def build_rf_submission():
X, y, X_holdout, ids = prepare_data("./data/", drop_categorical=False)
# Right now we look at an extra y_train, y_test to assess the quality of our cv-estimates.
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=42)
print "Run Random Forest with {} data points and {} features.".format(X_train.shape[0], X_train.shape[1])
t0 = time()
grid_cv = find_cv_rf_model(X_train, y_train, grid=False) # stochastic search now
best_clf = grid_cv.best_estimator_
y_pred = best_clf.predict_proba(X_test)
print "Done in %0.3fs" % (time() - t0)
print "Best params {}: ".format(grid_cv.best_params_)
print "Best CV score {}: ".format(grid_cv.best_score_)
print "Training log-loss: {}".format(log_loss(y_train, best_clf.predict_proba(X_train)))
print "Training accuracy: {}".format(best_clf.score(X_train, y_train))
print "Test log-loss: {}".format(log_loss(y_test, y_pred))
print "Test accuracy: {}".format(best_clf.score(X_test, y_test))
submission_name = "submission_{}.csv".format(time())
util.note_submission_info("Model: {}".format(best_clf), submission_name)
util.build_submission(best_clf, X_holdout, ids, submission_name)
encoder = OneHotEncoder(categorical_features=cat_idx, sparse=True, handle_unknown="ignore")
n_rows = X.shape[0]
X[:, cat_idx] = X[:, cat_idx] + 1
X_holdout[:, cat_idx] = X_holdout[:, cat_idx] + 1
X = encoder.fit_transform(X)
X_holdout = encoder.transform(X_holdout)
print "Run LogReg with {} data points and {} features.".format(X.shape[0], X.shape[1])
t0 = time()
#grid_cv = find_cv_rf_model(X, y)
#best_clf = grid_cv.best_estimator_
best_clf = LogisticRegression(C=0.25, penalty='l1')
best_clf.fit(X, y)
# CV log-loss -0.483927951479 (+- 0.00121618173757) for C = 0.1
# CV log-loss -0.484415686138 (+- 0.00105883337937) for C = 0.5
# CV log-loss -0.483759409049 (+- 0.00121414467795) for C = 0.25
print "Done in %0.3fs" % (time() - t0)
cv_scores = cross_validation.cross_val_score(best_clf, X, y, scoring='log_loss', n_jobs=7, cv=7, verbose=1)
print "CV log-loss {} (+- {})".format(cv_scores.mean(), cv_scores.std())
M = np.hstack((best_clf.predict_proba(X)[:, 1], best_clf.predict_proba(X_holdout)[:, 1]))
print "Probability output shape: {}".format(M.shape) # just to be sure we do not mess up here
M.tofile("./features/logreg_features.npy")
submission_name = "submission_lr_{}.csv".format(time())
util.note_submission_info("Model: {}\n".format(best_clf), submission_name)
util.build_submission(best_clf, X_holdout, ids, submission_name)
