table=0,
status="active",
drop=False,
direction="right",
method="copy",
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.RowIndex(column=[],
table=0,
status="active",
drop=False,
indices=[0, 1, 2])
])))
# Fold split1, split2, split3, split4... using 1, 2, 3 as keys
w.add(
dw.Fold(column=[
"split1", "split2", "split3", "split4", "split5", "split6", "split7",
"split8", "split9", "split10", "split11", "split12", "split13",
"split14", "split15", "split16"
],
table=0,
status="active",
drop=False,
keys=[0, 1, 2]))
w.apply_to_file('migration.csv').print_csv('out.csv')
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.Empty(column=[],
table=0,
status="active",
drop=False,
percent_valid=0,
num_valid=0)])))
# Fold wrap, wrap1, wrap2, wrap3... using header as a key
w.add(dw.Fold(column=["wrap","wrap1","wrap2","wrap3","wrap4","wrap5"],
table=0,
status="active",
drop=False,
keys=[-1]))
# Translate value up
w.add(dw.Translate(column=["value"],
table=0,
status="active",
drop=False,
direction="up",
values=1))
# Drop value
w.add(dw.Drop(column=["value"],
table=0,
status="active",
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.IsNull(column=[],
table=0,
status="active",
drop=False,
lcol="Location",
value=None,
op_str="is null")])))
# Fold 2003, 2004, 2005, 2006... using header as a key
w.add(dw.Fold(column=["_2003","_2004","_2005","_2006","_2007","_2008","_2009","_2010","_2011","_2012","_2013","_2014","_2015","_2016","_2017","_2018","_2019"],
table=0,
status="active",
drop=False,
keys=[-1]))
# Set fold name to year
w.add(dw.SetName(column=["fold"],
table=0,
status="active",
drop=True,
names=["year"],
header_row=None))
# Delete rows where value is null
w.add(dw.Filter(column=[],
table=0,
status="active",
w.add(
dw.SetName(column=["split3"],
table=0,
status="active",
drop=True,
names=["4"],
header_row=None))
# Drop split4
w.add(dw.Drop(column=["split4"], table=0, status="active", drop=True))
# Fold 1, 2, 3, 4 using header as a key
w.add(
dw.Fold(column=["_1", "_2", "_3", "_4"],
table=0,
status="active",
drop=False,
keys=[-1]))
# Set fold name to Rank
w.add(
dw.SetName(column=["fold"],
table=0,
status="active",
drop=True,
names=["Rank"],
header_row=None))
# Set extract name to Nation
w.add(
dw.SetName(column=["extract"],
w.add(
dw.Split(column=["data"],
table=0,
status="active",
drop=True,
result="column",
update=False,
insert_position="right",
row=None,
on=",",
before=None,
after=None,
ignore_between=None,
which=1,
max=0,
positions=None,
quote_character=None))
# Fold split1, split2 using 1 as a key
w.add(
dw.Fold(column=["split1", "split2"],
table=0,
status="active",
drop=False,
keys=[0]))
# Drop fold
w.add(dw.Drop(column=["fold"], table=0, status="active", drop=True))
w.apply_to_file('pldi-figure-6.csv').print_csv('out.csv')
drop=True,
result="row",
update=False,
insert_position="right",
row=None,
on="\n",
before=None,
after=None,
ignore_between=None,
which=1,
max=0,
positions=None,
quote_character=None))
# Fold using 1 as a key
w.add(dw.Fold(column=[], table=0, status="active", drop=False, keys=[0]))
# Delete every 7 rows
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.RowCycle(column=[],
table=0,
status="active",
drop=True,
names=["3"],
header_row=None))
# Set split4 name to 4
w.add(dw.SetName(column=["split4"],
table=0,
status="active",
drop=True,
names=["4"],
header_row=None))
# Fold using header as a key
w.add(dw.Fold(column=[],
table=0,
status="active",
drop=False,
keys=[-1]))
# Extract from value between '|' and '}'
w.add(dw.Extract(column=["value"],
table=0,
status="active",
drop=False,
result="column",
update=False,
insert_position="right",
row=None,
on=".*",
before="}",
after="\\|",