gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-22 15:28:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(Reporting): only report the last model's results, moved wandb-related functions to reporting (#69)

Browse Source 
* refactor(Reporting): only report the last model's results, moved wandb-related functions to `reporting`

* fix(Reporting): use .mean() on axis 1 to retain the metrics, fixed get_model_name()

* fix(Config): sweep file syntax

* fix(Config): changed hyperparameter search method to "bayes"

* chore(Sweep): adjusted sweep config based on the results we saw (removed Momentum as well)

* fix(Sweep): only use classification method for now, we're not yet prepared for regression
This commit is contained in:
Mark Aron Szulyovszky
2021-12-22 12:04:38 +01:00
committed by GitHub
parent cfc9529274
commit 25b64f5a3d
8 changed files with 78 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+7 -3
View File
@@ -1,9 +1,9 @@
from utils.load_data import load_data
import pandas as pd
from training.training import run_single_asset_trainig
from utils.launch_wandb import launch_wandb, seperate_configs
from reporting.wandb import launch_wandb, send_report_to_wandb, seperate_configs
from models.model_map import map_model_name_to_function
from default_config import get_default_config
from config import get_default_config, validate_config, get_model_name
def setup_pipeline(project_name:str, with_wandb: bool, sweep: bool):
model_config, training_config, data_config = get_default_config()
@@ -17,8 +17,10 @@ def setup_pipeline(project_name:str, with_wandb: bool, sweep: bool):
pipeline(project_name, wandb, sweep, model_config, training_config, data_config)
def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_config:dict, data_config:dict ):
results = pd.DataFrame()
validate_config(model_config, training_config, data_config)
for asset in data_config['all_assets']:
print('--------\nPredicting: ', asset)
@@ -72,7 +74,9 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
results = pd.concat([results, ensemble_result], axis=1)
all_predictions = pd.concat([all_predictions, ensemble_preds], axis=1)
# 4. Save & report results
send_report_to_wandb(results, wandb, project_name, get_model_name(model_config))
results.to_csv('results.csv')
level1_columns = results[[column for column in results.columns if 'Ensemble' not in column]]