1103 lines
267 KiB
Plaintext
1103 lines
267 KiB
Plaintext
{
|
||
"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','Air_P','RH'], 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",
|
||
"high_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\\high_re.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",
|
||
"high_re = pd.DataFrame(pd.read_csv(high_re))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" column_name\n",
|
||
"0 -1.426824\n",
|
||
"1 -1.426819\n",
|
||
"2 -1.426815\n",
|
||
"3 -1.426812\n",
|
||
"4 -1.426810\n",
|
||
"... ...\n",
|
||
"104251 -1.629381\n",
|
||
"104252 -1.629328\n",
|
||
"104253 -1.629271\n",
|
||
"104254 -1.629213\n",
|
||
"104255 -1.629152\n",
|
||
"\n",
|
||
"[104256 rows x 1 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"reconstructed_data_high= high_re\n",
|
||
"# # 打印重构的原始数据\n",
|
||
"print(reconstructed_data_high)"
|
||
]
|
||
},
|
||
{
|
||
"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(reconstructed_data_high[200:1000], 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 -1.426824\n",
|
||
"1 19.714937 39.605961 3.194991 1.576346 0.0 -1.426819\n",
|
||
"2 19.549330 39.608631 3.070866 1.576157 0.0 -1.426815\n",
|
||
"3 19.405870 39.680702 3.038623 1.482489 0.0 -1.426812\n",
|
||
"4 19.387363 39.319881 2.656474 1.134153 0.0 -1.426810\n",
|
||
"... ... ... ... ... ... ...\n",
|
||
"104251 13.303740 34.212711 1.210789 0.787026 0.0 -1.629381\n",
|
||
"104252 13.120920 34.394939 2.142980 1.582670 0.0 -1.629328\n",
|
||
"104253 12.879215 35.167400 1.926214 1.545889 0.0 -1.629271\n",
|
||
"104254 12.915867 35.359989 1.317695 0.851529 0.0 -1.629213\n",
|
||
"104255 13.134816 34.500034 1.043269 0.597816 0.0 -1.629152\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(reconstructed_data_high)\n",
|
||
"\n",
|
||
"# # 合并data3_df和imf1_df\n",
|
||
"merged_df = pd.concat([data3_df, imf1_df], axis=1)\n",
|
||
"\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 0.245160 0.490360 \n",
|
||
"97 0.564819 0.315350 0.211335 0.044613 0.0 0.264683 0.489088 \n",
|
||
"98 0.576854 0.288321 0.229657 0.047549 0.0 0.283988 0.485824 \n",
|
||
"99 0.581973 0.268243 0.247775 0.053347 0.0 0.303131 0.482997 \n",
|
||
"100 0.586026 0.264586 0.266058 0.057351 0.0 0.322308 0.482632 \n",
|
||
"\n",
|
||
" 1(t-96) 2(t-96) 3(t-96) ... 2(t-1) 3(t-1) 4(t-1) 5(t-1) \\\n",
|
||
"96 0.369105 0.002088 0.002013 ... 0.166009 0.036794 0.0 0.225396 \n",
|
||
"97 0.364859 0.002061 0.001839 ... 0.190042 0.040558 0.0 0.245160 \n",
|
||
"98 0.364886 0.001973 0.001839 ... 0.211335 0.044613 0.0 0.264683 \n",
|
||
"99 0.365615 0.001950 0.001697 ... 0.229657 0.047549 0.0 0.283988 \n",
|
||
"100 0.361965 0.001679 0.001167 ... 0.247775 0.053347 0.0 0.303131 \n",
|
||
"\n",
|
||
" 0(t+1) 1(t+1) 2(t+1) 3(t+1) 4(t+1) 5(t+1) \n",
|
||
"96 0.564819 0.315350 0.211335 0.044613 0.0 0.264683 \n",
|
||
"97 0.576854 0.288321 0.229657 0.047549 0.0 0.283988 \n",
|
||
"98 0.581973 0.268243 0.247775 0.053347 0.0 0.303131 \n",
|
||
"99 0.586026 0.264586 0.266058 0.057351 0.0 0.322308 \n",
|
||
"100 0.590772 0.258790 0.282900 0.060958 0.0 0.340588 \n",
|
||
"\n",
|
||
"[5 rows x 588 columns]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"n_steps_in =96 #历史时间长度\n",
|
||
"n_steps_out=1#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": 31,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\n",
|
||
"# processedData1.to_csv('processedData1.csv', index=False)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"data_x = processedData1.loc[:,'0(t-96)':'5(t-1)']\n",
|
||
"data_y = processedData1.loc[:,'5']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(104159, 576)"
|
||
]
|
||
},
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data_x.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"96 0.245160\n",
|
||
"97 0.264683\n",
|
||
"98 0.283988\n",
|
||
"99 0.303131\n",
|
||
"100 0.322308\n",
|
||
" ... \n",
|
||
"104250 0.000090\n",
|
||
"104251 0.000099\n",
|
||
"104252 0.000109\n",
|
||
"104253 0.000118\n",
|
||
"104254 0.000128\n",
|
||
"Name: 5, Length: 104159, dtype: float64"
|
||
]
|
||
},
|
||
