UPDATE

fd8bb69b · 63c50e17543b320f79aa675e · e6376ef1 · e6376ef1 · fd8bb69b · fd8bb69b
6 changed file
--- a/a.ipynb
+++ b/a.ipynb
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# 异常值检测"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Looking in indexes: http://mirrors.csdn.net.cn/repository/csdn-pypi-mirrors/simple\n",
-      "Requirement already satisfied: pandas in /usr/local/lib/python3.8/dist-packages (2.0.1)\n",
-      "Requirement already satisfied: openpyxl in /usr/local/lib/python3.8/dist-packages (3.1.2)\n",
-      "Requirement already satisfied: xlrd==1.2.0 in /usr/local/lib/python3.8/dist-packages (1.2.0)\n",
-      "Requirement already satisfied: python-dateutil>=2.8.2 in /root/.local/lib/python3.8/site-packages (from pandas) (2.8.2)\n",
-      "Requirement already satisfied: numpy>=1.20.3 in /usr/local/lib/python3.8/dist-packages (from pandas) (1.24.3)\n",
-      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.8/dist-packages (from pandas) (2023.3)\n",
-      "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.8/dist-packages (from pandas) (2023.3)\n",
-      "Requirement already satisfied: et-xmlfile in /usr/local/lib/python3.8/dist-packages (from openpyxl) (1.1.0)\n",
-      "Requirement already satisfied: six>=1.5 in /root/.local/lib/python3.8/site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
-      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
-      "\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.2.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "pip install pandas openpyxl xlrd==1.2.0"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'outlier_values': array([  51. , 6607.4,  865. ]),\n",
-       " 'outlier_index': array([ 0,  8, 15]),\n",
-       " 'outlier_ratio': 0.15789473684210525}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import numpy as np\n",
-    "\n",
-    "def detect_outliers(data):\n",
-    "    # 使用numpy中的percentile函数计算百分位数\n",
-    "    data=np.array(data)\n",
-    "    q1, q3 = np.percentile(data, [25, 75])\n",
-    "    iqr = q3 - q1  # 计算四分位距\n",
-    "    upper_bound = q3 + 1.5 * iqr  # 计算上界\n",
-    "    lower_bound = q1 - 1.5 * iqr  # 计算下界\n",
-    "\n",
-    "    # 判断异常值，大于上界或小于下界的值即为异常值\n",
-    "    outliers = data[(data > upper_bound) | (data < lower_bound)]\n",
