In [1]:

    

import sys
import pandas as pd
import numpy as np
import difflib
import gzip
from scipy import stats
import time
from implementations import all_implementations
from random import randint


    

In [2]:

    

ARR_SIZE = 20000
SORT_TRIALS = 40
random_arrays = []
for i in range(SORT_TRIALS):
    random_arrays.append(np.random.randint(0, ARR_SIZE, ARR_SIZE))
    
df_result = pd.DataFrame(np.nan, index=np.array(range(SORT_TRIALS)),columns = [fn.__name__ for fn in all_implementations])
df_result


    

    
Out[2]:






  

    

      

      
qs1
      
qs2
      
qs3
      
qs4
      
qs5
      
merge1
      
partition_sort
    
  
  

    

      
0
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
1
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
2
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
3
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
5
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
    
  

In [6]:

    

for sort in all_implementations:
    for i in range(SORT_TRIALS):
        st = time.time()
        res = sort(random_arrays[i])
        en = time.time()
        df_result.iloc[i][sort.__name__]=en-st
df_result.to_csv('data.csv', index=False)
df_result


    

    
Out[6]:






  

    

      

      
qs1
      
qs2
      
qs3
      
qs4
      
qs5
      
merge1
      
partition_sort
    
  
  

    

      
0
      
0.070015
      
0.086740
      
0.090054
      
0.080109
      
0.079434
      
0.103288
      
0.070164
    
    

      
1
      
0.060803
      
0.100727
      
0.105186
      
0.080522
      
0.082376
      
0.105341
      
0.069865
    
    

      
2
      
0.055306
      
0.093214
      
0.088574
      
0.075300
      
0.081900
      
0.118308
      
0.069995
    
    

      
3
      
0.058639
      
0.083317
      
0.090863
      
0.085878
      
0.087948
      
0.112951
      
0.072464
    
    

      
4
      
0.053843
      
0.086972
      
0.085555
      
0.080957
      
0.082159
      
0.105686
      
0.070707
    
    

      
5
      
0.054615
      
0.086939
      
0.088410
      
0.083436
      
0.080924
      
0.107570
      
0.088915
    
  

In [ ]:

    

def main():
    ARR_SIZE = 20000
    SORT_TRIALS = 40
    random_arrays = []
    for i in range(SORT_TRIALS):
        random_arrays.append(np.random.randint(0, ARR_SIZE, ARR_SIZE))
        
    df_result = pd.DataFrame(np.nan, index=np.array(range(SORT_TRIALS)),columns = [fn.__name__ for fn in all_implementations])
    
    for sort in all_implementations:
        for i in range(SORT_TRIALS):
            st = time.time()
            res = sort(random_arrays[i])
            en = time.time()
            df_result.iloc[i][sort.__name__]=en-st
            
    df_result.to_csv('data.csv', index=False)
if __name__ == '__main__':
    main()