MCQs

Disclaimer:

Educational Use Only:

The website links provided are to be used strictly for educational and knowledge-gaining purposes only.

No Misuse:

Do not misuse the links or the information contained therein for any commercial, illegal, or unethical activities.

Respect for Websites and Businesses:

Respect the intellectual property and business interests of the websites and their owners. Do not attempt to alter, copy, or redistribute content without proper authorization.

Acknowledge Value of Knowledge:

Recognize and value the knowledge and resources shared by these websites. Use the information responsibly and ethically.

No Endorsement:

The provision of these links does not imply endorsement of the linked sites, their content, or their products and services. Users are responsible for evaluating the suitability and accuracy of the information.

User Responsibility:

By accessing these links, you agree to use the information at your own risk and to comply with all applicable laws and website terms of use.

Overall MCQs for Reference

1. What is a column in a dataset?
   a. A single value
   b. A group of datasets
   c. An attribute representing a variable
   d. A set of labels
   Answer: c. An attribute representing a variablesalesforce​
2. In a pandas DataFrame, each column is typically associated with:
   a. A row index
   b. A variable or feature
   c. A shape property
   d. A function
   Answer: b. A variable or featuresalesforce​
3. What is the main role of columns in feature engineering?
   a. Store training logs
   b. Represent variables for model learning
   c. Save test results
   d. Visualize model predictions
   Answer: b. Represent variables for model learningpecan​
4. Which technique transforms categorical columns into numeric format?
   a. Feature scaling
   b. Log transform
   c. One-hot encoding
   d. Polynomial regression
   Answer: c. One-hot encodingdev​
5. What term describes columns containing both numbers and text?
   a. Binary columns
   b. Mixed-type columns
   c. String columns
   d. Index columns
   Answer: b. Mixed-type columnscodesignal​
6. What is the first recommended step when handling columns with missing values?
   a. Ignore the column
   b. Visualize missing data
   c. Inspect and quantify missing values
   d. Automatically drop rows
   Answer: c. Inspect and quantify missing valuesdatacamp​
7. Which transformation spreads column values so that their mean is 0 and variance is 1?
   a. Min-max scaling
   b. Log transform
   c. Standardization
   d. Label encoding
   Answer: c. Standardizationdev​
8. What is column importance in machine learning?
   a. How columns look visually
   b. Measure of a column’s predictive power
   c. Frequency of missing data
   d. Initial column order
   Answer: b. Measure of a column’s predictive powerpecan​
9. Which library is commonly used for column-based data manipulation in Python?
   a. Tkinter
   b. Pandas
   c. Flask
   d. PIL
   Answer: b. Pandasyoutube​
10. What is a common technique to handle categorical columns with many unique values?
    a. Drop duplicates
    b. One-hot encoding
    c. Min-max normalization
    d. Label smoothing
    Answer: b. One-hot encodingdev​
11. To convert date-strings in a column to time series, use:
    a. pd.date()
    b. pd.time()
    c. pd.to_datetime()
    d. pd.datetime()
    Answer: c. pd.to_datetime()opengenus​
12. What is a wide format data structure?
    a. Data with very large values
    b. Data with many rows
    c. Each variable in its own column
    d. Each variable in a single cell
    Answer: c. Each variable in its own columnopengenus​
13. Which transformation is effective for skewed numeric columns?
    a. Feature scaling
    b. Polynomial transformation
    c. Log transformation
    d. Mean encoding
    Answer: c. Log transformationdev​
14. What is the outcome of dropping a column from a dataset?
    a. Reduce the number of features
    b. Increase accuracy automatically
    c. Change the row count
    d. Randomize data order
    Answer: a. Reduce the number of featuresnextbrain​
15. What is feature selection?
    a. Choosing visualization methods
    b. Selecting columns for model input
    c. Dropping all columns
    d. Interpolating data
    Answer: b. Selecting columns for model inputnextbrain​
16. Which method fills missing column values with the mean?
    a. Forward fill
    b. Mode fill
    c. Mean imputation
    d. Median interpolation
    Answer: c. Mean imputationdatacamp​
17. What is the usual effect of adding irrelevant columns to a model?
    a. Improves interpretability
    b. Might decrease accuracy
    c. Reduces noise
    d. Fixes missing data
    Answer: b. Might decrease accuracynextbrain​
18. What does column aggregation typically involve?
    a. Multiplying column names
    b. Summarizing values (sum, mean, etc.)
    c. Dropping all columns
    d. Encoding strings
    Answer: b. Summarizing values (sum, mean, etc.)pecan​
19. Which technique is used for handling text columns in data science?
    a. Smoothing
    b. Tokenization
    c. Simple scaling
    d. Min-max normalization
    Answer: b. Tokenizationcodesignal​
20. In database design, columns can represent:
    a. Multiple datasets
    b. Categories of information
    c. Only numbers
    d. Only text
    Answer: b. Categories of informationsalesforce​
21. What is column transformation?
    a. Rearranging row order
    b. Preprocessing values in a column
    c. Plotting distributions
    d. Hyperparameter tuning
    Answer: b. Preprocessing values in a columndev​
22. Feature scaling is necessary for columns when:
    a. Using deep learning
    b. Data values have differing ranges
    c. Data has text values
    d. No missing data
    Answer: b. Data values have differing rangesdev​
23. The pandas function to count unique values in a column is:
    a. count_unique()
    b. nunique()
    c. sum()
