上传聚类结果

kmeans.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+@Project ：recommender 
+@File    ：kmeans.py
+@IDE     ：PyCharm 
+@Author  ：rengengchen
+@Time    ：2023/12/29 11:53 
+"""
+import torch
+import time
+from tqdm import tqdm
+
+
+class KMEANS:
+    def __init__(self, n_clusters=20, max_iter=None, verbose=True, device=torch.device("cpu")):
+
+        self.n_clusters = n_clusters
+        self.labels = None
+        self.dists = None  # shape: [x.shape[0],n_cluster]
+        self.centers = None
+        self.variation = torch.Tensor([float("Inf")]).to(device)
+        self.verbose = verbose
+        self.started = False
+        self.representative_samples = None
+        self.max_iter = max_iter
+        self.count = 0
+        self.device = device
+
+    def fit(self, X):
+        x = int(np.random.uniform(0, k))
+        self.centers = x[0].reshape(1, -1)
+        # kmeans++
+        for i in range(self.n_clusters - 1):
+            dis = 0
+            for j, cj in enumerate(self.centers):
+                d = ((x - cj) ** 2).sum(1)
+                if j == 0:
+                    dis = d
+                else:
+                    dis += d
+            self.centers = torch.cat((self.centroids, x[dis.argmax(0)].reshape(1, -1)), 0)
+
+        self.centers = init_points
+        while True:
+            # 聚类标记
+            self.nearest_center(x)
+            # 更新中心点
+            self.update_center(x)
+            if self.verbose:
+                print(self.variation, torch.argmin(self.dists, (0)))
+            if torch.abs(self.variation) < 1e-3 and self.max_iter is None:
+                break
+            elif self.max_iter is not None and self.count == self.max_iter:
+                break
+
+            self.count += 1
+
+        self.representative_sample()
+
+    def nearest_center(self, x):
+        labels = torch.empty((x.shape[0],)).long().to(self.device)
+        dists = torch.empty((0, self.n_clusters)).to(self.device)
+        for i, sample in enumerate(x):
+            dist = torch.sum(torch.mul(sample - self.centers, sample - self.centers), (1))
+            labels[i] = torch.argmin(dist)
+            dists = torch.cat([dists, dist.unsqueeze(0)], (0))
+        self.labels = labels
+        if self.started:
+            self.variation = torch.sum(self.dists - dists)
+        self.dists = dists
+        self.started = True
+
+    def update_center(self, x):
+        centers = torch.empty((0, x.shape[1])).to(self.device)
+        for i in range(self.n_clusters):
+            mask = self.labels == i
+            cluster_samples = x[mask]
+            centers = torch.cat([centers, torch.mean(cluster_samples, (0)).unsqueeze(0)], (0))
+        self.centers = centers
+
+    def representative_sample(self):
+        # 查找距离中心点最近的样本，作为聚类的代表样本，更加直观
+        self.representative_samples = torch.argmin(self.dists, (0))
+
+
+def time_clock(matrix, device):
+    a = time.time()
+    k = KMEANS(max_iter=10, verbose=False, device=device)
+    k.fit(matrix)
+    b = time.time()
+    return (b - a) / k.count
+
+
+def choose_device(cuda=False):
+    if cuda:
+        device = torch.device("cuda:0")
+    else:
+        device = torch.device("cpu")
+    return device
+
+
+if __name__ == "__main__":
+    import matplotlib.pyplot as plt
+
+    plt.figure()
+
+    device = choose_device(False)
+
+    cpu_speeds = []
+    for i in tqdm([20, 100, 500, 2000, 8000, 20000]):
+        matrix = torch.rand((10000, i)).to(device)
+        speed = time_clock(matrix, device)
+        cpu_speeds.append(speed)
+    l1, = plt.plot([20, 100, 500, 2000, 8000, 20000], cpu_speeds, color='r', label='CPU')
+
+    device = choose_device(True)
