Start Discovering Solved Questions and Your Course Assignments
TextBooks Included
Active Tutors
Asked Questions
Answered Questions
often in statistics when we combine two methods the resulting hybrid outperforms the two pure methods for example
an alternative to recursive partitioning is the k th nearest neighbor method this method computes the distance between
the function compute freqs in section 36 uses a default bag of words constructed directly from the words passed to it
in section 364 we saw a few alternative mathematical expressions for the naiumlve bayes approximation to the log
consider other variables that are not listed in table 31 that might by useful in the classification problem write
choose several of the ideas listed in table 31 for deriving features from the email and write functions for them be
write alternative implementations for the is re function in section 39 for one alternative instead of only checking
write the process attach function for section 382 this function has two inputs the body of a message and the
write a function that uses read fwf to read the 28 text tables in men txt and women txt into r these are called
find the record where the time is only 15 what happened determine how to handle the problem and which function needs to
examine the head and tail of the 2006 mens file look at both the character matrix in the list called men res mat and
create a variation of the plot look code that produces the plot figure 49 divide the points into separate sub-groups
try to improve the text cleaning in find msg words of section 353 by stemming the words in the messages that is make
write the function find msg words of section 353 this function takes as input the message body with no attachments and
use cross-validation on the 100 final looks to determine the best values of the tuning parameters max ss ratio min
in the streaming data case where we process one look at a time and then determine where to move to next wed like to be
implement the eval segment function described above also implement a function eval segments that takes a look and
the get segments function has similarities to the plotlook2 function the function we developed in q5 page 189 rewrite
our fit function used the sum of squares between the radii we could use other criteria such as absolute value ie the l1
write the drop attach function for section 352 this function has two inputs the body of a message and the boundary
the string manipulation functions in r can be used instead of regular expression functions for finding changing and
in the text mining approach to detecting spam we ignored all attachments in creating the set of words belonging to a
study the code in this case study and modify it to allow a user to substitute his her own functions for each of the
can we vectorize the computations in get segments to avoid the for loop given that we are looping over the number of
how many different robots were used for these experiments are there any differences in their operating characteristics