mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Mark Aron Szulyovszky
cc70d3f907
* feat(Selection): added prototype feature selection python script * feat(Utils): added some helpers for the future from Advances in Financial ML book * feat(Selection): added RFECV * feat(Selection): added configurable feature selection step into pipeline * feat(Config): added level_1 & level_2 default config, PCA before feature selection process starts * feat(Selection): added backup feature selector models if current one can't output feature importance, removed unnecessary array for level-2 models * fix(Training): deal with zero first value coming out of static models * feat(Sweep): added feature selection sweep * fix(Sweep): config problem * fix(Sweep): config * chore(Utils): removed unnecessary purged k-fold crossval class * feat(Config): added dimensionality_reduction as a separate flag * fix(Sweep): config updated * fix(Sweep): sweep name * chore(Config): updated level_2 config to the best performing configuation
29 lines
875 B
Python
29 lines
875 B
Python
from typing import Literal
|
|
import pandas as pd
|
|
import numpy as np
|
|
|
|
def get_first_valid_return_index(series: pd.Series) -> int:
|
|
double_nested_results = np.where(np.logical_and(series != 0, np.logical_not(np.isnan(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.DataFrame:
|
|
if df.shape[0] == 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
|
|
|