Exam DP-100 topic 7 question 5 discussion

MedianValue should be made uncategorical to be consistent as the original formats are in text and numeric.

I think the answer should be floating and make uncategorical, becuase it's a regression model and MedianValue is the target column. Uncategorical would make sense.

For the configuration options in the Edit Metadata module, you should select: Launch column selector: Integer Unchanged: This will ensure that the MedianValue column in both datasets is recognized as an integer type and is not modified.

Should it not be 'Integer'? The value is in $1000s.

if your source dataset has numbers handled as text, you must change them to a numeric data type before using math operations. The supported data types are String, Integer, Double, Boolean, and DateTime. Floating point and time span is not an option For example, you might have a column that contains the numbers 0, 1, and 2, but know that the numbers actually mean "Smoker," "Non-smoker," and "Unknown." In that case, by flagging the column as categorical you ensure that the values are used only to group data and not in numeric calculations. Since it is numeric the option should be either "unchanged" or "make uncategorical". The original data is text so it should be made uncategorical

if you google "make uncategorical" + edit metadata, you only get references to this particular exam question... I'm not convinced that "make uncategorical" even exists.

Integer and uncategorical as the MedianValue is written in 1000 (no decimal point) and it's a regression model so must be numeric.

The table that shows types indicate MedianValue is in the $1000s. It's an integer. Where did Floating Point come from? Also, the Paris data must be noncategorical, too, like the London data.

I don't think it is necessary to make it uncategorical as text data is not categorical in this case which we have to make uncategorical. Answer is correct.

there is no floating point. Select the Data type option if you need to assign a different data type to the selected columns. You might need to change the data type for certain operations. For example, if your source dataset has numbers handled as text, you must change them to a numeric data type before using math operations. The supported data types are String, Integer, Double, Boolean, and DateTime. If you select multiple columns, you must apply the metadata changes to all selected columns. For example, let's say you choose two or three numeric columns. You can change them all to a string data type and rename them in one operation. However, you can't change one column to a string data type and another column from a float to an integer. If you don't specify a new data type, the column metadata is unchanged. The column type and values will change after you perform the Edit Metadata operation. You can recover the original data type at any time by using Edit Metadata to reset the column data type.

I dont think there is such a thing as make uncategorical. Since the string version of the MedianValue we had is already not categorical we do not need to switch the MedianValue, thus leaving it unchanged would leave us with a non categorical Median integer value..maybe

The answer is Floating point, Make Categorical

as the Paris dataset needs to match London dataset types and London has numerical data types in MoedianValues columns, shouldn't the answer be 'Integer' and 'Make Uncategorical'?

"You must ensure that the datatype of the MedianValue column of the Paris dataset matches the structure of the London dataset." If we run Summary on the data, it might end up as Categorical due to the nature of data. That said "Unchanged" might do it here.

yes, I too agree with Yong2020.

Correct me if I'm wrong, but I believe the answer should be "Make Categorical" if you don't want the MedianValue column to be numerical calculated.