Question 1
The analysis metric slope can be observed through which of the following ways?
Trend Line in Line Chart
SLOPE function
Both Trend Line in Line Chart and SLOPE function
None of these
Tools in Data Science (TDS) End Term: 30 April 2023, Set QPD1-S2 (January 2023 term)
The IIT Madras BS Tools in Data Science (Tools in Data Science (TDS)) End Term paper sat on 30 Apr 2023, in the January 2023 term, set QPD1-S2: 62 questions for 70 marks in 180 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.
- 62
- 70
- 180 min
- 60
- 2
Show answer
Correct answer
Both Trend Line in Line Chart and SLOPE function
Question 2
Quill provides the option to turn on/off, for displaying the individual comments from the narrative generation process?
TRUE
FALSE
Show answer
Correct answer
TRUE
Question 3
We are analyzing how much the use of fertilizers affects the agricultural yield of the farmers. Which Excel function would you use as a starting point in this analysis?
STDEV.P()
STDEV.S()
SLOPE()
EXACT()
Show answer
Correct answer
SLOPE()
Question 4
Subjectivity score in TextBlob ranges from ___________.
0 to 1
-1 to +1
-inf to +inf
0 to inf
0 to 10
Show answer
Correct answer
0 to 1
Question 5
Flourish cannot be used to create animated bar charts.
TRUE
FALSE
Show answer
Correct answer
FALSE
Question 6
A very large Matrix A has a lot of zero entries in it. Which function from the scipy library is useful in efficient storage of such a matrix A?
csr_matrix
interpolate
compressed_mat
zip_mat
Show answer
Correct answer
csr_matrix
Question 7
Kumu is a tool that allows you to (select the most appropriate answer):
Visualize complex network data
create stunning dashboards for large projects
merge Comicgen characters into a comic
Narrate data stories
Show answer
Correct answer
Visualize complex network data
Question 8
Which of the following Python libraries has functions and tools that are useful in the analysis of large graphs?
scikit-network
pandas-network
numpy-network
pd-network
Show answer
Correct answer
scikit-network
Question 9
Which of the following Python libraries has functions extensively written to perform numerical operations?
csr_matrix
numpy
seaborn
itertools
Show answer
Correct answer
numpy
Question 10
You developed a sudden interest in English Premier League. Post the TDS course, you wanted to perform an analysis on all teams which played EPL from the year 1992. You performed PDF scraping using ‘tabula’ and appended every year standings of teams one below the other and saved as a single csv file. For looking at aggregating at various levels (viz Year wise, Team wise) the following can be used in Excel:
Pilot Table
Pivot Table
Pivol Table
None of these
Show answer
Correct answer
Pivot Table
Question 11
Assume you have data with a column “Direction” which takes the values “Left”, “Right”. If you had used one hot encoding, the new columns added would be:
Direction_Left, Direction_Right
Left_Direction, Right_Direction
Left-Direction, Right-Direction
Direction-Left, Right-Direction
Show answer
Correct answer
Direction_Left, Direction_Right
Question 12
One of quick ways to generate a descriptive stats file for variables along with correlation is to use
pandas_profiling
profiling_pandas
describe_dataset
Dataframe_profile
Show answer
Correct answer
pandas_profiling
Question 13
You decide to use keras to classify images into one of the following categories: cat, dog, bull. Which of the following loss functions from Keras would you pick for the task?
binary_crossentropy
categorical_crossentropy
mean_squared_error
mean_absolute_error
Show answer
Correct answer
categorical_crossentropy
Question 14
Logical calculations in tableau helps to determine if a certain condition is true or false. Is the following expression valid?
TRUE
FALSE
Show answer
Correct answer
TRUE
Question 15
The dataset consists of geographic, demographic information about countries and their respective GDPs. You would like to visualize this data and study the relationship between the location of countries and their GDPs. You decide to use Tableau to visualize the dataset. But you would also like to generate a summary of the data. Choose the most suitable answer among the given options.
The summary can be generated using Quill and this is possible because Quill can be used as an extension in Tableau.
Tableau can be used for visualization. But Quill is incompatible with Tableau.
