def test_multi_target_random_forest():
import shap
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
X_train, X_test, Y_train, _ = train_test_split(*shap.datasets.linnerud(),
test_size=0.2,
random_state=0)
est = RandomForestRegressor(random_state=202,
n_estimators=10,
max_depth=10)
est.fit(X_train, Y_train)
predicted = est.predict(X_test)
explainer = shap.TreeExplainer(est)
expected_values = np.asarray(explainer.expected_value)
assert len(
expected_values
) == est.n_outputs_, "Length of expected_values doesn't match n_outputs_"
shap_values = np.asarray(explainer.shap_values(X_test)).reshape(
est.n_outputs_ * X_test.shape[0], X_test.shape[1])
phi = np.hstack((shap_values, np.repeat(expected_values,
X_test.shape[0]).reshape(-1, 1)))
assert np.allclose(phi.sum(1), predicted.flatten(order="F"), atol=1e-4)
#Train Models
device = "Device001"
resultsPdf = pd.DataFrame()
for numTrees, maxDepth in [(numTrees,maxDepth) for numTrees in numTreesList for maxDepth in maxDepthList]:
with mlflow.start_run(run_name="Sensor Regression"):
mlflow.log_param("maxDepth", maxDepth)
mlflow.log_param("numTrees", numTrees)
mlflow.log_param("model", "Radom Forest Regressor - scikit")
# Fit, train, and score the model
model = RandomForestRegressor(max_depth = maxDepth, n_estimators = numTrees)
model.fit(train_x, train_y)
preds = model.predict(test_x)
# Get Metrics
mse = mean_squared_error(test_y, preds)
r2 = r2_score(test_y, preds)
# Log Metrics and Model
mlflow.log_metric('mse', mse)
mlflow.log_metric('r2', r2)
mlflow.sklearn.log_model(model, "model")
# Build Metrics Table
results = [[device, maxDepth, numTrees, mse, r2]]
runResultsPdf = pd.DataFrame(results, columns =['Device', 'MaxDepth', 'NumTrees', 'MSE', 'r2'])
resultsPdf = resultsPdf.append(runResultsPdf)
