which=1,
max=0,
positions=None,
quote_character=None))
# Delete empty rows
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.Empty(column=[],
table=0,
status="active",
drop=False)
])))
# Extract from split after 'in '
w.add(
dw.Extract(column=["split"],
table=0,
status="active",
drop=False,
result="column",
update=False,
insert_position="right",
row=None,
max=0,
positions=None,
quote_character=None))
# Delete rows 1,2
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.RowIndex(column=[],
table=0,
status="active",
drop=False,
indices=[0, 1])
])))
# Delete empty rows
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
ignore_between=None,
which=1,
max=1,
positions=None))
# Delete rows where data = '|-'
w.add(dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.Eq(column=[],
table=0,
status="active",
drop=False,
lcol="data",
value="|-",
op_str="=")])))
# Cut from data on '| any number '
w.add(dw.Cut(column=["data"],
table=0,
status="active",
drop=False,
result="column",
update=True,
insert_position="right",
row=None,
# Edit data rows where data = 'Women' to ' WOMEN '
w.add(
dw.Edit(column=["data"],
table=0,
status="active",
drop=False,
result="column",
update=True,
insert_position="right",
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.Eq(column=[],
table=0,
status="active",
drop=False,
lcol="data",
value="Women",
op_str="=")
]),
on=None,
before=None,
after=None,
ignore_between=None,
which=1,
max=1,
positions=None,
to="WOMEN",
update_method=None))
which=1,
max=0,
positions=None,
quote_character=None))
# Delete rows where split2 is null
w.add(dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.IsNull(column=[],
table=0,
status="active",
drop=False,
lcol="split2",
value=None,
op_str="is null")])))
# Drop split4
w.add(dw.Drop(column=["split4"],
table=0,
status="active",
drop=True))
# Drop split1
w.add(dw.Drop(column=["split1"],
table=0,
def get_transform():
w = dw.DataWrangler()
# Split data repeatedly on newline into rows
w.add(
dw.Split(column=["data"],
table=0,
status="active",
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))
# Delete empty rows
w.add(
dw.Filter(column=[],
table=0,
status="active",
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)
])))
# Delete rows where data starts with '==='
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.StartsWith(column=[],
table=0,
status="active",
drop=False,
lcol="data",
value="===",
op_str="starts with")
])))
# Delete rows where data = '<!-- KBDX was Broadus Airport ...
w.add(
dw.Filter(
column=[],
table=0,
status="active",
drop=False,
row=dw.Row(
column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.
Eq(column=[],
table=0,
status="active",
drop=False,
lcol="data",
value=
"<!-- KBDX was Broadus Airport in Broadus, Montana. Replaced by new airport with FAA ID: 00F -->",
op_str="=")
])))
# Delete rows where data contains '<s>''''
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.Contains(column=[],
table=0,
status="active",
drop=False,
lcol="data",
value="<s>'''",
op_str="contains")
])))
# Extract from data between positions 5, 9
w.add(
dw.Extract(column=["data"],
table=0,
status="active",
drop=False,
result="column",
update=False,
insert_position="right",
row=None,
on=None,
before=None,
after=None,
ignore_between=None,
which=1,
max=1,
positions=[5, 9]))
# Drop data
w.add(dw.Drop(column=["data"], table=0, status="active", drop=True))
return w
after=None,
ignore_between=None,
which=1,
max=0,
positions=None,
quote_character=None))
# Delete empty rows
w.add(dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.Empty(column=[],
table=0,
status="active",
drop=False)])))
# Extract from split after 'in '
w.add(dw.Extract(column=["split"],
table=0,
status="active",
drop=False,
result="column",
update=False,
insert_position="right",
row=None,
on=".*",
before=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=False,
cycle=7,
start=0,
end=None)
])))
# Extract from value between ' any lowercase word |' and '}'
w.add(
dw.Extract(column=["value"],
table=0,
status="active",
drop=False,
result="column",
update=False,
which=1,
max=0,
positions=None,
quote_character=None))
# Delete empty rows
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[
dw.Empty(column=[],
table=0,
status="active",
drop=False)
])))
# Delete rows 1,2
w.add(
dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
ignore_between=None,
which=1,
max="0",
positions=None,
quote_character=None))
# Delete row 1
w.add(dw.Filter(column=[],
table=0,
status="active",
drop=False,
row=dw.Row(column=[],
table=0,
status="active",
drop=False,
conditions=[dw.RowIndex(column=[],
table=0,
status="active",
drop=False,
indices=[0])])))
# Set split1 name to 1
w.add(dw.SetName(column=["split1"],
table=0,
status="active",
drop=True,
names=["1"],
header_row=None))
# Set split2 name to 2
w.add(dw.SetName(column=["split2"],
