exercise2.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## numpy 综合案例：花萼长度数据统计分析\n",
    "### 现有 iris 数据集中的花萼长度数据一份，已保存为 csv 格式，请按下方要求先对数据进行清洗整理，再进行相关统计分析。\n",
    "### 1. 利用 numpy 读取 csv 文件数据，命名为 iris，并以 ndarry 形式展示出来"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5.1, 4.9, 4.7, 4.6, 5. , 5.4, 4.6, 5. , 4.4, 4.9, 5.4, 4.8, 4.8,\n",
       "       4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5. ,\n",
       "       5. , 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5. , 5.5, 4.9, 4.4,\n",
       "       5.1, 5. , 4.5, 4.4, 5. , 5.1, 4.8, 5.1, 4.6, 5.3, 5. , 7. , 6.4,\n",
       "       6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5. , 5.9, 6. , 6.1, 5.6,\n",
       "       6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7,\n",
       "       6. , 5.7, 5.5, 5.5, 5.8, 6. , 5.4, 6. , 6.7, 6.3, 5.6, 5.5, 5.5,\n",
       "       6.1, 5.8, 5. , 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3,\n",
       "       6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5,\n",
       "       7.7, 7.7, 6. , 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2,\n",
       "       7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6. , 6.9, 6.7, 6.9, 5.8,\n",
       "       6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9])"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "with open('iris.csv') as f:\n",
    "    iris = np.loadtxt(f, delimiter = \",\")\n",
    "iris"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. 找出原数据中最小值和最大值出现的位置\n",
    "（任务提示：numpy 中 argmax 和 argmin 函数可以定位到最大值和最小值的索引位置。）"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "max_index: 131\n",
      "min_index: 13\n"
     ]
    }
   ],
   "source": [
    "print('max_index:',np.argmax(iris))\n",
    "print('min_index:',np.argmin(iris))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. 利用 numpy 找出花萼最小值与最大值"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "max: 7.9\n",
      "min: 4.3\n"
     ]
    }
   ],
   "source": [
    "# max()和min()是python的内置函数\n",
    "print('max:',max(iris))\n",
    "print('min:',min(iris))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. 将 iris 原数据进行从小到大排序，并以 ndarray 形式展示出来\n",
    "（任务提示：排序函数为 sort。）"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([4.3, 4.4, 4.4, 4.4, 4.5, 4.6, 4.6, 4.6, 4.6, 4.7, 4.7, 4.8, 4.8,\n",
       "       4.8, 4.8, 4.8, 4.9, 4.9, 4.9, 4.9, 4.9, 4.9, 5. , 5. , 5. , 5. ,\n",
       "       5. , 5. , 5. , 5. , 5. , 5. , 5.1, 5.1, 5.1, 5.1, 5.1, 5.1, 5.1,\n",
       "       5.1, 5.1, 5.2, 5.2, 5.2, 5.2, 5.3, 5.4, 5.4, 5.4, 5.4, 5.4, 5.4,\n",
       "       5.5, 5.5, 5.5, 5.5, 5.5, 5.5, 5.5, 5.6, 5.6, 5.6, 5.6, 5.6, 5.6,\n",
       "       5.7, 5.7, 5.7, 5.7, 5.7, 5.7, 5.7, 5.7, 5.8, 5.8, 5.8, 5.8, 5.8,\n",
       "       5.8, 5.8, 5.9, 5.9, 5.9, 6. , 6. , 6. , 6. , 6. , 6. , 6.1, 6.1,\n",
       "       6.1, 6.1, 6.1, 6.1, 6.2, 6.2, 6.2, 6.2, 6.3, 6.3, 6.3, 6.3, 6.3,\n",
       "       6.3, 6.3, 6.3, 6.3, 6.4, 6.4, 6.4, 6.4, 6.4, 6.4, 6.4, 6.5, 6.5,\n",
       "       6.5, 6.5, 6.5, 6.6, 6.6, 6.7, 6.7, 6.7, 6.7, 6.7, 6.7, 6.7, 6.7,\n",
       "       6.8, 6.8, 6.8, 6.9, 6.9, 6.9, 6.9, 7. , 7.1, 7.2, 7.2, 7.2, 7.3,\n",
