Skip to content

Reuse of genePT_w_emebed where genePT_s_emebed should be used #10

@jeremyadamsfisher

Description

@jeremyadamsfisher

In block 36 of aorta_data_analysis.ipynb, it seems that genePT_s_emebed is not used and genePT_w_emebed is re-used inappropriately

# Split the data into training and test sets (80/20)
genePT_s_emebed = sampled_cell_aorta_gpt[np.where(sampled_adata.obs.celltype!='Unknown')[0]]
y_celltype_remove_unknown = sampled_adata.obs.celltype[np.where(sampled_adata.obs.celltype!='Unknown')[0]]
#                                                                               vvvvvvvvvvvvvvv
genePT_s_emebed_train, genePT_s_emebed_test, y_train, y_test = train_test_split(genePT_w_emebed, 
                                                    y_celltype_remove_unknown,
                                                    test_size=0.20, random_state=2023)

It seems this code wasn't actually run, because the notebook fails unless I substitute genePT_w_emebed with genePT_s_emebed.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions