You
are
a
data
mining
consultant
who
is
billing
a
grocery
store
$125/hour
for
your
expertise.
The
client
has
provided
you
with
two
files:
items.csvRownload,
items.csv
(attached)
transactions.csyDownload
transactions.csv
(attached)
Each
row
in
the
transactions
file
is
a
list
of
item
codes
in
a
single
basket.
Before
analyzing
the
transactions
(baskets),
you
must
first
replace
the
item
codes
with
their
text
descriptions
from
the
items
file.
Answer
the
following
questions
and
present
your
findings
in
a
PowerPoint
presentation:
Q1:
How
many
items
are
there?
Q2:
How
many
transactions
are
there?
Q3:
Which
items
are
the
top
5
in
terms
of
support?
Q4:
Produce
a
bar
plot
of
the
top
5
support
items
by
relative
frequency.
Q5:
Produce
a
collection
of
association
rules
and
state
how
many
there
are.
Qé6:
What
is
the
rule
length
distribution
by
size?
Q7:
Calculate
the
support,
confidence
and
lift
of
the
top
10
rules
as
sorted
by
confidence
and
then
by
lift.
Q8:
What
are
the
top
10
rules
by
confidence?
Q9:
What
are
the
top
ten
rules
by
lift?
Q10:
What
are
the
top
10
item
sets that
lead
to
the
purchase
of
the
item
with
the
highest
support?
Q11:
Of
those
who
bought
the
item
with
the
second
highest
support,
what
are
the
top
10
item
sets
in
their
baskets?
Q12:
From
what
you
have
learned
from
this
analysis,
what
three
recommendations
would
you
make
to
the
Director
of
Merchandising?
