13hannes11/UU_NCML_Project
1
0
Fork 0
mirror of https://github.com/13hannes11/UU_NCML_Project.git synced 2024-09-03 20:50:59 +02:00
Code Issues Projects Releases Wiki Activity

improve convert to csv and copy title_file

Browse Source
This commit is contained in:
Hannes Kuchelmeister
2021-04-26 18:05:01 +02:00
parent 5a735427d3
commit 2998717cb4
1 changed files with 21 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
convert_to_csv_de.py
View File

@@ -1,15 +1,29 @@
import pandas as pd
import os
# Convert data to csv
base_dir = "./de/"
out_dir = "csv/"
in_dir = "input/"
title_file = "filename_to_titles.csv"
out_dir = "csv"
if not os.path.exists(base_dir + out_dir):
os.makedirs(base_dir + out_dir)
for dirname, _, filenames in os.walk(base_dir + 'input'):
if not os.path.exists(os.path.join(base_dir, out_dir)):
os.makedirs(os.path.join(base_dir, out_dir))
# Copy titles file and replace file endings
print(f'Copying Title File')
with open(os.path.join(base_dir, in_dir, title_file), 'r') as file:
file_content = file.read()
file_content = file_content.replace('.xlsx', '.csv')
with open(os.path.join(base_dir, out_dir, title_file), 'w') as file:
file.write(file_content)
# Convert xlsx files to csv
for dirname, _, filenames in os.walk(os.path.join(base_dir, in_dir)):
for filename in filenames:
read_file = pd.read_excel (os.path.join(dirname, filename))
read_file.to_csv (os.path.join(base_dir + out_dir, filename.split(".", 1)[0] + ".csv"), index = None, header=True)
if filename != title_file:
print(f'Reading {filename}')
read_file = pd.read_excel (os.path.join(dirname, filename))
print(f'Saving {filename}')
read_file.to_csv (os.path.join(base_dir, out_dir, filename.split(".", 1)[0] + ".csv"), index = None, header=True)