Practical deep text learning

User 2 | 5/5/2015, 10:52:07 PM

        <div class="EmbeddedContent"><img src="https://dato.com/images/dato-logo-stacked-1200x630.png" class="LeftAlign" /><strong>Practical deep text learning</strong>
           <p>This notebook presents practical methods for learning from natural text. Using simple combinations of deep learning, classification, and regression, I demonstrate how to predict a blogger's gender and age with high accuracy based on his or her blog posts.</p>
           <p><a href="https://dato.com/learn/gallery/notebooks/deep_text_learning.html?_ga=1.168922281.922008578.1422310937">Read the full story here</a></p>
           <div class="ClearFix"></div>
        </div>

Comments

User 1887 | 5/5/2015, 10:52:08 PM

Hi, looks good. Just one comment - before calling DeepTextAnalyzer, you need to do something like sf['posts'] = sf['posts'].apply(lambda x:' '.join(x)) so that the argument passed to txt2words is a string not a list.


User 1891 | 5/6/2015, 12:10:56 PM

Thanks for the feedback.

I believe this is exactly what I did: see Section 3.1.1 sf['posts'] = sf['posts'].apply(lambda posts:"\n".join(posts))

BR, Michael