Quill does not support generation of summary. Therefore using other visualization tools such as Tableau would work.
None of the options are appropriate for the generation of summary for the given question.
Show answer
Correct answer
The summary can be generated using Quill and this is possible because Quill can be used as an extension in Tableau.
Question 16
What are the two outputs provided by the Excel Azure Machine Learning plugin?
Percentage, Labels
Sentiment, Percentage
Sentiment, Score
Score, Labels
Show answer
Correct answer
Sentiment, Score
Question 17
The final output from the BBC Weather Location Service API is in CSV format:
TRUE
FALSE
Show answer
Correct answer
FALSE
Question 18
Which among the following properties are returned by the sentiment function of the TextBlob library?
Score, Polarity
Polarity, Negativity
Median, Subjectivity
Polarity, Subjectivity
Show answer
Correct answer
Polarity, Subjectivity
Question 19
Subjectivity score ranges between -1 to +1.
TRUE
FALSE
Show answer
Correct answer
FALSE
Question 20
A subjectivity score of 0.4 means that the text statement:
has a positive sentiment
has a negative sentiment
is more of an opinion statement
is more of a factual statement
Show answer
Correct answer
is more of a factual statement
Question 21
A polarity score of 0.1 means that the text statement:
has a positive sentiment
has a negative sentiment
is more of an opinion statement
is more of a factual statement
Show answer
Correct answer
has a positive sentiment
Question 22
We are interested in analyzing the effect of money spent on TV advertising on the sales volume of a product. Which Excel function would you use as a starting point in this analysis?
STDEV.P()
STDEV.S()
SLOPE()
EXACT()
Show answer
Correct answer
SLOPE()
Question 23
You are working on a piece of code that classifies different vehicles into its respective class (car, LCV, truck, earth movers). Which of the following loss functions from Keras would you pick for the task?
binary_crossentropy
categorical_crossentropy
mean_squared_error
Mean_absolute_error
Show answer
Correct answer
categorical_crossentropy
Question 24
Tableau automatically divides the data fields into two categories. What are they..?
Measures and categories
Dimensions and Measures
Columns and rows
Matrices and columns
Show answer
Correct answer
Dimensions and Measures
Question 25
Which Extension in Tableau transforms visualizations into narratives.?
Narrator
Navigator
Quill
Quora
Show answer
Correct answer
Quill
Question 26
If you want to create comical characters while building business stories, which tool would be helpful.?
Cartoongen
Image size
Comicgen
Gentoon
Show answer
Correct answer
Comicgen
Question 27
Which of the following is used to build and host web applications?
Streamlit for building web applications, Heroku for hosting web applications
Heroku for building web applications, Streamlit for hosting web applications
Streamlit for building web applications, Streamlit for hosting web applications
Heroku for building web applications, Heroku for hosting web applications
Show answer
Correct answer
Streamlit for building web applications, Heroku for hosting web applications
Question 28
Which among the following excel charts is the most suitable for detecting outliers in the data?
Bar chart
Line chart
Box and Whisker chart
Histogram
Show answer
Correct answer
Box and Whisker chart
Question 29
Which of the following libraries is used to construct API urls?
Urllib
BeautifulSoup
Requests
Pandas
Show answer
Correct answer
Urllib
Question 30
Which of the following tabs is used to identify API calls in the Inspect element in any browser?
Network
Elements
Console
Sources
Show answer
Correct answer
Network
Question 31
Google Studio is a tool that allows you to
merge Comicgen characters into a comic
visualize complex network data
create dashboards for small scale projects
Edit photographs and videos
Show answer
Correct answer
create dashboards for small scale projects
Question 32
csr_matrix from the scipy library:
always helps reduce matrix space
helps reduce matrix space when there are a lot of zero entries in the matrix
helps reduce matrix space when there are a lot of negative entries in the matrix
makes matrix multiplication more meaningful and powerful
Show answer
Correct answer
helps reduce matrix space when there are a lot of zero entries in the matrix
Question 33
classification_report function from the sklearn.metrics module
builds a decision tree classifier and prints the accuracy of the classifier
reports the root mean square error of the model
runs different classification models and compares the results
builds a text report displaying the main classification metrics
Show answer
Correct answer
builds a text report displaying the main classification metrics
Question 34
pycaret is a
Visualization tool
Dashboard helper
low-code machine learning library
Data cleaning solution
Show answer
Correct answer
low-code machine learning library
Question 35
We are interested in fitting an ARIMA model to our time series data. Specifically, we are interested in a moving average model of 0, setting a lag value of 4 for autoregression, and a difference order of 1. Which of the following gives you such a model?
