ICEEMDAN-Solar_power-forecast/iceemdan-low-LSTM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\asus\\AppData\\Roaming\\Python\\Python39\\site-packages\\pandas\\core\\computation\\expressions.py:21: UserWarning: Pandas requires version '2.8.4' or newer of 'numexpr' (version '2.8.3' currently installed).\n",
      "  from pandas.core.computation.check import NUMEXPR_INSTALLED\n",
      "C:\\Users\\asus\\AppData\\Roaming\\Python\\Python39\\site-packages\\pandas\\core\\arrays\\masked.py:60: UserWarning: Pandas requires version '1.3.6' or newer of 'bottleneck' (version '1.3.5' currently installed).\n",
      "  from pandas.core import (\n"
     ]
    }
   ],
   "source": [
    "from math import sqrt\n",
    "from numpy import concatenate\n",
    "from matplotlib import pyplot\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from tensorflow.keras import Sequential\n",
    "\n",
    "from tensorflow.keras.layers import Dense\n",
    "from tensorflow.keras.layers import LSTM\n",
    "from tensorflow.keras.layers import Dropout\n",
    "from sklearn.model_selection import train_test_split\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "这段代码是一个函数 time_series_to_supervised，它用于将时间序列数据转换为监督学习问题的数据集。下面是该函数的各个部分的含义：\n",
    "\n",
    "data: 输入的时间序列数据，可以是列表或2D NumPy数组。\n",
    "n_in: 作为输入的滞后观察数，即用多少个时间步的观察值作为输入。默认值为96，表示使用前96个时间步的观察值作为输入。\n",
    "n_out: 作为输出的观测数量，即预测多少个时间步的观察值。默认值为10，表示预测未来10个时间步的观察值。\n",
    "dropnan: 布尔值，表示是否删除具有NaN值的行。默认为True，即删除具有NaN值的行。\n",
    "函数首先检查输入数据的维度，并初始化一些变量。然后，它创建一个新的DataFrame对象 df 来存储输入数据，并保存原始的列名。接着，它创建了两个空列表 cols 和 names，用于存储新的特征列和列名。\n",
    "\n",
    "接下来，函数开始构建特征列和对应的列名。首先，它将原始的观察序列添加到 cols 列表中，并将其列名添加到 names 列表中。然后，它依次将滞后的观察序列添加到 cols 列表中，并构建相应的列名，格式为 (原始列名)(t-滞后时间)。这样就创建了输入特征的部分。\n",
    "\n",
    "接着，函数开始构建输出特征的部分。它依次将未来的观察序列添加到 cols 列表中，并构建相应的列名，格式为 (原始列名)(t+未来时间)。\n",
    "\n",
    "最后，函数将所有的特征列拼接在一起，构成一个新的DataFrame对象 agg。如果 dropnan 参数为True，则删除具有NaN值的行。最后，函数返回处理后的数据集 agg。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def time_series_to_supervised(data, n_in=96, n_out=10,dropnan=True):\n",
    "    \"\"\"\n",
    "    :param data:作为列表或2D NumPy数组的观察序列。需要。\n",
    "    :param n_in:作为输入的滞后观察数（X）。值可以在[1..len（数据）]之间可选。默认为1。\n",
    "    :param n_out:作为输出的观测数量（y）。值可以在[0..len（数据）]之间。可选的。默认为1。\n",
    "    :param dropnan:Boolean是否删除具有NaN值的行。可选的。默认为True。\n",
    "    :return:\n",
    "    \"\"\"\n",
    "    n_vars = 1 if type(data) is list else data.shape[1]\n",
    "    df = pd.DataFrame(data)\n",
    "    origNames = df.columns\n",
    "    cols, names = list(), list()\n",
    "    cols.append(df.shift(0))\n",
    "    names += [('%s' % origNames[j]) for j in range(n_vars)]\n",
    "    n_in = max(0, n_in)\n",
    "    for i in range(n_in, 0, -1):\n",
    "        time = '(t-%d)' % i\n",
    "        cols.append(df.shift(i))\n",
    "        names += [('%s%s' % (origNames[j], time)) for j in range(n_vars)]\n",
    "    n_out = max(n_out, 0)\n",
    "    for i in range(1, n_out+1):\n",
    "        time = '(t+%d)' % i\n",
    "        cols.append(df.shift(-i))\n",
    "        names += [('%s%s' % (origNames[j], time)) for j in range(n_vars)]\n",
    "    agg = pd.concat(cols, axis=1)\n",
    "    agg.columns = names\n",
    "    if dropnan:\n",
    "        agg.dropna(inplace=True)\n",
    "    return agg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        Temp   Humidity       GHI       DHI  Rainfall  Power\n",
      "0  19.779453  40.025826  3.232706  1.690531       0.0    0.0\n",
      "1  19.714937  39.605961  3.194991  1.576346       0.0    0.0\n",
      "2  19.549330  39.608631  3.070866  1.576157       0.0    0.0\n",
      "3  19.405870  39.680702  3.038623  1.482489       0.0    0.0\n",
      "4  19.387363  39.319881  2.656474  1.134153       0.0    0.0\n",
      "(104256, 6)\n"
     ]
    }
   ],
   "source": [
    "# 加载数据\n",
    "path1 = r\"D:\\project\\小论文1-基于ICEEMDAN分解的时序高维变化的短期光伏功率预测模型\\CEEMAN-PosConv1dbiLSTM-LSTM\\模型代码流程\\data6.csv\"#数据所在路径\n",
    "#我的数据是excel表，若是csv文件用pandas的read_csv()函数替换即可。\n",
    "datas1 = pd.DataFrame(pd.read_csv(path1))\n",
    "#我只取了data表里的第3、23、16、17、18、19、20、21、27列，如果取全部列的话这一行可以去掉\n",
    "# data1 = datas1.iloc[:,np.r_[3,23,16:22,27]]\n",
    "data1=datas1.interpolate()\n",
    "values1 = data1.values\n",
    "print(data1.head())\n",
