Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added k fold cross validation script #152

Merged
merged 109 commits into from
Nov 17, 2022
Merged

Added k fold cross validation script #152

merged 109 commits into from
Nov 17, 2022

Commits on Oct 7, 2022

  1. Added k fold cross validation script

    @niekdejonge
    niekdejonge committed Oct 7, 2022
    Configuration menu
    Copy the full SHA
    48df61f View commit details
    Browse the repository at this point in the history

Commits on Oct 10, 2022

  1. Added functions for cross validation

    @niekdejonge
    niekdejonge committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    ce22048 View commit details
    Browse the repository at this point in the history

  2. moved scripts for creating new library to seperate directory

    @niekdejonge
    niekdejonge committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    094fbe9 View commit details
    Browse the repository at this point in the history

  3. Sort unique inchikeys

    @niekdejonge
    niekdejonge committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    f5a83d9 View commit details
    Browse the repository at this point in the history

  4. Added created tanimoto score df and test

    @niekdejonge
    niekdejonge committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    62bcbee View commit details
    Browse the repository at this point in the history

  5. Added function for training ms2deepscore

    @niekdejonge
    niekdejonge committed Oct 10, 2022
    Configuration menu
    Copy the full SHA
    7cbfebc View commit details
    Browse the repository at this point in the history

Commits on Oct 17, 2022

  1. Added function and tests for splitting spectra on inchikey

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    489881b View commit details
    Browse the repository at this point in the history

  2. Finished functions for splitting on inchikey

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    8fed375 View commit details
    Browse the repository at this point in the history

  3. Added tests for splitting spectra on inchikey

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    7860493 View commit details
    Browse the repository at this point in the history

  4. added train spec2vec

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    c6d4da5 View commit details
    Browse the repository at this point in the history

  5. Add function train spec2vec

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    74e2e28 View commit details
    Browse the repository at this point in the history

  6. Start for k fold validation pipeline

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    4b49690 View commit details
    Browse the repository at this point in the history

  7. update train ms2deepscore model

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    f431d44 View commit details
    Browse the repository at this point in the history

  8. Add matplotlib to setup.py

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    e531bcf View commit details
    Browse the repository at this point in the history

  9. fixed path for tests

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    c17126c View commit details
    Browse the repository at this point in the history

  10. Don't load spectra within ms2query data generator

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    0e6550f View commit details
    Browse the repository at this point in the history

  11. small change

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    9058c08 View commit details
    Browse the repository at this point in the history

  12. small changes

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    4a1a4ba View commit details
    Browse the repository at this point in the history

  13. calculate tanimoto scores within function

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    72d81cf View commit details
    Browse the repository at this point in the history

  14. Calculate tanimoto scores when needed, instead of tanimoto_df

    @niekdejonge
    niekdejonge committed Oct 17, 2022
    Configuration menu
    Copy the full SHA
    f09811b View commit details
    Browse the repository at this point in the history

Commits on Oct 18, 2022

  1. Big restructure and simplification of datacollectorForTraining

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    3dc0f76 View commit details
    Browse the repository at this point in the history

  2. Fix docstring

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    ae9dbd0 View commit details
    Browse the repository at this point in the history

  3. Added function for training ms2query model, from start to end

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    3138d3e View commit details
    Browse the repository at this point in the history

  4. Added save as pickled file function

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    3b7a965 View commit details
    Browse the repository at this point in the history

  5. finished draft train all models

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    0a7a9ad View commit details
    Browse the repository at this point in the history

  6. Remove ion mode from standard input library files creator

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    7b68111 View commit details
    Browse the repository at this point in the history

  7. clean up docstrings

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    76a5c25 View commit details
    Browse the repository at this point in the history

  8. Remove ion mode from train all models

    @niekdejonge
    niekdejonge committed Oct 18, 2022
    Configuration menu
    Copy the full SHA
    21fa022 View commit details
    Browse the repository at this point in the history

Commits on Oct 21, 2022

  1. Merge branch 'main' of https://github.com/iomega/ms2query into workfl… 

    …ow_k_fold_validation
    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    0c1677d View commit details
    Browse the repository at this point in the history

  2. removed ms2query prediction step from calculate features single spect… 

    …rum to implement in get training data
    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    6811387 View commit details
    Browse the repository at this point in the history

  3. restructured get matches info and tanimoto

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    2cec890 View commit details
    Browse the repository at this point in the history

  4. Finished ms2deepscore model test

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    41dc57d View commit details
    Browse the repository at this point in the history

  5. add settings option

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    26a581a View commit details
    Browse the repository at this point in the history

  6. Changed file name

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    8c599cf View commit details
    Browse the repository at this point in the history

  7. Fixed circular import

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    774583c View commit details
    Browse the repository at this point in the history

  8. added clean_library_spectra functions

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    f9983f6 View commit details
    Browse the repository at this point in the history

  9. changed test file name

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    056b81d View commit details
    Browse the repository at this point in the history

  10. Moved cleaning steps from library files creator to seperate functions

    @niekdejonge
    niekdejonge committed Oct 21, 2022
    Configuration menu
    Copy the full SHA
    48091cb View commit details
    Browse the repository at this point in the history

