searcharray 0.0.49__tar.gz → 0.0.51__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {searcharray-0.0.49 → searcharray-0.0.51}/PKG-INFO +6 -2
- {searcharray-0.0.49 → searcharray-0.0.51}/README.md +5 -1
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/__init__.py +1 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/roaringish_ops.c +117 -117
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/snp_ops.c +117 -117
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/spans.c +117 -117
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/solr.py +44 -3
- searcharray-0.0.51/searcharray/utils/sort.py +45 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/PKG-INFO +6 -2
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/SOURCES.txt +1 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/setup.py +1 -1
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_msmarco.py +71 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_solr.py +40 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/pyproject.toml +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/indexing.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/__init__.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/bigram_freqs.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/middle_out.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/posn_diffs.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/scan_merge.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/phrase/spans.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/postings.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/__init__.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/roaringish.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/roaringish_ops.pyx +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/snp_ops.pxd +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/snp_ops.pyx +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/roaringish/spans.pyx +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/similarity.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/term_dict.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/utils/__init__.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/utils/bitcount.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/utils/mat_set.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray/utils/row_viewable_matrix.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/dependency_links.txt +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/entry_points.txt +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/requires.txt +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/searcharray.egg-info/top_level.txt +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/setup.cfg +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_bitcount64.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_extension_array.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_minmax_posns.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_phrase_matches.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_search.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_similarity.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_slop_matches.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_snp_ops.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_tmdb.py +0 -0
- {searcharray-0.0.49 → searcharray-0.0.51}/test/test_utils.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: searcharray
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.51
|
|
4
4
|
Summary: Searchable pandas text extension arrays for prototyping search
|
|
5
5
|
Home-page: https://github.com/softwaredoug/searcharray
|
|
6
6
|
Author: Doug Turnbull
|
|
@@ -29,7 +29,7 @@ Requires-Dist: coverage; extra == "test"
|
|
|
29
29
|
|
|
30
30
|
# SearchArray
|
|
31
31
|
|
|
32
|
-
[](https://github.com/softwaredoug/searcharray/actions/workflows/test.yml)
|
|
32
|
+
[](https://github.com/softwaredoug/searcharray/actions/workflows/test.yml) | Discuss at [Relevance Slack](https://join.slack.com/t/relevancy/shared_invite/zt-2ccxvzn1w-2_50zf9xBOSv3n06Cu15jg)
|
|
33
33
|
|
|
34
34
|
SearchArray turns Pandas string columns into a term index. It alows efficient BM25 / TFIDF scoring of phrases and individual tokens.
|
|
35
35
|
|
|
@@ -206,6 +206,10 @@ df['score'] = df['title_indexed'].score('Cat') * df['hrs_into_past']
|
|
|
206
206
|
|
|
207
207
|
We focus on the lexical, ie "BM25-ish" and adjacent problems. There are other great tools for vector search out there.
|
|
208
208
|
|
|
209
|
+
## Need help?
|
|
210
|
+
|
|
211
|
+
Visit the [#searcharray channel on Relevance Slack](https://join.slack.com/t/relevancy/shared_invite/zt-2ccxvzn1w-2_50zf9xBOSv3n06Cu15jg)
|
|
212
|
+
|
|
209
213
|
## TODOs / Future Work / Known issues
|
|
210
214
|
|
|
211
215
|
* Always more efficient
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# SearchArray
|
|
2
2
|
|
|
3
|
-
[](https://github.com/softwaredoug/searcharray/actions/workflows/test.yml)
|
|
3
|
+
[](https://github.com/softwaredoug/searcharray/actions/workflows/test.yml) | Discuss at [Relevance Slack](https://join.slack.com/t/relevancy/shared_invite/zt-2ccxvzn1w-2_50zf9xBOSv3n06Cu15jg)
|
|
4
4
|
|
|
5
5
|
SearchArray turns Pandas string columns into a term index. It alows efficient BM25 / TFIDF scoring of phrases and individual tokens.
|
|
6
6
|
|
|
@@ -177,6 +177,10 @@ df['score'] = df['title_indexed'].score('Cat') * df['hrs_into_past']
|
|
|
177
177
|
|
|
178
178
|
We focus on the lexical, ie "BM25-ish" and adjacent problems. There are other great tools for vector search out there.
|
|
179
179
|
|
|
180
|
+
## Need help?
|
|
181
|
+
|
|
182
|
+
Visit the [#searcharray channel on Relevance Slack](https://join.slack.com/t/relevancy/shared_invite/zt-2ccxvzn1w-2_50zf9xBOSv3n06Cu15jg)
|
|
183
|
+
|
|
180
184
|
## TODOs / Future Work / Known issues
|
|
181
185
|
|
|
182
186
|
* Always more efficient
|