"execution_count": 15,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data_y"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(104159,)"
|
||
]
|
||
},
|
||
"execution_count": 16,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"data_y.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 17,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"(83328, 96, 6) (83328,) (20831, 96, 6) (20831,)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# 7.划分训练集和测试集\n",
|
||
"\n",
|
||
"test_size = int(len(data_x) * 0.2)\n",
|
||
"# 计算训练集和测试集的索引范围\n",
|
||
"train_indices = range(len(data_x) - test_size)\n",
|
||
"test_indices = range(len(data_x) - test_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",
|
||
"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",
|
||
"test_y = data_y.iloc[test_indices].values\n",
|
||
"\n",
|
||
"\n",
|
||
"# # 多次运行代码时希望得到相同的数据分割，可以设置 random_state 参数为一个固定的整数值\n",
|
||
"# train_X1,test_X1, train_y, test_y = train_test_split(data_x.values, data_y.values, test_size=0.2, random_state=343)\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",
|
||
"test_X = test_X1.reshape((test_X1.shape[0], n_steps_in,scaledData1.shape[1]))\n",
|
||
"print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)\n",
|
||
"# 使用train_test_split函数划分训练集和测试集，测试集的比重是40%。\n",
|
||
"# 然后将train_X1、test_X1进行一个升维，变成三维，维数分别是[samples,timesteps,features]。\n",
|
||
"# 打印一下他们的shape：\\\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 18,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(83328, 96, 6)"
|
||
]
|
||
},
|
||
"execution_count": 18,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"train_X1.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"WARNING:tensorflow:From d:\\Anaconda3\\lib\\site-packages\\keras\\src\\backend\\tensorflow\\core.py:192: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
|
||
"\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: \"functional\"</span>\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1mModel: \"functional\"\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>┃<span style=\"font-weight: bold\"> Connected to </span>┃\n",
|
||
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
||
"│ input_layer │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">96</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ - │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ conv1d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">95</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">832</span> │ input_layer[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ max_pooling1d │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">95</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ conv1d[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling1D</span>) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">95</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">49,920</span> │ max_pooling1d[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Bidirectional</span>) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ attention_with_imp… │ [(<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">66,304</span> │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">AttentionWithImpr…</span> │ <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>), (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, │ │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||
"│ │ <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>)] │ │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ global_average_poo… │ (<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\">0</span> │ attention_with_i… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePool…</span> │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ dense_4 (<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> │ global_average_p… │\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┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
|
||
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
||
"│ input_layer │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m96\u001b[0m, \u001b[38;5;34m6\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
|
||
