Always getting the same prediction for the different input using MLClassifier in Core ML

Question

I have a pretty simple .csv table:

I use this table as an input parameter when creating a model in Create ML, where the target is PRICE, CITY and DATE are feature columns.

I need to get a price prediction for a giving date in the future for a particular city.

The code below gives a different price for different dates, as it should work, however, it gives the same result regardless of the given city:

let prediction = try? model.prediction(
 CITY: name, DATE: date
)

let price = prediction?.PRICE

The price for a given date in the future in Paris should not be equal to the price for the same date in New York.
Do I really need to create 2 different models for each of the cities?
Thank you!

score 0 · Answer 1 · answered Jul 01 '20 at 13:22

0

Is this all the data your are giving it? You're going to need to give it a lot more to go off of.

answered Jul 01 '20 at 13:22

Scott

91
6

In addition, you may want to change the way you're handling dates. – Matthijs Hollemans Jul 01 '20 at 15:39
@Scott This table is used as an example, the real one is much larger, but it does not change anything - the result to cities is always the same. – instback Jul 01 '20 at 18:38
@MatthijsHollemans Dates work fine in this format, but changing the city does not give any effect. – instback Jul 01 '20 at 18:43

score 0 · Accepted Answer · answered Jul 03 '20 at 05:38

0

So, it was a bug in the .csv file, it looks like the CITY column was recorded with invisible characters.

answered Jul 03 '20 at 05:38

instback

131
2
15

Always getting the same prediction for the different input using MLClassifier in Core ML

2 Answers2