1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
| import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import graphviz
def cal_entropy(data, feature_name):
'''
计算给定特征的信息熵
:param data: 输入的DataFrame数据集
:param feature_name: 需要计算熵的目标特征名称
:return: 保留三位小数的熵值
'''
entropy = 0
num = data.shape[0]
freq_stats = data[feature_name].value_counts()
for freq in freq_stats:
prob = freq / num
entropy -= prob * np.log2(prob)
return round(entropy, 3)
def cal_infoGain(data, base_entropy):
'''
计算所有特征的信息增益并选择最优特征
:param data: 输入的DataFrame数据集
:param base_entropy: 数据集的初始熵值
:return: 信息增益列表和最优特征名称
'''
infogain_list = []
total_samples = data.shape[0]
feature_list = list(data.columns.values)
target_feature = [col for col in feature_list if col not in data.columns][0]
feature_list = [col for col in data.columns if col != target_feature]
for feature in feature_list:
sub_entropy = 0
value_counts = data[feature].value_counts()
for value, count in value_counts.items():
subset = data[data[feature] == value]
subset_samples = subset.shape[0]
weight = subset_samples / total_samples
sub_entropy += weight * cal_entropy(subset, target_feature)
info_gain = base_entropy - sub_entropy
infogain_list.append(round(info_gain, 4))
max_gain = max(infogain_list)
max_index = infogain_list.index(max_gain)
best_feature = feature_list[max_index]
return infogain_list, best_feature
class ID3DecisionTree:
def __init__(self):
self.tree = None
self.target = None
def fit(self, data, target_feature):
'''
训练决策树模型
:param data: 包含特征和目标列的DataFrame
:param target_feature: 目标特征名称(如'销量')
'''
self.target = target_feature
features = [col for col in data.columns if col != target_feature]
self.tree = self._build_tree(data, features)
def _build_tree(self, data, features):
'''
递归构建决策树
:param data: 当前节点的数据集
:param features: 当前可用的特征列表
:return: 字典形式的树节点
'''
if len(data[self.target].unique()) == 1:
return {
'class': data[self.target].values[0],
'samples': len(data)
}
if not features:
class_counts = data[self.target].value_counts()
return {
'class': class_counts.idxmax(),
'samples': len(data)
}
base_entropy = cal_entropy(data, self.target)
info_gains, best_feature = cal_infoGain(data, base_entropy)
node = {
'feature': best_feature,
'info_gain': info_gains[features.index(best_feature)],
'samples': len(data),
'children': {}
}
remaining_features = [f for f in features if f != best_feature]
for value in data[best_feature].unique():
subset = data[data[best_feature] == value]
if subset.empty:
class_counts = data[self.target].value_counts()
node['children'][value] = {
'class': class_counts.idxmax(),
'samples': 0
}
else:
node['children'][value] = self._build_tree(subset, remaining_features)
return node
def predict(self, X):
'''
对新样本进行预测
:param X: 特征数据(DataFrame格式)
:return: 预测结果列表
'''
predictions = []
for _, sample in X.iterrows():
current_node = self.tree
while 'children' in current_node:
feature = current_node['feature']
value = sample[feature]
if value not in current_node['children']:
class_counts = self._get_class_counts(current_node)
predictions.append(max(class_counts, key=class_counts.get))
break
current_node = current_node['children'][value]
if 'class' in current_node:
predictions.append(current_node['class'])
return predictions
def _get_class_counts(self, node):
'''
递归统计节点中的类别分布
:param node: 当前节点
:return: 类别计数字典
'''
counts = {}
if 'class' in node:
return {node['class']: node['samples']}
for child in node['children'].values():
child_counts = self._get_class_counts(child)
for cls, cnt in child_counts.items():
counts[cls] = counts.get(cls, 0) + cnt
return counts
def visualize(self, feature_names, class_names):
'''
可视化决策树
:param feature_names: 特征名称列表
:param class_names: 类别名称列表
:return: graphviz对象
'''
dot = graphviz.Digraph()
self._build_graph(dot, self.tree, feature_names, class_names)
return dot
def _build_graph(self, dot, node, feature_names, class_names, parent=None, edge_label=""):
'''
递归构建graphviz图形
:param dot: graphviz.Digraph对象
:param node: 当前节点
:param feature_names: 特征名称列表
:param class_names: 类别名称列表
:param parent: 父节点(用于连接边)
:param edge_label: 边标签(特征取值)
'''
if 'class' in node:
label = f"{class_names[int(node['class'])]}\\n{node['samples']} samples"
dot.node(
str(id(node)),
label,
shape="box",
style="filled",
fillcolor="lightblue"
)
else:
label = f"{node['feature']}\\nIG={node['info_gain']:.3f}\\n{node['samples']} samples"
dot.node(
str(id(node)),
label,
shape="ellipse",
style="filled",
fillcolor="lightgreen"
)
if parent:
dot.edge(
str(id(parent)),
str(id(node)),
label=edge_label
)
if 'children' in node:
for value, child in node['children'].items():
self._build_graph(
dot,
child,
feature_names,
class_names,
node,
str(value)
)
|