For those who are not familiar with machine learning (ML), we recommend starting with Weka. Weka is software that incorporate several ML techniques and allows researchers with limited familiarity with ML and programming to fit ML models to their datasets with easy-to-use interfaces. Weka is also useful for an expert as a data exploration tool.
To get started, you can download Weka
http://www.cs.waikato.ac.nz/ml/weka/downloading.html
If you're not familiar with Weka or Java, we suggest you install the stable version (3.8). For Windows users, we suggest "a self-extracting executable for 64-bit Windows that includes Oracle's 64-bit Java VM 1.8". If you already have the JRE 1.8, feel free to choose the one without the Java VM.
After you download and install Weka, you can try it out with our training set of the dataset: "training.arff".
https://drive.google.com/open?id=0B7S-fo3P_sKoWXIybGJxZXBxOVE
For that at a little more sohpiciated and happy to use python, we have have some other suggestions
Using Weka
Weka offers several sub-applications, each focuses on different tasks. For now, we will focus on "Explorer"
When you are in the Explorer, click "Open file" then select "training.arff" that you just downloaded and click "open"
Now that the dataset is loaded, let's train some ML models. Let's start with Logistic Regression. First, click "Classify" on the top menu. Then, click "Choose", and choose "weka -> classifiers -> functions -> Logistic"
Then you click "Start", and a logistic regression model is now trained and tested on your dataset with 10-fold cross-validation!
Let's train a more complicated model: feed-forward Neural Network (FFNN). To train FFNN, click "Choose", and choose "weka -> classifiers -> functions -> MultilayerPerceptron", then click "Start". Then, a few seconds later, the FFNN model is now trained and tested on your dataset with 10-fold cross-validation! And now you are a data miner!
If you are interested in digging deeper with Weka, you can find the online appendix on the WEKA workbench here
http://www.cs.waikato.ac.nz/ml/weka/documentation.html