Skip to content
GitLab
Menu
Projects
Groups
Snippets
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
Iker Martín Álvarez
Proteo
Commits
fe94510f
Commit
fe94510f
authored
Mar 30, 2023
by
Iker Martín Álvarez
Browse files
Refactor in recollector to use tuples instead of lists. Other minor changes in data gatherer codes.
parent
c3f4d98c
Changes
3
Hide whitespace changes
Inline
Side-by-side
Analysis/CreateResizeDataframe.py
View file @
fe94510f
...
@@ -87,7 +87,7 @@ def create_resize_dataframe(dfG, dataM):
...
@@ -87,7 +87,7 @@ def create_resize_dataframe(dfG, dataM):
#-----------------------------------------------
#-----------------------------------------------
if
len
(
sys
.
argv
)
<
2
:
if
len
(
sys
.
argv
)
<
2
:
print
(
"The files name is missing
\n
Usage: python3 CreateResizeDataframe.py input_file.
csv
output_name
.csv
"
)
print
(
"The files name is missing
\n
Usage: python3 CreateResizeDataframe.py input_file.
pkl
output_name"
)
exit
(
1
)
exit
(
1
)
input_name
=
sys
.
argv
[
1
]
input_name
=
sys
.
argv
[
1
]
...
@@ -95,7 +95,7 @@ if len(sys.argv) > 2:
...
@@ -95,7 +95,7 @@ if len(sys.argv) > 2:
name
=
sys
.
argv
[
2
]
name
=
sys
.
argv
[
2
]
else
:
else
:
name
=
"dataM"
name
=
"dataM"
print
(
"
Csv
name will be: "
+
name
+
".pkl"
)
print
(
"
File
name will be: "
+
name
+
".pkl"
)
dfG
=
pd
.
read_pickle
(
input_name
)
dfG
=
pd
.
read_pickle
(
input_name
)
...
...
Analysis/MallTimes.py
View file @
fe94510f
...
@@ -213,8 +213,38 @@ def read_global_file(f, dataG, it):
...
@@ -213,8 +213,38 @@ def read_global_file(f, dataG, it):
return
it
,
runs_in_file
return
it
,
runs_in_file
#-----------------------------------------------
#-----------------------------------------------
#-----------------------------------------------
def
convert_to_tuples
(
dfG
):
array_list_items
=
[
G_enum
.
GROUPS
.
value
,
G_enum
.
FACTOR_S
.
value
,
G_enum
.
DIST
.
value
,
G_enum
.
ITERS
.
value
,
\
G_enum
.
ASYNCH_ITERS
.
value
,
G_enum
.
RED_METHOD
.
value
,
G_enum
.
RED_STRATEGY
.
value
,
G_enum
.
SPAWN_METHOD
.
value
,
\
G_enum
.
SPAWN_STRATEGY
.
value
,
G_enum
.
T_SPAWN
.
value
,
G_enum
.
T_SPAWN_REAL
.
value
,
G_enum
.
T_SR
.
value
,
\
G_enum
.
T_AR
.
value
,
G_enum
.
STAGE_TYPES
.
value
,
G_enum
.
STAGE_TIMES
.
value
,
G_enum
.
STAGE_BYTES
.
value
]
array_multiple_list_items
=
[
G_enum
.
T_ITER
.
value
,
G_enum
.
T_STAGES
.
value
]
for
item
in
array_list_items
:
name
=
columnsG
[
item
]
values
=
dfG
[
name
].
copy
()
for
index
in
range
(
len
(
values
)):
values
[
index
]
=
tuple
(
values
[
index
])
dfG
[
name
]
=
values
for
item
in
array_multiple_list_items
:
name
=
columnsG
[
item
]
values
=
dfG
[
name
].
copy
()
for
i
in
range
(
len
(
values
)):
for
j
in
range
(
len
(
values
[
i
])):
if
(
type
(
values
[
i
][
j
][
0
])
==
list
):
for
r
in
range
(
len
(
values
[
i
][
j
])):
values
[
i
][
j
][
r
]
=
tuple
(
values
[
i
][
j
][
r
])
values
[
i
][
j
]
=
tuple
(
values
[
i
][
j
])
values
[
i
]
=
tuple
(
values
[
i
])
dfG
[
name
]
=
values
#-----------------------------------------------
if
len
(
sys
.
argv
)
<
2
:
if
len
(
sys
.
argv
)
<
2
:
print
(
"The files name is missing
\n
Usage: python3 MallTimes.py
results
Name directory
csv
OutName"
)
print
(
"The files name is missing
\n
Usage: python3 MallTimes.py
common
Name directory OutName"
)
exit
(
1
)
exit
(
1
)
common_name
=
sys
.
argv
[
1
]
common_name
=
sys
.
argv
[
1
]
...
