Data Engineering - 4

What is a dataframe in Pandas?

• A table format with rows and columns

• A view of the database

• a CSV file

Ok, now that we see some part of the data, what cleaning/transformation is needed for the column titles?

• Columns titles are too wordy and need to be reduced to descriptive words.

• NA values need to be removed.

• Only question marks need to be removed.

• No cleaning is needed.

What needs to be cleaned in the ID column? Choose all that apply.

• One Participant ID has been entered incorrectly

• Participant ID 'P1110' should be replaced with 'P110'

• There is nothing to be cleaned in the ID column

• Duplicate IDs should be removed.

What part of the timestamp column needs transformation?

• We only need the date part to keep track of days data was recorded

• Timestamp should be kept as is.

• We only need the time part.

• Timestamp column is not necessary and can be removed.

What transformations may the 'bed_time' and 'wake_time' columns need? Choose all that apply.

• No transformation needed.

• The format needs to be changed to 24 hours instead of AM and PM.

• We may need to create new columns to keep the bed_time hour and wake_time hour only.

• We just need to remove AM and PM from the time.

What transformations the columns 'time_fall_asleep' and 'sleep_quality' may need? Choose all that apply.

• Convert the categories to numbers for easier processing.

• Keep them as is.

• Remove duplicate values.

• Remove the columns.

What transformation may the column 'condition' need? Choose all that apply.

• Replace sentences with numbers or short words.

• Create a boolean variable for each condition to keep a record of which conditions disturbed sleep in a given night.

• Leave it as is