-
-
Save beckernick/22e0c117a96832ea2afab05484e30580 to your computer and use it in GitHub Desktop.
TPOT Timed Higgs Boson Experiments
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 | |
import time | |
import sys | |
import yaml | |
import json | |
import pandas as pd | |
import numpy as np | |
from sklearn.model_selection import train_test_split | |
from sklearn.metrics import accuracy_score | |
from sklearn.datasets import fetch_covtype | |
import cudf | |
from dask.utils import parse_bytes | |
cudf.set_allocator( | |
pool=True, | |
initial_pool_size=parse_bytes("20GB") | |
) | |
from tpot import TPOTClassifier | |
import cuml | |
class Timer: | |
def __enter__(self): | |
self.tick = time.time() | |
return self | |
def __exit__(self, *args, **kwargs): | |
self.tock = time.time() | |
self.elapsed = self.tock - self.tick | |
def get_highest_internal_cv(fitted_tpot): | |
top_score = 0 | |
for k, v in fitted_tpot.evaluated_individuals_.items(): | |
current_score = v.get('internal_cv_score', 0) | |
if current_score > top_score: | |
top_score = current_score | |
return top_score | |
benchamrk_config_path = sys.argv[1] | |
with open(benchamrk_config_path) as fp: | |
BENCHMARK_CONFIG = yaml.safe_load(fp.read()) | |
DATA_DIRECTORY = "/raid/nicholasb" | |
def prepare_airlines(nrows=None): | |
# see https://transtats.bts.gov/Tables.asp?DB_ID=120&DB_Name=Airline%20On-Time%20Performance%20Data&DB_Short_Name=On-Time# | |
# mirror: https://rapidsai-cloud-ml-sample-data.s3-us-west-2.amazonaws.com/airline_20000000.parquet" | |
DATASET_PATH = os.path.join(DATA_DIRECTORY, "airline_20000000.parquet") | |
df = pd.read_parquet(DATASET_PATH) | |
df = df.head(nrows) | |
X = df.drop(["ArrDelayBinary"], axis=1) | |
y = df["ArrDelayBinary"].astype('int32') | |
return X, y | |
def prepare_higgs(nrows=None): | |
# see https://github.com/NVIDIA/gbm-bench/blob/04f052febb95436762c67c59eaa33d6cd3ebcdbc/datasets.py#L176 | |
DATASET_PATH = os.path.join(DATA_DIRECTORY, "HIGGS.csv.gz") | |
higgs = pd.read_csv(DATASET_PATH, nrows=nrows) | |
X = higgs.iloc[:, 1:].to_numpy(dtype=np.float32) | |
y = higgs.iloc[:, 0].to_numpy(dtype=np.int64) | |
return X, y | |
dataset_mapping = { | |
"airline": prepare_airlines, | |
"higgs": prepare_higgs, | |
} | |
NROWS = BENCHMARK_CONFIG.get("nrows") | |
DATASET = BENCHMARK_CONFIG.get("dataset") | |
X, y = dataset_mapping[DATASET](nrows=NROWS) | |
print(f"X.shape: {X.shape}") | |
print(f"y.shape: {y.shape}") | |
# TPOT configuration | |
seed = BENCHMARK_CONFIG.get("seed") | |
generations = BENCHMARK_CONFIG.get("generations") | |
pop_size = BENCHMARK_CONFIG.get("population_size") | |
cv = BENCHMARK_CONFIG.get("cv") | |
max_time_mins = BENCHMARK_CONFIG.get("max_time_mins") | |
config_mapping = { | |
"Default": None, | |
"cuML": "TPOT cuML", | |
"Light": "TPOT Light", | |
} | |
config_dict = config_mapping[BENCHMARK_CONFIG.get("config_dict")] | |
njobs = 1 if config_dict == "TPOT cuML" else -1 | |
verbosity = BENCHMARK_CONFIG.get("verbosity") | |
scoring_metric = BENCHMARK_CONFIG.get("scoring_metric") | |
tpot = TPOTClassifier( | |
generations=generations, | |
population_size=pop_size, | |
random_state=seed, | |
config_dict=config_dict, | |
n_jobs=njobs, | |
max_time_mins=max_time_mins, | |
cv=cv, | |
scoring=scoring_metric, | |
verbosity=2, | |
) | |
with Timer() as fit_time: | |
tpot.fit(X, y) | |
with Timer() as predict_time: | |
preds = tpot.predict(X) | |
benchmark_payload = BENCHMARK_CONFIG.copy() | |
benchmark_payload["n_jobs"] = njobs | |
benchmark_payload["evaluated_pipelines"] = len(tpot.evaluated_individuals_.keys()) | |
benchmark_payload["fit_time"] = fit_time.elapsed | |
benchmark_payload["predict_time"] = predict_time.elapsed | |
benchmark_payload["best_cv_score"] = get_highest_internal_cv(tpot) | |
benchmark_payload["fitted_pipeline"] = str(tpot.fitted_pipeline_) | |
benchmark_payload["exported_pipeline"] = tpot.export() | |
benchmark_payload["cuml_version"] = cuml.__version__ | |
outpath = f"tpot-benchmark-all-results.txt" | |
with open(outpath, "a") as fh: | |
fh.write(json.dumps(benchmark_payload)) | |
fh.write("\n") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment