Adrasteia

In [2]:

    

import dask


    

In [1]:

    

from distributed import Client


    

In [3]:

    

client = Client()


    

In [7]:

    

client.close()


    

In [1]:

    

#client.scheduler_info()


    

In [4]:

    

import dask.dataframe as dd


    

In [3]:

    

%%time
df = dd.read_csv('../data/TgasSource_000-000-*.csv')


    

    




CPU times: user 163 ms, sys: 26.8 ms, total: 189 ms
Wall time: 229 ms

In [4]:

    

df.head()


    

    
Out[4]:







  

    

      

      
hip
      
tycho2_id
      
solution_id
      
source_id
      
random_index
      
ref_epoch
      
ra
      
ra_error
      
dec
      
dec_error
      
...
      
scan_direction_mean_k4
      
phot_g_n_obs
      
phot_g_mean_flux
      
phot_g_mean_flux_error
      
phot_g_mean_mag
      
phot_variable_flag
      
l
      
b
      
ecl_lon
      
ecl_lat
    
  
  

    

      
0
      
13989.0
      
NaN
      
1635378410781933568
      
7627862074752
      
243619
      
2015.0
      
45.034330
      
0.305989
      
0.235392
      
0.218802
      
...
      
26.201841
      
77
      
1.031233e+07
      
10577.365273
      
7.991378
      
NOT_AVAILABLE
      
176.740413
      
-48.714422
      
42.641825
      
-16.121052
    
    

      
1
      
NaN
      
55-28-1
      
1635378410781933568
      
9277129363072
      
487238
      
2015.0
      
45.165007
      
2.583882
      
0.200068
      
1.197789
      
...
      
22.890602
      
62
      
9.495646e+05
      
1140.173576
      
10.580959
      
NOT_AVAILABLE
      
176.916420
      
-48.645004
      
42.761180
      
-16.193033
    
    

      
2
      
NaN
      
55-1191-1
      
1635378410781933568
      
13297218905216
      
1948952
      
2015.0
      
45.086155
      
0.213836
      
0.248825
      
0.180326
      
...
      
26.715704
      
60
      
8.178376e+05
      
1827.383676
      
10.743102
      
NOT_AVAILABLE
      
176.780400
      
-48.667845
      
42.697502
      
-16.123363
    
    

      
3
      
NaN
      
55-624-1
      
1635378410781933568
      
13469017597184
      
102321
      
2015.0
      
45.066542
      
0.276039
      
0.248211
      
0.200958
      
...
      
25.878560
      
61
      
6.020535e+05
      
905.877286
      
11.075682
      
NOT_AVAILABLE
      
176.760412
      
-48.682365
      
42.677791
      
-16.118216
    
    

      
4
      
NaN
      
55-849-1
      
1635378410781933568
      
15736760328576
      
409284
      
2015.0
      
45.136038
      
0.170697
      
0.335044
      
0.170130
      
...
      
26.755468
      
96
      
1.388122e+06
      
2826.428866
      
10.168701
      
NOT_AVAILABLE
      
176.739184
      
-48.572035
      
42.773370
      
-16.055481
    
  

5 rows × 59 columns

In [7]:

    

df.phot_g_mean_mag.mean().compute()


    

    
Out[7]:





10.814073743893747