This is A Cluster-Stacking-based Approach to Forecasting Seasonal Chlorophyll-a Concentration in Coastal Waters
Pictures: experimental results.
Cluster_function.py: group stations through various clustering algorithms.
Different_model.py: regression learners.
Distribution.py: obtain a vector distribution and normal distribution fitting function.
Feature_selector.py: feature selection.
Importance_analyse.py: a basic learner for calculating the importance of features.
Plot_feature_importances.py: draw feature importance figures.
Plot_result_scatter.py: draw scatter map according to clustering results.
Pre_processing.py: data preprocessing.
Stacking_model_no_cluster.py: Stacking-based approach to forecasting Chl-a concentration.
Stacking_model_print_result.py: Cluster-Stacking-based approach to forecasting Chl-a concentration.
- Cluster monitoring stations by cluster_function.py.
- Plot the clustering results by plot_result_scatter.py (optional).
- Data preprocessing through pre processing.py
- Draw the result of feature importance analysis by plot_feature_importants.py (optional).
- Achieve stacking-based approach through Stacking_model_no_cluster.py.
- Achieve Cluster-Stacking-based approach through Stacking_model_print_result.py.
Some of the intermediate documents are not shown in this project.