gistfile1.py

#read all files, concat
from pathlib import Path
import pandas as pd
pathlist = Path('./Reports_Base').glob('*.tsv')
df_array = []
for path in pathlist:
    df = pd.read_csv(path, sep='\t', encoding='iso-8859-1')
    df_array.append(df)

df = pd.concat(df_array)

#rename columns to our column names
df = df.rename(columns={
    'Patient_Sex': 'gender',
    'Pacient_Age_Anonym': 'age',
    'Exam_Data': 'exam_date',
    'Modality_PACS': 'modality_pacs',
    'Exams_Description_PACS' : 'orig_exam_description',
    'Exams_Body_Part' : 'orig_body_part',
    'Modality_FIDI': 'modality_pacs_fidi', # ???
    'Exams_Description_FIDI' : 'exam_desc_fidi',
    'Flag_Bedridden' : 'is_bedridden',
    'REPORT' : 'report_text',
})