Frequent-Pattern-Mining | Frequent pattern mining application on text mining | Data Mining library

Frequent-Pattern-Mining is a Python library typically used in Institutions, Learning, Education, Data Processing, Data Mining applications. Frequent-Pattern-Mining has no bugs, it has no vulnerabilities and it has low support. However Frequent-Pattern-Mining build file is not available. You can download it from GitHub.

LDA is run on a data set made up of titles from 5 domains' conference papers. Using the results of the LDA, a topic is assigned to each word of each title. Each topic represents one of five domains in computer science: Data Mining (DM), Machine Learning (ML), Database (DB), Information Retrieval (IR), Theory (TH). Each file in the data-assign3/ folder represents a topic in which each line contains words assigned to that topic. A basic Apriori algorithm is implemented in apriori.py which takes and input file, output file, and support level. This algorithm generates frequent patterns that meet the support level based on the algorithm. The output of running this algorithm on each topic can be found in the patterns/ folder. Mining frequent patterns often generates a large number of frequent patterns. This number can grow exponentially as the min_sup levels decrease, resulting in excessive runtimes and relatively cluttered results. Mining closed and max patterns has the same power as mining the complete set of frequent patterns, but reduces the number of redundant rules generated. Maximal and closed patterns are mined using max.py and closed.py, with outputs in max/ and closed/, respectively.