Your results won't look exactly like this notebook, as I did slightly different processing locally.

In [1]:

import dask.dataframe as dd
from dask.distributed import Client, progress
Client()

Out[1]:

Client

Scheduler: tcp://127.0.0.1:35429
Dashboard: http://127.0.0.1:8787/status

Cluster

Workers: 4
Cores: 12
Memory: 33.35 GB

In [3]:

df = dd.read_parquet('/home/bird/Data/tt/full/overscripted.parquet/', columns=('argument_0', 'symbol', 'operation'))
df.head()

Out[3]:

	symbol	operation
0	window.navigator.userAgent	get
1	window.navigator.userAgent	get
2	window.navigator.userAgent	get
3	window.navigator.appName	get
4	window.navigator.appVersion	get

In [4]:

fillText = df[df.symbol == 'CanvasRenderingContext2D.fillText']
fillText = fillText.persist()

In [ ]:

progress(fillText, notebook=False)

In [13]:

fillText.head()

Out[13]:

	argument_0	symbol	operation
call_id
1_0001213aecc8140d73918b7fcd11af181a850ce5b7d258f82771a4b3.json__125	Soft Ruddy Foothold 2	CanvasRenderingContext2D.fillText	call
1_0001213aecc8140d73918b7fcd11af181a850ce5b7d258f82771a4b3.json__132	!H71JCaj)]# 1@#	CanvasRenderingContext2D.fillText	call
1_0001213aecc8140d73918b7fcd11af181a850ce5b7d258f82771a4b3.json__188	<@nv45. F1n63r,Pr1n71n6!	CanvasRenderingContext2D.fillText	call
1_0001213aecc8140d73918b7fcd11af181a850ce5b7d258f82771a4b3.json__197	668	CanvasRenderingContext2D.fillText	call
1_00021485d883465dc356bceabf4203dec5012044c643ab3498da2d1c.json__30	Soft Ruddy Foothold 2	CanvasRenderingContext2D.fillText	call

In [14]:

_arg_counts = fillText.argument_0.value_counts().persist()
progress(_arg_counts, notebook=False)

[########################################] | 100% Completed |  8.6s

In [15]:

arg_counts = _arg_counts.compute().reset_index().rename(columns={
    'index': 'argument_0',
    'argument_0': 'count'
}).sort_values('count', ascending=False)
arg_counts.head(40)

Out[15]:

	argument_0	count
0	😃	37327
1	Cwm fjordbank glyphs vext quiz, 😃	21436
2		14313
3	🇺🇳	12062
4	🧚‍♂️	10422
5	🧚♂️	10422
6	🇺🇳	10422
7	45	8637
8	38	8340
9	!H71JCaj)]# 1@#	8149
10	Soft Ruddy Foothold 2	8149
11	!image!	7301
12	e	6045
13	201708	5785
14	201706	5785
15	201704	5785
16	0	5550
17	a	4787
18	i	4471
19	n	4194
20	o	4096
21	t	3974
22	http://valve.github.io	3912
23	r	3621
24	s	3447
25	<@nv45. F1n63r,Pr1n71n6!	3347
26	🐨	3315
27	10	3289
28	11	3230
29	月份	3087
30	06	2799
31	07	2794
32	08	2785
33	09	2782
34	2,000	2706
41	$201000	2697
39	$197000	2697
40	$196000	2697
36	$200000	2697
38	$198000	2697

In [16]:

_operation_counts = fillText.operation.value_counts().persist()
progress(_operation_counts, notebook=False)

[########################################] | 100% Completed |  8.5s

In [17]:

operation_counts = _operation_counts.compute()
operation_counts

Out[17]:

call            542838
set                 58
set (failed)         0
get                  0
Name: operation, dtype: int64

In [ ]: