Realizar engenharia de atributos avançada no Keras avaliações

Pvrmallikharjuna rao P. · Revisado há almost 5 years

Juliana B. · Revisado há almost 5 years

Francesco N. · Revisado há almost 5 years

Nikita K. · Revisado há almost 5 years

What happened to the processed timestamp feature?

Marcus W. · Revisado há almost 5 years

Manfred S. · Revisado há almost 5 years

Shubham K. · Revisado há almost 5 years

Murilo A. · Revisado há almost 5 years

Chan S. · Revisado há almost 5 years

kazokada k. · Revisado há almost 5 years

Oskar F. · Revisado há almost 5 years

Iago A. · Revisado há almost 5 years

John K. · Revisado há almost 5 years

Eric T. · Revisado há almost 5 years

Good!

Alex C. · Revisado há almost 5 years

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. · Revisado há almost 5 years

Samuel Angel R. · Revisado há almost 5 years

Manu M. · Revisado há almost 5 years

Lu Y. · Revisado há almost 5 years

Kevin D. · Revisado há almost 5 years

Christian C. · Revisado há almost 5 years

akhil s. · Revisado há almost 5 years

Rahul D. · Revisado há almost 5 years

Domenico S. · Revisado há almost 5 years

Merin S. · Revisado há almost 5 years