python expert & data analysis -- 2
Budget: $10 – $30 USD
Project Goal: Generate heatmap plots based on similarity matrix
Project Details: Please use Python or R to calculate the similarity matrix of the word lists of three firms. Based on the similarity matrix, please plot the heatmaps in the style of figures in the following website: https://www.conniefan.com/2017/03/measures-of-similarity-in-the-20-newsgroups-dataset/
We need three similarity measures: cosine, Jaccard, and a similarity measure based on the "max" percentage of overlap. Here is the definition of the last similarity measure: similarity(x, y) = max(% of x in y, % of y in x).
We will need the final R/Python script - so please add necessary comments to the script for better readability. Thanks!
Project Details: Please use Python or R to calculate the similarity matrix of the word lists of three firms. Based on the similarity matrix, please plot the heatmaps in the style of figures in the following website: https://www.conniefan.com/2017/03/measures-of-similarity-in-the-20-newsgroups-dataset/
We need three similarity measures: cosine, Jaccard, and a similarity measure based on the "max" percentage of overlap. Here is the definition of the last similarity measure: similarity(x, y) = max(% of x in y, % of y in x).
We will need the final R/Python script - so please add necessary comments to the script for better readability. Thanks!