def run_training():
df = read_data_as_df(DATA_PATH)
new_df = get_feature_df(df)
tfidf_df = get_tfidf(new_df)
X, y = preprocess_data(tfidf_df)
X_test, y_test = X.loc[X.index == 'TEST'], y.loc[y.index == 'TEST'].values
X_train, y_train = X.loc[(X.index == 'TRAIN') | (
X.index == 'VALIDATION')], y.loc[(y.index == 'TRAIN') |
(y.index == 'VALIDATION')].values
LOG.info(f"Training set: {X_train.shape}, Testing set: {X_test.shape}")
LOG.info(
f"Training set positive examples: {y_train.sum()}, Testing set positive examples: {y_test.sum()}"
)
clf_d = get_trained_models(["RF", "SGD", "LR", "SVM"], X_train, y_train)
evaluate_models(clf_d, X_train, X_test, y_train, y_test)
import pytest
from utils import get_trained_models
def _assert_eq(left, right):
assert left == right, f"{left} != {right}"
FOLDER = "rl-trained-agents/"
N_STEPS = 100
LOG_FOLDER = "logs/tests/"
trained_models = get_trained_models(FOLDER)
@pytest.mark.parametrize("trained_model", trained_models.keys())
def test_enjoy(trained_model):
algo, env_id = trained_models[trained_model]
args = ["-n", str(N_STEPS), "-f", FOLDER, "--algo", algo, "--env", env_id, "--no-render"]
# Skip mujoco envs
if "Fetch" in trained_model:
return
if "-MiniGrid-" in trained_model:
args = args + ["--gym-packages", "gym_minigrid"]
return_code = subprocess.call(["python", "enjoy.py"] + args)
type=int)
parser.add_argument('--verbose',
help='Verbose mode (0: no output, 1: INFO)',
default=1,
type=int)
parser.add_argument('--seed',
help='Random generator seed',
type=int,
default=0)
parser.add_argument('--test-mode',
action='store_true',
default=False,
help='Do only one experiments (useful for testing)')
args = parser.parse_args()
trained_models = get_trained_models(args.log_dir)
n_experiments = len(trained_models)
results = {
'algo': [],
'env_id': [],
'mean_reward': [],
'std_reward': [],
'n_timesteps': [],
'n_episodes': []
}
for idx, trained_model in enumerate(trained_models.keys()):
algo, env_id = trained_models[trained_model]
n_envs = args.n_envs
n_timesteps = args.n_timesteps
if algo in ['dqn', 'ddpg', 'sac']:
