background: var(--border);
|
||
border-top: 1px solid var(--border);
|
||
}}
|
||
.spark-cell {{
|
||
background: var(--surface);
|
||
padding: 10px 12px 8px;
|
||
cursor: pointer;
|
||
transition: background 0.12s;
|
||
}}
|
||
.spark-cell:hover {{ background: #1a2030; }}
|
||
.spark-cell.active {{ background: #131b2a; outline: 1px solid #3b82f644; }}
|
||
.spark-label {{
|
||
font-family: var(--mono);
|
||
font-size: 0.68rem;
|
||
color: var(--muted);
|
||
margin-bottom: 4px;
|
||
white-space: nowrap;
|
||
overflow: hidden;
|
||
text-overflow: ellipsis;
|
||
}}
|
||
.spark-badge {{
|
||
font-size: 0.58rem;
|
||
color: var(--warn);
|
||
background: #f59e0b22;
|
||
border-radius: 2px;
|
||
padding: 0 3px;
|
||
}}
|
||
|
||
/* ── Footer ── */
|
||
.footer {{
|
||
text-align: center;
|
||
font-family: var(--mono);
|
||
font-size: 0.68rem;
|
||
color: #334155;
|
||
margin-top: 16px;
|
||
letter-spacing: 0.05em;
|
||
}}
|
||
</style>
|
||
</head>
|
||
<body>
|
||
|
||
<!-- ═══════════════════════════════════════════ HEADER -->
|
||
<div class="header">
|
||
<div class="header-eyebrow">Carmignac × ENSAE · Data Challenge 2025</div>
|
||
<h1>Pipeline Results — Analysis Report</h1>
|
||
<div class="header-sub">Registrar ID repair · Score propagation · Surgery audit</div>
|
||
</div>
|
||
|
||
<!-- ═══════════════════════════════════════════ KPI STRIP -->
|
||
<div class="kpi-strip">
|
||
<div class="kpi">
|
||
<span class="kpi-label">Σ score at t_ref</span>
|
||
<span class="kpi-value success">{tl['sum_post'].iloc[-1]:.4f}</span>
|
||
<span class="kpi-sub">post-surgery</span>
|
||
</div>
|
||
<div class="kpi">
|
||
<span class="kpi-label">Σ score at t_min</span>
|
||
<span class="kpi-value accent">{tl['sum_post'].iloc[0]:.4f}</span>
|
||
<span class="kpi-sub">post-surgery</span>
|
||
</div>
|
||
<div class="kpi">
|
||
<span class="kpi-label">Max recovery</span>
|
||
<span class="kpi-value warn">{tl['recovery_pct'].max():.1f}%</span>
|
||
<span class="kpi-sub">score rescued by surgery</span>
|
||
</div>
|
||
<div class="kpi">
|
||
<span class="kpi-label">Total surgeries</span>
|
||
<span class="kpi-value">{len(surgery)}</span>
|
||
<span class="kpi-sub">operations performed</span>
|
||
</div>
|
||
<div class="kpi">
|
||
<span class="kpi-label">Reg IDs universe</span>
|
||
<span class="kpi-value">{piv.shape[1]}</span>
|
||
<span class="kpi-sub">at reference date</span>
|
||
</div>
|
||
<div class="kpi">
|
||
<span class="kpi-label">Ever remapped</span>
|
||
<span class="kpi-value warn">{len(analytics['ever_remapped'])}</span>
|
||
<span class="kpi-sub">reg IDs w/ code change</span>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- ═══════════════════════════════════════════ MAIN -->
|
||
<div class="main">
|
||
|
||
<div class="section-label">01 · Score Integrity Over Time</div>
|
||
|
||
<!-- Chart 1: Σ score with vs without surgery -->
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Sum of scores — pre vs post surgery</span>
|
||
<span class="card-desc">
|
||
Post-surgery (solid) shows the corrected score after code repairs.
|
||
Pre-surgery (dashed) is the counterfactual without any remapping.
|
||
Gap = score rescued.
|
||
</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap-tall">
|
||
<canvas id="chartSigma"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Chart 2: Score drop (pre) -->
|
||
<div class="grid-2">
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Score recovered by surgery</span>
|
||
<span class="card-desc">Difference post − pre at each date</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap">
|
||
<canvas id="chartRecovery"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Portfolio concentration (entropy)</span>
|
||
<span class="card-desc">Shannon entropy of score distribution — higher = more spread</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap">
|
||
<canvas id="chartEntropy"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="section-label">02 · Individual Score Trajectories</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Score explorer — per Registrar Account</span>
|
||
<span class="card-desc">
|
||
Click an account to inspect its full history.
