diff --git a/iceemdan分解 逐步分解.ipynb b/iceemdan分解 逐步分解.ipynb deleted file mode 100644 index 223087f..0000000 --- a/iceemdan分解 逐步分解.ipynb +++ /dev/null @@ -1,418 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "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": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "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": null, - "metadata": {}, - "outputs": [], - "source": [ - "data1" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from PyEMD import EMD\n", - "import pandas as pd\n", - "import numpy as np\n", - "\n", - "def ICEEMDAN(data, num_siftings=18, Nstd=0.2, NR=100):\n", - " \"\"\"\n", - " 改进的完全集合经验模态分解与自适应噪声（ICEEMDAN）。\n", - " \"\"\"\n", - " emd = EMD()\n", - " T = len(data)\n", - " std_data = np.std(data)\n", - " \n", - " # 通过添加白噪声获取数据的 IMFs 集合\n", - " E_IMFs = np.zeros((NR, T, num_siftings))\n", - " for r in range(NR):\n", - " wn = np.random.normal(scale=std_data*Nstd, size=T)\n", - " noisy_data = data + wn\n", - " \n", - " # 分解带噪声的数据\n", - " imfs = emd.emd(noisy_data)\n", - " \n", - " # 仅保留前 `num_siftings` 个 IMFs\n", - " for i in range(min(num_siftings, imfs.shape[0])):\n", - " E_IMFs[r, :, i] = imfs[i]\n", - " \n", - " # 所有实验的 IMFs 平均值\n", - " mean_IMFs = np.mean(E_IMFs, axis=0)\n", - " \n", - " return mean_IMFs\n", - "\n", - "# 假设您有一个名为 'data1' 的 DataFrame，其中包含一个 'Power' 列\n", - "data_power = data1['Power'].values\n", - "\n", - "# 定义分解的数据窗口大小\n", - "window_size = 104256\n", - "\n", - "# 遍历以 'window_size' 为单位的数据块\n", - "for i in range(0, len(data_power), window_size):\n", - " # 提取当前数据块\n", - " current_data = data_power[i:i+window_size]\n", - " \n", - " # 对当前数据块应用 ICEEMDAN 分解\n", - " IMFs = ICEEMDAN(current_data)\n", - " \n", - " # 创建一个新的 DataFrame 来保存 ICEEMDAN 分解结果\n", - " data_ICEEMDAN = pd.DataFrame(IMFs, columns=[f'IMF{i}' for i in range(IMFs.shape[1])])\n", - " \n", - " # 计算 IMFs 的总和\n", - " IMFs_sum = data_ICEEMDAN[[f'IMF{i}' for i in range(IMFs.shape[1])]].sum(axis=1)\n", - " \n", - " # 计算 IMFs 总和与原始信号之间的差值\n", - " residue = current_data - IMFs_sum\n", - " \n", - " # 将残差添加到 DataFrame\n", - " data_ICEEMDAN['Residue'] = residue\n", - " \n", - " # 打印当前数据块的分解结果\n", - " print(f\"数据块 {i+1}-{i+len(current_data)} 的分解结果:\")\n", - " print(data_ICEEMDAN)\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 将分解后的 IMFs 与残差相加以恢复原始数据\n", - "reconstructed_signal = IMFs_sum + residue\n", - "\n", - "# 绘制重构的数据与原始数据进行比较\n", - "plt.figure(figsize=(30, 18))\n", - "plt.plot(current_data[0:2900], label='Original Signal', color='blue')\n", - "plt.plot(reconstructed_signal[0:2900], label='Reconstructed Signal', color='red')\n", - "plt.xlabel('Time')\n", - "plt.ylabel('Amplitude')\n", - "plt.title('Comparison between Original and Reconstructed Signal')\n", - "plt.legend()\n", - "plt.grid(True)\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# 设置全局字体大小\n", - "plt.rcParams.update({'font.size': 60}) # 设置字体大小为 16\n", - "\n", - "# 在这里放置您的绘图代码\n", - "num_imfs = IMFs.shape[1]\n", - "\n", - "plt.figure(figsize=(64,128))\n", - "\n", - "# 绘制每个 IMF\n", - "for i in range(num_imfs):\n", - " if i <= 19: # 只绘制前 14 个 IMF\n", - " plt.subplot(num_imfs, 1, i + 1)\n", - " plt.plot(data_ICEEMDAN[f'IMF{i}'], label=f'IMF {i}')\n", - " plt.legend()\n", - "plt.legend()\n", - "\n", - "# 绘制残差\n", - "plt.subplot(num_imfs + 1, 1, num_imfs + 1)\n", - "plt.plot(data_ICEEMDAN[f'IMF{17}'], label='Residue', color='red')\n", - "plt.legend()\n", - "\n", - "plt.tight_layout()\n", - "plt.show()\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import numpy as np\n", - "import matplotlib.pyplot as plt\n", - "from scipy.signal import welch\n", - "\n", - "def plot_frequency_spectrum(signal, sampling_rate, title):\n", - " \"\"\"\n", - " 绘制信号的频谱图。