+
+    gpu_speeds = []
+    for i in tqdm([20, 100, 500, 2000, 8000, 20000]):
+        matrix = torch.rand((10000, i)).to(device)
+        speed = time_clock(matrix, device)
+        gpu_speeds.append(speed)
+    l2, = plt.plot([20, 100, 500, 2000, 8000, 20000], gpu_speeds, color='g', label="GPU")

notebook/cluster_items.ipynb

@@ -0,0 +1,184 @@
+{
+ "cells": [
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-31T09:24:30.589401Z",
+     "start_time": "2024-12-31T09:24:30.582530Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import shutil\n",
+    "\n",
+    "from sklearn.metrics import silhouette_score\n",
+    "from sklearn.cluster import KMeans\n",
+    "from tfidf import TFIDF\n",
+    "import os"
+   ],
+   "id": "bba700bd32b05545",
+   "outputs": [],
+   "execution_count": 22
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-31T08:43:07.638098Z",
+     "start_time": "2024-12-31T08:43:07.632218Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "filenames = os.listdir(\"../data/items/SV300\")\n",
+    "items = []\n",
+    "for filename in filenames:\n",
+    "    with open(os.path.join(\"../data/items/SV300\", filename), \"r\", encoding=\"utf8\") as f:\n",
+    "        items.extend(item.strip() for item in f.readlines() if item)\n",
+    "print(f\"参数数量： {len(items)}\")"
+   ],
+   "id": "6744375bdcb289a9",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "参数数量： 390\n"
+     ]
+    }
+   ],
+   "execution_count": 13
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-31T08:43:08.372427Z",
+     "start_time": "2024-12-31T08:43:08.314269Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "tfidf = TFIDF(1, 0.1, 300)\n",
+    "feature_names, tfidf_matrix = tfidf.fit(items)\n",
+    "print(feature_names)"
+   ],
+   "id": "669c32f927f120d9",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['amv' 'aprv' 'asv' 'atrc' 'auto' 'autoflow' 'bilevel' 'bipap' 'btps'\n",
+      " 'cmh2o' 'co2' 'cpap' 'cprv' 'duolevel' 'ibw' 'nif' 'p0.1' 'pbw' 'peep'\n",
+      " 'prvc' 'psv' 'sigh' 'simv' 'tft' 'trc' 'tve' 'usb' 'vc' 'vdaw' 'vent'\n",
+      " 'vt' 'vtalv' 'vte' '℃' '≤' '一体化' '一键' '上' '上升时间' '下' '两种' '中文' '主机'\n",
+      " '二氧化碳' '交叉感染' '交流' '人机' '传感器' '低' '低压' '体重' '使' '供电' '便利' '信息' '值' '值同屏'\n",
+      " '儿童' '充电电池' '内源性' '内置' '冻结' '减少' '出' '分析' '分级' '分辨率' '分钟' '判断' '剩余' '力学'\n",
+      " '功' '动态' '动态显示' '包含' '包括' '医护人员' '升级' '单位理想' '压' '双' '双相' '变化' '口腔' '可充电'\n",
+      " '可拆卸' '可调' '台' '台车' '叹息' '同屏' '同步' '同步性' '后备' '吸' '吸入' '吸呼' '吸氧' '吸痰' '呼'\n",
+      " '呼吸机' '呼比' '品牌' '回顾' '图' '图形化' '增氧' '声光报警' '复苏' '如自' '婴幼儿' '孔径' '存储'\n",
+      " '安全阀' '实时' '容积' '容量' '对比' '导出' '小儿' '小时' '屏' '屏幕' '屏幕显示' '峰值' '峰压' '工作'\n",
+      " '工具' '常用' '常规' '平台' '平均' '年' '年限' '开机' '张' '形态' '彩色' '待机' '心肺' '总' '患者'\n",
+      " '成人' '截图' '手动' '手提' '技术' '拓展' '持续' '指令' '指数' '接口' '控制' '控制屏' '提供' '提示'\n",
+      " '提示信息' '提高' '插管' '操作' '操作界面' '数据' '整机' '文字' '方式' '方案' '方波' '无创' '无需' '日志'\n",
+      " '时' '时间' '时间常数' '显示' '智能' '智能化' '最佳' '最小' '未来' '末' '末端' '机器' '机控' '条'\n",
+      " '标配' '检查' '检测' '模块' '模式' '次' '正压' '死腔' '气体' '气源' '气管' '气道' '气阀' '氧' '氧气'\n",
+      " '氧疗' '水平' '泄漏' '波' '波形' '流量' '浅快' '测定' '测试' '浓度' '消毒' '涡轮' '漏气' '潮气量'\n",
+      " '灌注' '灵敏度' '环' '环可' '环图' '理想' '电动' '电控' '电池' '电源' '电量' '界面' '病人' '百分比'\n",
+      " '监护' '监护仪' '盘' '目标' '直流' '确认' '种' '种环图' '科室' '空气' '窒息' '管路' '管道' '系统'\n",
+      " '纯氧' '组件' '肺' '肺复' '肺泡' '脱机' '自主' '自动' '自动识别' '自检' '至少' '舒适度' '英寸' '蒸汽'\n",
+      " '补偿' '表' '视图' '触发' '触摸' '计时' '计算' '认证' '记录' '设' '设定' '设置' '设计' '调节' '负压'\n",
+      " '趋势' '身高' '转运' '辅助' '过低' '过高' '选配' '递减' '道' '部件' '采用' '释放' '重量' '量' '锁'\n",
+      " '锂电池' '闭合' '间歇' '阻力' '阻抗' '雾化' '静态' '顺应性' '频率' '驱动' '高' '高压' '高温' '高温高压'\n",
