mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +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
9 lines
347 B
Python
9 lines
347 B
Python
import pandas as pd
|
|
from sklearn.decomposition import PCA
|
|
|
|
def reduce_dimensionality(X: pd.DataFrame, no_of_compoments: int) -> pd.DataFrame:
|
|
pca = PCA(n_components= no_of_compoments)
|
|
result = pd.DataFrame(pca.fit_transform(X), index= X.index)
|
|
result.columns = ['PCA_' + str(i) for i in range(1, no_of_compoments+1)]
|
|
return result
|