annotate csopraSplitInput.py @ 11:097985b1b7c6 draft

"planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/f3192a3a79e9265b088c9c126972718cfb375643/toos/CarboSeqSimulator commit f3192a3a79e9265b088c9c126972718cfb375643-dirty"
author siwaa
date Thu, 19 Sep 2024 11:11:46 +0000
parents 20886bc40659
children e455667fe22f
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
1 import pandas as pd
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
2 import os
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
3 import shutil
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
4 import math
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
5 import sys
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
6
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
7 def split_csv(input_folder, output_folder, max_chunck_size):
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
8 unit_path = input_folder + "/units.csv"
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
9 soil_path = input_folder + "/soil.csv"
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
10 crop_path = input_folder + "/crop.csv"
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
11
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
12 os.mkdir(output_folder)
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
13
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
14 dfs = pd.read_csv(soil_path)
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
15 dfc = pd.read_csv(crop_path)
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
16
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
17 dfs['ID'] = dfs['ID'].astype('int')
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
18 dfc['ID'] = dfc['ID'].astype('int')
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
19
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
20 IDs = dfs['ID'].unique()
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
21
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
22 max_ID = len(IDs)
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
23
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
24 step = max_chunck_size
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
25
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
26 nb_split = math.ceil(max_ID / max_chunck_size)
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
27
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
28 for i in range(1, nb_split + 1):
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
29
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
30 firstID = IDs[(i-1) * step]
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
31 lastID = IDs[min((i * step) - 1 , max_ID - 1)]
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
32
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
33 splitIDs = IDs[(i-1) * step : min((i * step) , max_ID)]
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
34
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
35
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
36 dfSplit = pd.DataFrame()
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
37 dfSplit = dfs[dfs['ID'].isin(splitIDs)]
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
38
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
39 dfcSplit = pd.DataFrame()
10
20886bc40659 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf/toos/CarboSeqSimulator commit b1cafd3eb61b631ee0b1f8f6c5ef2f9a0e2b4ccf-dirty"
siwaa
parents: 5
diff changeset
40 dfcSplit = dfc[dfc['ID'].isin(splitIDs)]
5
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
41
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
42 os.mkdir(os.path.join(output_folder, f"{input_folder}_{i}"))
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
43 shutil.copy(unit_path, os.path.join(output_folder, f"{input_folder}_{i}"))
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
44 dfSplit.to_csv(os.path.join(output_folder, f"{input_folder}_{i}", "soil.csv"), index=False)
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
45 dfcSplit.to_csv(os.path.join(output_folder, f"{input_folder}_{i}", "crop.csv"), index=False)
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
46 shutil.make_archive( os.path.join(output_folder,f"{input_folder}_{i}"), 'zip', os.path.join(output_folder, f"{input_folder}_{i}"))
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
47
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
48 # Example usage
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
49 input_folder = "input"
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
50 output_folder = "outputs"
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
51
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
52 input_file = sys.argv[1]
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
53 max_chunck_size = int(sys.argv[2])
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
54
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
55 shutil.unpack_archive(input_file, input_folder, 'zip')
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
56
3e7978af2ba2 "planemo upload for repository https://forgemia.inra.fr/carboseq/record-projet-carboseq/-/tree/5f761ea7dab0a6f8c978cbbe4946e16edc6d032e/toos/CarboSeqSimulator commit 5f761ea7dab0a6f8c978cbbe4946e16edc6d032e-dirty"
siwaa
parents:
diff changeset
57 split_csv(input_folder, output_folder, max_chunck_size)