机器学习大作业-预测电站的小时净电能输出.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "weight = [-14.594  -3.069   0.347  -2.301]\n",
      "bais = 454.353\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#导入包\n",
    "from tkinter import W\n",
    "import pandas\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "#设置参数\n",
    "iterations = 10000\n",
    "learning_rate = 0.01\n",
    "\n",
    "#读取数据\n",
    "\n",
    "ds=pandas.read_csv('Folds5x2_pp.csv')\n",
    "data = np.array(ds)\n",
    "m_all = ds.shape[0]\n",
    "d = ds.shape[1] - 1\n",
    "m_train = 7176\n",
    "m_test = m_all - m_train \n",
    "\n",
    "#特征缩放（标准化）\n",
    "mean = np.mean(data[0:m_train,:d],axis=0)\n",
    "\n",
    "std = np.std(data[0:m_train,:d],axis=0)\n",
    "data[:,:d] = (data[:,:d] - mean)/std\n",
    "\n",
    "\n",
    "\n",
    "#划分训练集与测试集\n",
    "rng = np.random.default_rng(1)\n",
    "rng.shuffle(data)\n",
    "\n",
    "train_x = data[0:m_train,0:4].T\n",
    "\n",
    "train_y = data[0:m_train,4].T\n",
    "\n",
    "test_x = data[m_train:m_all,:4].T\n",
    "test_y = data[m_train:m_all,4].T\n",
    "\n",
    "\n",
    "#初始化w,b,cost[]\n",
    "w = np.zeros((1,d)).T\n",
    "b = 0\n",
    "v = np.ones((1,m_train))\n",
    "costs_save = []\n",
    "\n",
    "\n",
    "#迭代\n",
    "for i in range(iterations):\n",
    "\n",
    "    y_hat = np.dot(w.T,train_x) + b*v\n",
    "    e = y_hat - train_y\n",
    "\n",
    "    w = w - 2*learning_rate*np.dot(train_x,e.T)/m_train\n",
    "    b = b - 2*learning_rate*np.dot(v,e.T)/m_train\n",
    "\n",
    "    cost = np.dot(e,e.T) / m_train\n",
    "    costs_save.append(cost.item(0))\n",
    "\n",
    "# 输出训练完成的w,b\n",
    "\n",
    "print(f'weight = {np.around(np.squeeze(w),3)}')\n",
    "print(f'bais = {np.around(np.squeeze(b),3)}')\n",
    "\n",
    "#画出代价函数随迭代次数的变化图\n",
    "plt.figure()\n",
    "plt.plot(range(1,iterations+1),costs_save,'r-o')\n",
    "plt.xlabel(\"iterations\")\n",
    "plt.ylabel(\"cost\")\n",
    "plt.title(\"Learning_rate = \" +str(learning_rate))\n",
    "\n",
    "plt.show()\n",
    "\n",
    "\n",
    "#计算训练集和测试集的RMSE\n",
    "\n",
    "\n",
    "\n",
    "#计算指标性能\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.12 ('base')",
   "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": "3.9.12"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "2de64d48b397309e85ec6e005dc67bd86cbca9029b67c7a68e6c5e4c08605d48"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}