Dependencies:
	-python 3+
	-pandas
	-numpy
	-spaCy
	-en_core_web_sm
	-umap
	-sklearn
	-unicodedata
	-matplotlib

Outside References:
	https://github.com/peter3125/enhanced-subject-verb-object-extraction

Notes:

		/introMDFiles: contains the intro.md files from the epicookbook

		/cleanedTexts: generated .txt files from intro.mdFiles by running
			svoExtract.extract(<filename>)
		svo.csv: generated from running svoExtract.extractSVO(cleanedTexts/)

		clusteringLabels.csv: generated by running expUtil.createCluster(svo.csv)
			creates DBScan labels using Umap/Spacy Token embeddings
			computes insamplecluster similarity and out-sample cluster similarity ratios(time expensive)

		ExpermentData/
			CSV files generated from running runKMeansExp() and runUmapSimExp()

			JuliaVariableData.csv contains ground truths from labels and preprocess filtering of
			extraneous and repetitive variables
			
		mergedSVO.csv final subject-verb-object file that should be made into knowledge graph