"│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ conv1d (\u001b[38;5;33mConv1D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m95\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m832\u001b[0m │ input_layer[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ max_pooling1d │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m95\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ conv1d[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"│ (\u001b[38;5;33mMaxPooling1D\u001b[0m) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m95\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m49,920\u001b[0m │ max_pooling1d[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||
"│ (\u001b[38;5;33mBidirectional\u001b[0m) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ attention_with_imp… │ [(\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m66,304\u001b[0m │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||
"│ (\u001b[38;5;33mAttentionWithImpr…\u001b[0m │ \u001b[38;5;34m128\u001b[0m), (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, │ │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||
"│ │ \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m)] │ │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ global_average_poo… │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ attention_with_i… │\n",
|
||
"│ (\u001b[38;5;33mGlobalAveragePool…\u001b[0m │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m129\u001b[0m │ global_average_p… │\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\">117,185</span> (457.75 KB)\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m117,185\u001b[0m (457.75 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\">117,185</span> (457.75 KB)\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m117,185\u001b[0m (457.75 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": [
|
||
"import tensorflow as tf\n",
|
||
"from tensorflow.keras.layers import Input, Conv1D, Bidirectional, GlobalAveragePooling1D, Dense, GRU, MaxPooling1D\n",
|
||
"from tensorflow.keras.models import Model\n",
|
||
"from tensorflow.keras.initializers import RandomUniform\n",
|
||
"class AttentionWithImproveRelativePositionEncoding(tf.keras.layers.Layer):\n",
|
||
" def __init__(self, d_model, num_heads, max_len=5000):\n",
|
||
" super(AttentionWithImproveRelativePositionEncoding, self).__init__()\n",
|
||
" self.num_heads = num_heads\n",
|
||
" self.d_model = d_model\n",
|
||
" self.max_len = max_len\n",
|
||
" self.wq = tf.keras.layers.Dense(d_model)\n",
|
||
" self.wk = tf.keras.layers.Dense(d_model)\n",
|
||
" self.wv = tf.keras.layers.Dense(d_model)\n",
|
||
" self.dense = tf.keras.layers.Dense(d_model)\n",
|
||
" self.position_encoding = ImproveRelativePositionEncoding(d_model)\n",
|
||
"\n",
|
||
" def call(self, v, k, q, mask):\n",
|
||
" batch_size = tf.shape(q)[0]\n",
|
||
" q = self.wq(q)\n",
|
||
" k = self.wk(k)\n",
|
||
" v = self.wv(v)\n",
|
||
"\n",
|
||
" # 添加位置编码\n",
|
||
" k += self.position_encoding (k)\n",
|
||
" q += self.position_encoding (q)\n",
|
||
"\n",
|
||
" q = self.split_heads(q, batch_size)\n",
|
||
" k = self.split_heads(k, batch_size)\n",
|
||
" v = self.split_heads(v, batch_size)\n",
|
||
"\n",
|
||
" scaled_attention, attention_weights = self.scaled_dot_product_attention(q, k, v, mask)\n",
|
||
" scaled_attention = tf.transpose(scaled_attention, perm=[0, 2, 1, 3])\n",
|
||
" concat_attention = tf.reshape(scaled_attention, (batch_size, -1, self.d_model))\n",
|
||
" output = self.dense(concat_attention)\n",
|
||
" return output, attention_weights\n",
|
||
"\n",
|
||
" def split_heads(self, x, batch_size):\n",
|
||
" x = tf.reshape(x, (batch_size, -1, self.num_heads, self.d_model // self.num_heads))\n",
|
||
" return tf.transpose(x, perm=[0, 2, 1, 3])\n",
|
||
"\n",
|
||
" def scaled_dot_product_attention(self, q, k, v, mask):\n",
|
||
" matmul_qk = tf.matmul(q, k, transpose_b=True)\n",
|
||
" dk = tf.cast(tf.shape(k)[-1], tf.float32)\n",
|
||
" scaled_attention_logits = matmul_qk / tf.math.sqrt(dk)\n",
|
||
"\n",
|
||
" if mask is not None:\n",
|
||
" scaled_attention_logits += (mask * -1e9)\n",
