df_weight_signaling, df_weight_metabolic_signaling = tfm_data.def_load_weight_pathways(
)
df_paper_9437, df_signaling, df_metabolic_signaling = tfm_data.def_load_dataset(
['cell_type'] + list(df_weight_signaling.index.values),
['cell_type'] + list(df_weight_metabolic_signaling.index.values),
row_scaling=TYPE_OF_SCALING)
df_weight_ppi_tf_signaling, df_weight_ppi_tf_metabolic_signaling = tfm_data.def_load_weight_ppi_tf(
list(df_weight_signaling.index.values),
list(df_weight_metabolic_signaling.index.values))
df_weight_both = pd.concat(
[df_weight_ppi_tf_metabolic_signaling, df_weight_metabolic_signaling],
axis=1)
print('df_weight_both shape , ', df_weight_both.shape)
print('Normalization metabolic and signaling data')
df_ss = tfm_data.def_dataframe_normalize(df_metabolic_signaling,
StandardScaler(), 'cell_type')
# DELETE UNUSED DATASET
del (df_paper_9437)
del (df_signaling)
del (df_weight_ppi_tf_signaling)
del (df_weight_signaling)
del (df_metabolic_signaling)
del (df_weight_ppi_tf_metabolic_signaling)
# METABOLIC and SIGNALING PATHWAY
# EXPERIMENT DATASETS
print('the index of experiment dataset, ', list_experiments)
for i_experiment in list_experiments:
df_weight_paper_signaling_dense_pathway.shape)
df_weight_paper_metabolic_signaling_dense_pathway = df_weight_dense.merge(
pd.DataFrame(df_paper.columns[1:]).set_index('Sample').merge(
df_weight_metabolic_signaling,
left_index=True,
right_index=True,
how='left').fillna(0),
left_index=True,
right_index=True,
how='inner')
print('df_weight_paper_metabolic_signaling_dense_pathway shape , ',
df_weight_paper_metabolic_signaling_dense_pathway.shape)
print('Normalization paper data - 9437 genes')
df_ss = tfm_data.def_dataframe_normalize(df_paper, StandardScaler(),
'cell_type')
# df_mms = tfm_data.def_dataframe_normalize(df_paper, MinMaxScaler(), 'cell_type')
# # ORIGINAL DATASET (9437 genes)
# EXPERIMENT DATASETS
array_train_X_ss, array_train_y_ss = [], []
array_test_X_ss, array_test_y_ss = [], []
X_train_ss, X_test_ss, y_train_ss, y_test_ss = tfm_data.def_split_train_test_by_index(
dataframe_=df_ss,
train_index_=df_ss.index,
test_index_=[0],
target_feature_=target_)
array_train_X_ss.append(np.array(X_train_ss))