Data Science for Change SAMPLE QUESTIONS

In which phase of the data science life cycle would a researcher be most concerned with the possibility of confirmation bias?

• Ask Questions

• Consider Data

• Analyze Data

• Interpret Data

Which question is unbiased?

• Why is it best for a dress code to exist?

• Would you prefer to eat a delicious steak or a plain sandwich?

• How many hours do you typically sleep per night?

• Should concerned dog owners vaccinate their pets?

You are asked to rephrase the following question so that it is not biased: "Where do you like to party on the weekends?" Which would be the best replacement for this question?

• It is not biased as is.

• Do you like to party or stay home on the weekends?

• When you party on the weekends, where do you like to go?

• What do you like to do on the weekends?

The columns of a data frame named df are as follows: - customer name - phone number - email - company - date of service Which use of dot notation would not cause an error?

• print(df.customername)

• print(df.phone_number)

• print(df.company)

• print(df.email.company)

Which rows and columns would be printed using the following command? print(df.iloc[6: , 20:24])

• Rows with indices 0 to 5 and columns with indices 20 to 23

• Rows with indices 0 to 6 and columns with indices 20 to 24

• Rows with indices 20 to 23 and columns with indices 0 to 5

• Rows with indices 20 to 24 and columns with indices 0 to 6

Consider the following Series named s: Which command would print d as its output?

• print(s.loc[2])

• print(s.iloc[47])

• print(s.iloc[2])

• print(s.iloc[3])

What does the function df.isnull().sum() do?

• Lists which rows are duplicate entries.

• Fills missing values with a specific value.

• Drops all rows that have a missing value.

• Lists the number of null values in each column.

What should be added as a parameter to df.dropna() to drop columns instead of rows?

• axis=0

• axis=1

• inplace=True

• method="column"

Which of the following would change a value of 84.59 to 84 in the grade column?

• df.grade = round(df.grade, 0)

• df.grade = pd.to_numeric(df.grade)

• df.grade = df.grade.astype(int)

• df.grade.fillna(float)