ARIMA(..., trend = (4,1,0))
ARIMA(..., order = (4,1,0))
ARIMA(..., order = (0,4,1))
ARIMA(..., trend = (0,4,1))
Show answer
Correct answer
ARIMA(..., order = (4,1,0))
Question 36
Scikit-learn has a DecisionTreeClassifier module that is useful in building decision tree classifiers. Suppose, our dataset is imbalanced in class. Which feature in the DecisionTreeClassifier() will help us tackle this problem?
random_state
min_sample_split
class_balance
class_weight
Show answer
Correct answer
class_weight
Question 37
The data consists of prices of three shares in the stock market over a period of six months. To compute the correlation coefficients between these three shares: (Choose the most suitable option)
It is sufficient if you specify these three shares as input variables in the excel ‘data analysis toolpak’ feature.
You must specify both input and target variables in the excel ‘data analysis toolpak’ to obtain the correlation coefficient values.
It is sufficient if you specify these three shares as target variables in the excel ‘data analysis toolpak’ feature.
Show answer
Correct answer
It is sufficient if you specify these three shares as input variables in the excel ‘data analysis toolpak’ feature.
Question 38
Assume the data provided to you has a column that consists of sales dates. You would want to extract the week number from the column for further analysis. Which among the following excel function enables you to perform the above-mentioned task?
WEEKGET()
GETWEEKNUM()
NUMWEEK()
None of these
Show answer
Correct answer
None of these
Question 39
Which among the following features in excel enables you to scrape data from websites?
Data Analysis Toolpak
Connections
New Query
Data Validation
Show answer
Correct answer
New Query
Question 40
Which of the following statements about the k-means clustering algorithm is false?
It is guaranteed to converge to the global optimum solution for any given dataset and initial centroids.
It can be sensitive to the choice of initial centroids, and different initializations can lead to different final cluster assignments.
The k-means algorithm minimizes the within-cluster sum of squares as its objective function.
It can be used to cluster both continuous and categorical data.
Show answer
Correct answer
It is guaranteed to converge to the global optimum solution for any given dataset and initial centroids.
Question 41
Which of the following is NOT a method of the Beautiful Soup object?
find()
get()
find_all()
prettify()
Show answer
Correct answer
get()
Question 42
What is ComicGen?
A web development framework for comic creators.
A Python library for data analysis and storytelling using comics.
A tool for generating comic strips.
A game development engine.
Show answer
Correct answer
A tool for generating comic strips.
Question 43
Network tab in Chrome Devtools (Inspect) tracks all api calls that happen in a website.
TRUE
FALSE
Show answer
Correct answer
TRUE
Question 44
Flourish is a web-based:
Data visualization platform
Machine learning platform
Business intelligence platform
None of these
Show answer
Correct answer
Data visualization platform
Question 45
Which of the tools below are used for data storytelling?
Excel
Quill
Comicgen
Flourish
Excel, Quill, Comicgen
All of these
Show answer
Correct answer
Excel, Quill, Comicgen
Question 46
______ data consists of any value within the finite or infinite intervals. _______ data displayed as green icons in the data window and green pills on shelves.
Discrete,Continuous
Continuous,Continuous
None
Show answer
Correct answer
Continuous,Continuous
Question 47
From the below options identify the statement that is False
Measures contain numeric, quantitative values that you can measure.
Measures can be aggregated.
When you drag a measure into the view, Tableau applies an aggregation to that measure (by default).
None of these
Show answer
Correct answer
None of these
Question 48
Which of the following statements about Heroku is true?
Heroku is a cloud-based platform for deploying, managing, and scaling web applications.
