Problem $6$: Applying the Model to New Data

In the last problem, we will apply our model to a new set of observations. Suppose that this new set of data

consists of four patients with the characteristics shown below. Note that many of the column names have been

abbreviated for the purposes of fitting all of the columns within the instructions.

Create a DataFrame named new$\_$data containing the information shown above. Use the original names for

the columns. Set the column data types to be consistent with the original stroke$\_$df DataFrame. Display the

contents of this new DataFrame.

We will now use our model to generate predictions for the observations in this DataFrame.

Apply the processing pipeline to new$\_$data, storing the resulting DataFrame in a variable. Then apply your

model to the processed data, again storing the results in a variable. Display the probability and

prediction columns of this final DataFrame. Set truncate$=$False.Problem $6$: Applying the Model to New Data

In the last problem, we will apply our model to a new set of observations. Suppose that this new set of data

consists of four patients with the characteristics shown below. Note that many of the column names have been

abbreviated for the purposes of fitting all of the columns within the instructions.

$+------+----+---+-----+-------+-------------+--------+--------+----+---------------+$

$|$gender$|$ age$|$hyp$|$heart$|$married$|$ work$\_$type$|$res$\_$type$|$avg$\_$gluc$|$ bmi$|$ smoking$\_$status$|$

$+------+----+---+-----+-------+-------------+--------+--------+----+---------------+$

$|$Female$|42\mathrm{.}0|1|0|$ No$|$ Private$|$ Urban$|182\mathrm{.}1|26\mathrm{.}8|$ smokes$|$

$|$Female$|64\mathrm{.}0|1|1|$ Yes$|$Self$-$employed$|$ Rural$|171\mathrm{.}5|32\mathrm{.}5|$formerly smoked$|$

$|$ Male$|37\mathrm{.}0|0|0|$ Yes$|$ Private$|$ Rural$|79\mathrm{.}2|18\mathrm{.}4|$ Unknown$|$

$|$ Male$|72\mathrm{.}0|0|1|$ No$|$ Govt$\_$job$|$ Urban$|125\mathrm{.}7|19\mathrm{.}4|$ never smoked$|$

$+------+----+---+-----+-------+-------------+--------+--------+----+---------------+$

Create a DataFrame named new$\_$data containing the information shown above. Use the original names for

the columns. Set the column data types to be consistent with the original stroke$\_$df DataFrame. Display the

contents of this new DataFrame.

We will now use our model to generate predictions for the observations in this DataFrame.

Apply the processing pipeline to new$\_$data, storing the resulting DataFrame in a variable. Then apply your

model to the processed data, again storing the results in a variable. Display the probability and

prediction columns of this final DataFrame. Set truncate$=$False.