|
||
<span class="badge-surgery">◆ remapped</span> = surgery was applied.
|
||
</span>
|
||
</div>
|
||
<div class="card-body" style="padding:0">
|
||
|
||
<!-- Selector pill bar -->
|
||
<div class="traj-selector" id="trajSelector"></div>
|
||
|
||
<!-- Focused chart + metadata -->
|
||
<div class="traj-focus-wrap">
|
||
<div class="traj-account-meta" id="trajMeta"></div>
|
||
<div style="position:relative;height:300px">
|
||
<canvas id="chartTrajFocus"></canvas>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Sparkline overview grid -->
|
||
<div class="spark-section-label">All accounts — overview</div>
|
||
<div class="spark-grid" id="sparkGrid"></div>
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div class="section-label">03 · Surgery Operations</div>
|
||
|
||
<div class="grid-2">
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Surgeries per time step</span>
|
||
<span class="card-desc">Number of code remappings performed at each month</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap">
|
||
<canvas id="chartNSurg"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Score gain per surgery</span>
|
||
<span class="card-desc">Average gain in Σ score from surgery at each month</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap">
|
||
<canvas id="chartGain"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Jaccard similarity of surgery matches</span>
|
||
<span class="card-desc">
|
||
Composite Jaccard score of the matched code pair — closer to 1.0 = stronger portfolio overlap.
|
||
Low values may indicate uncertain matches.
|
||
</span>
|
||
</div>
|
||
<div class="card-body">
|
||
<div class="chart-wrap">
|
||
<canvas id="chartJaccard"></canvas>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="section-label">04 · Surgery Detail Log</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">All surgery operations</span>
|
||
</div>
|
||
<div class="card-body" style="padding:0">
|
||
{'<div class="no-surg">No surgeries were performed on this dataset.</div>' if len(surgery) == 0 else f"""
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>Date</th>
|
||
<th>Reg orig</th>
|
||
<th>Code from</th>
|
||
<th></th>
|
||
<th>Code to</th>
|
||
<th>Jaccard</th>
|
||
<th>Score gain</th>
|
||
<th>% of score</th>
|
||
<th>Lookback</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>{surg_rows_html}</tbody>
|
||
</table>"""}
|
||
</div>
|
||
</div>
|
||
|
||
<div class="section-label">05 · Score Ranking at t_ref</div>
|
||
|
||
<div class="card">
|
||
<div class="card-header">
|
||
<span class="card-title">Accounts ranked by weight at reference date</span>
|
||
<span class="card-desc">✓ in last column = account was remapped at some point in history</span>
|
||
</div>
|
||
<div class="card-body" style="padding:0">
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>Rank</th>
|
||
<th>Registrar ID</th>
|
||
<th>Score (weight)</th>
|
||
<th style="width:140px">Relative size</th>
|
||
<th>Remapped</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>{top_rows_html}</tbody>
|
||
</table>
|
||
</div>
|
||
</div>
|
||
|
||
{err_section_html}
|
||
|
||
|
||
</div><!-- /main -->
|
||
|
||
<div class="footer">Generated by carmignac_analysis.py · Carmignac × ENSAE Data Challenge 2025</div>
|
||
|
||
<!-- ═══════════════════════════════════════════ CHARTS JS -->
|
||
<script>
|
||
Chart.defaults.color = '#64748b';
|
||
Chart.defaults.borderColor = '#1e2535';
|
||
Chart.defaults.font.family = "'IBM Plex Mono', monospace";
