mirror of
https://github.com/SheffieldML/GPy.git
synced 2026-05-01 07:46:22 +02:00
re-doing the lee dataset
This commit is contained in:
parent
0812a0e15c
commit
322d0d6d01
1 changed files with 7 additions and 6 deletions
|
|
@ -405,12 +405,13 @@ def lee_yeast_ChIP(data_set='lee_yeast_ChIP'):
|
|||
import zipfile
|
||||
dir_path = os.path.join(data_path, data_set)
|
||||
filename = os.path.join(dir_path, 'binding_by_gene.tsv')
|
||||
X = read_csv(filename, header=1, index_col=0, sep='\t')
|
||||
transcription_factors = [col for col in X.columns if col[:7] != 'Unnamed']
|
||||
annotations = X[['Unnamed: 1', 'Unnamed: 2', 'Unnamed: 3']]
|
||||
X = X[transcription_factors]
|
||||
return data_details_return({'annotations' : annotations, 'X' : X, 'transcription_factors': transcription_factors}, data_set)
|
||||
|
||||
S = read_csv(filename, header=1, index_col=0, sep='\t')
|
||||
transcription_factors = [col for col in S.columns if col[:7] != 'Unnamed']
|
||||
annotations = S[['Unnamed: 1', 'Unnamed: 2', 'Unnamed: 3']]
|
||||
S = S[transcription_factors]
|
||||
return data_details_return({'annotations' : annotations, 'Y' : S, 'transcription_factors': transcription_factors}, data_set)
|
||||
|
||||
|
||||
|
||||
def fruitfly_tomancak(data_set='fruitfly_tomancak', gene_number=None):
|
||||
if not data_available(data_set):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue