Author | Message |
---|---|
Darren76
Posts: 39
|
Posted 22:42 Nov 16, 2018 |
How do you normalize a future matrix? I did not see it on any of the labs and I cannot figure it out. so I have this future matrix X = hearts_df[['Age', 'RestBP', 'Chol', 'RestECG', 'MaxHR', 'Oldpeak']] how can I normalize(scale) its data? thanks |
jpatel77
Posts: 44
|
Posted 22:47 Nov 16, 2018 |
You can use scikit's normalization API, namely scale() from sklearn.preprocessing package. For instance, X being the DataFrame object, scale(X) will return the scaled X. |
Darren76
Posts: 39
|
Posted 22:52 Nov 16, 2018 |
got it thank you |
mpourhoma
Posts: 39
|
Posted 23:13 Nov 16, 2018 |
preprocessing.scale() in sklearn. We learned it in previous homework. |
jrmendoza21
Posts: 9
|
Posted 23:25 Nov 16, 2018 |
Why does tpr come out as nan, this is the error message: C:\Programs\Anaconda3\lib\site-packages\sklearn\metrics\ranking.py:571: UndefinedMetricWarning: No positive samples in y_true, true positive value should be meaningless Thank you |
mpourhoma
Posts: 39
|
Posted 23:28 Nov 16, 2018 |
You have to change your pos sample to "Yes". In this dataset, your positive sample is "Yes" not "1". |