CIS 5450 - Midterm 1, Fall 2023Questions and
Correct Answers
Which of the following is least likely to be a good example of big data
(Purchase behavior for 1000 users, Hundreds of gene sequences, Points on the trajectory of
a falling object, A thousand YouTube videos)
Points on the trajectory of a falling object
Which of the following tasks is not part of preprocessing data?
(Model and annotate data, Extract the key parts of the data, Run machine learning
algorithms on the data, Clean the data)
Run machine learning algorithms on the data
Features are:
Values used to predict classes or groups
What are the three basic encodings of structured data?
tables, arrays, nested
What kinds of data might need pattern-based extraction?
web or text data
Which of the following is not a part of the standard data structuring process?
training
When we read a structured file into a dataframe, what will occur?
, column names may be assigned based on the file header
When we store a dataframe in a SQL database, what do we have an option of saving or
dropping?
the dataframe index
What does projection do?
returns a subset of the columns in a dataframe
The document object model is what kind of data structure?
tree
XPath returns what as its result?
set of matching nodes in order, as a list
The XPath //span matches what?
the span element(s) at any level
An outerjoin will return the exact same results as an innerjoin if
every tuple in the input relations has a match.
If we join relations that each have an id column, what happens in Pandas?
The input columns will be renamed in the output, to be unique, by appending suffixes to the
names
What does my_df['col1'] > 3 return?
A series of Boolean values, true only for rows where col1 is above 3
Correct Answers
Which of the following is least likely to be a good example of big data
(Purchase behavior for 1000 users, Hundreds of gene sequences, Points on the trajectory of
a falling object, A thousand YouTube videos)
Points on the trajectory of a falling object
Which of the following tasks is not part of preprocessing data?
(Model and annotate data, Extract the key parts of the data, Run machine learning
algorithms on the data, Clean the data)
Run machine learning algorithms on the data
Features are:
Values used to predict classes or groups
What are the three basic encodings of structured data?
tables, arrays, nested
What kinds of data might need pattern-based extraction?
web or text data
Which of the following is not a part of the standard data structuring process?
training
When we read a structured file into a dataframe, what will occur?
, column names may be assigned based on the file header
When we store a dataframe in a SQL database, what do we have an option of saving or
dropping?
the dataframe index
What does projection do?
returns a subset of the columns in a dataframe
The document object model is what kind of data structure?
tree
XPath returns what as its result?
set of matching nodes in order, as a list
The XPath //span matches what?
the span element(s) at any level
An outerjoin will return the exact same results as an innerjoin if
every tuple in the input relations has a match.
If we join relations that each have an id column, what happens in Pandas?
The input columns will be renamed in the output, to be unique, by appending suffixes to the
names
What does my_df['col1'] > 3 return?
A series of Boolean values, true only for rows where col1 is above 3
