issues
search
HoloClean
/
holoclean
A Machine Learning System for Data Enrichment.
http://www.holoclean.io
Apache License 2.0
514
stars
129
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[ready] Breakout total number of repairs on ground truth into repairs on correct and incorrect cells
#67
richardwu
closed
5 years ago
0
[ip] Correlations as normalized conditional entropy
#66
minafarid
closed
5 years ago
0
Upgrade python package requirements
#65
minafarid
closed
5 years ago
0
Properly set random seeds
#64
minafarid
closed
5 years ago
0
Revert to NaiveBayes for weak labelling and revert to -1 for InitAttrFeaturizer
#63
richardwu
closed
5 years ago
0
Use Cramer's V Correlations instead of Pearons
#62
minafarid
closed
5 years ago
0
Support single predicate dcs #44, #60
#61
minafarid
closed
5 years ago
0
implement single tuple constraints
#60
minafarid
closed
5 years ago
1
Add batched featurization logic to reduce memory usage in repair model
#59
jonmio
closed
5 years ago
1
[ip] parser ignores comments and empty lines
#58
totemw
closed
5 years ago
0
Readme; conda download version
#57
minafarid
closed
5 years ago
0
Fixed get_infer_data to always return DK cells when infer_labeled=False.
#56
richardwu
closed
5 years ago
0
Using pytest
#55
minafarid
closed
5 years ago
0
[ci] run unit tests in travis
#54
minafarid
closed
5 years ago
1
Added a simple implementation for a constant/fixed/preloaded detector.
#53
oattia
closed
5 years ago
0
some styling, adding comments, fixing some wrong documentatin references
#52
oattia
closed
5 years ago
0
Memoize get_corr_attributes and a few style changes.
#51
richardwu
closed
5 years ago
0
Support Python3
#50
minafarid
closed
5 years ago
1
Documentation and styling
#49
minafarid
closed
5 years ago
0
Fix broken link in README for Conda installation
#48
jonmio
closed
5 years ago
0
Merge latest changes from dev into master
#47
richardwu
closed
5 years ago
1
Added feature names to weight output
#46
richardwu
closed
5 years ago
0
Using HoloClean for creating labels on tabular numerical datasets
#45
asstergi
closed
4 years ago
6
translation of simple DCs with a constant to SQL queries not working
#44
pmaetzig
closed
4 years ago
0
Use Logistic Regression with co-occur to generate weak labels
#43
richardwu
closed
5 years ago
0
clean up debugging information
#42
minafarid
closed
5 years ago
2
Repairs are no longer being found as the size of a dataset is increased
#41
j-r77
closed
4 years ago
7
Fix problems in README
#40
lbiester
closed
5 years ago
0
Fix NullDetector and regression with status (dev branch)
#39
richardwu
closed
5 years ago
0
Add Travis CI
#38
minafarid
closed
5 years ago
1
Remove jupyter checkpoints
#37
richardwu
closed
5 years ago
0
fixing reporting function
#36
laferrieren
closed
5 years ago
1
Updating docs + Adding support for env vars
#35
laferrieren
closed
5 years ago
0
Extend domain generation
#34
thodrek
closed
5 years ago
1
Non learnable featurizers
#33
thodrek
closed
5 years ago
0
Added EM iterations to repair process, allow multiple init values, and select best init value as current via co-occurrence probability
#32
richardwu
opened
5 years ago
5
Fixed encoding issue where dataframes were not encoded as unicode
#31
richardwu
closed
5 years ago
1
Created separate column for init values (1 or more) and current value (singular value, old 'init_value')
#30
richardwu
closed
5 years ago
1
Merge pull request #28 from HoloClean/dev
#29
minafarid
closed
5 years ago
0
Syncing with dev
#28
minafarid
closed
5 years ago
0
Update dev branch with master commits
#27
richardwu
closed
5 years ago
0
Investigate missing values from self.single_stats
#26
richardwu
closed
5 years ago
2
Replace print statements with logging
#25
richardwu
closed
5 years ago
2
Do not downcase attributes and use quotes when referring to columns in Postgres.
#24
richardwu
closed
5 years ago
4
Properly re-raise exceptions to propagate stack trace for exceptions.
#23
richardwu
closed
5 years ago
0
Zhihan/debugging mode
#22
ScarletGuo
closed
5 years ago
0
Fusion: initialize init_value as majority and domain as values across sources
#21
richardwu
closed
5 years ago
0
Re-factor use of exception handlers
#20
richardwu
closed
5 years ago
0
Replace print statements with logging.X statements
#19
richardwu
closed
5 years ago
0
Groundwork for fusion implementation and assorted bug fixes
#18
richardwu
closed
5 years ago
3
Previous
Next