|
||
Chart.defaults.font.size = 11;
|
||
|
||
const DATES = {js(dates_str)};
|
||
const SUM_POST = {jf(tl['sum_post'].values)};
|
||
const SUM_PRE = {jf(tl['sum_pre'].values)};
|
||
const RECOVERY = {jf(tl['recovery_pct'].values, 4)};
|
||
const ENTROPY = {jf(tl['entropy'].values, 4)};
|
||
const SURG_DATES = {js(surg_dates)};
|
||
const N_SURG = {n_surg};
|
||
const TOTAL_GAIN = {total_gain};
|
||
const AVG_GAIN = {avg_gain};
|
||
const AVG_JACCARD = {avg_jaccard};
|
||
const TRAJ = {traj_json};
|
||
|
||
// ── Shared options helpers ────────────────────────────────────
|
||
function timeAxis(label) {{
|
||
return {{
|
||
type: 'category',
|
||
ticks: {{ maxTicksLimit: 10, maxRotation: 0 }},
|
||
grid: {{ color: '#1a2030' }},
|
||
title: {{ display: !!label, text: label, color: '#475569' }},
|
||
}};
|
||
}}
|
||
function yAxis(label, opts={{}}) {{
|
||
return {{
|
||
grid: {{ color: '#1a2030' }},
|
||
title: {{ display: !!label, text: label, color: '#475569' }},
|
||
...opts,
|
||
}};
|
||
}}
|
||
function tooltip() {{
|
||
return {{
|
||
backgroundColor: '#0d1117',
|
||
borderColor: '#252a35',
|
||
borderWidth: 1,
|
||
titleFont: {{ family: "'IBM Plex Mono'" }},
|
||
bodyFont: {{ family: "'IBM Plex Mono'" }},
|
||
padding: 10,
|
||
}};
|
||
}}
|
||
|
||
// ── 1. Sigma pre/post ─────────────────────────────────────────
|
||
new Chart(document.getElementById('chartSigma'), {{
|
||
type: 'line',
|
||
data: {{
|
||
labels: DATES,
|
||
datasets: [
|
||
{{
|
||
label: 'Σ score (post-surgery)',
|
||
data: SUM_POST,
|
||
borderColor: '#10b981',
|
||
backgroundColor: '#10b98115',
|
||
borderWidth: 2.5,
|
||
pointRadius: 0,
|
||
fill: false,
|
||
tension: 0.2,
|
||
}},
|
||
{{
|
||
label: 'Σ score (pre-surgery / counterfactual)',
|
||
data: SUM_PRE,
|
||
borderColor: '#ef4444',
|
||
borderDash: [6, 4],
|
||
borderWidth: 1.5,
|
||
pointRadius: 0,
|
||
fill: false,
|
||
tension: 0.2,
|
||
backgroundColor: 'transparent',
|
||
}},
|
||
],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
interaction: {{ mode: 'index', intersect: false }},
|
||
plugins: {{
|
||
legend: {{ position: 'top', labels: {{ boxWidth: 12, padding: 16 }} }},
|
||
tooltip: tooltip(),
|
||
}},
|
||
scales: {{
|
||
x: timeAxis(),
|
||
y: yAxis('Σ scores', {{ min: 0, max: 1.05, ticks: {{ stepSize: 0.1 }} }}),
|
||
}},
|
||
}},
|
||
}});
|
||
|
||
// ── 2. Recovery ───────────────────────────────────────────────
|
||
new Chart(document.getElementById('chartRecovery'), {{
|
||
type: 'bar',
|
||
data: {{
|
||
labels: DATES,
|
||
datasets: [{{
|
||
label: 'Score recovered (%)',
|
||
data: RECOVERY,
|
||
backgroundColor: '#3b82f6aa',
|
||
borderColor: '#3b82f6',
|
||
borderWidth: 1,
|
||
borderRadius: 2,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
plugins: {{ legend: {{ display: false }}, tooltip: tooltip() }},
|
||
scales: {{
|
||
x: timeAxis(),
|
||
y: yAxis('Recovery (% of Σ)', {{ min: 0 }}),
|
||
}},
|
||
}},
|
||
}});
|
||
|
||
// ── 3. Entropy ────────────────────────────────────────────────
|
||
new Chart(document.getElementById('chartEntropy'), {{
|
||
type: 'line',
|
||
data: {{
|
||
labels: DATES,
|
||
datasets: [{{
|
||
label: 'Shannon entropy',
|
||
data: ENTROPY,
|
||
borderColor: '#d97706',
|
||
backgroundColor: '#d9770622',
|
||
borderWidth: 2,
|
||
pointRadius: 0,
|
||
fill: true,
|
||
tension: 0.3,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
plugins: {{ legend: {{ display: false }}, tooltip: tooltip() }},
|
||
scales: {{ x: timeAxis(), y: yAxis('Entropy (nats)') }},