-    "    outlier_index = np.where((data > upper_bound) | (data < lower_bound))[0]\n",
-    "\n",
-    "    # 计算异常值比例\n",
-    "    outlier_ratio = len(outliers) / len(data)\n",
-    "\n",
-    "    # 将结果存储到字典中\n",
-    "    result = {\n",
-    "        'outlier_values': outliers,\n",
-    "        'outlier_index': outlier_index,\n",
-    "        'outlier_ratio': outlier_ratio\n",
-    "    }\n",
-    "    return result\n",
-    "detect_outliers([51, 2618.2, 2608.4, 2651.9, 3442.1, 3393.1, 3136.1, 3744.1,\n",
-    "                  6607.4, 4060.3, 3614.7, 3295.5, 2332.1, 2699.3, 3036.8,\n",
-    "                  865, 3014.3, 2742.8, 2173.5])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.10"
-  },
-  "orig_nbformat": 4,
-  "vscode": {
-   "interpreter": {
-    "hash": "916dbcbb3f70747c44a77c7bcd40155683ae19c65e1c03b4aa3499c5328201f1"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
--- a/code/数据预测.ipynb
+++ b/code/数据预测.ipynb
--- a/data/EEG Eye State.arff.txt
+++ b/data/EEG Eye State.arff.txt
--- a/data/fertility_Diagnosis.txt
+++ b/data/fertility_Diagnosis.txt
+进行分析的季节,分析时的年龄,是否患有幼稚病,事故或严重创伤,手术干预,去年高烧,饮酒频率,吸烟习惯,每天花费在坐的小时数,诊断结果
+-0.33,0.69,0,1,1,0,0.8,0,0.88,0
+-0.33,0.94,1,0,1,0,0.8,1,0.31,1
+-0.33,0.5,1,0,0,0,1,-1,0.5,0
+-0.33,0.75,0,1,1,0,1,-1,0.38,0
+-0.33,0.67,1,1,0,0,0.8,-1,0.5,1
+-0.33,0.67,1,0,1,0,0.8,0,0.5,0
+-0.33,0.67,0,0,0,-1,0.8,-1,0.44,0
+-0.33,1,1,1,1,0,0.6,-1,0.38,0
+1,0.64,0,0,1,0,0.8,-1,0.25,0
+1,0.61,1,0,0,0,1,-1,0.25,0
+1,0.67,1,1,0,-1,0.8,0,0.31,0
+1,0.78,1,1,1,0,0.6,0,0.13,0
+1,0.75,1,1,1,0,0.8,1,0.25,0
+1,0.81,1,0,0,0,1,-1,0.38,0
+1,0.94,1,1,1,0,0.2,-1,0.25,0
+1,0.81,1,1,0,0,1,1,0.5,0
+1,0.64,1,0,1,0,1,-1,0.38,0
+1,0.69,1,0,1,0,0.8,-1,0.25,1
+1,0.75,1,1,1,0,1,1,0.25,0
+1,0.67,1,0,0,0,0.8,1,0.38,1
+1,0.67,0,0,1,0,0.8,-1,0.25,0
+1,0.75,1,0,0,0,0.6,0,0.25,0
+1,0.67,1,1,0,0,0.8,-1,0.25,0
+1,0.69,1,0,1,-1,1,-1,0.44,1
+1,0.56,1,0,1,0,1,-1,0.63,0
+1,0.67,1,0,0,0,1,-1,0.25,0
+1,0.67,1,0,1,0,0.6,-1,0.38,1
+1,0.78,1,1,0,1,0.6,-1,0.38,1
+1,0.58,0,0,1,0,1,-1,0.19,0
+1,0.67,0,0,1,0,0.6,0,0.5,1
+1,0.61,1,0,1,0,1,-1,0.63,0
+1,0.56,1,0,0,0,1,-1,0.44,0
+1,0.64,0,0,0,0,1,-1,0.63,0
+1,0.58,1,1,1,0,0.8,0,0.44,0
+1,0.56,1,1,1,0,1,-1,0.63,0
+-1,0.78,1,1,0,1,0.6,-1,0.38,0
+-1,0.78,1,0,1,0,1,-1,0.25,0
