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,
after="in ",
ignore_between=None,
which=1,
max=1,
positions=None))
# Fill extract with values from below
# (here is where this test differs from crime_5.py)
w.add(
dw.Fill(column=["extract"],
table=0,
status="active",
drop=False,
# Drop value
w.add(dw.Drop(column=["value"],
table=0,
status="active",
drop=True))
# Extract from fold between positions 4, 5
w.add(dw.Extract(column=["fold"],
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=[4,5]))
# Drop fold
w.add(dw.Drop(column=["fold"],
table=0,
status="active",
drop=True))
# Extract from translate on ' any word '
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
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,
insert_position="right",
row=None,
on=".*",
before="}",
after="[a-z]+\\|",
ignore_between=None,
which=1,
max=1,
positions=None))
# Fill extract with values from above
w.add(
dw.Fill(column=["extract"],
table=0,
status="active",
drop=False,
direction="down",
w.add(dw.SetName(column=["split5"],
table=0,
status="active",
drop=True,
names=["Waitlist"],
header_row=None))
# Extract from split6 on ' any number : any number any lowercase word - any number : any number any lowercase word '
w.add(dw.Extract(column=["split6"],
table=0,
status="active",
drop=False,
result="column",
update=False,
insert_position="right",
row=None,
on="\\d+:\\d+[a-z]+ - \\d+:\\d+[a-z]+",
before=None,
after=None,
ignore_between=None,
which=1,
max=1,
positions=None))
# Set extract name to Time
w.add(dw.SetName(column=["extract"],
table=0,
status="active",
drop=True,
names=["Time"],
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="\\|",
ignore_between=None,
which=1,
max=1,
positions=None))
# Fill extract with values from above
w.add(dw.Fill(column=["extract"],
table=0,
status="active",
drop=False,
direction="down",
method="copy",