@@ -228,7 +258,7 @@ if len(sys.argv) >= 4:
...
@@ -228,7 +258,7 @@ if len(sys.argv) >= 4:
name
=
sys
.
argv
[
3
]
name
=
sys
.
argv
[
3
]
else
:
else
:
name
=
"data"
name
=
"data"
print
(
"
Csv
name will be: "
+
name
+
"G.
csv & "
+
name
+
"M.csv
"
)
print
(
"
File
name will be: "
+
name
+
"G.
pkl
"
)
insideDir
=
"Run"
insideDir
=
"Run"
lista
=
glob
.
glob
(
BaseDir
+
insideDir
+
"*/"
+
common_name
+
"*_Global.out"
)
lista
=
glob
.
glob
(
BaseDir
+
insideDir
+
"*/"
+
common_name
+
"*_Global.out"
)
...
@@ -253,6 +283,8 @@ for elem in lista:
...
@@ -253,6 +283,8 @@ for elem in lista:
dfG
=
pd
.
DataFrame
(
dataG
,
columns
=
columnsG
)
dfG
=
pd
.
DataFrame
(
dataG
,
columns
=
columnsG
)
convert_to_tuples
(
dfG
)
print
(
dfG
)
dfG
.
to_pickle
(
name
+
'G.pkl'
)
dfG
.
to_pickle
(
name
+
'G.pkl'
)
#dfM = pd.DataFrame(dataM, columns=columnsM)
#dfM = pd.DataFrame(dataM, columns=columnsM)
...
...
Analysis/joinDf.py
View file @
fe94510f
...
@@ -4,7 +4,7 @@ import numpy as numpy
...
@@ -4,7 +4,7 @@ import numpy as numpy
import
pandas
as
pd
import
pandas
as
pd
if
len
(
sys
.
argv
)
<
3
:
if
len
(
sys
.
argv
)
<
3
:
print
(
"The files name is missing
\n
Usage: python3 joinDf.py resultsName1.
csv
resultsName2.
csv csv
OutName"
)
print
(
"The files name is missing
\n
Usage: python3 joinDf.py resultsName1.
pkl
resultsName2.
pkl
OutName"
)
exit
(
1
)
exit
(
1
)
if
len
(
sys
.
argv
)
>=
4
:
if
len
(
sys
.
argv
)
>=
4
:
...
@@ -12,11 +12,11 @@ if len(sys.argv) >= 4:
...
@@ -12,11 +12,11 @@ if len(sys.argv) >= 4:
else
:
else
:
name
=
"dataJOINED"
name
=
"dataJOINED"
print
(
"
Csv
name will be: "
+
name
+
".
csv
"
)
print
(
"
File
name will be: "
+
name
+
".
pkl
"
)
df1
=
pd
.
read_
csv
(
sys
.
argv
[
1
]
)
df1
=
pd
.
read_
pickle
(
sys
.
argv
[
1
]
)
df2
=
pd
.
read_
csv
(
sys
.
argv
[
2
]
)
df2
=
pd
.
read_
pickle
(
sys
.
argv
[
2
]
)
frames
=
[
df1
,
df2
]
frames
=
[
df1
,
df2
]
df3
=
pd
.
concat
(
frames
)
df3
=
pd
.
concat
(
frames
)
df3
=
df3
.
drop
(
columns
=
df3
.
columns
[
0
])
df3
=
df3
.
drop
(
columns
=
df3
.
columns
[
0
])
df3
.
to_
csv
(
name
+
'.
csv
'
)
df3
.
to_
pickle
(
name
+
'.
pkl
'
)
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment