999 lines
382 KiB
Plaintext
999 lines
382 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": 4,
|
|||
|
|
"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(data1)\n",
|
|||
|
|
"print(scaledData1.shape)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 5,
|
|||
|
|
"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 0.236302 0.490360 \n",
|
|||
|
|
"97 0.564819 0.315350 0.211335 0.044613 0.0 0.258204 0.489088 \n",
|
|||
|
|
"98 0.576854 0.288321 0.229657 0.047549 0.0 0.279860 0.485824 \n",
|
|||
|
|
"99 0.581973 0.268243 0.247775 0.053347 0.0 0.301336 0.482997 \n",
|
|||
|
|
"100 0.586026 0.264586 0.266058 0.057351 0.0 0.322851 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 0.214129 \n",
|
|||
|
|
"97 0.364859 0.002061 0.001839 ... 0.190042 0.040558 0.0 0.236302 \n",
|
|||
|
|
"98 0.364886 0.001973 0.001839 ... 0.211335 0.044613 0.0 0.258204 \n",
|
|||
|
|
"99 0.365615 0.001950 0.001697 ... 0.229657 0.047549 0.0 0.279860 \n",
|
|||
|
|
"100 0.361965 0.001679 0.001167 ... 0.247775 0.053347 0.0 0.301336 \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 0.258204 \n",
|
|||
|
|
"97 0.576854 0.288321 0.229657 0.047549 0.0 0.279860 \n",
|
|||
|
|
"98 0.581973 0.268243 0.247775 0.053347 0.0 0.301336 \n",
|
|||
|
|
"99 0.586026 0.264586 0.266058 0.057351 0.0 0.322851 \n",
|
|||
|
|
"100 0.590772 0.258790 0.282900 0.060958 0.0 0.343360 \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": 10,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"data_x = processedData1.loc[:,'0(t-96)':'5(t-1)']#去除power剩下的做标签列\n",
|
|||
|
|
"data_y = processedData1.loc[:,'5']"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 11,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"(104159, 576)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 11,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"data_x.shape"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 12,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"96 0.236302\n",
|
|||
|
|
"97 0.258204\n",
|
|||
|
|
"98 0.279860\n",
|
|||
|
|
"99 0.301336\n",
|
|||
|
|
"100 0.322851\n",
|
|||
|
|
" ... \n",
|
|||
|
|
"104250 0.000000\n",
|
|||
|
|
"104251 0.000000\n",
|
|||
|
|
"104252 0.000000\n",
|
|||
|
|
"104253 0.000000\n",
|
|||
|
|
"104254 0.000000\n",
|
|||
|
|
"Name: 5, Length: 104159, dtype: float64"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 12,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"data_y"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 13,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"(104159,)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 13,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"data_y.shape"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 14,
|
|||
|
|
"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": 15,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"(83328, 96, 6)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 15,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"train_X1.shape"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 16,
|
|||
|
|
"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",
|
|||
|
|
"│ self_attention │ [(<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\">66,048</span> │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
|||
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">SelfAttention</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> │ self_attention[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>… │\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",
|
|||
|
|
"│ self_attention │ [(\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m66,048\u001b[0m │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
|||
|
|
"│ (\u001b[38;5;33mSelfAttention\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 │ self_attention[\u001b[38;5;34m0\u001b[0m… │\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\">116,929</span> (456.75 KB)\n",
|
|||
|
|
"</pre>\n"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m116,929\u001b[0m (456.75 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\">116,929</span> (456.75 KB)\n",
|
|||
|
|
"</pre>\n"
|
|||
|
|
],
|
|||
|
|
"text/plain": [
|
|||
|
|
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m116,929\u001b[0m (456.75 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",
|
|||
|
|
"class SelfAttention(tf.keras.layers.Layer):\n",
|
|||
|
|
" def __init__(self, d_model, num_heads):\n",
|
|||
|
|
" super(SelfAttention, self).__init__()\n",
|
|||
|
|
" self.num_heads = num_heads\n",
|
|||
|
|
" self.d_model = d_model\n",
|
|||
|
|
" assert d_model % self.num_heads == 0\n",
|
|||
|
|
" self.depth = d_model // self.num_heads\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",
|
|||
|
|
"\n",
|
|||
|
|
" def split_heads(self, x, batch_size):\n",
|
|||
|
|
" x = tf.reshape(x, (batch_size, -1, self.num_heads, self.depth))\n",
|
|||
|
|
" return tf.transpose(x, perm=[0, 2, 1, 3])\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",
|
|||
|
|
" 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 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 SelfAttentionWithRelativePositionEncoding(tf.keras.layers.Layer):\n",
