جواب «Readable Rules» چالش 4 از جلسهی 51
سؤال
تابع بازگشتی print_rules را کامل کن: برای یک گره if <name> < <threshold>: چاپ کن، بعد شاخهی چپ را با ۴ فاصلهی بیشتر، بعد else: و بعد شاخهی راست را با ۴ فاصلهی بیشتر. برگها آمادهاند (-> yes). خروجی ده خط است: if homework < 2:، if rain < 1:، -> yes، else:، -> no، else:، if temp < 31:، -> no، else:، -> yes.
راهنما
اسم ویژگی names[node["feature"]] است؛ برای شاخهها print_rules(node["left"], names, indent + " ").
یک جواب درست
DATA = '''
temp,homework,rain,play
24,1,0,yes
30,0,0,yes
18,3,0,no
22,2,1,no
27,1,0,yes
15,0,0,yes
20,4,0,no
33,1,1,no
26,0,0,yes
19,2,0,no
28,3,0,no
23,0,1,no
21,1,0,yes
31,2,0,yes
'''.strip()
lines = DATA.splitlines()
features = lines[0].split(",")[:-1]
rows = []
labels = []
for line in lines[1:]:
parts = line.split(",")
rows.append([int(v) for v in parts[:-1]])
labels.append(parts[-1])
def gini(group):
if len(group) == 0:
return 0.0
score = 1.0
for c in sorted(set(group)):
p = group.count(c) / len(group)
score -= p * p
return score
def split(rows, labels, f, t):
left = [labels[i] for i in range(len(rows)) if rows[i][f] < t]
right = [labels[i] for i in range(len(rows)) if rows[i][f] >= t]
return left, right
def weighted_gini(left, right):
n = len(left) + len(right)
return len(left) / n * gini(left) + len(right) / n * gini(right)
def best_split(rows, labels):
best = None
for f in range(len(rows[0])):
for t in sorted(set(row[f] for row in rows))[1:]:
left, right = split(rows, labels, f, t)
score = weighted_gini(left, right)
if best is None or score < best[0]:
best = (score, f, t)
return best
def majority(labels):
return max(sorted(set(labels)), key=labels.count)
def build(rows, labels, depth, max_depth, min_samples):
if depth == max_depth or len(rows) < min_samples or gini(labels) == 0:
return {"leaf": majority(labels)}
best = best_split(rows, labels)
if best is None:
return {"leaf": majority(labels)}
score, f, t = best
left_rows, left_labels, right_rows, right_labels = [], [], [], []
for i in range(len(rows)):
if rows[i][f] < t:
left_rows.append(rows[i])
left_labels.append(labels[i])
else:
right_rows.append(rows[i])
right_labels.append(labels[i])
left = build(left_rows, left_labels, depth + 1, max_depth, min_samples)
right = build(right_rows, right_labels, depth + 1, max_depth, min_samples)
if "leaf" in left and "leaf" in right and left["leaf"] == right["leaf"]:
return left # both sides say the same thing: the question is useless
return {"feature": f, "threshold": t, "left": left, "right": right}
def print_rules(node, names, indent=""):
if "leaf" in node:
print(indent + "-> " + node["leaf"])
return
print(indent + "if " + names[node["feature"]] + " < " + str(node["threshold"]) + ":")
print_rules(node["left"], names, indent + " ")
print(indent + "else:")
print_rules(node["right"], names, indent + " ")
print_rules(build(rows, labels, 0, 2, 2), features)
اول خودت امتحان کن؛ جوابهای دیگر هم قبول است. برگرد و خودت حلش کن