Please enable JavaScript.

Coggle requires JavaScript to display documents.

Chapters 13-15 (Model selection process: (SAMPLE, CROSS VALIDATION,…

- - - - Sometimes CSVs can cause a lot of problems in how data robot picks up the information. it may be better to store the data as a
        tab separated file (.tsv) where instead of commas, tabs are used to separate columns. With tab separated files, text data is less likely to be problematic.
        .xls (excel files) are typically the safest but they need to be pretty small.
        
        if stored on a data base use "ODBC
        
        If data is in a hadoop system use "HDFS."
        
        If data is located on web use "url"
        
        The current data limit for DataRobot is that the uploaded dataset must be 100 data rows or more, less than or equal to 20,000 columns, and less than or equal to 1.5.
        
        Important things to do while code is running is to change file name, you can also create tags.
- - - - Unique is listed after variable type. So it tells you how many unique values exist under a certain feature. a "feature" may be race for example.
        
        any feature name can be clicked to display more details about the
        feature. When a new feature is selected, DataRobot will close the previous feature
        detail screen.
        
        To the right of the mean column lies information on standard descriptive statistics.
        
        The difference
        between brackets [] and parentheses () is important. A bracket denotes an
        inclusive range whereas a parenthesis denotes an exclusive range. In other words,
        the range includes the number next to a bracket, but not the number next to a
        parenthesis.
        
        DataRobot will only present the data in the third position above, bracket followed
        by parenthesis, meaning that the first number is counted in this bar on the
        histogram, but the last number is not.
        
        When looking at the example from the book, the mean is listed as 4.43, suggesting that the average hospital stay is a bit more than four days
- - - - Readmitted feature: is a type of variable that holds two values "true" or "false"
        
        Bar charts are good for seeing which values may come up the most in a set.
- - - - LogLoss (Accuracy) simply means that rather than evaluating the model directly on whether it assigns cases (rows) to the correct “label” (False and True), the model is evaluated instead based on probabilities generated by the model and their distance from the correct answer.
- - - - The Group approach accomplishes much of the same as with the partition feature, but with some key differences