Performing Advanced Feature Engineering in Keras Reviews

archana g. · Reviewed ما يقرب من 5 سنوات ago

Yuan L. · Reviewed ما يقرب من 5 سنوات ago

George N. · Reviewed ما يقرب من 5 سنوات ago

Maciej M. · Reviewed ما يقرب من 5 سنوات ago

Julio T. · Reviewed ما يقرب من 5 سنوات ago

JASPAL V. · Reviewed ما يقرب من 5 سنوات ago

Pvrmallikharjuna rao P. · Reviewed ما يقرب من 5 سنوات ago

Juliana B. · Reviewed ما يقرب من 5 سنوات ago

Francesco N. · Reviewed ما يقرب من 5 سنوات ago

Nikita K. · Reviewed ما يقرب من 5 سنوات ago

What happened to the processed timestamp feature?

Marcus W. · Reviewed ما يقرب من 5 سنوات ago

Manfred S. · Reviewed ما يقرب من 5 سنوات ago

Shubham K. · Reviewed ما يقرب من 5 سنوات ago

Murilo A. · Reviewed ما يقرب من 5 سنوات ago

Chan S. · Reviewed ما يقرب من 5 سنوات ago

kazokada k. · Reviewed ما يقرب من 5 سنوات ago

Oskar F. · Reviewed ما يقرب من 5 سنوات ago

Iago A. · Reviewed ما يقرب من 5 سنوات ago

John K. · Reviewed ما يقرب من 5 سنوات ago

Eric T. · Reviewed ما يقرب من 5 سنوات ago

Good!

Alex C. · Reviewed ما يقرب من 5 سنوات ago

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. · Reviewed ما يقرب من 5 سنوات ago

Samuel Angel R. · Reviewed ما يقرب من 5 سنوات ago

Manu M. · Reviewed ما يقرب من 5 سنوات ago

Lu Y. · Reviewed ما يقرب من 5 سنوات ago