if build_tree:
# Build tree to predict age:
f = file("data/%s_age.csv" % filename, "r")
max_depth = 6
root = construct(f, ind_vars, target_var, max_depth)
f.close()
f = file("trees/age.tree", "w")
write_tree(root, f)
f.close()
# Trim tree: TODO
# Use tree to predict age:
# Compile list of independent variables used to predict target variable
tree = read_tree("trees/age.tree")
f = file("data/%s_no_age.csv" % filename, "r")
ind_vars[("PassengerId", "continuous")] = None
data = get_data(f, ind_vars)
var_dict = simplify_var_dict(ind_vars, None)
# Output target variable predictions to csv.
f = file("predictions/ages.csv", "w")
f.write("PassengerId,%s\n" % target_var[0])
for datum in data:
distribution = tree.predict(datum, var_dict)
write_prediction(f, distribution, target_var, int(datum[var_dict["PassengerId"]]))
f.close()
# Write a new data file with age values.
write_age_file(filename)
max_key = None
for key in distribution.keys():
val = distribution[key]
if val > max_val:
max_val = val
max_key = key
f.write(',%s\n' % max_key)
elif target_var[1] == 'continuous':
f.write(',%f\n' % distribution[0])
else:
raise Exception('Invalid varaible type: %s' % target_var[1])
if __name__ == '__main__':
# Build tree from a .tree file.
tree = read_tree('trees/cat_cont_with_age.tree')
# Compile list of independent variables used to predict target variable
f = file('data/test_titles_tickets_ages.csv', 'r')
ind_vars = {
('Sex', 'categorical'): ['male', 'female'],
('Pclass', 'categorical'): ['1', '2', '3'],
('Embarked', 'categorical'): ['S', 'C', 'Q'],
('Title', 'categorical'): titles,
('Ticket_Code', 'categorical'): ticket_codes,
('SibSp', 'continuous'): None,
('Parch', 'continuous'): None,
('Fare', 'continuous'): None,
('Ticket_Val', 'continuous'): None,
('PassengerId', 'continuous'): None,
}