|
|||
|
|
" def __init__(self, d_model, num_heads, max_len=5000):\n",
|
|||
|
|
" super(SelfAttentionWithRelativePositionEncoding, 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.relative_position_encoding = AdvancedRelativePositionalEncoding(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",
|
|||
|
|
" # 添加相对位置编码\n",
|
|||
|
|
" k += self.relative_position_encoding(k)\n",
|
|||
|
|
" q += self.relative_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",
|
|||
|
|
"import tensorflow as tf\n",
|
|||
|
|
"import numpy as np\n",
|
|||
|
|
"\n",
|
|||
|
|
"import tensorflow as tf\n",
|
|||
|
|
"\n",
|
|||
|
|
"class AdvancedRelativePositionalEncoding(tf.keras.layers.Layer):\n",
|
|||
|
|
" def __init__(self, d_model, max_len=5000):\n",
|
|||
|
|
" super(AdvancedRelativePositionalEncoding, self).__init__()\n",
|
|||
|
|
" self.max_len = max_len\n",
|
|||
|
|
" self.d_model = d_model\n",
|
|||
|
|
" # #创新点 引入可变化的参数u，v 进行线性变化\n",
|
|||
|
|
" self.u = tf.Variable(tf.random(self.add_weight(shape=(d_model,), initializer='random_normal', trainable=True)))\n",
|
|||
|
|
" self.v = tf.Variable(tf.random(self.add_weight(shape=(d_model,), initializer='random_normal', trainable=True)))\n",
|
|||
|
|
"\n",
|
|||
|
|
" def call(self, inputs):\n",
|
|||
|
|
" seq_length = tf.shape(inputs)[1]\n",
|
|||
|
|
" pos_encoding = self.relative_positional_encoding(seq_length, self.d_model)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 保留Sinusoidal生成方案\n",
|
|||
|
|
" angle_rads_sin = pos_encoding[:, :, 0]\n",
|
|||
|
|
" angle_rads_cos = pos_encoding[:, :, 1]\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 线性维度转换层\n",
|
|||
|
|
" ti = tf.expand_dims(inputs, axis=1) # shape: [batch_size, 1, seq_length, d_model]\n",
|
|||
|
|
" tj = tf.expand_dims(inputs, axis=2) # shape: [batch_size, seq_length, 1, d_model]\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 计算表征 t_i * W_q * W_k^T * t_j\n",
|
|||
|
|
" t_wq_wk_t = tf.einsum('bijd,d->bij', tf.einsum('bijd,d->bijd', ti, self.u), tf.transpose(tj, perm=[0, 1, 3, 2]))\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 计算基于全局的偏置 t_i * W_q * W_k^T * R_(i-j)^T\n",
|
|||
|
|
" t_wq_wk_r = tf.einsum('bijd,d->bij', tf.einsum('bijd,d->bijd', ti, self.u), angle_rads_sin)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 计算基于表征的偏置 u * W_q * W_k^T * t_j\n",
|
|||
|
|
" E_u = tf.einsum('bd,bijd->bij', self.u, ti)\n",
|
|||
|
|
"\n",
|
|||
|
|
" # 计算基于表征的局部偏置 v * W_q * W_k^T * R_(i-j)^T\n",
|
|||
|
|
" R_v = tf.einsum('bd,bijd->bij', self.v, angle_rads_cos)\n",
|
|||
|
|
"\n",
|
|||
|
|
" \n",
|
|||
|
|
" pe_with_params = t_wq_wk_t + R_v + t_wq_wk_r + E_u\n",
|
|||
|
|
"\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",
|
|||
|
|
"\n",
|
|||
|
|
" pos_encoding = tf.stack([tf.sin(angle_rads[:, 0::2]), tf.cos(angle_rads[:, 1::2])], axis=-1)\n",
|
|||
|
|
" pos_encoding = tf.pad(pos_encoding, [[0, 0], [0, 0], [0, 0]]) #embbing维度嵌入层\n",
|
|||
|
|
"\n",
|
|||
|
|
" return pos_encoding\n",
|
|||
|
|
"\n",
|
|||
|
|
"\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 = SelfAttention(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": 17,
|
|||
|
|
"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[1m90s\u001b[0m 68ms/step - loss: 0.0267 - val_loss: 0.0024\n",
|
|||
|
|
"Epoch 2/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m86s\u001b[0m 66ms/step - loss: 0.0015 - val_loss: 0.0026\n",
|
|||
|
|
"Epoch 3/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m98s\u001b[0m 76ms/step - loss: 0.0013 - val_loss: 0.0020\n",
|
|||
|
|
"Epoch 4/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m95s\u001b[0m 73ms/step - loss: 0.0013 - val_loss: 0.0020\n",
|
|||
|
|
"Epoch 5/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m102s\u001b[0m 78ms/step - loss: 0.0012 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 6/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m96s\u001b[0m 74ms/step - loss: 0.0012 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 7/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m98s\u001b[0m 75ms/step - loss: 0.0012 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 8/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m109s\u001b[0m 84ms/step - loss: 0.0011 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 9/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m113s\u001b[0m 87ms/step - loss: 0.0012 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 10/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m115s\u001b[0m 88ms/step - loss: 0.0012 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 11/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m117s\u001b[0m 90ms/step - loss: 0.0011 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 12/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m115s\u001b[0m 89ms/step - loss: 0.0011 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 13/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m116s\u001b[0m 89ms/step - loss: 0.0011 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 14/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m112s\u001b[0m 86ms/step - loss: 0.0011 - val_loss: 0.0018\n",
