This is an open solution to the Home Credit Default Risk challenge ๐Ÿก

Related tags

Deep Learningpythoncompetitionopen-sourcemachine-learningdeep-learningpipelineneptunepipeline-frameworkpython3kagglexgboostlightgbmfeature-engineeringreproducibilitypython35credit-scoringreproducib
Overview

Home Credit Default Risk: Open Solution

Join the chat at https://gitter.im/minerva-ml/open-solution-home-credit license

This is an open solution to the Home Credit Default Risk challenge ๐Ÿก .

More competitions ๐ŸŽ‡

Check collection of public projects ๐ŸŽ , where you can find multiple Kaggle competitions with code, experiments and outputs.

Our goals

We are building entirely open solution to this competition. Specifically:

  1. Learning from the process - updates about new ideas, code and experiments is the best way to learn data science. Our activity is especially useful for people who wants to enter the competition, but lack appropriate experience.
  2. Encourage more Kagglers to start working on this competition.
  3. Deliver open source solution with no strings attached. Code is available on our GitHub repository ๐Ÿ’ป . This solution should establish solid benchmark, as well as provide good base for your custom ideas and experiments. We care about clean code ๐Ÿ˜ƒ
  4. We are opening our experiments as well: everybody can have live preview on our experiments, parameters, code, etc. Check: Home Credit Default Risk ๐Ÿ“ˆ and screens below.
Train and validation results on folds ๐Ÿ“Š LightGBM learning curves ๐Ÿ“Š
train-validation-results-on-folds LightGBM-learning-curves

Disclaimer

In this open source solution you will find references to the neptune.ml. It is free platform for community Users, which we use daily to keep track of our experiments. Please note that using neptune.ml is not necessary to proceed with this solution. You may run it as plain Python script ๐Ÿ .

Note

As of 1.07.2019 we officially discontinued neptune-cli client project making neptune-client the only supported way to communicate with Neptune. That means you should run experiments via python ... command or update loggers to neptune-client. For more information about the new client go to neptune-client read-the-docs page.

How to start?

Learn about our solutions

  1. Check Kaggle forum and participate in the discussions.
  2. Check our Wiki pages ๐Ÿก , where we document our work. See solutions below:
link to code name CV LB link to description
solution 1 chestnut ๐ŸŒฐ ? 0.742 LightGBM and basic features
solution 2 seedling ๐ŸŒฑ ? 0.747 Sklearn and XGBoost algorithms and groupby features
solution 3 blossom ๐ŸŒผ 0.7840 0.790 LightGBM on selected features
solution 4 tulip ๐ŸŒท 0.7905 0.801 LightGBM with smarter features
solution 5 sunflower ๐ŸŒป 0.7950 0.804 LightGBM clean dynamic features
solution 6 four leaf clover ๐Ÿ€ 0.7975 0.806 priv. LB 0.79804, Stacking by feature diversity and model diversity

Start experimenting with ready-to-use code

You can jump start your participation in the competition by using our starter pack. Installation instruction below will guide you through the setup.

Installation (fast track)

  1. Clone repository and install requirements (use Python3.5)
pip3 install -r requirements.txt
  1. Register to the neptune.ml (if you wish to use it)
  2. Run experiment based on LightGBM:

๐Ÿ”ฑ 

neptune account login
neptune run --config configs/neptune.yaml main.py train_evaluate_predict_cv --pipeline_name lightGBM

๐Ÿ 

python main.py -- train_evaluate_predict_cv --pipeline_name lightGBM

Installation (step by step)

Step by step installation ๐Ÿ–ฅ๏ธ

Hyperparameter Tuning

Various options of hyperparameter tuning are available

  1. Random Search

    configs/neptune.yaml

      hyperparameter_search__method: random
  hyperparameter_search__runs: 100

    src/pipeline_config.py

        'tuner': {'light_gbm': {'max_depth': ([2, 4, 6], "list"),
                            'num_leaves': ([2, 100], "choice"),
                            'min_child_samples': ([5, 10, 15 25, 50], "list"),
                            'subsample': ([0.95, 1.0], "uniform"),
                            'colsample_bytree': ([0.3, 1.0], "uniform"),
                            'min_gain_to_split': ([0.0, 1.0], "uniform"),
                            'reg_lambda': ([1e-8, 1000.0], "log-uniform"),
                            },
              }

Get involved

You are welcome to contribute your code and ideas to this open solution. To get started:

  1. Check competition project on GitHub to see what we are working on right now.
  2. Express your interest in paticular task by writing comment in this task, or by creating new one with your fresh idea.
  3. We will get back to you quickly in order to start working together.
  4. Check CONTRIBUTING for some more information.

