summaryrefslogtreecommitdiff
path: root/scoring
diff options
context:
space:
mode:
authoralex <[email protected]>2026-07-28 14:22:32 +0200
committeralex <[email protected]>2026-07-28 14:22:32 +0200
commit152c73d8205a252d4311595ffba562110334fd0f (patch)
treeac53d51b85d1148bebf66ecdfe8320a3e99ed155 /scoring
parent49a21882354c1a92fcb9c5b555c0331ab83c2e69 (diff)
downloadsearch-engine-152c73d8205a252d4311595ffba562110334fd0f.tar.xz
search-engine-152c73d8205a252d4311595ffba562110334fd0f.zip
begin work on better searching algorithms, created logic for tf-idf
Diffstat (limited to 'scoring')
-rw-r--r--scoring/idf.go17
1 files changed, 17 insertions, 0 deletions
diff --git a/scoring/idf.go b/scoring/idf.go
new file mode 100644
index 0000000..6d96089
--- /dev/null
+++ b/scoring/idf.go
@@ -0,0 +1,17 @@
+package scoring
+
+import (
+ "math"
+ "searchEngine/index"
+)
+
+func CalculateIDF(totalDocs int, docFrequency int) float64 {
+ if docFrequency == 0 {
+ return 0.0
+ }
+ return math.Log10(float64(totalDocs) / float64(docFrequency))
+}
+func ScoreTFIDF(p index.Posting, idf float64) float64 {
+
+ return float64(p.Count) * idf
+}