worldbank/realtabformer issues and pull requests

#79 - Generating Balanced Synthesized Data

Issue - State: open - Opened by erland-ramadhan about 1 month ago - 1 comment

#78 - Error on mps device

Issue - State: open - Opened by qzhu2017 about 1 month ago

#77 - How can we create more synthetic data?

Issue - State: open - Opened by limhasic 2 months ago - 1 comment

#76 - Use 'int64' and bump version to v0.1.7

Pull Request - State: closed - Opened by avsolatorio 2 months ago

#75 - Bug in process_datetime_data() converting datetime to int

Issue - State: closed - Opened by efstathios-chatzikyriakidis 2 months ago - 2 comments

#74 - Missing value imputation on regular data

Issue - State: open - Opened by RejwankabirHamim 2 months ago

#73 - Bump version to v0.1.6

Pull Request - State: closed - Opened by avsolatorio 2 months ago

#72 - Remove use of .view when casting timestamp to int

Pull Request - State: closed - Opened by avsolatorio 2 months ago

#71 - Bug in process_datetime_data() when using pandas 2.2.1

Issue - State: closed - Opened by efstathios-chatzikyriakidis 2 months ago - 1 comment

#70 - missing data

Issue - State: open - Opened by limhasic 3 months ago - 2 comments

#69 - RuntimeError: Error(s) in loading state_dict for GPT2LMHeadModel: size mismatch for transformer.wte.weight

Issue - State: open - Opened by akefhabbal-qu 3 months ago

#68 - Documentation page not working

Issue - State: closed - Opened by sfragkoul 3 months ago - 2 comments

#67 - Question for Generate Synthetic data To compare HMA and REaLTabFormer

Issue - State: open - Opened by limhasic 3 months ago - 2 comments

#66 - OSError: rtf_checkpoints/not-best-disc-model does not appear to have a file named config.json.

Issue - State: open - Opened by AhmadKajjan-QU 3 months ago - 2 comments

#65 - Could order of columns affect performance of synthetic data quality?

Issue - State: open - Opened by efstathios-chatzikyriakidis 4 months ago - 2 comments

#64 - Python datetime.date data type is handled as str and datatype handling in general

Issue - State: open - Opened by efstathios-chatzikyriakidis 4 months ago

#63 - Parallelization of inference/generation in both tabular and child models.

Issue - State: open - Opened by efstathios-chatzikyriakidis 4 months ago

#62 - Maximum number of columns limitation in tabular GPT-2 model?

Issue - State: open - Opened by efstathios-chatzikyriakidis 4 months ago

#61 - rtf_checkpoints bug when fitting the GeoValidator example model

Issue - State: open - Opened by martinjurkovic 5 months ago

#60 - Early stopping with sensitivity vs validation loss metric and the effects on synthetic data quality.

Issue - State: closed - Opened by efstathios-chatzikyriakidis 5 months ago - 2 comments

#59 - Out of memory exception on tabular model with 25k rows and 37 columns

Issue - State: closed - Opened by efstathios-chatzikyriakidis 5 months ago - 3 comments

#58 - Is it possible to run REalTabFormer on AWS Inferentia and Trainium VM instances?

Issue - State: open - Opened by efstathios-chatzikyriakidis 5 months ago

#57 - Inquiries on fitting parent and child tables

Issue - State: open - Opened by ThomasK1018 6 months ago

#56 - Multi-GPU training

Issue - State: open - Opened by vinay-k12 6 months ago - 1 comment

#55 - Update docs requirements

Pull Request - State: closed - Opened by avsolatorio 8 months ago

#54 - Fix docs sphinx-autoapi version and run action on push to main

Pull Request - State: closed - Opened by avsolatorio 8 months ago

#53 - Apply patches and build new release

Pull Request - State: closed - Opened by avsolatorio 8 months ago

#52 - cannot import name 'is_fairscale_available' from 'transformers.integrations

Issue - State: closed - Opened by waylonli 8 months ago - 1 comment

#51 - Bug in REaLTabFormer.sample() when relational model generates no data

Issue - State: closed - Opened by efstathios-chatzikyriakidis 8 months ago - 3 comments

#50 - Bump version for release v0.1.4

Pull Request - State: closed - Opened by avsolatorio 8 months ago

#49 - Possible Improvements for CPU inference

Issue - State: open - Opened by australDream 8 months ago

#48 - Conditional generation?

