X_trans = np.hstack((X_num_trans, X_cat_trans))
print 'Training model... '
#rf = RandomForestClassifier(n_estimators=10)
#rf = RandomForestClassifier(n_estimators=100)
rf = RandomForestClassifier(n_estimators=1000)
rf.fit(X_trans, y, sample_weight=w)
joblib.dump(rf, 'models/rf.pkl')
print
print 'Predicting in sample... '
evaluator = ModelEvaluator(
imputer=imp, scaler=scaler,
encoder=enc, model=rf
)
y_pred = evaluator.predict(X_num, X_cat)
print 'Training Error = {0}'.format(np.sum(w[y != y_pred]) / np.sum(w))
print 'Predicted +, - counts = {0}, {1}'.format(y_pred[y_pred==1].shape[0], y_pred[y_pred==0].shape[0])
print
print 'Importing test sample... '
adapter = LearningDataAdapter(for_learning=True)
adapter.adapt_file('data/validate.csv')
X_num, X_cat = adapter.X_num, adapter.X_cat
w, y = adapter.w, adapter.y
print
print 'Predicting out of sample... '
y_pred = evaluator.predict(X_num, X_cat)
print 'Testing Error = {0}'.format(np.sum(w[y != y_pred]) / np.sum(w))
print 'Training model... '
#rf = RandomForestClassifier(n_estimators=10)
#rf = RandomForestClassifier(n_estimators=100)
#rf = RandomForestClassifier(n_estimators=200)
rf = RandomForestClassifier(n_estimators=1000)
#rf.fit(X_trans, y, sample_weight=w)
rf.fit(X_trans, y)
joblib.dump(rf, 'models/rf.pkl')
print
print 'Predicting in sample... '
evaluator = ModelEvaluator(imputer=imp,
scaler=scaler,
encoder=enc,
model=rf)
y_pred = evaluator.predict(X_num, X_cat)
#print 'Training Error = {0}'.format(np.sum(w[y != y_pred]) / np.sum(w))
print 'Training Error = {0}'.format(y_pred[y != y_pred].shape[0] /
float(y_pred.shape[0]))
print 'Predicted +, - counts = {0}, {1}'.format(
y_pred[y_pred == 1].shape[0], y_pred[y_pred == 0].shape[0])
print
print 'Importing test sample... '
adapter = LearningDataAdapter(for_learning=True)
adapter.adapt_file('data/validate.csv')
X_num, X_cat = adapter.X_num, adapter.X_cat
w, y = adapter.w, adapter.y
print
