Python program of empirical mode decomposition algorithm based on CEEMDAN set
Can be used in time series and other fields
Features: 1. Based on Python
2. The data is read from the excel file, easy to replace
All the complete code, the code that is guaranteed to run can be seen here.
http://t.csdn.cn/obJlC
http://t.csdn.cn/obJlC
! ! ! If the first link cannot be opened, please click on the personal homepage to view my personal introduction.
(After searching for the product, click on the avatar to see all the codes)
Blog of Black Technology Little Potato_CSDN Blog-Deep Learning, Blogger in 32 MCU Field
1. Background introduction: This model is a time series forecasting model based on the CEEMDAN ensemble empirical mode decomposition algorithm. The CEEMDAN algorithm is a data decomposition technique that can decompose nonlinear and non-stationary time series into controllable internal mode functions, thereby improving the interpretability of the data itself and reducing the correlation between data. For the decomposed modal data, the model uses machine learning related algorithms such as neural network or support vector regression (SVR) to predict time series.
2. Summary of advantages:
- The CEEMDAN algorithm can effectively deal with nonlinear and non-stationary time series data, making the data more interpretable after decomposition;
- The model can use the decomposed modal data for prediction, which can reduce the correlation between data, thereby improving the accuracy of prediction;
# 参数设置
K = 3 # EEMD中该参数设置无效，固定为3，改变该参数可能导致绘图出错
target_value = "预测量" # 要预测的列在excel中的名字
if_plot = True # 是否绘制分解图 True绘制，False不绘制，请注意，该功能在Linux子系统，MacOS等环境中可能不可用
# 数据读取
raw_data = pd.read_excel('./data.xlsx')[target_value].values