def main(col_names=None):
# parse command-line arguments to read the name of the input csv file
# and optional 'draw tree' parameter
if len(sys.argv) < 2: # input file name should be specified
print("Please specify input csv file name")
return
csv_file_name = sys.argv[1]
data = []
with open(csv_file_name) as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
for row in readCSV:
data.append(list(row))
print("Total number of records = ", len(data))
tree = regression_tree.buildtree(data, min_gain=0.001, min_samples=5)
regression_tree.printtree(tree, '', col_names)
max_tree_depth = regression_tree.max_depth(tree)
print("max number of questions=" + str(max_tree_depth))
print("ODE: ")
print(
regression_tree.classify([
'tenured', 'not minority', 'male', 'english', 'young', 'small',
'upper', 'not handsome/beautiful)', 'good'
], tree))
print("Linear Algebra: ")
print(
regression_tree.classify([
'tenured', 'not minority', 'male', 'english', 'young', 'small',
'lower', 'not handsome/beautiful)', 'bad'
], tree))
print("Intro to Stats: ")
print(
regression_tree.classify([
'tenured', 'not minority', 'female', 'english', 'young', 'small',
'lower', 'not handsome/beautiful)', 'good'
], tree))
if len(sys.argv) > 2: # draw option specified
import dtree_draw_regression_tree
dtree_draw_regression_tree.drawtree(tree, jpeg=csv_file_name + '.jpg')
if len(sys.argv) > 3: # create json file for d3.js visualization
import json
import dtree_to_json
json_tree = dtree_to_json.dtree_to_jsontree(tree, col_names)
print(json_tree)
# create json data for d3.js interactive visualization
with open(csv_file_name + ".json", "w") as write_file:
json.dump(json_tree, write_file)
def main(col_names=None):
# parse command-line arguments to read the name of the input csv file
if len(sys.argv) < 2: # input file name should be specified
print("Please specify input csv file name")
return
csv_file_name = sys.argv[1]
data = []
with open(csv_file_name) as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
for row in readCSV:
data.append(list(row))
tree = regression_tree.buildtree(data, min_gain=0.01, min_samples=5)
max_tree_depth = regression_tree.max_depth(tree)
print("max number of questions=" + str(max_tree_depth))
json_tree = dtree_to_jsontree(tree, col_names)
print(json_tree)
# create json data for d3.js interactive visualization
with open(csv_file_name + ".json", "w") as write_file:
json.dump(json_tree, write_file)