       "       7.4, 7.6, 7.7, 7.7, 7.7, 7.7, 7.9])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris.sort()\n",
    "iris"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5. 去除该组数据中的重复值"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5. , 5.1, 5.2, 5.3, 5.4, 5.5,\n",
       "       5.6, 5.7, 5.8, 5.9, 6. , 6.1, 6.2, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8,\n",
       "       6.9, 7. , 7.1, 7.2, 7.3, 7.4, 7.6, 7.7, 7.9])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "uni_iris = np.unique(iris)\n",
    "uni_iris"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6. 请利用 numpy 计算出该组花萼的平均长度"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5.843333333333334"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(iris)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 7. 用numpy计算出该组数据的标准差和方差"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "标准差 0.8253012917851409\n",
      "方差 0.6811222222222223\n"
     ]
    }
   ],
   "source": [
    "print('标准差', np.std(iris))\n",
    "print('方差', np.var(iris))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 8. 求出所有花瓣累积总和"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "876.5"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sum(iris)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 9. 对已排序的 iris 数据进行累积求和运算\n",
    "任务提示：累积求和与求和有区别，累积求和是前几个数相加成新的元素从而组成新的数组"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([  4.3,   8.7,  13.1,  17.5,  22. ,  26.6,  31.2,  35.8,  40.4,\n",
       "        45.1,  49.8,  54.6,  59.4,  64.2,  69. ,  73.8,  78.7,  83.6,\n",
       "        88.5,  93.4,  98.3, 103.2, 108.2, 113.2, 118.2, 123.2, 128.2,\n",
       "       133.2, 138.2, 143.2, 148.2, 153.2, 158.3, 163.4, 168.5, 173.6,\n",
       "       178.7, 183.8, 188.9, 194. , 199.1, 204.3, 209.5, 214.7, 219.9,\n",
       "       225.2, 230.6, 236. , 241.4, 246.8, 252.2, 257.6, 263.1, 268.6,\n",
       "       274.1, 279.6, 285.1, 290.6, 296.1, 301.7, 307.3, 312.9, 318.5,\n",
       "       324.1, 329.7, 335.4, 341.1, 346.8, 352.5, 358.2, 363.9, 369.6,\n",
       "       375.3, 381.1, 386.9, 392.7, 398.5, 404.3, 410.1, 415.9, 421.8,\n",
       "       427.7, 433.6, 439.6, 445.6, 451.6, 457.6, 463.6, 469.6, 475.7,\n",
       "       481.8, 487.9, 494. , 500.1, 506.2, 512.4, 518.6, 524.8, 531. ,\n",
       "       537.3, 543.6, 549.9, 556.2, 562.5, 568.8, 575.1, 581.4, 587.7,\n",
       "       594.1, 600.5, 606.9, 613.3, 619.7, 626.1, 632.5, 639. , 645.5,\n",
       "       652. , 658.5, 665. , 671.6, 678.2, 684.9, 691.6, 698.3, 705. ,\n",
       "       711.7, 718.4, 725.1, 731.8, 738.6, 745.4, 752.2, 759.1, 766. ,\n",
       "       772.9, 779.8, 786.8, 793.9, 801.1, 808.3, 815.5, 822.8, 830.2,\n",
       "       837.8, 845.5, 853.2, 860.9, 868.6, 876.5])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.cumsum(iris)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 10. 统计花萼长度比平均值 5.84 高的有多少\n",
    "任务提示：例如 (arr>1).sum() 可统计大于1的个数"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "70"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(iris > 5.84).sum()"
   ]
  }
 ],
 "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": "3.7.6"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}