News for hackers. Stuff that matters.
Re:Show HN: Sketch – AI code-writing assistant that understa... by bluecoconut on Monday January 16, 2023 @01:19PM (#34403728)
to get the strings of the results back out, add the kwarg `call_display=False` to the functions.

so: ``` print(data_pd.sketch.ask("Is there any PII in this dataset ?", call_display=False)) ``` should work for you.

Right now it by default assumes its in an ipython context that can display HTML objects.

Re:Show HN: Sketch – AI code-writing assistant that understa... by tdebroc on Monday January 16, 2023 @03:21PM (#34405036)
Ah yes it displayed the string, thanks!

But the result looks wrong with this input:

     age                                         address
  0   34  106 DOYERS ST. 8 ARLINGTON DR. 599 NW BAY BLVD
  1   34                 694 Short Street, Austin, Texas
It says:

  No, there is no PII (personally identifiable information) in this dataset. The only columns are index, age, and address, none of which contain any sensitive information.

Sometimes, it seems to work with phone number though. Here: age address phone 0 34 106 DOYERS ST. 8 ARLINGTON DR. 599 NW BAY BLVD 1-541-754-3010 1 34 694 Short Street, Austin, Texas 001-541-754-3010

  Yes, this dataset contains PII (personally identifiable information) such as age, address, and phone number.
I retried:

     pirce                                         address             phone
  0    123  106 DOYERS ST. 8 ARLINGTON DR. 599 NW BAY BLVD    1-541-754-3010
  1  43543                 694 Short Street, Austin, Texas  001-541-754-3010

  No, there is no personally identifiable information (PII) in this dataset. The columns contain only generic information such as index, price, address, and phone number. None of these columns contain any information that could be used to identify an individual.
Which is wrong. Is there explanation ?