| #!/bin/bash | |
| #================================================================================ | |
| # MIT License | |
| # | |
| # Copyright (c) 2024 Simon Andersen | |
| # | |
| # Permission is hereby granted, free of charge, to any person obtaining a copy | |
| # of this software and associated documentation files (the "Software"), to deal | |
| # in the Software without restriction, including without limitation the rights | |
| # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
Files in this gist are things that do not exactly fit in a general utility repository because I don't use them in every single project, but they are generic enough that someone else might also want to use them in their own project.
You are free to use and/or sell copies of this software according to the following MIT License. Credits are not required, but greately appreciated.
MIT License
Copyright (c) 2020 Simon Andersen
| import numpy as np | |
| sorted_centroids = kmeans.cluster_centers_.argsort()[:, ::-1] | |
| terms = cv.get_feature_names() | |
| clusters_terms = sorted_centroids[:, :100].get() | |
| for i, c1 in enumerate(clusters_terms): | |
| cluster = set(c1) |
| def document_search(text_df, query, vectorizer, tfidf_matrix, top_n=3): | |
| query_vec = vectorizer.transform(Series([query])) | |
| similarities = efficient_csr_cosine_similarity(query_vec, tfidf_matrix, matrix_normalized=True) | |
| similarities = similarities.todense().reshape(-1) | |
| best_idx = similarities.argsort()[-top_n:][::-1] | |
| pp = cudf.DataFrame({ | |
| 'text': text_df['text'].iloc[best_idx], | |
| 'similarity': similarities[best_idx] | |
| }) |
| import time | |
| import sys | |
| class ProgressBarPrinter: | |
| def __init__(self, width, step, stream, fname): | |
| self.width = width | |
| self.block_progress = 0 | |
| self.current_progress = 0 | |
| self.start_time = time.time() |