\n", - " \n", - " 参数：\n", - " - signal: 输入信号\n", - " - sampling_rate: 信号的采样率\n", - " - title: 图表标题\n", - " \"\"\"\n", - " f, Pxx = welch(signal, fs=sampling_rate, nperseg=len(signal))\n", - " plt.figure(figsize=(10, 5))\n", - " plt.semilogy(f, Pxx)\n", - " plt.title(title)\n", - " plt.xlabel('Frequency (Hz)')\n", - " plt.ylabel('Power spectral density')\n", - " plt.grid(True)\n", - " plt.show()\n", - "\n", - "def compute_zero_crossings(signal):\n", - " \"\"\"\n", - " 计算信号的过零率。\n", - " \"\"\"\n", - " zero_crossings = np.where(np.diff(np.sign(signal)))[0]\n", - " zero_crossing_rate = len(zero_crossings) / len(signal)\n", - " return zero_crossing_rate\n", - "\n", - "def classify_frequency_component(imfs, threshold):\n", - " \"\"\"\n", - " 将每个 IMF 分为高频和低频成分。\n", - " \"\"\"\n", - " high_frequency_imfs = []\n", - " low_frequency_imfs = []\n", - " for i in range(imfs.shape[1]):\n", - " imf = imfs[:, i]\n", - " zero_crossing_rate = compute_zero_crossings(imf)\n", - " if zero_crossing_rate > threshold:\n", - " high_frequency_imfs.append(imf)\n", - " else:\n", - " low_frequency_imfs.append(imf)\n", - " return high_frequency_imfs, low_frequency_imfs\n", - "\n", - "# 定义过零率的阈值\n", - "threshold = 0.2 # 可根据具体情况调整阈值\n", - "\n", - "# 根据过零率判断高频和低频成分\n", - "high_freq_imfs, low_freq_imfs = classify_frequency_component(IMFs, threshold)\n", - "sampling_rate = 1000 \n", - "# 可选：绘制高频和低频成分的频谱图\n", - "for i, imf in enumerate(high_freq_imfs):\n", - " plot_frequency_spectrum(imf, sampling_rate, f'High Frequency IMF {i+1}')\n", - "\n", - "for i, imf in enumerate(low_freq_imfs):\n", - " plot_frequency_spectrum(imf, sampling_rate, f'Low Frequency IMF {i+1}')\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 打印高频和低频成分的 IMF 列表\n", - "print(\"High Frequency IMFs:\")\n", - "for i, imf in enumerate(high_freq_imfs):\n", - " print(f\"IMF {i+1}: {imf}\")\n", - "\n", - "print(\"\\nLow Frequency IMFs:\")\n", - "for i, imf in enumerate(low_freq_imfs):\n", - " print(f\"IMF {i+1}: {imf}\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import pandas as pd\n", - "\n", - "# 将高频和低频信号相加\n", - "high_freq_sum = np.sum(high_freq_imfs, axis=0)\n", - "low_freq_sum = np.sum(low_freq_imfs, axis=0)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "high_freq_sum" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "low_freq_sum" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "residue" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "re_low=residue+low_freq_sum" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "re_high=residue+high_freq_sum\n", - "re_high" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_low = pd.DataFrame(low_freq_sum, columns=['column_name'])\n", - "df_low.to_csv('iceemdan_reconstructed_data_low.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_high = pd.DataFrame(high_freq_sum, columns=['column_name'])\n", - "df_high.to_csv('iceemdan_reconstructed_data_high.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_high = pd.DataFrame(residue, columns=['column_name'])\n", - "df_high.to_csv('iceemdan_reconstructed_data_residue.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_re_low = pd.DataFrame(re_low, columns=['column_name'])\n", - "df_re_low.to_csv('iceemdan_reconstructed_data_re_low.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_re_high = pd.DataFrame(re_high, columns=['column_name'])\n", - "df_re_high.to_csv('iceemdan_reconstructed_data_re_high.csv', index=False)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "IMFs_sum" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 指定文件路径和文件名，保存DataFrame到CSV文件中\n", - "df_high = pd.DataFrame(IMFs_sum, columns=['column_name'])\n", - "df_high.to_csv('iceemdan_reconstructed_data_IMFs_sum.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 -}