def test_max_depth_None_rfqr():
# Since each leaf is pure and has just one unique value.
# the mean equals any quantile.
rng = np.random.RandomState(0)
X = rng.randn(10, 1)
y = np.linspace(0.0, 100.0, 10.0)
rfqr = RandomForestQuantileRegressor(random_state=0,
bootstrap=False,
max_depth=None)
rfqr.fit(X, y)
for quantile in [20, 40, 50, 60, 80, 90]:
assert_array_almost_equal(rfqr.predict(X, quantile=None),
rfqr.predict(X, quantile=quantile), 5)
def test_tree_forest_equivalence():
"""
Test that a DecisionTree and RandomForest give equal quantile
predictions when bootstrap is set to False.
"""
rfqr = RandomForestQuantileRegressor(random_state=0,
bootstrap=False,
max_depth=2)
rfqr.fit(X_train, y_train)
dtqr = DecisionTreeQuantileRegressor(random_state=0, max_depth=2)
dtqr.fit(X_train, y_train)
assert_true(np.all(rfqr.y_train_leaves_ == dtqr.y_train_leaves_))
assert_array_almost_equal(rfqr.predict(X_test, quantile=10),
dtqr.predict(X_test, quantile=10), 5)
def test_base_forest_quantile():
"""
Test that the base estimators belong to the correct class.
"""
rng = np.random.RandomState(0)
X = rng.randn(10, 1)
y = np.linspace(0.0, 100.0, 10.0)
rfqr = RandomForestQuantileRegressor(random_state=0, max_depth=1)
rfqr.fit(X, y)
for est in rfqr.estimators_:
assert_true(isinstance(est, DecisionTreeQuantileRegressor))
etqr = ExtraTreesQuantileRegressor(random_state=0, max_depth=1)
etqr.fit(X, y)
for est in etqr.estimators_:
assert_true(isinstance(est, ExtraTreeQuantileRegressor))
def train_RandomForestQuantileRegressor(
population, plpData, train, modelOutput, seed, quiet, n_estimators,
criterion, max_features, max_depth, min_samples_split,
min_samples_leaf, min_weight_fraction_leaf, max_leaf_nodes, bootstrap,
oob_score, warm_start):
print("Training RandomForestQuantileRegressor ")
y = population[:, 1]
X = plpData[population[:, 0], :]
trainInds = population[:, population.shape[1] - 1] > 0
print("Dataset has %s rows and %s columns" % (X.shape[0], X.shape[1]))
print("population loaded- %s rows and %s columns" %
(np.shape(population)[0], np.shape(population)[1]))
###########################################################################
if train:
pred_size = int(np.sum(population[:, population.shape[1] - 1] > 0))
print("Calculating prediction for train set of size %s" % (pred_size))
test_pred = np.zeros(
pred_size
) # zeros length sum(population[:,population.size[1]] ==i)
for i in range(1,
int(np.max(population[:, population.shape[1] - 1]) + 1),
1):
testInd = population[population[:, population.shape[1] - 1] > 0,
population.shape[1] - 1] == i
trainInd = (population[population[:, population.shape[1] - 1] > 0,
population.shape[1] - 1] != i)
train_x = X[trainInds, :][trainInd, :]
train_y = y[trainInds][trainInd]
test_x = X[trainInds, :][testInd, :]
print("Fold %s split %s in train set and %s in test set" %
(i, train_x.shape[0], test_x.shape[0]))
print("Train set contains %s outcomes " % (np.sum(train_y)))
print("Training fold %s" % (i))
start_time = timeit.default_timer()
tmodel = RandomForestQuantileRegressor(
n_estimators=n_estimators,
criterion=criterion,
max_features=max_features,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_leaf_nodes=max_leaf_nodes,
bootstrap=bootstrap,
oob_score=oob_score,
warm_start=warm_start,
random_state=seed,
n_jobs=-1)
tmodel = tmodel.fit(X=csr_matrix(train_x), y=train_y)
end_time = timeit.default_timer()
print("Training fold took: %.2f s" % (end_time - start_time))
print("Calculating predictions on left out fold set...")
ind = (population[:, population.shape[1] - 1] > 0)
ind = population[ind, population.shape[1] - 1] == i
test_pred[ind] = tmodel.predict(csr_matrix(test_x))
print("Prediction complete: %s rows " %
(np.shape(test_pred[ind])[0]))
print("Mean: %s prediction value" % (np.mean(test_pred[ind])))
# merge pred with indexes[testInd,:]
test_pred.shape = (
population[population[:, population.shape[1] - 1] > 0, :].shape[0],
1)
prediction = np.append(
population[population[:, population.shape[1] - 1] > 0, :],
test_pred,
axis=1)
return prediction
# train final:
else:
print("Training final adaBoost model on all train data...")
print("X- %s rows and Y %s length" %
(X[trainInds, :].shape[0], y[trainInds].shape[0]))
start_time = timeit.default_timer()
tmodel = RandomForestQuantileRegressor(
n_estimators=n_estimators,
criterion=criterion,
max_features=max_features,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_leaf_nodes=max_leaf_nodes,
bootstrap=bootstrap,
oob_score=oob_score,
warm_start=warm_start,
random_state=seed,
n_jobs=-1)
tmodel = tmodel.fit(X=csr_matrix(X[trainInds, :]), y=y[trainInds])
end_time = timeit.default_timer()
print("Training final took: %.2f s" % (end_time - start_time))
# save the model:
if not os.path.exists(modelOutput):
os.makedirs(modelOutput)
print("Model saved to: %s" % (modelOutput))
joblib.dump(tmodel, os.path.join(modelOutput, "model.pkl"))
pred = tmodel.predict(csr_matrix(X[trainInds, :]))[:, 0]
pred.shape = (
population[population[:, population.shape[1] - 1] > 0, :].shape[0],
1)
prediction = np.append(
population[population[:, population.shape[1] - 1] > 0, :],
pred,
axis=1)
return prediction, tmodel.feature_importances_