    "print(data1.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# data2= data1.drop(['date'], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # 获取重构的原始数据\n",
    "# # 获取重构的原始数据\n",
    "# # 获取重构的原始数据\n",
    "path_re = r\"D:\\project\\小论文1-基于ICEEMDAN分解的时序高维变化的短期光伏功率预测模型\\CEEMAN-PosConv1dbiLSTM-LSTM\\模型代码流程\\完整的模型代码流程\\iceemdan_reconstructed_data_low.csv\"#数据所在路径\n",
    "# #我的数据是excel表，若是csv文件用pandas的read_csv()函数替换即可。\n",
    "data_re = pd.DataFrame(pd.read_csv(path_re))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>column_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.460307</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.460504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.460698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.460886</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.461071</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104251</th>\n",
       "      <td>1.663370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104252</th>\n",
       "      <td>1.664516</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104253</th>\n",
       "      <td>1.665650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104254</th>\n",
       "      <td>1.666774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104255</th>\n",
       "      <td>1.667887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>104256 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        column_name\n",
       "0          1.460307\n",
       "1          1.460504\n",
       "2          1.460698\n",
       "3          1.460886\n",
       "4          1.461071\n",
       "...             ...\n",
       "104251     1.663370\n",
       "104252     1.664516\n",
       "104253     1.665650\n",
       "104254     1.666774\n",
       "104255     1.667887\n",
       "\n",
       "[104256 rows x 1 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# # 假设你已经有了原始数据和重构数据\n",
    "# # 原始数据\n",
    "original_data = data1['Power'].values\n",
    "\n",
    "# # 创建时间序列（假设时间序列与数据对应）\n",
    "time = range(len(original_data))\n",
    "\n",
    "# # 创建画布和子图\n",
    "plt.figure(figsize=(10, 6))\n",
    "\n",
    "# # 绘制原始数据\n",
    "# plt.plot(time, original_data, label='Original Data', color='blue')\n",
    "\n",
    "# # 绘制重构数据\n",
    "plt.plot( data_re[:], label='Reconstructed Data', color='red')\n",
    "\n",
    "# # 添加标题和标签\n",
    "plt.title('Comparison between Original and reconstructed_data_high')\n",
    "plt.xlabel('Time')\n",
    "plt.ylabel('Power')\n",
    "plt.legend()\n",
    "\n",
    "# # 显示图形\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "data3=data1.iloc[:,:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "             Temp   Humidity       GHI       DHI  Rainfall  column_name\n",
      "0       19.779453  40.025826  3.232706  1.690531       0.0     1.460307\n",
      "1       19.714937  39.605961  3.194991  1.576346       0.0     1.460504\n",
      "2       19.549330  39.608631  3.070866  1.576157       0.0     1.460698\n",
      "3       19.405870  39.680702  3.038623  1.482489       0.0     1.460886\n",
      "4       19.387363  39.319881  2.656474  1.134153       0.0     1.461071\n",
      "...           ...        ...       ...       ...       ...          ...\n",
      "104251  13.303740  34.212711  1.210789  0.787026       0.0     1.663370\n",
      "104252  13.120920  34.394939  2.142980  1.582670       0.0     1.664516\n",
      "104253  12.879215  35.167400  1.926214  1.545889       0.0     1.665650\n",
      "104254  12.915867  35.359989  1.317695  0.851529       0.0     1.666774\n",
      "104255  13.134816  34.500034  1.043269  0.597816       0.0     1.667887\n",
      "\n",
      "[104256 rows x 6 columns]\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# # 创建data3和imf1_array对应的DataFrame\n",
    "data3_df = pd.DataFrame(data3)\n",
    "imf1_df = pd.DataFrame(data_re)\n",
    "\n",
    "# # 合并data3_df和imf1_df\n",
    "merged_df = pd.concat([data3_df, imf1_df], axis=1)\n",
    "\n",
    "# # 设置行数为35040行\n",
    "merged_df = merged_df.iloc[:104256]\n",
    "\n",
    "# # 打印合并后的表\n",
    "print(merged_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(104256, 6)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(104256, 6)\n"
     ]
    }
   ],
   "source": [