Commits on Oct 24, 2022

  1. Do spectrum cleaning 1 by 1

    @niekdejonge
    niekdejonge committed Oct 24, 2022
    Configuration menu
    Copy the full SHA
    9a3d444 View commit details
    Browse the repository at this point in the history

  2. Made returning a result dataframe optional

    @niekdejonge
    niekdejonge committed Oct 24, 2022
    Configuration menu
    Copy the full SHA
    d4a46ab View commit details
    Browse the repository at this point in the history

  3. Merged clean library spectra and processing spectra into one

    @niekdejonge
    niekdejonge committed Oct 24, 2022
    Configuration menu
    Copy the full SHA
    4d5ff84 View commit details
    Browse the repository at this point in the history

  4. Remove unused import statements

    @niekdejonge
    niekdejonge committed Oct 24, 2022
    Configuration menu
    Copy the full SHA
    1eed4b8 View commit details
    Browse the repository at this point in the history

  5. split annotated and unannoted instead of removing

    @niekdejonge
    niekdejonge committed Oct 24, 2022
    Configuration menu
    Copy the full SHA
    6d9d16b View commit details
    Browse the repository at this point in the history

Commits on Oct 25, 2022

  1. remove spec2vec training script and store history of ms2ds

    @niekdejonge
    niekdejonge committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    fd1e053 View commit details
    Browse the repository at this point in the history

  2. make sure None values are removed after peak filtering

    @niekdejonge
    niekdejonge committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    527e2e3 View commit details
    Browse the repository at this point in the history

  3. Added some default settings to model settings

    @niekdejonge
    niekdejonge committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    a1b9bb4 View commit details
    Browse the repository at this point in the history

  4. Moved k_fold_cross_validation to benchmarking directory

    @niekdejonge
    niekdejonge committed Oct 25, 2022
    Configuration menu
    Copy the full SHA
    4c9b6ed View commit details
    Browse the repository at this point in the history

Commits on Oct 26, 2022

  1. Added ms2library fixture

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    3f92fef View commit details
    Browse the repository at this point in the history

  2. removed file_names fixture

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    5bec41c View commit details
    Browse the repository at this point in the history

  3. Make calculate tanimoto scores into function instead of method

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    dab1e9e View commit details
    Browse the repository at this point in the history

  4. Add create library to train models

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    819236f View commit details
    Browse the repository at this point in the history

  5. Create collect_test_data, finnish create ms2query results

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    5a6f2bc View commit details
    Browse the repository at this point in the history

  6. add save json

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    4d92f2c View commit details
    Browse the repository at this point in the history

  7. add create test results cos and ms2ds

    @niekdejonge
    niekdejonge committed Oct 26, 2022
    Configuration menu
    Copy the full SHA
    135f5cf View commit details
    Browse the repository at this point in the history

Commits on Oct 31, 2022

  1. Fixed issue with not returning removed spectra

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    4e49dd6 View commit details
    Browse the repository at this point in the history

  2. Added comment

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    86b6ba8 View commit details
    Browse the repository at this point in the history

  3. restructure tanimoto calculation functions

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    27da83c View commit details
    Browse the repository at this point in the history

  4. Added load from json

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    9f0b1e0 View commit details
    Browse the repository at this point in the history

  5. linting

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    be4e372 View commit details
    Browse the repository at this point in the history

  6. Restructured all tanimoto score calculating functions

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    b4713ad View commit details
    Browse the repository at this point in the history

  7. Added create optimal results

    @niekdejonge
    niekdejonge committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    508b065 View commit details
    Browse the repository at this point in the history

Commits on Nov 1, 2022

  1. added assert statement to test equal length embeddings and sqlite spe… 

    …ctra
    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    a05d593 View commit details
    Browse the repository at this point in the history

  2. Use temporary files for ms2query csv

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    9f5645d View commit details
    Browse the repository at this point in the history

  3. check complete annotation before pubchem lookup

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    30f33f6 View commit details
    Browse the repository at this point in the history

  4. Change name clean function

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    20316cb View commit details
    Browse the repository at this point in the history

  5. finish k fold split

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    57f1e8f View commit details
    Browse the repository at this point in the history

  6. Check if completely annotated checks correct smiles

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    d99d1da View commit details
    Browse the repository at this point in the history

  7. fix test for fully annotated spectra

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    a47d8cb View commit details
    Browse the repository at this point in the history

  8. use file name instead of dir for collecting test results

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    e9d84a2 View commit details
    Browse the repository at this point in the history

  9. do not check if fingerpring sum is > 0 and add progress bars

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    ada5193 View commit details
    Browse the repository at this point in the history

  10. Remove the cleaning of spectra from train models

    @niekdejonge
    niekdejonge committed Nov 1, 2022
    Configuration menu
    Copy the full SHA
    da562a9 View commit details
    Browse the repository at this point in the history

Commits on Nov 2, 2022

  1. Create dictonary if it does not yet exist

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    23db435 View commit details
    Browse the repository at this point in the history