+-1,0.56,1,0,1,0,1,-1,0.63,0
+-1,0.67,0,0,1,0,0.6,0,0.5,1
+-1,0.69,1,0,0,0,1,-1,0.31,0
+-1,0.53,1,1,1,0,0.8,1,0.5,0
+-1,0.56,1,1,0,0,0.8,1,0.5,0
+-1,0.58,1,0,1,-1,0.8,1,0.5,0
+-1,0.56,1,0,0,0,1,-1,0.44,0
+-1,0.53,1,1,0,1,1,0,0.31,0
+-1,0.53,1,0,0,1,1,0,0.44,0
+-0.33,0.56,1,0,0,0,1,-1,0.63,0
+-0.33,0.72,1,1,0,0,0.6,1,0.19,0
+-0.33,0.64,1,1,1,0,0.8,-1,0.31,0
+-0.33,0.75,1,1,1,0,0.6,-1,0.19,0
+-0.33,0.67,1,0,1,0,0.8,-1,0.19,0
+-0.33,0.53,1,1,0,1,1,-1,0.75,0
+-0.33,0.53,1,1,0,0,0.8,0,0.5,0
+-0.33,0.58,1,1,1,-1,0.8,0,0.19,0
+-0.33,0.61,1,0,1,0,1,-1,0.63,0
+-0.33,0.58,1,0,1,0,0.8,1,0.19,0
+-0.33,0.53,1,1,0,0,0.8,0,0.75,0
+-0.33,0.69,1,1,1,-1,1,-1,0.75,0
+-0.33,0.56,1,1,0,0,0.4,1,0.63,0
+1,0.58,0,0,0,1,0.8,1,0.44,0
+1,0.56,0,0,0,1,0.8,0,1,0
+-1,0.64,1,0,0,1,1,1,0.25,0
+-1,0.61,1,1,1,0,0.6,-1,0.38,0
+-1,0.56,1,0,0,1,1,-1,0.5,0
+-1,0.53,1,0,0,1,0.8,-1,0.31,0
+-0.33,0.56,0,0,1,0,1,-1,0.56,0
+-0.33,0.5,1,1,0,-1,0.8,0,0.88,0
+-0.33,0.5,1,0,0,1,1,-1,0.47,0
+-0.33,0.5,1,0,0,1,0.8,0,0.31,0
+-0.33,0.5,1,0,1,-1,0.8,-1,0.5,0
+-0.33,0.5,1,1,0,-1,0.8,0,0.88,1
+0.33,0.69,1,0,0,1,1,-1,0.31,0
+1,0.56,1,0,0,1,0.6,0,0.5,0
+-1,0.5,1,0,0,1,0.8,-1,0.44,0
+-1,0.53,1,0,0,1,0.8,-1,0.63,0
+-1,0.78,1,0,1,1,1,1,0.25,0
+-1,0.75,1,0,1,1,0.6,0,0.56,0
+-1,0.72,1,1,1,1,0.8,-1,0.19,0
+-1,0.53,1,1,0,1,0.8,-1,0.38,0
+-1,1,1,0,1,1,0.6,0,0.25,0
+-0.33,0.92,1,1,0,1,1,-1,0.63,0
+-1,0.81,1,1,1,1,0.8,0,0.19,0
+-0.33,0.92,1,0,0,1,0.6,-1,0.19,0
+-0.33,0.86,1,1,1,1,1,-1,0.25,0
+-0.33,0.78,1,0,0,1,1,1,0.06,1
+-0.33,0.89,1,1,0,0,0.6,1,0.31,0
+-0.33,0.75,1,1,1,0,0.6,1,0.25,0
+-0.33,0.75,1,1,1,1,0.8,1,0.25,0
+-0.33,0.83,1,1,1,0,1,-1,0.31,0
+-0.33,0.81,1,1,1,0,1,1,0.38,0
+-0.33,0.81,1,1,1,1,0.8,-1,0.38,0
+0.33,0.78,1,0,0,0,1,1,0.06,0
+0.33,0.75,1,1,0,0,0.8,-1,0.38,0
+0.33,0.75,1,0,1,0,0.8,-1,0.44,1
+1,0.58,1,0,0,0,0.6,1,0.5,0
+-1,0.67,1,0,0,0,1,-1,0.5,0
+-1,0.61,1,0,0,0,0.8,0,0.5,0
+-1,0.67,1,1,1,0,1,-1,0.31,0
+-1,0.64,1,0,1,0,1,0,0.19,0
+-1,0.69,0,1,1,0,0.6,-1,0.19,0
--- a/data/pima-indians-diabetes.data.txt
+++ b/data/pima-indians-diabetes.data.txt
--- a/data/美国女性的平均身高和体重.csv
+++ b/data/美国女性的平均身高和体重.csv
+"","height","weight"
+"1",58,115
+"2",59,117
+"3",60,120
+"4",61,123
+"5",62,126
+"6",63,129
+"7",64,132
+"8",65,135
+"9",66,139
+"10",67,142
+"11",68,146
+"12",69,150
+"13",70,154
+"14",71,159
+"15",72,164