Issue - State: closed - Opened by gminorcoles 10 months ago - 4 comments

#47 - Possible mix-up of token columns

Issue - State: closed - Opened by liu305 10 months ago - 2 comments

#46 - See "IndexError: index out of range in self" when related_num parameter is specified in child model sampler

Issue - State: closed - Opened by liu305 11 months ago - 1 comment

#45 - Transaction datetime in the child table is not sequential

Issue - State: closed - Opened by liu305 11 months ago - 1 comment

#44 - Generated datetime value in the child table is invalid

Issue - State: open - Opened by liu305 11 months ago - 2 comments

#43 - Running Realtab on Macs

Issue - State: closed - Opened by vinay-k12 11 months ago - 4 comments

#42 - Logistic detection metric

Issue - State: closed - Opened by zechchair 11 months ago - 5 comments

#41 - Resolves #37: Use explicit optim="adamw_torch" to suppress deprecation warning

Pull Request - State: closed - Opened by avsolatorio 11 months ago

#40 - ERROR: multiprocess 0.70.15 has requirement dill>=0.3.7, but you'll have dill 0.3.6 which is incompatible.

Issue - State: open - Opened by echatzikyriakidis 12 months ago - 1 comment

#39 - Add pathlib import to readme example

Pull Request - State: closed - Opened by cbusenbu 12 months ago

#38 - Docker image to run REalTabFormer to support NVIDIA CUDA and GPU

Issue - State: closed - Opened by echatzikyriakidis 12 months ago - 3 comments

#37 - Future warnings for AdamW and encoder-decoder loss (v4.12.0).

Issue - State: closed - Opened by echatzikyriakidis 12 months ago - 2 comments

#36 - Bug in model.sample() when column contains integer values while column type is string.

Issue - State: open - Opened by echatzikyriakidis 12 months ago - 1 comment

#35 - Resolves #31: Only attempt to cast numeric values to pd.Int64Dtype type

Pull Request - State: closed - Opened by avsolatorio 12 months ago

#34 - Resolves #32: Auto-detect available device when cuda is not present

Pull Request - State: closed - Opened by avsolatorio 12 months ago

#33 - Bug when running tabular.fit() and tabular.sample() with CPU

Issue - State: open - Opened by ChristinaChr 12 months ago - 2 comments

#32 - _validate_get_device() could be nice to be called also in model.sample() and model.predict()

Issue - State: closed - Opened by echatzikyriakidis 12 months ago - 2 comments

#31 - Bug in model.sample() when column contains integer values while column type is string.

Issue - State: closed - Opened by echatzikyriakidis 12 months ago - 5 comments

#30 - AssertionError: The target length 10 of the data doesn't include the numeric precision at 20. Increase max_len to at least 22.

Issue - State: closed - Opened by vinay-k12 about 1 year ago - 2 comments

#29 - How to model a child table with multiple foreign keys?

Issue - State: open - Opened by echatzikyriakidis about 1 year ago

#28 - Is it possible to do iterative training? Load the weight and retrain on new data.

Issue - State: closed - Opened by vinay-k12 about 1 year ago - 2 comments

#27 - Use different join columns (parent_join_on, child_join_on) in relational model fit method.

Issue - State: open - Opened by echatzikyriakidis about 1 year ago

#26 - Speeding the training on mixed data set - categorical data, numerical and text.

Issue - State: closed - Opened by vinay-k12 about 1 year ago - 1 comment

#25 - Add accelerate dependency and bump version for release v0.1.3

Pull Request - State: closed - Opened by avsolatorio about 1 year ago

#24 - Unable to complete training in colab

Issue - State: closed - Opened by vinay-k12 about 1 year ago - 2 comments

#23 - CPU OOM during tokenization - Tabular format

Issue - State: closed - Opened by mohanvrk about 1 year ago - 3 comments

#22 - Relational Training: CUDA OOM Out of Memory Error

Issue - State: closed - Opened by solitaryangler about 1 year ago - 4 comments

#21 - How to model N-M association tables?

Issue - State: open - Opened by echatzikyriakidis about 1 year ago

#20 - Include Documentation

Pull Request - State: closed - Opened by g4brielvs about 1 year ago - 2 comments
Labels: documentation, enhancement

#19 - Update version for release 0.1.2

Pull Request - State: closed - Opened by avsolatorio about 1 year ago

#18 - New PyPi release

Issue - State: closed - Opened by echatzikyriakidis about 1 year ago - 2 comments

#17 - No progress in model training for large number of columns

Issue - State: closed - Opened by vinay-k12 about 1 year ago - 4 comments

#16 - Support for pre-computation, saving, and loading of the sensitivity threshold

Issue - State: open - Opened by avsolatorio about 1 year ago
Labels: good first issue

#15 - Is it possible to utilize Distributed Training and/or Parallel Sampling with the library?

Issue - State: closed - Opened by echatzikyriakidis over 1 year ago - 5 comments