    "# 使用MinMaxScaler进行归一化\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "scaledData1 = scaler.fit_transform(merged_df)\n",
    "print(scaledData1.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "            0         1         2         3    4         5   0(t-96)  \\\n",
      "96   0.555631  0.349673  0.190042  0.040558  0.0  0.777807  0.490360   \n",
      "97   0.564819  0.315350  0.211335  0.044613  0.0  0.777601  0.489088   \n",
      "98   0.576854  0.288321  0.229657  0.047549  0.0  0.777391  0.485824   \n",
      "99   0.581973  0.268243  0.247775  0.053347  0.0  0.777176  0.482997   \n",
      "100  0.586026  0.264586  0.266058  0.057351  0.0  0.776958  0.482632   \n",
      "\n",
      "      1(t-96)   2(t-96)   3(t-96)  ...    2(t+2)    3(t+2)  4(t+2)    5(t+2)  \\\n",
      "96   0.369105  0.002088  0.002013  ...  0.229657  0.047549     0.0  0.777391   \n",
      "97   0.364859  0.002061  0.001839  ...  0.247775  0.053347     0.0  0.777176   \n",
      "98   0.364886  0.001973  0.001839  ...  0.266058  0.057351     0.0  0.776958   \n",
      "99   0.365615  0.001950  0.001697  ...  0.282900  0.060958     0.0  0.776735   \n",
      "100  0.361965  0.001679  0.001167  ...  0.299668  0.065238     0.0  0.776508   \n",
      "\n",
      "       0(t+3)    1(t+3)    2(t+3)    3(t+3)  4(t+3)    5(t+3)  \n",
      "96   0.581973  0.268243  0.247775  0.053347     0.0  0.777176  \n",
      "97   0.586026  0.264586  0.266058  0.057351     0.0  0.776958  \n",
      "98   0.590772  0.258790  0.282900  0.060958     0.0  0.776735  \n",
      "99   0.600396  0.249246  0.299668  0.065238     0.0  0.776508  \n",
      "100  0.607019  0.247850  0.313694  0.066189     0.0  0.776277  \n",
      "\n",
      "[5 rows x 600 columns]\n"
     ]
    }
   ],
   "source": [
    "n_steps_in =96 #历史时间长度\n",
    "n_steps_out=3#预测时间长度\n",
    "processedData1 = time_series_to_supervised(scaledData1,n_steps_in,n_steps_out)\n",
    "print(processedData1.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# processedData1.to_csv('processedData1.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_x = processedData1.loc[:,'0(t-96)':'5(t-1)']\n",
    "data_y = processedData1.loc[:,'5(t+3)']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(104157, 576)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "96        0.777176\n",
       "97        0.776958\n",
       "98        0.776735\n",
       "99        0.776508\n",
       "100       0.776277\n",
       "            ...   \n",
       "104248    0.897435\n",
       "104249    0.898092\n",
       "104250    0.898742\n",
       "104251    0.899387\n",
       "104252    0.900025\n",
       "Name: 5(t+3), Length: 104157, dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(104157,)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(83325, 96, 6) (83325,) (10417, 96, 6) (10417,) (10415, 96, 6) (10415,)\n"
     ]
    }
   ],
   "source": [
    "# 计算训练集、验证集和测试集的大小\n",
    "train_size = int(len(data_x) * 0.8)\n",
    "test_size = int(len(data_x) * 0.1)\n",
    "val_size = len(data_x) - train_size - test_size\n",
    "\n",
    "# 计算训练集、验证集和测试集的索引范围\n",
    "train_indices = range(train_size)\n",
    "val_indices = range(train_size, train_size + val_size)\n",
    "test_indices = range(train_size + val_size, len(data_x))\n",
    "\n",
    "# 根据索引范围划分数据集\n",
    "train_X1 = data_x.iloc[train_indices].values.reshape((-1, n_steps_in, scaledData1.shape[1]))\n",
    "val_X1 = data_x.iloc[val_indices].values.reshape((-1, n_steps_in, scaledData1.shape[1]))\n",
    "test_X1 = data_x.iloc[test_indices].values.reshape((-1, n_steps_in, scaledData1.shape[1]))\n",
    "train_y = data_y.iloc[train_indices].values\n",
    "val_y = data_y.iloc[val_indices].values\n",
    "test_y = data_y.iloc[test_indices].values\n",
    "\n",
    "# reshape input to be 3D [samples, timesteps, features]\n",
    "train_X = train_X1.reshape((train_X1.shape[0], n_steps_in, scaledData1.shape[1]))\n",
    "val_X = val_X1.reshape((val_X1.shape[0], n_steps_in, scaledData1.shape[1]))\n",
    "test_X = test_X1.reshape((test_X1.shape[0], n_steps_in, scaledData1.shape[1]))\n",
    "\n",
    "print(train_X.shape, train_y.shape, val_X.shape, val_y.shape, test_X.shape, test_y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(83325, 96, 6)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_X1.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\Anaconda3\\lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:204: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
