gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-14 19:38:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Events): added EventFilter, EventLabeller (#186)

Browse Source
This commit is contained in:
Mark Aron Szulyovszky
2022-01-26 23:22:43 +01:00
committed by GitHub
parent 1042c82333
commit 42a1bc59cb
65 changed files with 759 additions and 276571 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/helpers.py
+1 -9
View File
@@ -3,9 +3,6 @@ import numpy as np
import os
import string
import random
from typing import Union
from config.config import Config
def get_files_from_dir(path: str) -> list[str]:
return [f for f in os.listdir(path) if os.path.isfile(os.path.join(path,f)) and not f.startswith('.')]
@@ -19,10 +16,7 @@ def get_first_valid_return_index(series: pd.Series) -> int:
return 0
return nested_result[0]
def has_enough_samples_to_train(X: pd.DataFrame, y: pd.Series, config: Config) -> bool:
first_valid_index = get_first_valid_return_index(X.iloc[:,0])
samples_to_train = len(y) - first_valid_index
return samples_to_train > config.sliding_window_size_base + config.sliding_window_size_meta_labeling + 100
def flatten(list_of_lists: list) -> list:
return [item for sublist in list_of_lists for item in sublist]
@@ -39,8 +33,6 @@ def weighted_average(df: pd.DataFrame, weights_source: str) -> pd.Series:
return mean_df
def deduplicate_indexes(df: pd.DataFrame) -> pd.DataFrame: return df[~df.index.duplicated(keep='last')]
def drop_columns_if_exist(df: pd.DataFrame, columns: list) -> pd.DataFrame:
for column in columns:
if column in df.columns: