mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-31 20:57:51 +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
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
import pandas as pd
|
|
from typing import Optional
|
|
from utils.helpers import weighted_average
|
|
|
|
def launch_wandb(project_name:str, default_config:dict, sweep:bool=False):
|
|
from wandb_setup import get_wandb
|
|
wandb = get_wandb()
|
|
|
|
if wandb is None:
|
|
return None
|
|
elif sweep:
|
|
wandb.init(project=project_name, config = default_config)
|
|
return wandb
|
|
else:
|
|
wandb.init(project=project_name, config = default_config, reinit=True)
|
|
return wandb
|
|
|
|
|
|
def register_config_with_wandb(wandb: Optional[object], model_config:dict, training_config:dict, data_config:dict):
|
|
if wandb is None: return
|
|
|
|
config: dict = wandb.config
|
|
|
|
for k in training_config:
|
|
training_config[k] = config[k]
|
|
for k in model_config:
|
|
model_config[k] = config[k]
|
|
for k in data_config:
|
|
data_config[k] = config[k]
|
|
|
|
|
|
def send_report_to_wandb(results: pd.DataFrame, wandb:Optional[object], project_name: str, model_name: str):
|
|
if wandb is None: return
|
|
|
|
run = wandb.init(project=project_name, config={"model_type": model_name}, reinit=True)
|
|
wandb.run.name = model_name+ "-" + wandb.run.id
|
|
wandb.run.save()
|
|
|
|
mean_results = weighted_average(results, 'no_of_samples')
|
|
for key, value in mean_results.iteritems():
|
|
run.log({"model_type": model_name, key: value })
|
|
|
|
run.finish()
|
|
|
|
|
|
|