      "  super().__init__(**kwargs)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ lstm (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">LSTM</span>)                     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">69,120</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">129</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ lstm (\u001b[38;5;33mLSTM\u001b[0m)                     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m69,120\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │           \u001b[38;5;34m129\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">69,249</span> (270.50 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m69,249\u001b[0m (270.50 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">69,249</span> (270.50 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m69,249\u001b[0m (270.50 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from keras.layers import GRU, Bidirectional\n",
    "from keras.models import Model\n",
    "from keras.layers import Input, Conv1D, MaxPooling1D, LSTM, Dense, Attention, Flatten\n",
    "import keras\n",
    "from keras.models import Sequential\n",
    "from keras.layers import LSTM, Dense\n",
    "\n",
    "# 创建模型\n",
    "model = Sequential()\n",
    "\n",
    "# 添加单层 LSTM\n",
    "model.add(LSTM(units=128, input_shape=(96, 6)))\n",
    "\n",
    "# 添加输出层\n",
    "model.add(Dense(1))\n",
    "\n",
    "# 编译模型\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "# 查看模型结构\n",
    "model.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m45s\u001b[0m 34ms/step - loss: 0.0071 - val_loss: 1.3979e-05\n",
      "Epoch 2/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m45s\u001b[0m 35ms/step - loss: 1.7388e-05 - val_loss: 2.4750e-05\n",
      "Epoch 3/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m55s\u001b[0m 42ms/step - loss: 9.4934e-06 - val_loss: 2.6778e-06\n",
      "Epoch 4/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 59ms/step - loss: 7.7084e-06 - val_loss: 8.5239e-06\n",
      "Epoch 5/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m59s\u001b[0m 46ms/step - loss: 1.0285e-05 - val_loss: 7.4017e-06\n",
      "Epoch 6/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m64s\u001b[0m 49ms/step - loss: 4.5950e-06 - val_loss: 4.3379e-06\n",
      "Epoch 7/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 56ms/step - loss: 7.2545e-06 - val_loss: 5.1982e-05\n",
      "Epoch 8/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 60ms/step - loss: 8.1455e-06 - val_loss: 5.4236e-06\n",
      "Epoch 9/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 57ms/step - loss: 4.0686e-06 - val_loss: 1.6651e-06\n",
      "Epoch 10/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 53ms/step - loss: 4.4366e-06 - val_loss: 1.1472e-06\n",
      "Epoch 11/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 57ms/step - loss: 5.2050e-06 - val_loss: 1.9424e-07\n",
      "Epoch 12/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 58ms/step - loss: 2.9417e-06 - val_loss: 7.2545e-06\n",
      "Epoch 13/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m46s\u001b[0m 35ms/step - loss: 3.5579e-06 - val_loss: 8.3836e-07\n",
      "Epoch 14/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 47ms/step - loss: 2.9325e-06 - val_loss: 1.8872e-06\n",
      "Epoch 15/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 50ms/step - loss: 1.1996e-06 - val_loss: 4.9818e-07\n",
      "Epoch 16/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 31ms/step - loss: 1.9083e-06 - val_loss: 1.1571e-06\n",
      "Epoch 17/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 32ms/step - loss: 2.5659e-06 - val_loss: 2.3767e-07\n",
      "Epoch 18/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 32ms/step - loss: 1.9273e-06 - val_loss: 2.9061e-07\n",
      "Epoch 19/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 32ms/step - loss: 1.8791e-06 - val_loss: 2.7131e-06\n",
      "Epoch 20/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 32ms/step - loss: 2.5186e-06 - val_loss: 1.0457e-06\n",
      "Epoch 21/100\n",
      "\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 32ms/step - loss: 1.6832e-06 - val_loss: 3.1923e-06\n",
      "\u001b[1m326/326\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 9ms/step\n"
     ]
    }
   ],
   "source": [
    "# Compile and train the model\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "from keras.callbacks import EarlyStopping, ModelCheckpoint\n",
    "\n",
    "# 定义早停机制\n",
    "early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=0, mode='min')\n",
    "\n",
    "# 拟合模型，并添加早停机制和模型检查点\n",
    "history = model.fit(train_X, train_y, epochs=100, batch_size=64, validation_data=(test_X, test_y), \n",
    "                    callbacks=[early_stopping])\n",
    "# 预测\n",
    "lstm_pred = model.predict(test_X)\n",
    "# 将预测结果的形状修改为与原始数据相同的形状"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10415, 1)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lstm_pred.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10415,)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_y1=test_y.reshape(10415,1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.7652725 ],\n",
       "       [0.76545048],\n",
       "       [0.76562896],\n",
       "       ...,\n",
       "       [0.8987423 ],\n",
       "       [0.89938682],\n",
       "       [0.90002507]])"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_y1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "results1 = np.broadcast_to(lstm_pred, (10415, 6))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_y2 = np.broadcast_to(test_y1, (10415, 6))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 反归一化\n",
    "inv_forecast_y = scaler.inverse_transform(results1)\n",
    "inv_test_y = scaler.inverse_transform(test_y2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  33.72769272,   79.19746393, 1078.1022603 ,  503.73660832,\n",
       "          18.21349214,    1.43294754],\n",
       "       [  33.73672318,   79.21506254, 1078.35293583,  503.85368135,\n",
       "          18.2177282 ,    1.43325785],\n",
       "       [  33.74577882,   79.23271021, 1078.60431013,  503.97108072,\n",
       "          18.22197608,    1.43356904],\n",
       "       ...,\n",
       "       [  40.49954372,   92.3944846 , 1266.08128876,  591.5284767 ,\n",
       "          21.39007466,    1.66565038],\n",
       "       [  40.53224485,   92.45821275, 1266.98903575,  591.95242188,\n",
       "          21.40541432,    1.6667741 ],\n",
       "       [  40.56462766,   92.52132055, 1267.88794639,  592.37224023,\n",
       "          21.42060465,    1.66788688]])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inv_test_y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test RMSE: 0.003\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 计算均方根误差\n",
    "rmse = sqrt(mean_squared_error(inv_test_y[:,5], inv_forecast_y[:,5]))\n",
    "print('Test RMSE: %.3f' % rmse)\n",
    "#画图\n",
    "plt.figure(figsize=(16,8))\n",
    "plt.plot(inv_test_y[:,5], label='true')\n",
    "plt.plot(inv_forecast_y[:,5], label='pre')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mean_squared_error: 3.192312293602162e-06\n",
      "mean_absolute_error: 0.0016849238078766036\n",
      "rmse: 0.001786704310623938\n",
      "r2 score: 0.9997179606290253\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error, mean_absolute_error  # 评价指标\n",
    "# 使用sklearn调用衡量线性回归的MSE 、 RMSE、 MAE、r2\n",
    "from math import sqrt\n",
    "from sklearn.metrics import mean_absolute_error\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn.metrics import r2_score\n",
    "print('mean_squared_error:', mean_squared_error(lstm_pred, test_y))  # mse)\n",
    "print(\"mean_absolute_error:\", mean_absolute_error(lstm_pred, test_y))  # mae\n",
    "print(\"rmse:\", sqrt(mean_squared_error(lstm_pred,test_y)))\n",
    "print(\"r2 score:\", r2_score(inv_test_y[:], inv_forecast_y[:]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "df1 = pd.DataFrame(inv_test_y[:,5], columns=['column_name'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n",
    "df1.to_csv('xin9996低频_test(T+3).csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = pd.DataFrame(inv_forecast_y[:,5], columns=['column_name'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n",
    "df2.to_csv('xin9996低频_forecast(T+3).csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}