    d. value_count()
    Answer: b. nunique()geeksforgeeks​
24. Label encoding converts:
    a. Numeric columns to strings
    b. Categorical columns to numbers
    c. Dates to strings
    d. Numbers to categories
    Answer: b. Categorical columns to numbersthedatascientist​
25. Which strategy manages columns with high cardinality categorical data?
    a. Drop the column
    b. Min-max scaling
    c. Hash encoding
    d. Forward fill
    Answer: c. Hash encodingthedatascientist​
26. Feature interactions can be created by:
    a. Subtracting column means
    b. Combining columns into new features
    c. Dropping missing rows
    d. Imputing data
    Answer: b. Combining columns into new featurespecan​
27. What does dropping duplicates in a column achieve?
    a. Reorders columns
    b. Removes repeated values
    c. Changes data type
    d. Scales data
    Answer: b. Removes repeated valuesgeeksforgeeks​
28. What does a column’s data type influence in data science?
    a. Visualization only
    b. Compatible analytical techniques
    c. Row order
    d. Number of columns displayed
    Answer: b. Compatible analytical techniquescodesignal​
29. Which library provides methods such as get_dummies() for column transformation?
    a. NumPy
    b. Matplotlib
    c. Pandas
    d. Scikit-learn
    Answer: c. Pandasyoutube​
30. Which technique handles missing column values using patterns in other columns?
    a. Mean imputation
    b. K-Nearest Neighbors (KNN) imputation
    c. Hash encoding
    d. Label smoothing
    Answer: b. KNN imputationdatacamp​
31. What is a dummy variable in the context of columns?
    a. Placeholder value
    b. Encoded binary column for categorical variable
    c. Unused column
    d. Dummy row
    Answer: b. Encoded binary column for categorical variablethedatascientist​
32. Why is column order sometimes important in data processing?
    a. For model interpretability
    b. For storage efficiency
    c. For data type changes
    d. For downloading data
    Answer: a. For model interpretabilitynextbrain​
33. Which visualization technique is commonly used for numeric columns?
    a. Scatter plot
    b. Pie chart
    c. Heatmap
    d. Bar chart
    Answer: a. Scatter plotgeeksforgeeks​
34. The process of splitting mixed-type columns into multiple columns is called:
    a. Normalization
    b. Decomposition
    c. Parsing
    d. Joining
    Answer: c. Parsingcodesignal​
35. What is often the result of discarding too many columns?
    a. Improved model performance
    b. Loss of important information
    c. Reduced noise
    d. Reduced row count
    Answer: b. Loss of important informationnextbrain​
36. What is the goal of dimensionality reduction regarding columns?
    a. Increase dataset size
    b. Reduce the number of irrelevant columns
    c. Add new features
    d. Change column order
    Answer: b. Reduce the number of irrelevant columnsnextbrain​
37. Which column transformation helps represent hierarchical categorical data?
    a. Label encoding
    b. Ordinal encoding
    c. Decomposition
    d. Forward fill
    Answer: b. Ordinal encodingthedatascientist​
38. For time-series data, columns often represent:
    a. Each time step
    b. Only numeric values
    c. Each identifier
    d. Only categories
    Answer: a. Each time stepsalesforce​
39. Why is it necessary to check for duplicate columns during preprocessing?
    a. To improve analysis accuracy
    b. To reduce row count
    c. For visualization
    d. To automatically encode values
    Answer: a. To improve analysis accuracygeeksforgeeks​
40. Which function in pandas removes a column from a DataFrame?
    a. drop_column()
    b. remove_column()
    c. df.drop()
    d. delete_column()
    Answer: c. df.drop()pecan​
41. Which metric helps assess the correlation between two columns?
    a. Accuracy
    b. R2 score
    c. Correlation coefficient
    d. Standard deviation
    Answer: c. Correlation coefficientgeeksforgeeks​
42. A column representing the target variable for prediction is called:
    a. Feature
    b. Output column
    c. Label
    d. Input column
    Answer: c. Labelpecan​
43. For large datasets, which type of columns may need feature hashing?
    a. Numeric columns
    b. High-cardinality categorical columns
    c. Date columns
    d. Boolean columns
    Answer: b. High-cardinality categorical columnsthedatascientist​
44. Which column transformation is critical before fitting a linear regression model?
    a. Feature scaling
    b. Parsing
    c. Tokenization
    d. Hash encoding
    Answer: a. Feature scalingdev​
45. What is the pandas method to rename columns?
    a. set_column_name()
    b. rename()
    c. change_column()
    d. update_names()
    Answer: b. rename()geeksforgeeks​
46. Which encoding can be used for ordinal categorical columns?
    a. One-hot encoding
    b. Mean encoding
    c. Ordinal encoding
    d. Hash encoding
    Answer: c. Ordinal encodingthedatascientist​
47. What is the process of converting raw column data into aggregated features known as?
    a. Data wrangling
    b. Feature engineering
    c. Data cleaning
    d. Data mining
    Answer: b. Feature engineeringpecan​
48. Why do data scientists check column data types before analysis?
    a. To improve visualization
    b. To choose suitable analytical methods
    c. To randomize column order
    d. To plot data
    Answer: b. To choose suitable analytical methodscodesignal​
49. Which column handling approach is recommended for high-dimensional sparse data?
    a. Label encoding
    b. Dimensionality reduction
    c. Drop columns
    d. Scatter plotting
    Answer: b. Dimensionality reductionnextbrain​
50. What is the main function of index columns in a DataFrame?
    a. Store model predictions
    b. Identify each row uniquely
    c. Scale data
    d. Aggregate features
    Answer: b. Identify each row uniquelysalesforce​

