adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #7243 from lolongcovas/newbranch_test

Browse Source 
Improve PCA and pairwise distance calcs
This commit is contained in:
Matthias 2022-08-20 08:13:40 +02:00 committed by GitHub
commit 7b8b73e651
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
freqtrade/freqai/data_kitchen.py
View File

@ -454,7 +454,6 @@ class FreqaiDataKitchen:
logger.info("reduced feature dimension by %s", n_components - n_keep_components) logger.info("reduced feature dimension by %s", n_components - n_keep_components)
logger.info("explained variance %f", np.sum(pca2.explained_variance_ratio_)) logger.info("explained variance %f", np.sum(pca2.explained_variance_ratio_))
train_components = pca2.transform(self.data_dictionary["train_features"]) train_components = pca2.transform(self.data_dictionary["train_features"])
test_components = pca2.transform(self.data_dictionary["test_features"])
self.data_dictionary["train_features"] = pd.DataFrame( self.data_dictionary["train_features"] = pd.DataFrame(
data=train_components, data=train_components,
@ -468,6 +467,7 @@ class FreqaiDataKitchen:
self.training_features_list = self.data_dictionary["train_features"].columns self.training_features_list = self.data_dictionary["train_features"].columns
if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0: if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
test_components = pca2.transform(self.data_dictionary["test_features"])
self.data_dictionary["test_features"] = pd.DataFrame( self.data_dictionary["test_features"] = pd.DataFrame(
data=test_components, data=test_components,
columns=["PC" + str(i) for i in range(0, n_keep_components)], columns=["PC" + str(i) for i in range(0, n_keep_components)],
@ -506,7 +506,10 @@ class FreqaiDataKitchen:
# logger.info("computing average mean distance for all training points") # logger.info("computing average mean distance for all training points")
pairwise = pairwise_distances( pairwise = pairwise_distances(
self.data_dictionary["train_features"], n_jobs=self.thread_count) self.data_dictionary["train_features"], n_jobs=self.thread_count)
avg_mean_dist = pairwise.mean(axis=1).mean() # remove the diagonal distances which are itself distances ~0
np.fill_diagonal(pairwise, np.NaN)
pairwise = pairwise.reshape(-1, 1)
avg_mean_dist = pairwise[~np.isnan(pairwise)].mean()
return avg_mean_dist return avg_mean_dist