|
|||
|
|
"Epoch 15/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m114s\u001b[0m 87ms/step - loss: 0.0011 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 16/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 108ms/step - loss: 0.0011 - val_loss: 0.0020\n",
|
|||
|
|
"Epoch 17/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 106ms/step - loss: 0.0011 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 18/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m120s\u001b[0m 92ms/step - loss: 0.0011 - val_loss: 0.0019\n",
|
|||
|
|
"Epoch 19/100\n",
|
|||
|
|
"\u001b[1m1302/1302\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m122s\u001b[0m 94ms/step - loss: 0.0010 - val_loss: 0.0021\n",
|
|||
|
|
"\u001b[1m651/651\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 19ms/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",
|
|||
|
|
"model_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": 18,
|
|||
|
|
"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": 19,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"(20831, 1)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 19,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"model_pred.shape"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 20,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"(20831,)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 20,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"test_y.shape"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 21,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"test_y1=test_y.reshape(20831,1)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 22,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"array([[0.42300856],\n",
|
|||
|
|
" [0.26651022],\n",
|
|||
|
|
" [0.28093082],\n",
|
|||
|
|
" ...,\n",
|
|||
|
|
" [0. ],\n",
|
|||
|
|
" [0. ],\n",
|
|||
|
|
" [0. ]])"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 22,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"test_y1"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 23,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"results1 = np.broadcast_to(model_pred, (20831, 6))"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 24,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"test_y2 = np.broadcast_to(test_y1, (20831, 6))"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 25,
|
|||
|
|
"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": 26,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"array([[ 1.63622638e+01, 4.53556200e+01, 5.96057328e+02,\n",
|
|||
|
|
" 2.78607105e+02, 1.00676074e+01, 2.18633342e+00],\n",
|
|||
|
|
" [ 8.42201514e+00, 2.98816195e+01, 3.75644883e+02,\n",
|
|||
|
|
" 1.75667855e+02, 6.34294548e+00, 1.37746668e+00],\n",
|
|||
|
|
" [ 9.15367247e+00, 3.13074773e+01, 3.95954874e+02,\n",
|
|||
|
|
" 1.85153232e+02, 6.68615591e+00, 1.45200002e+00],\n",
|
|||
|
|
" ...,\n",
|
|||
|
|
" [-5.09990072e+00, 3.53003502e+00, 2.91584611e-01,\n",
|
|||
|
|
" 3.66558254e-01, 0.00000000e+00, 0.00000000e+00],\n",
|
|||
|
|
" [-5.09990072e+00, 3.53003502e+00, 2.91584611e-01,\n",
|
|||
|
|
" 3.66558254e-01, 0.00000000e+00, 0.00000000e+00],\n",
|
|||
|
|
" [-5.09990072e+00, 3.53003502e+00, 2.91584611e-01,\n",
|
|||
|
|
" 3.66558254e-01, 0.00000000e+00, 0.00000000e+00]])"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
"execution_count": 26,
|
|||
|
|
"metadata": {},
|
|||
|
|
"output_type": "execute_result"
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"source": [
|
|||
|
|
"inv_test_y"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 49,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"Test RMSE: 0.234\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": 41,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"mean_squared_error: 0.0020579791273450843\n",
|
|||
|
|
"mean_absolute_error: 0.017256367420885\n",
|
|||
|
|
"rmse: 0.04536495483680199\n",
|
|||
|
|
"r2 score: 0.9906498316747805\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(model_pred, test_y)) # mse)\n",
|
|||
|
|
"print(\"mean_absolute_error:\", mean_absolute_error(model_pred, test_y)) # mae\n",
|
|||
|
|
"print(\"rmse:\", sqrt(mean_squared_error(model_pred,test_y)))\n",
|
|||
|
|
"#r2对比区域\n",
|
|||
|
|
"print(\"r2 score:\", r2_score(inv_test_y[:], inv_forecast_y[:]))"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 43,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"df1 = pd.DataFrame(inv_test_y[:,5], columns=['column_name'])"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 44,
|
|||
|
|
"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('test.csv', index=False)"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 45,
|
|||
|
|
"metadata": {},
|
|||
|
|
"outputs": [],
|
|||
|
|
"source": [
|
|||
|
|
"df2 = pd.DataFrame(inv_forecast_y[:,5], columns=['column_name'])"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"execution_count": 46,
|
|||
|
|
"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('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
|
|||
|
|
}
|