#Anaconda

If using Python, pandas is recommended for data manipulation. For prediction, one can start with some typical models in scikit-learn. **pandas, numpy, sklearn are all included in Anaconda.**

#Useful pandas functions
```
df_test = pd.read_csv('filename.csv', index_col=0)
df_test['Predicted'] = model.predict_proba(x_test)[:,1]
df_test[['Predicted']].to_csv('submission.csv')
```

#Don't be afraid to try things you haven't heard of before

After some basic models, one can progress to some more advanced models in other libraries. Maybe search around a bit for cool or successful models that people have used for classification.

#IDE/Shortcuts

Learn all the shortcuts to your development environment. Spyder and Jupyter are both included in Anaconda, and there are plenty of shortcuts to run specific code sections swiftly.

#Missing data

Think of how to fill in the missing data. Note that the id's for testing data is scrambled, so using the "previous" row is not necessarily reasonable.

#Feature engineering

Don't try any timeseries models, but you can certainly engineer a few more features out of the available columns.

#Model blending

Why use one model when you can take the average of multiple model outputs, or even use another model on top of the model outputs?

#Probability calibration

Some models don't have accurate classification probabilities, but one can calibrate them using various techniques. This doesn't help much for individual models due to the AUC metric, but allows for "fairer" model blending if you plan to take a simple average.

#Hyperparameter tuning

Try not to do tuning by hand unless you want to sit at the computer forever. Gain some intuition and then try some automatic tuners! You will likely learn how to save progress to disk.