|
||
"\n",
|
||
" attention_weights = tf.nn.softmax(scaled_attention_logits, axis=-1)\n",
|
||
" output = tf.matmul(attention_weights, v)\n",
|
||
" return output, attention_weights\n",
|
||
"\n",
|
||
"class ImproveRelativePositionEncoding(tf.keras.layers.Layer):\n",
|
||
" def __init__(self, d_model, max_len=5000):\n",
|
||
" super(ImproveRelativePositionEncoding, self).__init__()\n",
|
||
" self.max_len = max_len\n",
|
||
" self.d_model = d_model\n",
|
||
" # 引入可变化的参数u和v进行线性变化\n",
|
||
" self.u = self.add_weight(shape=(self.d_model,),\n",
|
||
" initializer=RandomUniform(),\n",
|
||
" trainable=True)\n",
|
||
" self.v = self.add_weight(shape=(self.d_model,),\n",
|
||
" initializer=RandomUniform(),\n",
|
||
" trainable=True)\n",
|
||
" def call(self, inputs):\n",
|
||
" seq_length = inputs.shape[1]\n",
|
||
" pos_encoding = self.relative_positional_encoding(seq_length, self.d_model)\n",
|
||
" \n",
|
||
" # 调整原始的相对位置编码公式，将u和v参数融入其中\n",
|
||
" pe_with_params = pos_encoding * self.u+ pos_encoding * self.v\n",
|
||
" return inputs + pe_with_params\n",
|
||
"\n",
|
||
" def relative_positional_encoding(self, position, d_model):\n",
|
||
" pos = tf.range(position, dtype=tf.float32)\n",
|
||
" i = tf.range(d_model, dtype=tf.float32)\n",
|
||
" \n",
|
||
" angles = 1 / tf.pow(10000.0, (2 * (i // 2)) / tf.cast(d_model, tf.float32))\n",
|
||
" angle_rads = tf.einsum('i,j->ij', pos, angles)\n",
|
||
" #保留了sinous机制\n",
|
||
" # Apply sin to even indices; 2i\n",
|
||
" angle_rads_sin = tf.sin(angle_rads[:, 0::2])\n",
|
||
" # Apply cos to odd indices; 2i+1\n",
|
||
" angle_rads_cos = tf.cos(angle_rads[:, 1::2])\n",
|
||
"\n",
|
||
" pos_encoding = tf.stack([angle_rads_sin, angle_rads_cos], axis=2)\n",
|
||
" pos_encoding = tf.reshape(pos_encoding, [1, position, d_model])\n",
|
||
"\n",
|
||
" return pos_encoding\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"def PosConv1biGRUWithSelfAttention(input_shape, gru_units, num_heads):\n",
|
||
" inputs = Input(shape=input_shape)\n",
|
||
" # CNN layer\n",
|
||
" cnn_layer = Conv1D(filters=64, kernel_size=2, activation='relu')(inputs)\n",
|
||
" cnn_layer = MaxPooling1D(pool_size=1)(cnn_layer)\n",
|
||
" gru_output = Bidirectional(GRU(gru_units, return_sequences=True))(cnn_layer)\n",
|
||
" \n",
|
||
" # Apply Self-Attention\n",
|
||
" self_attention =AttentionWithImproveRelativePositionEncoding(d_model=gru_units*2, num_heads=num_heads)\n",
|
||
" gru_output, _ = self_attention(gru_output, gru_output, gru_output, mask=None)\n",
|
||
" \n",
|
||
" pool1 = GlobalAveragePooling1D()(gru_output)\n",
|
||
" output = Dense(1)(pool1)\n",
|
||
" \n",
|
||
" return Model(inputs=inputs, outputs=output)\n",
|
||
"\n",
|
||
"\n",
|
||
"input_shape = (96, 6)\n",
|
||
"gru_units = 64\n",
|
||
"num_heads = 8\n",
|
||
"\n",
|
||
"# Create model\n",
|
||
"model = PosConv1biGRUWithSelfAttention(input_shape, gru_units, num_heads)\n",
|
||
"model.compile(optimizer='adam', loss='mse')\n",
|
||
"model.summary()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"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[1m88s\u001b[0m 65ms/step - loss: 0.0178 - val_loss: 0.0018\n",
|
||
"Epoch 2/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 64ms/step - loss: 0.0011 - val_loss: 0.0016\n",
|
||
"Epoch 3/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m93s\u001b[0m 71ms/step - loss: 0.0010 - val_loss: 0.0024\n",
|
||
"Epoch 4/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 64ms/step - loss: 9.7998e-04 - val_loss: 0.0015\n",
|
||
"Epoch 5/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m76s\u001b[0m 59ms/step - loss: 0.0010 - val_loss: 0.0015\n",
|
||
"Epoch 6/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 54ms/step - loss: 0.0010 - val_loss: 0.0016\n",
|
||
"Epoch 7/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m76s\u001b[0m 58ms/step - loss: 9.6638e-04 - val_loss: 0.0015\n",
|
||
"Epoch 8/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 58ms/step - loss: 8.8641e-04 - val_loss: 0.0017\n",
|
||
"Epoch 9/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m65s\u001b[0m 50ms/step - loss: 9.5932e-04 - val_loss: 0.0015\n",
