run.py

import json
import logging
import sys

sys.path.append("../..")
from src.loader import load_data
from src.run import run_algorithm

# logging settings
logger = logging.getLogger(__name__)
logging.basicConfig(
    filename="../../logs.log",
    level=logging.INFO,
    format="%(asctime)s - %(levelname)s - %(lineno)d - %(name)s: %(message)s",
    datefmt="%y-%m-%d %H:%M:%S"
)

DATASETSPATH = "../../datasets"

import warnings
warnings.filterwarnings("ignore")


def predict(x_test, y_test, z_test, z_test_xpos, dname):
    """Perform baseline lemmatization: lemma = token."""
    return x_test


# run all benchmarks
results = []

for x_test, y_test, z_test, z_test_xpos, dname in load_data(DATASETSPATH):
    try:
        results.append(run_algorithm(predict, x_test, y_test, z_test,
                                     z_test_xpos, dname, 'baseline'))
    except Exception as err:
        logger.error(err)


# store results
with open("../../nbs/results-baseline.json", "w") as fp:
    json.dump(results, fp, indent=4)