Running summarizing tools on a new article

Abstract: GWR based on a flow-distance composite weight matrix (FDWM GWR)OverviewThis repository contains simulation data and codes for the FDWM GWR method in "Reconceptualizing Proximity: A Flow-Distance Augmented GWR for Analyzing Urban Vitality".RequirementsMake sure to install the following dependencies:Python 3.8 or above.Required Python libraries: pip install numpy scipy pandas.Code StructureFDWM_GWR.py: The model and a usage example. Validity has been verified on Python 3.8 and 3.10.test_od.txt: A simulated OD matrix file.test_data.csv: A simulated data.Usage Instructions1. Prepare DataThe data should include a table file (e.g., 'test_data.csv') and an OD matrix (e.g., 'test_od.txt'). The table should contain the sample ID, coordinates, and variables.2. Run the ModelRunning the model should include the following steps:Load data.Calculate Euclidean distance and normalize it.Calculate flow space proximity and composite Euclidean distance.Run the model. You can select either Fixed or Adaptive bandwidth type, search for the optimal bandwidth using the golden section method, and fit the model.Save the results.The 'FDWM_GWR.py' file contains a complete usage example. You can modify it as needed or run it directly, and the results will be saved as a CSV file. After fitting the model, you can directly obtain its bandwidth, R2, and AICc.In the gravity model, the alpha and beta parameters can be directly modified in the 'FDWM_GWR.py' file. By using different parameter combinations, the impact of these parameters on the model can be further explored.3. Results AnalysisUse ArcGIS or other software for further visualization and analysis of the generated results.Charts and the Calculation ProcessThe calculation process for the charts and figures presented in Section 4.3 and Chapter 5 are listed in ‘The Process of Calculating Figures and Tables.docx’.