1. https://help.salesforce.com/s/articleView?id=analytics.bi_integrate_dataset_columns_and_rows.htm&language=en_US&type=5
2. https://help.pecan.ai/en/articles/7835868-understanding-column-importance
3. https://dev.to/simpleproxy/column-transformation-in-machine-learning-2ci0
4. https://codesignal.com/learn/courses/advanced-data-cleaning-handling-text-data-1/lessons/handling-mixed-data-types-in-columns-using-python
5. https://www.datacamp.com/tutorial/techniques-to-handle-missing-data-values
6. https://www.youtube.com/watch?v=rJVYOCr89AA
7. https://iq.opengenus.org/interview-questions-on-data-science/
8. https://nextbrain.ai/blog/understanding-column-importance-in-machine-learning-unveiling-the-power-of-feature-selection
9. https://www.geeksforgeeks.org/data-analysis/data-cleansing-introduction/
10. https://thedatascientist.com/a-detailed-guide-for-data-handling-techniques-in-data-science/
11. https://www.geeksforgeeks.org/data-science/key-pillars-of-data-science/
12. https://www.sanfoundry.com/1000-data-science-questions-answers/
13. https://www.interviewbit.com/data-science-mcq/
14. https://testbook.com/objective-questions/mcq-on-columns–5eea6a0b39140f30f369ded6
15. https://www.gyansetu.in/blog/data-science-objective-type-mcq-quiz-interview-preparation/
16. https://www.includehelp.com/mcq/data-science-mcqs.aspx
17. https://www.placementpreparation.io/mcq/data-science/page/2/
18. https://www.onlinemanipal.com/blogs/four-pillars-of-data-science
19. https://www.scribd.com/document/856379688/Data-Science-100-MCQs
20. https://towardsdatascience.com/best-practices-for-technical-columns-in-database-design-f3fce9357426/