|
||
}},
|
||
}});
|
||
|
||
// ── 4. Trajectory explorer ───────────────────────────────────
|
||
(function() {{
|
||
let focusChart = null;
|
||
let sparkCharts = [];
|
||
let activeIdx = 0;
|
||
|
||
// Surgery annotation plugin (vertical line + label)
|
||
const surgeryPlugin = {{
|
||
id: 'surgeryLines',
|
||
afterDraw(chart) {{
|
||
const surgeries = chart._surgeries || [];
|
||
if (!surgeries.length) return;
|
||
const {{ctx, chartArea, scales}} = chart;
|
||
surgeries.forEach(op => {{
|
||
const xIdx = DATES.indexOf(op.date);
|
||
if (xIdx < 0) return;
|
||
const x = scales.x.getPixelForValue(xIdx);
|
||
ctx.save();
|
||
ctx.strokeStyle = '#f59e0bcc';
|
||
ctx.lineWidth = 1.5;
|
||
ctx.setLineDash([4, 3]);
|
||
ctx.beginPath();
|
||
ctx.moveTo(x, chartArea.top);
|
||
ctx.lineTo(x, chartArea.bottom);
|
||
ctx.stroke();
|
||
// Label
|
||
ctx.font = "10px 'IBM Plex Mono'";
|
||
ctx.fillStyle = '#f59e0b';
|
||
ctx.textAlign = 'center';
|
||
ctx.fillText('✦', x, chartArea.top + 10);
|
||
ctx.restore();
|
||
}});
|
||
}}
|
||
}};
|
||
|
||
function buildFocusChart(idx) {{
|
||
const d = TRAJ[idx];
|
||
if (focusChart) focusChart.destroy();
|
||
|
||
const ctx = document.getElementById('chartTrajFocus').getContext('2d');
|
||
focusChart = new Chart(ctx, {{
|
||
type: 'line',
|
||
data: {{
|
||
labels: DATES,
|
||
datasets: [{{
|
||
label: d.label,
|
||
data: d.data,
|
||
borderColor: d.borderColor,
|
||
backgroundColor: d.borderColor + '18',
|
||
borderWidth: 2.5,
|
||
borderDash: d.borderDash,
|
||
pointRadius: d.data.map((_, i) => {{
|
||
return d.surgeries.some(s => DATES[i] === s.date) ? 6 : 0;
|
||
}}),
|
||
pointBackgroundColor: '#f59e0b',
|
||
pointBorderColor: '#f59e0b',
|
||
tension: 0.3,
|
||
fill: true,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
interaction: {{ mode: 'index', intersect: false }},
|
||
plugins: {{
|
||
legend: {{ display: false }},
|
||
tooltip: {{
|
||
...tooltip(),
|
||
callbacks: {{
|
||
afterBody(items) {{
|
||
const i = items[0].dataIndex;
|
||
const s = d.surgeries.find(x => DATES[i] === x.date);
|
||
if (!s) return [];
|
||
return [
|
||
'',
|
||
'✦ Surgery applied',
|
||
'From : ' + s.reg_from,
|
||
'To : ' + s.reg_to,
|
||
'Jaccard: ' + s.composite,
|
||
'Gain: +' + s.gain,
|
||
];
|
||
}}
|
||
}}
|
||
}},
|
||
}},
|
||
scales: {{
|
||
x: timeAxis(),
|
||
y: yAxis('Score (weight)', {{ min: 0 }}),
|
||
}},
|
||
}},
|
||
plugins: [surgeryPlugin],
|
||
}});
|
||
focusChart._surgeries = d.surgeries;
|
||
|
||
// Update meta panel
|
||
const meta = document.getElementById('trajMeta');
|
||
const surgHTML = d.surgeries.length
|
||
? d.surgeries.map(s =>
|
||
`<span class="surg-chip">✦ ${{s.date}} ${{s.reg_from}} → ${{s.reg_to}}</span>`
|
||
).join('')
|
||
: '<span style="color:#475569;font-size:0.75rem">No surgery applied</span>';
|
||
meta.innerHTML = `
|
||
<span class="meta-id" style="border-color:${{d.borderColor}};color:${{d.borderColor}}">${{d.label}}</span>
|
||
<div class="meta-surgs">${{surgHTML}}</div>
|
||
`;
|
||
}}
|
||
|
||
function buildSparkGrid() {{
|
||
const grid = document.getElementById('sparkGrid');
|
||
grid.innerHTML = '';
|
||
TRAJ.forEach((d, idx) => {{
|
||
const wrap = document.createElement('div');
|
||
wrap.className = 'spark-cell' + (idx === activeIdx ? ' active' : '');
|
||
wrap.dataset.idx = idx;
|
||
|
||
const label = document.createElement('div');
|
||
label.className = 'spark-label';
|
||
label.innerHTML = d.label + (d.remapped
|
||
