edevries
/
mamlr
2
0
Fork 0
Code Issues Pull Requests Releases 3 Wiki Activity
138 Commits
1 Branch
3 Tags
321 KiB
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '9e433ecf9e'
${ noResults }
Commit Graph

130 Commits (9e433ecf9e0a323b2596aa290d7e53cee3f2aadd)

Author SHA1 Message Date
Erik de Vries 7544e5323f modelizer: update to allow tf both as count (for naive bayes), and as proportion (for other machine learning algorithms)
6 years ago
Erik de Vries 5f5e4a03c8 modelizer: Changed tf-idf weighting from absolute tf count to proportional (normalized) tf! Also added initial support for neural networks
6 years ago
Erik de Vries 34a6adf64e changed udpipe output variable from tokens to ud
6 years ago
Erik de Vries 061da17c2a ud_update: Added function to lemmatize documents
6 years ago
Erik de Vries ef51ce60a9 Fixed dupe_detect error on documents with one sentence or less, and a maximum # of words in dfm_gen
6 years ago
Erik de Vries 0e8c127b86 bulk_writer: fixes for JSON generation and added exception for use of 'tokens' varname
6 years ago
Erik de Vries 755a58d84d dupe_detect: fix to prevent errors when a query returns no results
6 years ago
Erik de Vries 887f1aa774 dupe_detect: fix for empty results dataframe (no duplicates for given date and newspaper)
6 years ago
Erik de Vries 993f39957a dfm_gen: word cutoff now as final step in script, caused bugs with mutating code variables
6 years ago
Erik de Vries 02b8a8c1da dfm_gen & merger: Changed word cutoff point to be a general setting in dfm_gen. Cuts off at the last [.?!] before the cutoff point (so returns documents at a sentence, shorter than cutoff).
6 years ago
Erik de Vries 4a713ddc23 bulk_writer: setting names(x) <- NULL when there is only one value (list or otherwise) to be updated.
6 years ago
Erik de Vries 6bb8f9b635 class_update: added explicit httr::: references
6 years ago
Erik de Vries f543d658bd Major overhaul to ES bulk update integration. Added support for both setting and appending to variables
6 years ago
Erik de Vries 4adae2bbc6 Fixed bug in dupe_detect caused by switch from cutoff to cutoff_lower/upper
6 years ago
Erik de Vries 4cd46d1a5e dupe_detect: added support for both lower and upper cutoff point
6 years ago
Erik de Vries 11d8b31c60 Added generic actor search query generator. Updated elasticizer and elastic_update to connect either to the remote server, or a local ES instance
6 years ago
Erik de Vries 3e66c7e1cd Updated dfm_gen to have all topic vectors as numeric variables
6 years ago
Erik de Vries adc4b3c639 Updated feature selection in modelizer function (see comment on lines 166/167)
6 years ago
Erik de Vries 65f8c26ec6 Renamed dupe_detect, and added return output
6 years ago
Erik de Vries db418d7396 Add query_string function for generating query_string queries
6 years ago
Erik de Vries d203de0b2a Updated elasticizer docs, created modelizer and class_update functions
6 years ago
Erik de Vries c815dc7f2b Duplicate detection first commit
6 years ago
Erik de Vries 015411feaf Added refresh=wait_for to bulk update url. This should make update scripts less demanding on the server side, because the server only replies after refreshing (happens every second)
6 years ago
Erik de Vries 413ad02a87 Set default to "lemmas" for dfm_gen
6 years ago
Erik de Vries 217ee76568 V 0.1 for elasticizer function with updater support
6 years ago
Erik de Vries a273524105 Added support for custom update function to elasticizer
6 years ago
Erik de Vries 311838b34b Updated dfm_gen to only create derivative codes if majorTopic actually exists, and set docvars to NULL when no majorTopic codes
6 years ago
Erik de Vries dc4daf9de4 Added line to replace multiple whitespace characters in full text by a single regular whitespace
6 years ago
Erik de Vries 0e45c0f2d1 Added option for fulltext vs lemmas merged field
6 years ago
Erik de Vries 4bbe84ab83 First release of mamlr package
6 years ago