mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-05 15:17:46 +00:00
Mark Aron Szulyovszky
b1c04afb13
* refactor(Naming): use `primary_models` & `meta_labeling_models` * refactor(Naming): using primary * meta_labeling across config and in pipeline * feat(Pipeline): added back Ensemble models * fix(Pipeline): compiler error * fix(Config): typo * chore(Pipeline): removed unused averaging step * revert the changes in discretizing * chore(Pipeline): remove sharpe improvement logging * fix(Pipeline): ensemble predictions should be a pd.Series instead of a DataFrame * fix(Pipeline): discard unnecessary ensemble_probabilities * fix(Pipeline): fixes regarding various meta-labeling ensemble bugs * fix(Reporting): use the new naming convention * fix(Reporting): use the right variable * feat(Sweep): new sweep for ensemble models * fix(Sweep): config reference * fix(Config): simplified dev config * fix(Models): use the faster LR model * fix(Models): use LGBM in the meta-labeling model for speed * fix(Selection): always use the first model for feature selection, commented out caching from select_features() as it's close to redundant in terms of speed
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import os
|
|
import string
|
|
import random
|
|
from typing import Union
|
|
|
|
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('.')]
|
|
|
|
def get_first_valid_return_index(series: pd.Series) -> int:
|
|
double_nested_results = np.where(np.logical_and(series != 0, np.logical_not(pd.isna(series))))
|
|
if len(double_nested_results) == 0:
|
|
return 0
|
|
nested_result = double_nested_results[0]
|
|
if len(nested_result) == 0:
|
|
return 0
|
|
return nested_result[0]
|
|
|
|
def flatten(list_of_lists: list) -> list:
|
|
return [item for sublist in list_of_lists for item in sublist]
|
|
|
|
def weighted_average(df: pd.DataFrame, weights_source: str) -> pd.Series:
|
|
if df.shape[1] == 0:
|
|
return df
|
|
mean_df = df.iloc[:,0]
|
|
weights = df.loc[weights_source]
|
|
|
|
for i, row in df.iterrows():
|
|
if i == weights_source: continue
|
|
mean_df.loc[i] = (row * weights).sum() / df.loc[weights_source].sum()
|
|
|
|
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:
|
|
df = df.drop(column, axis=1)
|
|
return df
|
|
|
|
def random_string(n: int) -> str:
|
|
return ''.join(random.choices(string.ascii_uppercase + string.digits, k=n))
|
|
|
|
def equal_except_nan(row: pd.Series):
|
|
if np.isnan(row.iloc[0]) or np.isnan(row.iloc[1]):
|
|
return np.nan
|
|
if row.iloc[0] == row.iloc[1]:
|
|
return 1.
|
|
else:
|
|
return 0.
|
|
|
|
def drop_until_first_valid_index(df: pd.DataFrame, series: pd.Series) -> tuple[pd.DataFrame, pd.Series]:
|
|
first_valid_index = max(get_first_valid_return_index(df.iloc[:,0]), get_first_valid_return_index(series))
|
|
return df.iloc[first_valid_index:], series.iloc[first_valid_index:] |