Last active
December 4, 2020 16:48
-
-
Save ogrisel/955234a13d9d6bb9bf35e2b2fe65e296 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
os.environ["OMP_NUM_THREADS"] = "1" # avoid oversubscription | |
import pandas as pd | |
from distributed.client import performance_report | |
from time import perf_counter | |
from joblib import Memory, parallel_backend | |
from distributed import Client, LocalCluster | |
from sklearn.datasets import make_regression | |
from sklearn.experimental import enable_hist_gradient_boosting # noqa | |
from sklearn.ensemble import HistGradientBoostingRegressor | |
from sklearn.model_selection import RandomizedSearchCV | |
make_regression = Memory(location="/tmp").cache(make_regression) | |
param_grid = { | |
"max_iter": [10, 30, 50, 100, 300, 500], | |
"max_leaf_nodes": [3, 5, 7, 11, 31, 77, 151], | |
"learning_rate": [0.01, 0.05, 0.1, 0.5, 1], | |
"n_iter_no_change": [5, 10, 50, 100], | |
} | |
def run_grid_search(): | |
X, y = make_regression(n_samples=int(1e5), n_features=100, random_state=0) | |
with parallel_backend("dask"): | |
search = RandomizedSearchCV( | |
HistGradientBoostingRegressor(), | |
param_grid, | |
n_iter=100, | |
cv=5, | |
verbose=100, | |
random_state=0, | |
) | |
return search.fit(X, y) | |
if __name__ == "__main__": | |
cluster = LocalCluster(n_workers=8, processes=True, threads_per_worker=1) | |
client = Client(cluster) | |
print("OMP_NUM_THREADS on dask workers:", | |
client.submit(lambda: os.environ["OMP_NUM_THREADS"]).result()) | |
with performance_report("dask_perf_report.html"): | |
t0 = perf_counter() | |
search_cv = client.submit(run_grid_search).result() | |
print(f"duration={perf_counter() - t0:.3f}s") | |
cols = ["params", "mean_test_score"] | |
df = pd.DataFrame(search_cv.cv_results_)[cols] | |
print(df.sort_values("mean_test_score", ascending=False).head(10)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment