Mercurial > repos > jay > pdaug_addclasslabel
annotate PDAUG_Merge_Dataframes/PDAUG_Merge_Dataframes.py @ 0:2df11ea23f10 draft
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
| author | jay | 
|---|---|
| date | Wed, 28 Oct 2020 02:36:27 +0000 | 
| parents | |
| children | 378a786e9236 | 
| rev | line source | 
|---|---|
| 
0
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
1 import glob | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
2 import pandas as pd | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
3 import sys | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
4 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
5 files = sys.argv[1] | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
6 out_file = sys.argv[2] | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
7 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
8 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
9 data_frame = pd.read_csv(files.split(',')[0],sep='\t') | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
10 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
11 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
12 for file in files.split(',')[1:]: | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
13 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
14 df1 = pd.read_csv(file,sep='\t') | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
15 data_frame = pd.concat([data_frame,df1]) | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
16 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
17 final_DF = data_frame.fillna(0) | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
18 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
19 final_DF.to_csv(out_file,sep="\t", index=False) | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
20 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
21 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
22 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
23 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
24 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
25 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
26 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
27 | 
| 
 
2df11ea23f10
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit a9bd83f6a1afa6338cb6e4358b63ebff5bed155e"
 
jay 
parents:  
diff
changeset
 | 
28 | 