? ' <span class="spark-badge">R</span>' : '');
|
||
|
||
const canvasWrap = document.createElement('div');
|
||
canvasWrap.style.cssText = 'position:relative;height:52px';
|
||
const cv = document.createElement('canvas');
|
||
canvasWrap.appendChild(cv);
|
||
|
||
wrap.appendChild(label);
|
||
wrap.appendChild(canvasWrap);
|
||
grid.appendChild(wrap);
|
||
|
||
const sc = new Chart(cv, {{
|
||
type: 'line',
|
||
data: {{
|
||
labels: DATES,
|
||
datasets: [{{
|
||
data: d.data,
|
||
borderColor: d.borderColor,
|
||
borderWidth: 1.5,
|
||
pointRadius: 0,
|
||
tension: 0.3,
|
||
fill: false,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
animation: false,
|
||
plugins: {{ legend: {{ display: false }}, tooltip: {{ enabled: false }} }},
|
||
scales: {{
|
||
x: {{ display: false }},
|
||
y: {{ display: false, min: 0 }},
|
||
}},
|
||
}},
|
||
}});
|
||
sparkCharts.push(sc);
|
||
|
||
wrap.addEventListener('click', () => {{
|
||
document.querySelectorAll('.spark-cell').forEach(c => c.classList.remove('active'));
|
||
document.querySelectorAll('.traj-btn').forEach(b => b.classList.remove('active'));
|
||
wrap.classList.add('active');
|
||
document.querySelector(`.traj-btn[data-idx="${{idx}}"]`).classList.add('active');
|
||
activeIdx = idx;
|
||
buildFocusChart(idx);
|
||
}});
|
||
}});
|
||
}}
|
||
|
||
function buildSelector() {{
|
||
const sel = document.getElementById('trajSelector');
|
||
sel.innerHTML = '';
|
||
TRAJ.forEach((d, idx) => {{
|
||
const btn = document.createElement('button');
|
||
btn.className = 'traj-btn' + (idx === 0 ? ' active' : '');
|
||
btn.dataset.idx = idx;
|
||
btn.style.setProperty('--acc', d.borderColor);
|
||
btn.innerHTML = d.label + (d.remapped ? ' <span class="traj-btn-badge">R</span>' : '');
|
||
btn.addEventListener('click', () => {{
|
||
document.querySelectorAll('.traj-btn').forEach(b => b.classList.remove('active'));
|
||
document.querySelectorAll('.spark-cell').forEach(c => c.classList.remove('active'));
|
||
btn.classList.add('active');
|
||
const cell = document.querySelector(`.spark-cell[data-idx="${{idx}}"]`);
|
||
if (cell) cell.classList.add('active');
|
||
activeIdx = idx;
|
||
buildFocusChart(idx);
|
||
}});
|
||
sel.appendChild(btn);
|
||
}});
|
||
}}
|
||
|
||
buildSelector();
|
||
buildFocusChart(0);
|
||
buildSparkGrid();
|
||
}})();
|
||
|
||
// ── 5. N surgeries ────────────────────────────────────────────
|
||
new Chart(document.getElementById('chartNSurg'), {{
|
||
type: 'bar',
|
||
data: {{
|
||
labels: SURG_DATES,
|
||
datasets: [{{
|
||
label: 'Surgeries',
|
||
data: N_SURG,
|
||
backgroundColor: '#7c3aed99',
|
||
borderColor: '#7c3aed',
|
||
borderWidth: 1,
|
||
borderRadius: 3,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
plugins: {{ legend: {{ display: false }}, tooltip: tooltip() }},
|
||
scales: {{
|
||
x: timeAxis('Month'),
|
||
y: yAxis('# operations', {{ min: 0, ticks: {{ stepSize: 1 }} }}),
|
||
}},
|
||
}},
|
||
}});
|
||
|
||
// ── 6. Avg gain ───────────────────────────────────────────────
|
||
new Chart(document.getElementById('chartGain'), {{
|
||
type: 'bar',
|
||
data: {{
|
||
labels: SURG_DATES,
|
||
datasets: [
|
||
{{
|
||
label: 'Total gain',
|
||
data: TOTAL_GAIN,
|
||
backgroundColor: '#10b98199',
|
||
borderColor: '#10b981',
|
||
borderWidth: 1,
|
||
borderRadius: 3,
|
||
}},
|
||
{{
|
||
label: 'Avg gain / surgery',
|
||
data: AVG_GAIN,
|
||
backgroundColor: '#06b6d455',
|
||
borderColor: '#06b6d4',
|
||
borderWidth: 1,
|
||
borderRadius: 3,
|
||
}},
|
||
