factor-report

Name: factor-report
Author: minihellboy

95stars28forks

How to install factor-report?

minihellboy/factorminer/factor-report

$npx -y skills add minihellboy/factorminer --skill factor-report

Installs into the current project.

Summary

Generate static reports, tearsheets, and exports from FactorMiner artifacts — markdown/HTML research notes, plots, and library exports (JSON/CSV/formulas). Use to package a finished research run for review. Triggers on "generate report", "factor report", "research note", "tearshe

Files · 1

View on GitHub

SKILL.md

1	# Factor Report
2
3	This skill turns a finished run into reviewable artifacts: a static report, plots, and portable exports.
4
5	## Workflow
6
7	### 1. Static report
8
9	```bash
10	factorminer report output/run1/factor_library.json \
11	--session-log output/run1/session_log.json \
12	--format markdown --output output/run1/report.md
13	```
14
15	- `--format` — `markdown` or `html`. HTML is self-contained (no JavaScript).
16	- `--session-log` — includes run metadata (iterations, yield rate).
17	- `--benchmark path.json` — fold in benchmark results; repeatable.
18
19	The report defines every admission metric inline, lists each factor with its formula and IC/ICIR/correlation, and warns on stale artifacts.
20
21	### 2. Plots
22
23	```bash
24	factorminer -o output/run1 visualize output/run1/factor_library.json \
25	--data market_data.csv --period test \
26	--correlation --ic-timeseries --quintile --format png
27	```
28
29	### 3. Export the library
30
31	```bash
32	factorminer export output/run1/factor_library.json --format formulas --output output/run1/formulas.txt
33	```
34
35	`--format` options: `json` (full library), `csv` (tabular metrics), `formulas` (plain formula list for handoff).
36
37	## Assembling the research note
38
39	A complete note pairs the generated report with narrative the analyst can sign off on:
40
41	1. Objective & data — universe, horizon, split boundaries, validation status.
42	2. Method — loop used (Ralph/Helix), features enabled, iteration budget.
43	3. Library — admitted factors with formulas and out-of-sample IC/ICIR.
44	4. Composite — backtest result net of costs, with the decay caveat.
45	5. Benchmark — comparison vs. baselines, if run.
46	6. Limitations — overfit risk, capacity, what was not tested.
47
48	## Guardrails
49
50	- The report presents results; it does not certify them. Frame it as research staged for human review.
51	- Quote out-of-sample metrics as the headline; never the in-sample number.
52	- Cite the run directory so every figure is reproducible via `factorminer session inspect`.

People who liked this also viewed

6 picks

Type

factor-report

95stars28forks

View on GitHub

How to install factor-report?

minihellboy/factorminer/factor-report

$npx -y skills add minihellboy/factorminer --skill factor-report

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Factor Report
2
3	This skill turns a finished run into reviewable artifacts: a static report, plots, and portable exports.
4
5	## Workflow
6
7	### 1. Static report
8
9	```bash
10	factorminer report output/run1/factor_library.json \
11	--session-log output/run1/session_log.json \
12	--format markdown --output output/run1/report.md
13	```
14
15	- `--format` — `markdown` or `html`. HTML is self-contained (no JavaScript).
16	- `--session-log` — includes run metadata (iterations, yield rate).
17	- `--benchmark path.json` — fold in benchmark results; repeatable.
18
19	The report defines every admission metric inline, lists each factor with its formula and IC/ICIR/correlation, and warns on stale artifacts.
20
21	### 2. Plots
22
23	```bash
24	factorminer -o output/run1 visualize output/run1/factor_library.json \
25	--data market_data.csv --period test \
26	--correlation --ic-timeseries --quintile --format png
27	```
28
29	### 3. Export the library
30
31	```bash
32	factorminer export output/run1/factor_library.json --format formulas --output output/run1/formulas.txt
33	```
34
35	`--format` options: `json` (full library), `csv` (tabular metrics), `formulas` (plain formula list for handoff).
36
37	## Assembling the research note
38
39	A complete note pairs the generated report with narrative the analyst can sign off on:
40
41	1. Objective & data — universe, horizon, split boundaries, validation status.
42	2. Method — loop used (Ralph/Helix), features enabled, iteration budget.
43	3. Library — admitted factors with formulas and out-of-sample IC/ICIR.
44	4. Composite — backtest result net of costs, with the decay caveat.
45	5. Benchmark — comparison vs. baselines, if run.
46	6. Limitations — overfit risk, capacity, what was not tested.
47
48	## Guardrails
49
50	- The report presents results; it does not certify them. Frame it as research staged for human review.
51	- Quote out-of-sample metrics as the headline; never the in-sample number.
52	- Cite the run directory so every figure is reproducible via `factorminer session inspect`.

People who liked this also viewed

6 picks

Type