Mercurial > repos > siwaa > carboseq_s

comparison csopraSplitInput.py @ 5:3e7978af2ba2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
author siwaa
date Wed, 28 Aug 2024 14:53:30 +0000
parents
children 20886bc40659
comparison
equal deleted inserted replaced
4:a069fc43b0b1 5:3e7978af2ba2
1 import pandas as pd
2 import os
3 import shutil
4 import math
5 import sys
6
7 def split_csv(input_folder, output_folder, max_chunck_size):
8 unit_path = input_folder + "/units.csv"
9 soil_path = input_folder + "/soil.csv"
10 crop_path = input_folder + "/crop.csv"
11
12 os.mkdir(output_folder)
13
14 dfs = pd.read_csv(soil_path)
15 dfc = pd.read_csv(crop_path)
16
17 max_ID = dfs.loc[dfs['ID'].idxmax()]['ID']
18
19 step = max_chunck_size
20
21 nb_split = math.ceil(max_ID / max_chunck_size)
22
23 print(max_ID)
24
25 print(nb_split)
26
27 for i in range(1,nb_split + 1):
28
29 dfSplit = pd.DataFrame()
30 dfSplit = dfs.loc[((dfs['ID'] >= (((i-1) * step)) + 1) & (dfs['ID'] <= ((((i-1) * step)) + step )))]
31
32 dfcSplit = pd.DataFrame()
33 dfcSplit = dfc.loc[((dfc['ID'] >= (((i-1) * step)) + 1) & (dfc['ID'] <= ((((i-1) * step)) + step )))]
34
35 os.mkdir(os.path.join(output_folder, f"{input_folder}_{i}"))
36 shutil.copy(unit_path, os.path.join(output_folder, f"{input_folder}_{i}"))
37 dfSplit.to_csv(os.path.join(output_folder, f"{input_folder}_{i}", "soil.csv"), index=False)
38 dfcSplit.to_csv(os.path.join(output_folder, f"{input_folder}_{i}", "crop.csv"), index=False)
39 shutil.make_archive( os.path.join(output_folder,f"{input_folder}_{i}"), 'zip', os.path.join(output_folder, f"{input_folder}_{i}"))
40
41 # Example usage
42 input_folder = "input"
43 output_folder = "outputs"
44
45 input_file = sys.argv[1]
46 max_chunck_size = int(sys.argv[2])
47
48 shutil.unpack_archive(input_file, input_folder, 'zip')
49
50 split_csv(input_folder, output_folder, max_chunck_size)