label,

class,

COUNT(*)AS label_count

FROMpgml.imdb_shuffled_view

ORDER BYlabel;

ORDER BYclass;

class | label_count

negative |25000

positive |25000

(2 rows)

This query provides insights into the distribution of labels, helping you understand the balance or imbalance of classes in your dataset.

To get a glimpse of the data, you can retrieve a sample of records from the shuffled dataset:

FROMpgml.imdb_shuffled_view

LIMIT5;

text | class

This is a VERY entertaining movie. A few of the reviews that I have readon this forum have been wri | positive

This is one of those movieswhere I wish I had just stayedin the bar.<br/><br/>The film is quite | negative

Barbershop2: Backin Business wasn't as good as it's original but was justas funny. The movie itse | negative

Umberto Lenzi hits new lows with this recycled trash. Janet Agren plays a lady who is looking for he | negative

I saw this movie last night at the Phila. Film festival. It was an interestingand funny movie that | positive

(5 rows)

Time:101.985 ms

This query allows you to inspect a few records to understand the structure and content of the shuffled data.

Now, that we have fine-tuned model on Hugging Face Hub, we can use[`pgml.transform`](https://postgresml.org/docs/introduction/apis/sql-extensions/pgml.transform/text-classification) to perform real-time predictions as well as batch predictions.

**Real-time predictions**

Here is an example pgml.transform call for real-time predictions on the newly minted LLM fine-tuned on IMDB review dataset.

SELECTpgml.transform(