+      " '高级']\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\wystan\\anaconda3\\envs\\TenderAutomateSystem\\Lib\\site-packages\\sklearn\\feature_extraction\\text.py:517: UserWarning: The parameter 'token_pattern' will not be used since 'tokenizer' is not None'\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "execution_count": 14
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-12-31T09:26:57.905444Z",
+     "start_time": "2024-12-31T09:26:57.811280Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "# 定义聚类的数量\n",
+    "num_clusters = 50\n",
+    "kmeans = KMeans(n_clusters=num_clusters, random_state=42)\n",
+    "kmeans.fit(tfidf_matrix)\n",
+    "labels = kmeans.labels_\n",
+    "\n",
+    "# 初始化结果目录\n",
+    "clusters_dir = \"../data/clusters/SV300\"\n",
+    "shutil.rmtree(clusters_dir)\n",
+    "os.makedirs(clusters_dir)\n",
+    "# 输出每个文档对应的聚类标签\n",
+    "for idx, label in enumerate(labels):\n",
+    "    with open(os.path.join(clusters_dir, f\"{label}.txt\"), \"a\", encoding=\"utf8\") as f:\n",
+    "        f.write(items[idx])\n",
+    "        f.write(\"\\n\")\n",
+    "\n",
+    "# 可选：计算轮廓系数以评估聚类效果\n",
+    "score = silhouette_score(tfidf_matrix, labels)\n",
+    "print(f\"轮廓系数: {score}\")\n",
+    "\n",
+    "# 查看每个聚类的中心词\n",
+    "order_centroids = kmeans.cluster_centers_.argsort()[:, ::-1]\n",
+    "for label in range(num_clusters):\n",
+    "    top_terms = [feature_names[ind] for ind in order_centroids[label, :10]]\n",
+    "    with open(os.path.join(clusters_dir, f\"{label}_words.txt\"), \"a\", encoding=\"utf8\") as f:\n",
+    "        f.write(\", \".join(top_terms))\n"
+   ],
+   "id": "c36c60812d8c902b",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "轮廓系数: 0.3455008313963117\n"
+     ]
+    }
+   ],
+   "execution_count": 23
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "5540d5575e1d5965"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -1,3 +1,4 @@
 pandas==2.2.3
 numpy==2.2.1
-openpyxl==3.1.5
+openpyxl==3.1.5
+jieba==0.42.1

tfidf.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+@Project ：recommender
+@File    ：tf_idf.py
+@IDE     ：PyCharm
+@Author  ：rengengchen
+@Time    ：2024/3/13 15:38
+"""
+import os.path
+import re
+
+import jieba
+from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
+
+re_num = re.compile(r'\d+')
+
+stop_words_file = os.path.join(os.path.dirname(__file__), 'ai/stop_words.txt')
+with open(stop_words_file, mode='r', encoding='utf-8') as f:
+    stop_words = set(word.strip() for word in f.readlines())
+
+
+def filter_word(words):
+    filtered_words = []
+    for word in words:
+        if re_num.match(word):
+            continue
+        if word in stop_words:
+            continue
+        filtered_words.append(word)
+    return filtered_words
+
+
+def jieba_tokenize(text):
+    words = jieba.lcut(text)
+    words = filter_word(words)
+    return words
+
+
+class TFIDF:
+    def __init__(self, min_df, max_df, max_features):
+        self.min_df = min_df
+        self.max_df = max_df
+        self.max_features = max_features
+
+    def count_words(self, corpus):
+        cv = CountVectorizer(tokenizer=jieba_tokenize, min_df=self.min_df, max_df=self.max_df,
+                             max_features=self.max_features)
+        return cv, cv.fit_transform(corpus)
+
+    def fit(self, corpus, get_feature_names=True):
+        cv, words_matrix = self.count_words(corpus)
+
+        tfidf_transformer = TfidfTransformer()
+        tfidf = tfidf_transformer.fit_transform(words_matrix)
+        if get_feature_names:
+            return cv.get_feature_names_out(), tfidf.toarray()
+        # row doc   column word
+        return tfidf.toarray()