Here we go through our code to reproduce the result described in Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction.
You need kex library.
pip install kex- Run benchmark: MRR/P@k metric for each combination of algorithm and dataset.
python benchmark.py- Get average run time as a proxy for algorithm's complexity measure (note that the run-time depends on environment).
python complexity.py- High level statistics for each data.
python data_statistics_table.py