],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
interaction: {{ mode: 'index', intersect: false }},
|
||
plugins: {{ legend: {{ position: 'top', labels: {{ boxWidth: 10 }} }}, tooltip: tooltip() }},
|
||
scales: {{ x: timeAxis('Month'), y: yAxis('Score gain') }},
|
||
}},
|
||
}});
|
||
|
||
// ── 7. Jaccard ────────────────────────────────────────────────
|
||
new Chart(document.getElementById('chartJaccard'), {{
|
||
type: 'bar',
|
||
data: {{
|
||
labels: SURG_DATES,
|
||
datasets: [{{
|
||
label: 'Avg Jaccard composite',
|
||
data: AVG_JACCARD,
|
||
backgroundColor: '#f59e0b88',
|
||
borderColor: '#f59e0b',
|
||
borderWidth: 1,
|
||
borderRadius: 3,
|
||
}}],
|
||
}},
|
||
options: {{
|
||
responsive: true, maintainAspectRatio: false,
|
||
plugins: {{ legend: {{ display: false }}, tooltip: tooltip() }},
|
||
scales: {{
|
||
x: timeAxis('Month'),
|
||
y: yAxis('Jaccard composite', {{ min: 0, max: 1.05 }}),
|
||
}},
|
||
}},
|
||
}});
|
||
{err_js_block}
|
||
</script>
|
||
</body>
|
||
</html>"""
|
||
|
||
return html
|
||
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# 5. MAIN
|
||
# ─────────────────────────────────────────────────────────────
|
||
|
||
def main():
|
||
parser = argparse.ArgumentParser(description="Carmignac pipeline results analyser")
|
||
parser.add_argument("--scores", default="repair_results/carmignac_scores.csv")
|
||
parser.add_argument("--mapping", default="repair_results/carmignac_mapping.csv")
|
||
parser.add_argument("--surgery", default="repair_results/carmignac_surgery_log.csv")
|
||
parser.add_argument("--out", default="repair_results/carmignac_report.html")
|
||
parser.add_argument("--error-account-isin", default=None,
|
||
dest="error_isin",
|
||
help="Path to carmignac_error_account.csv (optional)")
|
||
parser.add_argument("--error-account-agg", default=None,
|
||
dest="error_agg",
|
||
help="Path to carmignac_error_account_agg.csv (optional)")
|
||
args = parser.parse_args()
|
||
|
||
# Resolve paths relative to this script's directory if files not found
|
||
base = os.path.dirname(os.path.abspath(__file__))
|
||
def resolve(p, required=True):
|
||
if p is None:
|
||
return None
|
||
if os.path.exists(p):
|
||
return p
|
||
alt = os.path.join(base, p)
|
||
if os.path.exists(alt):
|
||
return alt
|
||
if required:
|
||
sys.exit(f"[ERROR] File not found: {p}")
|
||
print(f"[WARN] Optional file not found: {p}")
|
||
return None
|
||
|
||
scores_path = resolve(args.scores)
|
||
mapping_path = resolve(args.mapping)
|
||
surgery_path = resolve(args.surgery)
|
||
error_isin_path = resolve(args.error_isin, required=False)
|
||
error_agg_path = resolve(args.error_agg, required=False)
|
||
|
||
print(f"[Load] scores : {scores_path}")
|
||
print(f"[Load] mapping : {mapping_path}")
|
||
print(f"[Load] surgery : {surgery_path}")
|
||
|
||
scores, mapping, surgery, df_err_isin, df_err_agg = load_outputs(
|
||
scores_path, mapping_path, surgery_path,
|
||
err_isin_path=error_isin_path, err_agg_path=error_agg_path
|
||
)
|
||
analytics = compute_analytics(scores, mapping, surgery)
|
||
|
||
print_summary(analytics, surgery)
|
||
|
||
html = build_html(analytics, surgery, scores, mapping,
|
||
df_err_isin=df_err_isin, df_err_agg=df_err_agg)
|
||
|
||
out_path = "../" + args.out
|
||
os.makedirs(os.path.dirname(out_path), exist_ok=True)
|
||
with open(out_path, "w", encoding="utf-8") as f:
|
||
f.write(html)
|
||
print(f"\n[Report] Written to → {out_path}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|