关于“Performing Advanced Feature Engineering in Keras”的评价

Dani V. · 评论about 3 years之前

Akshay S. · 评论about 3 years之前

NICE

Sanal B. · 评论about 3 years之前

Shivam P. · 评论about 3 years之前

Yasin S. · 评论about 3 years之前

Carolina G. · 评论about 3 years之前

桢楠 蔡. · 评论about 3 years之前

Gabriel G. · 评论about 3 years之前

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. · 评论about 3 years之前

JAYAVARAPU SIVA T. · 评论about 3 years之前

Julia W. · 评论about 3 years之前

Wijaya P. · 评论about 3 years之前

good experience

saggurthi a. · 评论about 3 years之前

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

Sadeka I. · 评论about 3 years之前

Vishnu Teja R. · 评论about 3 years之前

Manjesh G. · 评论about 3 years之前

poornika b. · 评论about 3 years之前

Giles W. · 评论about 3 years之前

Marco C. · 评论about 3 years之前

very useful

sathish s. · 评论about 3 years之前

Ty S. · 评论about 3 years之前

Koji H. · 评论about 3 years之前

Xenon X. · 评论about 3 years之前

Toshi S. · 评论about 3 years之前

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. · 评论about 3 years之前