Performing Advanced Feature Engineering in Keras Reviews

NICE

Sanal B. · Reviewed about 3 years ago

Shivam P. · Reviewed about 3 years ago

Yasin S. · Reviewed about 3 years ago

Carolina G. · Reviewed about 3 years ago

桢楠 蔡. · Reviewed about 3 years ago

Gabriel G. · Reviewed about 3 years ago

The transform function is a bit hard to comprehend. I suggest split it into two functions. The first one does the normalization and calculates euclidean distance. The second one creates the crossed feature.

Junhao Z. · Reviewed about 3 years ago

JAYAVARAPU SIVA T. · Reviewed about 3 years ago

Julia W. · Reviewed about 3 years ago

Wijaya P. · Reviewed about 3 years ago

good experience

saggurthi a. · Reviewed about 3 years ago

Some features, e.g., dayofweek and pickup_dropoff embedding features were defined but not used.

Sadeka I. · Reviewed about 3 years ago

Vishnu Teja R. · Reviewed about 3 years ago

Manjesh G. · Reviewed about 3 years ago

poornika b. · Reviewed about 3 years ago

Giles W. · Reviewed about 3 years ago

Marco C. · Reviewed about 3 years ago

very useful

sathish s. · Reviewed about 3 years ago

Ty S. · Reviewed about 3 years ago

Koji H. · Reviewed about 3 years ago

Xenon X. · Reviewed about 3 years ago

Toshi S. · Reviewed about 3 years ago

Just about enough time to complete. suggest to give 2 hours instead. Some questions: End of lab compares predicted taxi fare for both models with and without feature engineering. However there should be comparison back to either the actual taxi fare (if known) to see which model performs closer, or comparison using val RMSE for 2 models instead, or comparison of train/val loss/mse curves. Simply comparing 2 predicted taxi fares doesnt tell which performs better.

Joy L. · Reviewed about 3 years ago

Monjoy S. · Reviewed about 3 years ago

Jonathan C. · Reviewed about 3 years ago