|
2009 | 2009 | "cell_type": "markdown", |
2010 | 2010 | "metadata": {}, |
2011 | 2011 | "source": [ |
2012 | | - "#### Plot logloss redisuals\n", |
| 2012 | + "#### Plot logloss residuals\n", |
2013 | 2013 | "There are clear high-magnitude outliers in the logloss residuals for women who were issued false positive predictions. Given that those people were the people the model was most wrong about, those predictions will be checked first, just in case something very strange happened." |
2014 | 2014 | ] |
2015 | 2015 | }, |
|
4671 | 4671 | "name": "python", |
4672 | 4672 | "nbconvert_exporter": "python", |
4673 | 4673 | "pygments_lexer": "ipython3", |
4674 | | - "version": "3.6.3" |
| 4674 | + "version": "3.6.9" |
4675 | 4675 | } |
4676 | 4676 | }, |
4677 | 4677 | "nbformat": 4, |
|
0 commit comments