Merge pull request #38 from cvxgrp/37-load-tail-of-data-for-faster-cicd

experiments ci/cd

.github/workflows/basic.yml

@@ -21,4 +21,4 @@ jobs:
       - name: experiments
         shell: bash
         run: |
-          make experiment
+          make experiments

Makefile

@@ -18,8 +18,8 @@ fmt: install ## Run autoformatting and linting
 clean:  ## Clean up caches and build artifacts
 	@git clean -X -d -f
 
-.PHONY: experiment
-experiment: install ## Run all experiment
+.PHONY: experiments
+experiments: install ## Run all experiment
 	${VENV}/bin/python experiments.py
 
 .PHONY: help

experiments.py

@@ -2,9 +2,11 @@
 
 from experiments.taming import main as taming_main
 from experiments.scaling_small import main as scaling_small_main
+from experiments.scaling_large import main as scaling_large_main
 
 if __name__ == "__main__":
     Path("checkpoints").mkdir(exist_ok=True)
     Path("figures").mkdir(exist_ok=True)
     scaling_small_main()
+    scaling_large_main()
     taming_main()

experiments/backtest.py

@@ -2,6 +2,7 @@
 
 from dataclasses import dataclass
 from functools import lru_cache
+import os
 from pathlib import Path
 import pickle
 import time
@@ -21,6 +22,10 @@ def load_data() -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, pd.DataFrame]
     prices = pd.read_csv(data_folder() / "prices.csv", index_col=0, parse_dates=True)
     spread = pd.read_csv(data_folder() / "spreads.csv", index_col=0, parse_dates=True)
     rf = pd.read_csv(data_folder() / "rf.csv", index_col=0, parse_dates=True).iloc[:, 0]
+    if os.getenv("CI"):
+        prices = prices.tail(2000)
+        spread = spread.tail(2000)
+        rf = rf.tail(2000)
     return prices, spread, rf
 
 

experiments/scaling_large.py

@@ -1,7 +1,8 @@
+import os
 import cvxpy as cp
 import numpy as np
 import pandas as pd
-from utils import generate_random_inputs
+from experiments.utils import generate_random_inputs
 
 
 def main():
@@ -11,8 +12,10 @@ def main():
     for n_assets, n_factors in scenarios:
         print(f"Running scenario with {n_assets} assets and {n_factors} factors")
         solvers = [cp.MOSEK] if fitting else [cp.CLARABEL, cp.MOSEK]
+        solvers = [s for s in solvers if s in cp.installed_solvers()]
         for solver in solvers:
-            for _ in range(1):
+            n_iters = 1 if os.environ.get("CI") else 30
+            for _ in range(n_iters):
                 problem = run_scaling(n_assets, n_factors, solver)
                 assert problem.status in {
                     cp.OPTIMAL,

experiments/taming.py

@@ -116,7 +116,7 @@ def get_basic_data_and_parameters(
     return data, param
 
 
-def main(from_checkpoint: bool = True) -> None:
+def main(from_checkpoint: bool = False) -> None:
     annualized_target = 0.10
 
     if not from_checkpoint:
@@ -129,12 +129,15 @@ def main(from_checkpoint: bool = True) -> None:
     weight_limited_result = BacktestResult.load(
         f"checkpoints/weight_limited_{annualized_target}.pickle"
     )
+
     leverage_limit_result = BacktestResult.load(
         f"checkpoints/leverage_limit_{annualized_target}.pickle"
     )
+
     turnover_limit_result = BacktestResult.load(
         f"checkpoints/turnover_limit_{annualized_target}.pickle"
     )
+
     robust_result = BacktestResult.load(
         f"checkpoints/robust_{annualized_target}.pickle"
     )
@@ -165,9 +168,9 @@ def run_all_strategies(annualized_target: float) -> None:
     adjustment_factor = np.sqrt(equal_weights_results.periods_per_year)
     sigma_target = annualized_target / adjustment_factor
 
-    # print("Running basic Markowitz")
-    # basic_result = run_backtest(basic_markowitz, sigma_target, verbose=True)
-    # basic_result.save(f"checkpoints/basic_{annualized_target}.pickle")
+    print("Running basic Markowitz")
+    basic_result = run_backtest(basic_markowitz, sigma_target, verbose=True)
+    basic_result.save(f"checkpoints/basic_{annualized_target}.pickle")
 
     print("Running weight-limited Markowitz")
     weight_limited_result = run_backtest(