Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes
Due to the vast number of medical billing codes, it is generally infeasible to generate machine learning features from them as one-hot vectors. The paper Can...
Recent Posts
Snowflake: Show file formats
To list the file formats for which you have access privileges, use:
Explaining complex machine learning models with LIME
Another nice write-up on the use of Local Interpretable Model-Agnostic Explanations (LIME) to explain complex machine learning models.
Spark: Select all and add a new column
Here’s how to select all columns and add a new column.
Numpy: Extract days from timedelta64
To extract the integer value of days from a numpy.timedelta64, you divide it with a timedelta64 of one day: