Esecuzione del feature engineering avanzato in Keras recensioni

Pvrmallikharjuna rao P. · Recensione inserita quasi 5 anni fa

Juliana B. · Recensione inserita quasi 5 anni fa

Francesco N. · Recensione inserita quasi 5 anni fa

Nikita K. · Recensione inserita quasi 5 anni fa

What happened to the processed timestamp feature?

Marcus W. · Recensione inserita quasi 5 anni fa

Manfred S. · Recensione inserita quasi 5 anni fa

Shubham K. · Recensione inserita quasi 5 anni fa

Murilo A. · Recensione inserita quasi 5 anni fa

Chan S. · Recensione inserita quasi 5 anni fa

kazokada k. · Recensione inserita quasi 5 anni fa

Oskar F. · Recensione inserita quasi 5 anni fa

Iago A. · Recensione inserita quasi 5 anni fa

John K. · Recensione inserita quasi 5 anni fa

Eric T. · Recensione inserita quasi 5 anni fa

Good!

Alex C. · Recensione inserita quasi 5 anni fa

1. The provided csv does not match the expected column order in the notebook. It ends up reading passenger_count as if it was pickup_datetime, giving dates such as "1" and "5" -- which are not parseable as dates 2. The lab asks the student to parse pickup datetime to add it as a feature column, but ultimately that is not possible due to the input data -- the parsed picks the wrong column as pickup_datetime, and the csv does not have a pickup_datetime column which could be parsed as a result, the student will waste time trying to parse invalid columns and probably won't be able to get to the point where they would get to use such columns for training. The lab solution currently present in git (2021-04-06) gets around this problem by not using the pickup_datetime column at all -- it just defines functions to parse datetime, then drops pickup_datetime from the input. The proposed model ends up using a temporal feature completely by accident: it uses passenger_count as a feature -- but on the csv, the column taken as passenger_count is actually hourofday, already present in the dataset. As a result, the model inputs are incorrectly named, and predicting with passenger_count=5 is actually taking into account the predicted price for a ride at 5am

Rodrigo K. · Recensione inserita quasi 5 anni fa

Samuel Angel R. · Recensione inserita quasi 5 anni fa

Manu M. · Recensione inserita quasi 5 anni fa

Lu Y. · Recensione inserita quasi 5 anni fa

Kevin D. · Recensione inserita quasi 5 anni fa

Christian C. · Recensione inserita quasi 5 anni fa

akhil s. · Recensione inserita quasi 5 anni fa

Rahul D. · Recensione inserita quasi 5 anni fa

Domenico S. · Recensione inserita quasi 5 anni fa

Merin S. · Recensione inserita quasi 5 anni fa