Last active
November 11, 2021 05:48
-
-
Save jlmelville/fd6adc573594d5f935a84b5d1264241c to your computer and use it in GitHub Desktop.
reading CSV into Pandas but also pickling it at the same time
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 pickle | |
from pathlib import Path | |
def read_data(dataset, suffix=None, dir=None, repickle=False): | |
"""Set `repickle=True` to rewrite pickle file if CSV has changed""" | |
home = str(Path.home()) | |
if dir is None: | |
dataset_path = os.path.join(home, "dev", "datasets") | |
else: | |
dataset_path = dir | |
if suffix is not None: | |
dataset_basename = f"{dataset}-{suffix}" | |
else: | |
dataset_basename = dataset | |
pickle_name = f"{dataset_basename}.pickle" | |
pickle_path = os.path.join(dataset_path, pickle_name) | |
if os.path.exists(pickle_path) and not repickle: | |
with open(pickle_path, "rb") as f: | |
return pickle.load(f) | |
else: | |
csv_name = f"{dataset_basename}.csv" | |
csv_path = os.path.join(dataset_path, csv_name) | |
if not os.path.exists(csv_path): | |
raise FileNotFoundError(csv_path) | |
data = pd.read_csv(csv_path) | |
with open(pickle_path, "wb") as f: | |
pickle.dump(data, f, pickle.HIGHEST_PROTOCOL) | |
return data | |
def read_dataxy(dataset, repickle=False): | |
"""Read X and Y (Label) data from separate files""" | |
x = read_data(dataset, "x", repickle=repickle) | |
try: | |
y = read_data(dataset, "y", repickle=repickle) | |
except FileNotFoundError: | |
y = range(x.shape[0]) | |
return (x, y) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment