| 
            Last change
 on this file since adaf062 was             0a79fd9, checked in by Thierry Delisle <tdelisle@…>, 4 years ago           | 
        
        
          | 
             
Simple python tool to down sample data 
 
           | 
        
        
          
            
              - 
Property                 mode
 set to                 
100755
               
             
           | 
        
        
          | 
            File size:
            670 bytes
           | 
        
      
      
| Line |   | 
|---|
| 1 | #!/usr/bin/python3
 | 
|---|
| 2 | 
 | 
|---|
| 3 | import argparse, json, random, sys
 | 
|---|
| 4 | 
 | 
|---|
| 5 | parser = argparse.ArgumentParser()
 | 
|---|
| 6 | parser.add_argument('--infile', type=argparse.FileType('r'), default=sys.stdin)
 | 
|---|
| 7 | parser.add_argument('--outfile', type=argparse.FileType('w'), default=sys.stdout)
 | 
|---|
| 8 | 
 | 
|---|
| 9 | args = parser.parse_args()
 | 
|---|
| 10 | 
 | 
|---|
| 11 | data = json.load(args.infile)
 | 
|---|
| 12 | 
 | 
|---|
| 13 | 
 | 
|---|
| 14 | 
 | 
|---|
| 15 | print(len(data['values']))
 | 
|---|
| 16 | print(int(len(data['values']) / 1000))
 | 
|---|
| 17 | 
 | 
|---|
| 18 | sample = random.sample(data['values'], int(len(data['values']) / 1000))
 | 
|---|
| 19 | print(len(sample))
 | 
|---|
| 20 | 
 | 
|---|
| 21 | # Sort by timestamp (the second element)
 | 
|---|
| 22 | # take second element for sort
 | 
|---|
| 23 | def takeSecond(elem):
 | 
|---|
| 24 |     return elem[1]
 | 
|---|
| 25 | 
 | 
|---|
| 26 | sample.sort(key=takeSecond)
 | 
|---|
| 27 | 
 | 
|---|
| 28 | data['values'] = sample
 | 
|---|
| 29 | json.dump(data, args.outfile)
 | 
|---|
       
      
  Note:
 See   
TracBrowser
 for help on using the repository browser.