|
||
"Epoch 10/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 51ms/step - loss: 9.3643e-04 - val_loss: 0.0015\n",
|
||
"Epoch 11/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m67s\u001b[0m 52ms/step - loss: 9.2035e-04 - val_loss: 0.0017\n",
|
||
"Epoch 12/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 52ms/step - loss: 8.8128e-04 - val_loss: 0.0017\n",
|
||
"Epoch 13/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 57ms/step - loss: 8.7290e-04 - val_loss: 0.0016\n",
|
||
"Epoch 14/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 59ms/step - loss: 8.5652e-04 - val_loss: 0.0016\n",
|
||
"Epoch 15/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 62ms/step - loss: 8.6573e-04 - val_loss: 0.0018\n",
|
||
"Epoch 16/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 61ms/step - loss: 9.3113e-04 - val_loss: 0.0015\n",
|
||
"Epoch 17/100\n",
|
||
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 61ms/step - loss: 8.6217e-04 - val_loss: 0.0015\n",
|
||
"\u001b[1m651/651\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 17ms/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": 21,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.plot(history.history['loss'], label='train')\n",
|
||
"plt.plot(history.history['val_loss'], label='test')\n",
|
||
"plt.legend()\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(20831, 1)"
|
||
]
|
||
},
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"lstm_pred.shape"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(20831,)"
|
||
]
|
||
},
|
||
"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(20831,1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[4.52189913e-01],\n",
|
||
" [3.12516873e-01],\n",
|
||
" [3.25310588e-01],\n",
|
||
" ...,\n",
|
||
" [1.08522631e-04],\n",
|
||
" [1.18219088e-04],\n",
|
||
" [1.28327022e-04]])"
|
||
]
|
||
},
|
||
"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, (20831, 6))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"test_y2 = np.broadcast_to(test_y1, (20831, 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([[ 1.78428369e+01, 4.82409691e+01, 6.37156385e+02,\n",
|
||
" 2.97801603e+02, 1.07621239e+01, 9.90052500e-01],\n",
|
||
" [ 1.07562527e+01, 3.44305945e+01, 4.40440713e+02,\n",
|
||
" 2.05929459e+02, 7.43790432e+00, 1.80780551e-01],\n",
|
||
" [ 1.14053667e+01, 3.56955916e+01, 4.58459395e+02,\n",
|
||
" 2.14344726e+02, 7.74239484e+00, 2.54907916e-01],\n",
|
||
" ...,\n",
|
||
" [-5.09439462e+00, 3.54076535e+00, 4.44428011e-01,\n",
|
||
" 4.37940726e-01, 2.58283957e-03, -1.62932764e+00],\n",
|
||
" [-5.09390265e+00, 3.54172410e+00, 4.58084512e-01,\n",
|
||
" 4.44318723e-01, 2.81361533e-03, -1.62927146e+00],\n",
|
||
" [-5.09338980e+00, 3.54272354e+00, 4.72320538e-01,\n",
|
||
" 4.50967376e-01, 3.05418424e-03, -1.62921289e+00]])"
|
||
]
|
||
},
|
||
"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: 0.223\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[300:3000,5], label='true')\n",
|
||
"plt.plot(inv_forecast_y[300:3000,5], label='pre')\n",
|
||
"plt.legend()\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 32,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"mean_squared_error: 0.0014791752952266549\n",
|
||
"mean_absolute_error: 0.013799955472387545\n",
|
||
"rmse: 0.0384600480398381\n",
|
||
"r2 score: 0.9904178817149276\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[5000:10000], inv_forecast_y[5000:10000]))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 60,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df1 = pd.DataFrame(inv_test_y[:,5], columns=['column_name'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 62,
|
||
"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('高频re_test.csv', index=False)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 63,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df2 = pd.DataFrame(inv_forecast_y[:,5], columns=['column_name'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 64,
|
||
"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('高频re_forecast.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
|
||
}
|