def prepare_env(self):
"""Prepare running environment.
* Load parameters from json files.
* Initialize system folders, model name and the paths to be saved.
* Initialize resource monitor.
* Initialize random seed.
* Initialize logging.
"""
# Load config file from json
with open(self.args.config_file) as config_params:
print(f"loading config file {self.args.config_file}")
config = json.load(config_params)
# Update configs based on the received args from the command line .
update_args(config, self.args)
# obtain abspath for the project
config["system"]["root_dir"] = os.path.abspath(
config["system"]["root_dir"])
# construct unique model run id, which consist of model name, config id and a timestamp
timestamp_str = datetime.now().strftime("%Y%m%d_%H%M%S")
random_str = "".join(
[random.choice(string.ascii_lowercase) for n in range(6)])
config["system"]["model_run_id"] = (config["model"]["model"] + "_" +
config["model"]["config_id"] +
"_" + timestamp_str + "_" +
random_str)
# Initialize random seeds
set_seed(config["system"]["seed"] if "seed" in
config["system"] else 2020)
# Initialize working folders
self.initialize_folders(config)
config["system"]["process_dir"] = os.path.join(
config["system"]["root_dir"], config["system"]["process_dir"])
# Initialize log file
config["system"]["log_file"] = os.path.join(
config["system"]["root_dir"],
config["system"]["log_dir"],
config["system"]["model_run_id"],
)
logger.init_std_logger(config["system"]["log_file"])
print("Python version:", sys.version)
print("pytorch version:", torch.__version__)
# File paths to be saved
config["model"]["run_dir"] = os.path.join(
config["system"]["root_dir"],
config["system"]["run_dir"],
config["system"]["model_run_id"],
)
config["system"]["run_dir"] = config["model"]["run_dir"]
print(
"The intermediate running statuses will be reported in folder:",
config["system"]["run_dir"],
)
config["system"]["tune_dir"] = os.path.join(
config["system"]["root_dir"], config["system"]["tune_dir"])
def get_user_temp_dir():
tempdir = os.path.join(config["system"]["root_dir"], "tmp")
print(f"ray temp dir {tempdir}")
return tempdir
ray.utils.get_user_temp_dir = get_user_temp_dir
# Model checkpoints paths to be saved
config["system"]["model_save_dir"] = os.path.join(
config["system"]["root_dir"],
config["system"]["checkpoint_dir"],
config["system"]["model_run_id"],
)
ensureDir(config["system"]["model_save_dir"])
print("Model checkpoint will save in file:",
config["system"]["model_save_dir"])
config["system"]["result_file"] = os.path.join(
config["system"]["root_dir"],
config["system"]["result_dir"],
config["system"]["result_file"],
)
print("Performance result will save in file:",
config["system"]["result_file"])
print_dict_as_table(config["system"], "System configs")
return config
with open(config["config_file"]) as config_params:
print("loading config file", config["config_file"])
json_config = json.load(config_params)
json_config.update(config)
config = json_config
root_dir = config["root_dir"]
time_str = datetime.now().strftime("%Y%m%d_%H%M%S")
log_file = (root_dir + "logs/cornac" + "_" + config["dataset"] + "_" +
config["data_split"] + time_str)
config["result_file"] = (root_dir + "results/cornac" + "_" +
config["dataset"] + "_" + config["data_split"] +
".csv")
"""
init logger
"""
logger.init_std_logger(log_file)
# cornac.eval_methods.base_method.rating_eval = rating_eval
# Load the built-in MovieLens 100K dataset (will be downloaded if not cached):
# Here we are comparing Biased MF, PMF, and BPR:
# pop = cornac.models.most_pop.recom_most_pop.MostPop(name="MostPop")
# mf = cornac.models.MF(
# k=10, max_iter=25, learning_rate=0.01, lambda_reg=0.02, use_bias=True, seed=123
# )
# pmf = cornac.models.PMF(
# k=10, max_iter=100, learning_rate=0.001, lambda_reg=0.001, seed=123
# )
# bpr = cornac.models.BPR(
# k=10, max_iter=200, learning_rate=0.001, lambda_reg=0.01, seed=123
def prepare_env(config):
"""Prepare running environment
- Load parameters from json files.
- Initialize system folders, model name and the paths to be saved.
- Initialize resource monitor.
- Initialize random seed.
- Initialize logging.
Args:
config (dict): Global configs.
"""
# obtain abspath for the project
# You need specified it if it is running in the container.
if "root_dir" not in config:
file_dir = os.path.dirname(os.path.abspath(__file__))
config["root_dir"] = os.path.abspath(os.path.join(file_dir, ".."))
# load config file from json
with open(config["config_file"]) as config_params:
print("loading config file", config["config_file"])
json_config = json.load(config_params)
# update global parameters with these parameters received from the command line .
json_config.update(config)
config = json_config
# construct unique model run id, which consist of model name, config id and a timestamp
timestamp_str = datetime.now().strftime("%Y%m%d_%H%M%S")
random_str = "".join([random.choice(string.ascii_lowercase) for n in range(6)])
config["model_run_id"] = (
config["model"]
+ "_"
+ config["config_id"]
+ "_"
+ timestamp_str
+ "_"
+ random_str
)
set_seed(config["seed"] if "seed" in config else 2020)
initialize_folders(config["root_dir"])
# Initialize log file
config["log_file"] = os.path.join(
config["root_dir"], config["log_dir"], config["model_run_id"]
)
logger.init_std_logger(config["log_file"])
print("python version:", sys.version)
print("pytorch version:", torch.__version__)
# File paths to be saved
config["run_dir"] = os.path.join(
config["root_dir"], config["run_dir"], config["model_run_id"]
)
print(
"The intermediate running statuses will be reported in folder:",
config["run_dir"],
)
# Model checkpoints paths to be saved
config["model_save_dir"] = os.path.join(
config["root_dir"], config["checkpoint_dir"], config["model_run_id"]
)
ensureDir(config["model_save_dir"])
print("Model checkpoint will save in file:", config["model_save_dir"])
config["result_file"] = os.path.join(
config["root_dir"], config["result_dir"], config["result_file"]
)
print("Performance result will save in file:", config["result_file"])
# remove comments
print_dict_as_table(config, "Model configs")
return config