Files
drift/data_loader/process.py
T
2022-02-19 14:58:34 +01:00

22 lines
690 B
Python

import pandas as pd
from config.types import Config
import warnings
from utils.helpers import get_first_valid_return_index
from data_loader.types import XDataFrame
def check_data(X: XDataFrame, config: Config) -> bool:
"""Returns True if data is valid, else returns False."""
if has_enough_samples_to_train(X, config) == False:
warnings.warn("Not enough samples to train")
return False
return True
def has_enough_samples_to_train(X: XDataFrame, config: Config) -> bool:
first_valid_index = get_first_valid_return_index(X.iloc[:, 0])
samples_to_train = len(X) - first_valid_index
return samples_to_train > (config.sliding_window_size * 2) + 100