def random_forest_algorithm(train_df, n_trees, n_bootstrap, n_features, dt_max_depth):
forest = []
for i in range(n_trees):
df_bootstrapped = bootstrapping(train_df, n_bootstrap)
tree = decision_tree_algorithm(df_bootstrapped, max_depth=dt_max_depth, random_subspace=n_features)
forest.append(tree)
return forest
def random_forest_algorithm(train_df, val_df, n_trees, n_bootstrap, n_features, dt_max_depth, ml_task):
forest = []
for i in range(n_trees):
print("Decision-Tree # ", i+1)
df_bootstrapped = bootstrapping(train_df, n_bootstrap)
tree = decision_tree_algorithm(df_bootstrapped, ml_task=ml_task ,max_depth=dt_max_depth, random_subspace=n_features)
tree_pruned = post_pruning(tree, train_df, val_df, ml_task)
forest.append(tree_pruned)
return forest
random.seed(0)
df = df_input[features]
df = df.rename(columns={
target_name: 'label'
}) # decision_tree_functions.py requires the target name to be 'label'
train_df, test_df = dtf.train_test_split(df, test_size)
###########################
# DECISION TREE ALGORITHM #
###########################
# #sub_tree = {question: [yes_answer, no_answer]}
if is_ml_task_classification: # Classification
tree = dtf.decision_tree_algorithm(train_df,
ml_task="classification",
max_depth=3)
else:
train_df, test_df = dtf.train_test_split(df, test_size)
tree = dtf.decision_tree_algorithm(train_df,
ml_task="regression",
max_depth=3)
r_squared = dtf.calculate_r_squared(test_df, tree)
print('r_squared: ', r_squared)
#create_plot(test_df, tree, title="Test Data")
plot_target_vs_feature(test_df, tree, 'sig_z_all_legs', 'Unity Check [-]')
plot_target_vs_feature(test_df, tree, 'sig_roll', 'Unity Check [-]')
plot_target_vs_feature(test_df, tree, 'sig_pitch', 'Unity Check [-]')
plot_target_vs_feature(test_df, tree, 'wd', 'Unity Check [-]')
