import lib_data_operation as tfm_data
# Required libraries
import os
import numpy as np
import pandas as pd
import warnings
warnings.filterwarnings('ignore')
from sklearn.model_selection import LeavePGroupsOut
# IMPORTING REQUIRED DATASETS
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))
# DELETE UNUSED DATASET
del (df_weight_signaling)
del (df_weight_metabolic_signaling)
# DEFAULT VALUES
n_cells_out_list = [2, 4, 6, 8]
n_experiment_ = 20
# TARGET VARIABLE NAME
target_ = 'cell_type'
def def_get_n_psplits(X, y, groups, p, n):
for i_scaling in TYPE_OF_SCALING:
# THE LOCATION of THE RESULT of SCORE and MODEL
# path_hyperband_ = tfm_data.def_check_create_path('kt_result', '')
path_hyperband_ = tfm_data.def_check_create_path('kt_result', 'delete')
path_output_result = tfm_data.def_check_create_path(
'kt_result', 'design_no_co_' + str(i_scaling))
path_model = tfm_data.def_check_create_path(
'kt_result', 'models_no_co_' + str(i_scaling))
# LOADING REQUIRED DATASETS
df_weight_signaling, df_weight_metabolic_signaling = tfm_data.def_load_weight_pathways(
)
df_paper, 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=i_scaling,
retrieval=False)
df_weight_dense = pd.DataFrame(df_paper.columns[1:]).set_index('Sample')
for i in range(dense_layer):
df_weight_dense['dense' + str(i)] = 1.0
df_weight_paper_signaling_dense_pathway = df_weight_dense.merge(
pd.DataFrame(df_paper.columns[1:]).set_index('Sample').merge(
df_weight_signaling, left_index=True, right_index=True,
how='left').fillna(0),
left_index=True,
right_index=True,
how='inner')