Skip to content

Commit 0ee34ae

Browse files
Removed analysis of knowledge corpus text
1 parent 1d9f152 commit 0ee34ae

File tree

1 file changed

+0
-18
lines changed

1 file changed

+0
-18
lines changed

scripts/knowledge.jl

Lines changed: 0 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -60,23 +60,6 @@ function build_corpus_from_repo(repo_input::String)
6060
return corpus
6161
end
6262

63-
function analyze_corpus(corpus::Corpus)
64-
println("\nCorpus Analysis:")
65-
println("Number of documents: ", length(corpus))
66-
println("Lexicon size: ", length(lexicon(corpus)))
67-
68-
words_of_interest = ["julia", "function", "type", "performance"]
69-
println("\nWord frequencies:")
70-
for word in words_of_interest
71-
freq = lexical_frequency(corpus, word)
72-
println("$word: $freq")
73-
end
74-
75-
search_word = "julia"
76-
doc_indices = corpus[search_word]
77-
println("\nDocuments containing '$search_word': ", length(doc_indices))
78-
end
79-
8063
function save_corpus(corpus::Corpus, repo_input::String)
8164
current_dir = pwd()
8265
safe_repo_name = split(normalize_repo_url(repo_input), "/")[end] |> x -> replace(x, ".git" => "") |> x -> replace(x, r"[^a-zA-Z0-9_]" => "_")
@@ -114,7 +97,6 @@ function main()
11497

11598
try
11699
corpus = build_corpus_from_repo(repo_input)
117-
analyze_corpus(corpus)
118100
save_corpus(corpus, repo_input)
119101
return corpus
120102
catch e

0 commit comments

Comments
 (0)