Pythonic Data Science
from __future__ import machine_learning
Trey Causey
@treycausey
Who am I?
- Data Scientist at Facebook Seattle
- Former Senior Data Scientist at zulily
- Statistical consultant for an NFL team
Get data
Build model
Predict
From NumPy...
... comes PyData
pandas
scikit-learn
pandas
-
DataFrames
-
Fast ETL operations
-
Descriptive statistics
pd.read_csv()
NFL data!
(with pre-completed feature engineering)
scikit-learn
fast ML
algorithms += n
consistent API
open source
Classification
Regression
Clustering
Dimensionality reduction
Preprocessing
dat API tho!
-
Estimators extend BaseEstimator
-
Pretty much everything's an estimator
-
Estimators have fit(X, y=None), transform(), predict() methods
-
Some have predict_proba() methods
NFL win probability
Classification problem
Output a probability per-play
Pretend the plays are independent (shhh...)
Look at your data!
Class imbalance
Centering & scaling
Train-test splits
janitorial work
Random forests!
Ensembles of bootstrap aggregated decision trees!
How did we do?
Other considerations:
Calibration
Per-class performance
Performance associated with predictors
