mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
10 lines
320 B
Python
10 lines
320 B
Python
from hashlib import sha256
|
|
import pandas as pd
|
|
|
|
def hash_df(df: pd.DataFrame) -> str:
|
|
s = str(df.columns) + str(df.index) + str(df.values)
|
|
return sha256(s.encode()).hexdigest()
|
|
|
|
def hash_series(df: pd.Series) -> str:
|
|
s = str(df.name) + str(df.index) + str(df.values)
|
|
return sha256(s.encode()).hexdigest() |