def gif_lobes_from_excel_sheets():
"""
sort the gif parcellations as per excel gif sheet lobes.
e.g. GIF FL = GIF Frontal Lobe - has a list of gif parcellations
which we want to see in 3D slicer, using the GUI
"""
_, _, excel_path, _ = file_paths()
GIF_SHEET_NAMES = gif_sheet_names()
lobes_mapping = {}
for gif_lobe in GIF_SHEET_NAMES:
gif_parcellations = pd.read_excel(
excel_path,
header=None,
usecols="A:B",
sheet_name=gif_lobe,
engine="openpyxl",
)
gif_parcellations.dropna(axis=0, how='any', inplace=True)
gif_parcellations.dropna(axis=1, how='all', inplace=True)
gifs = gif_parcellations.astype({1: 'uint16'})
gifs = gifs.iloc[:, 1]
lobes_mapping[gif_lobe] = gifs.values
return lobes_mapping
def use_SemioBrainBeta_notDummyData(self):
"""
factor function.
Uses the beta version callled syst_review_single_table.
Note the arguments for MEGA_ANALYSIS differ for the beta version.
"""
# load the Beta SemioBrain Database:
repo_dir, resources_dir, SemioBrainBeta_data_path, SemioDict_path = \
file_paths(dummy_data=False, Beta=True)
SemioBrainBeta_df, _, _, _, _, _, _ = MEGA_ANALYSIS(
excel_data=SemioBrainBeta_data_path,
n_rows=2500,
usecols="A:DH",
header=1,
exclude_data=False,
plot=True,
)
return SemioBrainBeta_df
import unittest
import pandas as pd
from mega_analysis.crosstab.file_paths import file_paths
from mega_analysis.crosstab.gif_sheet_names import gif_sheet_names
from mega_analysis.crosstab.mega_analysis.exclusions import exclusions
from mega_analysis.crosstab.mega_analysis.MEGA_ANALYSIS import MEGA_ANALYSIS
from mega_analysis.semiology import ( # semiology_dict_path,
QUERY_SEMIOLOGY, Laterality, Semiology, gif_lat_file, map_df_dict)
from mega_analysis.crosstab.hierarchy_class import Hierarchy
# define paths: note dummy data has a tab called test_counts
# a hand crafted test fixture count
repo_dir, resources_dir, dummy_data_path, dummy_semiology_dict_path = \
file_paths(dummy_data=True)
# Define the gif sheet names
gif_sheet_names = gif_sheet_names()
# Read Excel file only three times at initialisation
test_df, _, _, _, _, _, _ = MEGA_ANALYSIS(
excel_data=dummy_data_path,
n_rows=100,
usecols="A:DH",
header=1,
exclude_data=False,
plot=True,
)
map_df_dict = pd.read_excel(
def summary_semio_loc_df_from_scripts(normalise=True):
"""
Lots of copy pasting from scripts/figures.py in kd_figures-v3 branch.
returns query_results which is a nested dictionary
full
spontaneous
topology
{semiologies}
query_inspection
num_query_loc
num_query_lat
"""
# Define paths
repo_dir, resources_dir, excel_path, semiology_dict_path = file_paths()
Semio2Brain_Database = excel_path
with open(semiology_dict_path) as f:
SemioDict = yaml.load(f, Loader=yaml.FullLoader)
region_names = all_localisations()
semiology_list = list(recursive_items(SemioDict))
(original_df,
df_ground_truth, df_study_type,
num_database_articles, num_database_patients, num_database_lat, num_database_loc) = \
MEGA_ANALYSIS(Semio2Brain_Database,
exclude_data=True)
# -----------------------------------
redistribution_spec = {
'FT': ['FL', 'INSULA', 'Lateral Temporal', 'TL'],
'TO': ['Lateral Temporal', 'TL', 'OL'],
'TP': ['Lateral Temporal', 'TL', 'PL'],
'FTP': ['INSULA', 'Lateral Temporal', 'TL', 'FL', 'PL'],
'TPO Junction': ['Lateral Temporal', 'TL', 'PL', 'OL'],
'PO': ['PL', 'OL'],
'FP': ['FL', 'PL'],
'Perisylvian': ['INSULA', 'Lateral Temporal', 'TL', 'FL', 'PL'],
'Sub-Callosal Cortex': ['Ant Cing (frontal, genu)', 'CING']
}
redistributed_df = copy.deepcopy(original_df)
# probably not needed as used exclude_data True when calling M_A
redistributed_df = exclude_postictals(redistributed_df)
for from_region, destination_regions in redistribution_spec.items():
for destination in destination_regions:
redistributed_df[destination] = original_df[destination].fillna(
0) + original_df[from_region].fillna(0)
redistributed_df = redistributed_df.drop(redistribution_spec.keys(),
'columns')
# -----------------------------------
# region_names_re = region_names
# region_names_re['top_level'] = ['TL',
# 'FL',
# 'CING',
# 'PL',
# 'OL',
# 'INSULA',
# 'Hypothalamus',
# 'Cerebellum', ]
# region_names_re['top_level_all_other'] = ['Cerebellum']
df = copy.deepcopy(redistributed_df)
df_SS = exclude_ET(df)
df_SS = exclude_cortical_stimulation(df_SS)
df_TS = exclude_spontaneous_semiology(df)
all_dfs = {
'full': df,
'spontaneous': df_SS,
'topology': df_TS,
}
query_results = {}
for key, df in all_dfs.items():
if normalise:
df, _ = normalise_top_level_localisation_cols(df, Bayesian=True)
query_results[key] = query_semiology_wrapper_from_scripts(
df, semiology_list, semiology_dict_path)
return query_results
