Calcium_Model/statistical_filter.py

import h5py
import os
import pandas as pd

h5_file = 'ltcc_current.h5'

sobiv_eid_list = []
ttx_eid_list = []
teised_eid_list = []

with h5py.File(h5_file, 'r') as h5_file:

    for eid in h5_file.keys():
        if 'tag' in h5_file[eid].attrs:
            tag_val = h5_file[eid].attrs['tag']

            if isinstance(tag_val, bytes):
                tag_val = tag_val.decode('utf-8')

        puhas_eid = eid.replace(" ", "_").replace(":", "-")
        fit_result_eid = "fit_results_" + puhas_eid

        if tag_val == 'iso':
            sobiv_eid_list.append(fit_result_eid)
        elif tag_val == 'ttx':
            ttx_eid_list.append(fit_result_eid)
        else:
            teised_eid_list.append(fit_result_eid)

file = 'ltcc_current.h5'

with h5py.File(file, 'r') as h5_file:
    for eid in h5_file.keys():
        puhastatud_eid = eid.replace(" ", "_").replace(":", "-")

        atribuudid = h5_file[eid].attrs
        sex = atribuudid.get('sex')
        spid = atribuudid.get('spid')

        csv_file_name = f"fit_results_{puhastatud_eid}.csv"

        if os.path.exists(csv_file_name):
            df = pd.read_csv(csv_file_name)

            df['sex'] = sex
            df['spid'] = spid.replace("Mouse AGAT", "")
            df['eid'] = eid
            df.to_csv(csv_file_name, index=False)

for fail in os.listdir():
    if fail.endswith('.csv'):

        eksperiment_id = fail.replace(".csv", "")

        if eksperiment_id in sobiv_eid_list:

            df = pd.read_csv(fail)
            df['tag'] = 'iso'
            df.to_csv(fail, index=False)

        elif eksperiment_id in ttx_eid_list:

            df = pd.read_csv(fail)
            df['tag'] = 'ttx'
            df.to_csv(fail, index=False)

        else:

            df = pd.read_csv(fail)
            df['tag'] = 'teised'
            df.to_csv(fail, index=False)

comb_df = pd.DataFrame()

for filename in os.listdir():

    if filename.endswith('.csv'):
        df = pd.read_csv(filename)

        if 'tag' in df.columns and df['tag'].isin(['iso', 'ttx']).all():

            comb_df = pd.concat([comb_df, df], ignore_index=True)

print(comb_df)