Heroku is a programming language used for developing front-end web applications.
Heroku is a database management system used for storing and retrieving data.
Heroku is a web browser used for accessing internet-based applications.
Show answer
Correct answer
Heroku is a cloud-based platform for deploying, managing, and scaling web applications.
Question 49
Which data type is not available in the ARX tool while you input data for anonymizing?
String
Date/Time
Continuous
Decimal
Integer
Show answer
Correct answer
Continuous
Question 50
Your model is performing well in your training dataset but is not performing well in test dataset. It means:
Model is overfit
Model is underfit
Problem with test dataset
None of these
Show answer
Correct answer
Model is overfit
Question 51
The following function in excel helps in removing extra spaces:
TRIM
REDUCE
REMOVESPACE
None of these
Show answer
Correct answer
TRIM
Question 52
For categorical variables, missing data can be replaced by:
Mode
Median
Mean
None of these
Show answer
Correct answer
Mode
Question 53
The given piece of code extract details of all Bollywood movies that were released in Jan – March 2009 and later prints out only those rows where the respective movie was categorized only as a Drama. Identify which block of code executes without any errors.
Show answer
Correct answer
Question 54
Identify which of the following statements is/are TRUE
1. A story contains a single view along with shelves, cards, legends, and the Data and Analytics panes in its side bar.
2. A worksheet contains a sequence of stories that work together to convey information 3. A dashboard is a collection of views from multiple worksheets
1 Only
3 Only
2 & 3 Only
1 & 2 Only
Show answer
Correct answer
3 Only
Question 55
geopy.distance(loc1, loc2).km
geopy.distance(loc1, loc2).km.km
geopy.distance.distance(loc1, loc2).km
geopy.distance.distance.distance(loc1_coord, loc2_coord).km
Show answer
Correct answer
geopy.distance.distance(loc1, loc2).km
Question 56
Show answer
Correct answer
Question 57
Provided below is a snapshot of the dataset which consists of movie reviews and respective labels.
To compute the sentiment scores the Azure Machine Learning add-in requires input and output values. In the figure provided below the input and output cells need to be populated with appropriate values to obtain sentiment scores.
Choose the most appropriate option that enables you to predict sentiment scores using the Excel Azure Machine Learning add-in.
Show answer
Correct answer
Question 58
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import median_absolute_error
from sklearn.metrics import median_absolute_percentage_error
from sklearn.metrics import average_absolute_percentage_error
Show answer
Correct answer
from sklearn.metrics import median_absolute_error
Question 59
Comicgen is a useful tool in narrating data stories using comics. Which of the following are capabilities of comicgen?
Comicgen can create comic characters
Comicgen provides options to custom create different comic characters and their emotions and pose
Comicgen can be easily integrated into Google sheets or Excel to narrate your data stories
You can type in your data story into comicgen to get your comic in return
Show answer
Correct answers
Comicgen can create comic characters
Comicgen provides options to custom create different comic characters and their emotions and pose
Comicgen can be easily integrated into Google sheets or Excel to narrate your data stories
Question 60
scikit-network package contains functions for (select all correct sentences):
analysis of faults in a computer network
social network analysis
analysis of large graphs
enhancing one’s social network
Show answer
Correct answers
social network analysis
analysis of large graphs
Question 61
You decided to perform analysis of the IPL teams year on year. You downloaded the teams standings table which got downloaded as a PDF.
Based on the above information, answer the given subquestions.
You wish to convert to a csv file for further analysis in Excel. The following method in ‘tabula’ can be used for the same:
convert_into
convert_file
convert_all
convert_csv
Show answer
Correct answer
convert_into
Question 62
You decided to perform analysis of the IPL teams year on year. You downloaded the teams standings table which got downloaded as a PDF.
Based on the above information, answer the given subquestions.
From the converted csv file in previous question , you realize that the team ‘Delhi Daredevil’ has changed its name to ‘Delhi Capital’. Using excel, you wish to replace the old name with a new name. It can be done in Excel using
Find and Replace
Finding and Replacing
Replace and Find
Search and Replace
Show answer
Correct answer
Find and Replace