  2. Do not store the annotated training spectra

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    cc01940 View commit details
    Browse the repository at this point in the history

  3. linting

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    913c773 View commit details
    Browse the repository at this point in the history

  4. replace assert with assert_almost_equal

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    3d9a6f1 View commit details
    Browse the repository at this point in the history

  5. make assert less strict

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    188ab9d View commit details
    Browse the repository at this point in the history

  6. Change error in notebook files

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    3d237a0 View commit details
    Browse the repository at this point in the history

  7. Comment out python files to prevent raising errors by prospector

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    5730983 View commit details
    Browse the repository at this point in the history

  8. Added test for optimal search and do not save within test data collector

    @niekdejonge
    niekdejonge committed Nov 2, 2022
    Configuration menu
    Copy the full SHA
    4d8273f View commit details
    Browse the repository at this point in the history

Commits on Nov 8, 2022

  1. add check for None in MS2Deepscore check

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    c4c0dc4 View commit details
    Browse the repository at this point in the history

  2. Changes to if __name__

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    b9d33c8 View commit details
    Browse the repository at this point in the history

  3. Add progress bar

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    6bd16dc View commit details
    Browse the repository at this point in the history

  4. Change preselection cut off and add automatic saving

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    a93b9ec View commit details
    Browse the repository at this point in the history

  5. Save results in between

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    34eef97 View commit details
    Browse the repository at this point in the history

  6. Add check for correct precursor mz step

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    b0d848d View commit details
    Browse the repository at this point in the history

  7. change wrapper functions

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    9f47181 View commit details
    Browse the repository at this point in the history

  8. Solve issue with modified cosines score len 1

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    411ff4b View commit details
    Browse the repository at this point in the history

  9. Add len 1 test for cosine score as well

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    4b0d5f3 View commit details
    Browse the repository at this point in the history

  10. Add only one within mass range test ms2deepscore

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    9fbd980 View commit details
    Browse the repository at this point in the history

  11. add the check if precorsor mz to clean metadata

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    b36edab View commit details
    Browse the repository at this point in the history

  12. Added a check for spectrum is none

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    703bc80 View commit details
    Browse the repository at this point in the history

  13. get ms2query results now handels spectra that do not pass filtering

    @niekdejonge
    niekdejonge committed Nov 8, 2022
    Configuration menu
    Copy the full SHA
    a78ad51 View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2022

  1. store values as float instead of numpy

    @niekdejonge
    niekdejonge committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    a6d0561 View commit details
    Browse the repository at this point in the history

  2. add check for None spectra to filter ion mode

    @niekdejonge
    niekdejonge committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    505f2fc View commit details
    Browse the repository at this point in the history

  3. uncomment part of test

    @niekdejonge
    niekdejonge committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    a2d1f5d View commit details
    Browse the repository at this point in the history

Commits on Nov 15, 2022

  1. Added train models to readme and added tests

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    b1cbde6 View commit details
    Browse the repository at this point in the history

  2. remove outdated docstring

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    cac23b0 View commit details
    Browse the repository at this point in the history

  3. fix created files issue with macos and ubunto

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    5cdd2a8 View commit details
    Browse the repository at this point in the history

  4. added experiment python files to gitignore

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    a8b1ae6 View commit details
    Browse the repository at this point in the history

  5. linting

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    36717f4 View commit details
    Browse the repository at this point in the history

  6. Speed up plotting average tanimoto scores

    @niekdejonge
    niekdejonge committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    b8bdf40 View commit details
    Browse the repository at this point in the history

Commits on Nov 16, 2022

  1. Added pytest mark

    @niekdejonge
    niekdejonge committed Nov 16, 2022
    Configuration menu
    Copy the full SHA
    def7e47 View commit details
    Browse the repository at this point in the history

  2. Added docstring at start of scripts

    @niekdejonge
    niekdejonge committed Nov 16, 2022
    Configuration menu
    Copy the full SHA
    d0ac27f View commit details
    Browse the repository at this point in the history

  3. Added temporary function for calculatin the average and percentages

    @niekdejonge
    niekdejonge committed Nov 16, 2022
    Configuration menu
    Copy the full SHA
    6fdded5 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'main' into workflow_k_fold_validation

    @niekdejonge
    niekdejonge committed Nov 16, 2022
    Configuration menu
    Copy the full SHA
    05e0a6a View commit details
    Browse the repository at this point in the history

Commits on Nov 17, 2022

  1. split visualization into script per type of plot

    @niekdejonge
    niekdejonge committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    14370dc View commit details
    Browse the repository at this point in the history

  2. updated version and changelog

    @niekdejonge
    niekdejonge committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    d2ff48a View commit details
    Browse the repository at this point in the history

  3. Merge branch 'workflow_k_fold_validation' of https://github.com/iomeg… 

    …a/ms2query into workflow_k_fold_validation
    @niekdejonge
    niekdejonge committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    9967cfc View commit details
    Browse the repository at this point in the history

  4. linting

    @niekdejonge
    niekdejonge committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    3053612 View commit details
    Browse the repository at this point in the history