DataAnalytics Content
DataClassifier.py
gender_classification_challenge (https://github.com/llSourcell/gender_classification_challenge)
##Overview
This is the code for the gender classification challenge for 'Learn Python for Data Science #1' by @Sirajology on YouTube. The code uses the scikit-learn machine learning library to train a decision tree on a small dataset of body metrics (height, width, and shoe size) labeled male or female. Then we can predict the gender of someone given a novel set of body metrics.
##Dependencies
Scikit-learn (http://scikit-learn.org/stable/install.html) numpy (pip install numpy) scipy (pip install scipy) Install missing dependencies using pip
##Challenge
Find 3 more classifiers from the sci-kit learn documentation and add them to the demo.py code. Train them on the same dataset and compare their results. You can determine accuracy by trying to predict testing you trained classifier on samples from the training data and see if it correctly classifies it. Push your code repository to github then post it in the comments.
##Credits
Credits for some of the code go to chribsen. I've merely created a wrapper to get people started easily.
Twitter-Sentimental-Analysis.py
twitter_sentiment_challenge (https://github.com/llSourcell/twitter_sentiment_challenge) Twitter Sentiment Analysis Challenge for Learn Python for Data Science #2 by @Sirajology on Youtube
##Overview
This is the code for the Twitter Sentiment Analyzer challenge for 'Learn Python for Data Science #2' by @Sirajology on YouTube. The code uses the tweepy library to access the Twitter API and the TextBlob library to perform Sentiment Analysis on each Tweet. We'll be able to see how positive or negative each tweet is about whatever topic we choose.
##Dependencies
tweepy (http://www.tweepy.org/) textblob (https://textblob.readthedocs.io/en/dev/) Install missing dependencies using pip
##Challenge
Instead of printing out each tweet, save each Tweet to a CSV file with an associated label. The label should be either 'Positive' or 'Negative'. You can define the sentiment polarity threshold yourself, whatever you think constitutes a tweet being positive/negative. Push your code repository to github then post it in the comments.
##Credits Siraj