def load_data(params, seed):
drop_cols = ['case_id']
onehot_cols = ['cancer_type']
y_cols = ['cancer_type']
if params['use_landmark_genes']:
lincs_file = 'lincs1000.tsv'
lincs_path = p1_common.get_p1_file(url_p1b1 + lincs_file)
df_l1000 = pd.read_csv(lincs_path, sep='\t')
x_cols = df_l1000['gdc'].tolist()
drop_cols = None
else:
x_cols = None
train_path = p1_common.get_p1_file(url_p1b1 + file_train)
test_path = p1_common.get_p1_file(url_p1b1 + file_test)
return p1_common.load_csv_data(train_path,
test_path,
x_cols=x_cols,
y_cols=y_cols,
drop_cols=drop_cols,
onehot_cols=onehot_cols,
n_cols=params['feature_subsample'],
shuffle=params['shuffle'],
scaling=params['scaling'],
dtype=params['datatype'],
validation_split=params['validation_split'],
return_dataframe=False,
return_header=True,
seed=seed)
def load_data_orig(params, seed):
if params['with_type']:
drop_cols = ['case_id']
onehot_cols = ['cancer_type']
else:
drop_cols = ['case_id', 'cancer_type']
onehot_cols = None
if params['use_landmark_genes']:
lincs_file = 'lincs1000.tsv'
lincs_path = p1_common.get_p1_file(url_p1b1 + lincs_file)
df_l1000 = pd.read_csv(lincs_path, sep='\t')
usecols = df_l1000['gdc']
drop_cols = None
else:
usecols = None
return p1_common.load_X_data(url_p1b1,
file_train,
file_test,
drop_cols=drop_cols,
onehot_cols=onehot_cols,
usecols=usecols,
n_cols=params['feature_subsample'],
shuffle=params['shuffle'],
scaling=params['scaling'],
validation_split=params['validation_split'],
dtype=params['datatype'],
seed=seed)
def stage_data():
server = 'http://ftp.mcs.anl.gov/pub/candle/public/benchmarks/P1B3/'
cell_expr_path = p1_common.get_p1_file(server+'P1B3_cellline_expressions.tsv')
cell_mrna_path = p1_common.get_p1_file(server+'P1B3_cellline_mirna.tsv')
cell_prot_path = p1_common.get_p1_file(server+'P1B3_cellline_proteome.tsv')
cell_kino_path = p1_common.get_p1_file(server+'P1B3_cellline_kinome.tsv')
drug_desc_path = p1_common.get_p1_file(server+'P1B3_drug_descriptors.tsv')
drug_auen_path = p1_common.get_p1_file(server+'P1B3_drug_latent.csv')
dose_resp_path = p1_common.get_p1_file(server+'P1B3_dose_response.csv')
test_cell_path = p1_common.get_p1_file(server+'P1B3_test_celllines.txt')
test_drug_path = p1_common.get_p1_file(server+'P1B3_test_drugs.txt')
return(cell_expr_path, cell_mrna_path, cell_prot_path, cell_kino_path,
drug_desc_path, drug_auen_path, dose_resp_path, test_cell_path,
test_drug_path)
def get_file(url):
return p1_common.get_p1_file(url)