def main(cl_args=sys.argv[1:]):
"""Main wrapper to run the classification app."""
args = parse_command_line_args(cl_args=cl_args)
datafile = os.path.realpath(args["data_path"])
testfile = os.path.realpath(args["test_path"])
output_root = os.path.realpath(args["output_path"])
random_seed = args["random_seed"]
info_level = "INFO"
if args["verbose"]:
info_level = "DEBUG"
# Configure the logger.
logging.basicConfig(format='%(asctime)s [%(levelname)s] %(name)s: %(message)s',
level=info_level)
num_trees = args["num_trees"]
if not os.path.exists(output_root):
os.makedirs(output_root)
# annotated training data
data = fileio(datafile)
# annotated test data
testdata=fileio(testfile)
# Invoking unit test for decision tree
if args["run_tests"]:
logger.info("Invoking test case for decision trees")
suite = unittest.TestLoader().loadTestsFromTestCase(TestDecisionTree)
unittest.TextTestRunner().run(suite)
sys.exit()
# Creating a set of test points from test data
test_points=[]
for line in testdata:
test_points.append(line[0:len(line)-1])
# Single decision tree for entire credit approval dataset
tree_credit = DecisionTree()
logger.info('Commencing single Decision Tree for credit approval data')
start_time = time.time()
tree_credit.build_tree(data)
end_time = time.time()
logger.info('time_lapsed: {:0.4f}'.format(end_time - start_time))
tree_credit.drawtree(jpeg=os.path.join(output_root, 'singletree.png'))
# Random forest of decision trees for the credit approval dataset
logger.info('Commencing single Random Forest for credit approval data')
forest = RandomForest(num_trees)
start_time = time.time()
forest.build_forest(data, output_path=output_root, seed=random_seed)
end_time = time.time()
logger.info('Time to build forest: {:0.4f}'.format(end_time - start_time))
evaluate(test_points, forest, testdata)
def main():
"""
N.B. Last DataFrame Column contains labels
"""
logger = logging.getLogger(__name__)
logger.debug('read data')
dframe_train = pd.read_excel(os.path.join(input_filepath, "train_data.xlsx"), index_col=0)
logger.debug('train model')
'''CREATE SINGLE TREE'''
d_t = DecisionTree(metrics = 'entropy') #max_depth = 8
#trained_dt = dt.build_tree(dframe,header)
#prediction = classify(small_train.values[0][:-1],t0)
'''CREATE RANDOM FOREST WITH TREES d_t'''
r_f = RandomForest(decision_tree_type=d_t, n_trees=20)
r_f = r_f.build_forest(dframe_train, n_selected_features="best", sample_ratio =.8)
'''GET MODEL ACCURACY ON VALIDATION DATA'''
logger.debug('get model accuracy')
dframe_val = pd.read_excel(os.path.join(input_filepath, "validate_data.xlsx"), index_col=0)
predictions_validation = r_f.get_model_accuracy(dframe_val.columns.values.tolist(), dframe_val)
#logger.debug('single prediction')
#rf.classify_forest(dframe_val.columns.values.tolist(),dframe_val.values[0],forest)
logger.debug('save model')
save_model(output_filepath, "model_00.npy", r_f)