User support

There are several ways to seek help:

  1. Kaggle discussion is our primary way of communication.
  2. Read project's Wiki, where we publish descriptions about the code, pipelines and supporting tools such as neptune.ml.
  3. Submit an issue directly in this repo.
Comments
  • ModuleNotFoundError: No module named 'deepsense'

    ModuleNotFoundError: No module named 'deepsense'

    There are two things that will make the processing of your issue faster:

    1. Make sure that you are using the latest version of the code,
    2. In case of bug issue, it would be nice to provide more technical details such like execution command, error message or script that reproduces your bug.

    Thanks!

    Kamil & Jakub,

    core contributors to the minerva.ml

    opened by poteman 9
  • use lightGBM_stacking pipeline raise error

    use lightGBM_stacking pipeline raise error

    There are two things that will make the processing of your issue faster:

    1. Make sure that you are using the latest version of the code,
    2. In case of bug issue, it would be nice to provide more technical details such like execution command, error message or script that reproduces your bug.

    Thanks!

    Kamil & Jakub,

    core contributors to the minerva.ml

    while I run the script python -W ignore main.py -- train_evaluate_predict_cv --pipeline_name lightGBM_stacking

    it raise error like following:

    2018-08-10 21:03:04 steppy >>> done: initializing experiment directories
2018-08-10 21:03:04 steppy >>> Step light_gbm_fold_0 initialized
2018-08-10 21-03-04 home-credit >>> Start pipeline fit and transform on train
2018-08-10 21:03:04 steppy >>> cleaning cache...
2018-08-10 21:03:04 steppy >>> cleaning cache done
Traceback (most recent call last):
  File "main.py", line 82, in <module>
    main()
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/click/core.py", line 722, in __call__
    return self.main(*args, **kwargs)
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/click/core.py", line 697, in main
    rv = self.invoke(ctx)
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/click/core.py", line 895, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/click/core.py", line 535, in invoke
    return callback(*args, **kwargs)
  File "main.py", line 78, in train_evaluate_predict_cv
    pipeline_manager.train_evaluate_predict_cv(pipeline_name, model_level, dev_mode, submit_predictions)
  File "/data1/huangzp/kaggle/home_risk_lightgbm/src/pipeline_manager.py", line 37, in train_evaluate_predict_cv
    train_evaluate_predict_cv(pipeline_name, model_level, dev_mode, submit_predictions)
  File "/data1/huangzp/kaggle/home_risk_lightgbm/src/pipeline_manager.py", line 173, in train_evaluate_predict_cv
    train_evaluate_predict_cv_first_level(pipeline_name, dev_mode, submit_predictions)
  File "/data1/huangzp/kaggle/home_risk_lightgbm/src/pipeline_manager.py", line 285, in train_evaluate_predict_cv_first_level
    model_level='first')
  File "/data1/huangzp/kaggle/home_risk_lightgbm/src/pipeline_manager.py", line 428, in _fold_fit_evaluate_predict_loop
    fold_id, pipeline_name, model_level)
  File "/data1/huangzp/kaggle/home_risk_lightgbm/src/pipeline_manager.py", line 517, in _fold_fit_evaluate_loop
    pipeline.fit_transform(train_data)
  File "/opt/anaconda2/envs/python3/lib/python3.6/site-packages/steppy/base.py", line 310, in fit_transform
    step_inputs[input_data_part] = data[input_data_part]
KeyError: 'input'
    opened by ghost 8
  • How to export the feature correlation?

    How to export the feature correlation?

    Dear,

    Could you tell me how to export the feature correlation? I saw some features in your wiki with some correlation scores. I would like to know how can you know the score? By the way, what is the scoring math metric you used? Thanks

    opened by OsloAI 4
  • PermissionError: [WinError 5] Access is denied

    PermissionError: [WinError 5] Access is denied

    Hi. Neptune is a very handy tool and I'm getting to use it. However I encountered some errors.

    It seems Neptune successfully read in the data, there are messages telling me the dataset has been initialized. But when the system wants to do gb training, such permission error happens.

    deepsense.neptune.client_library.threads.channel_values_thread WARNING channel_values_thread.py:389 - _validate() X-coordinate 1278101.8469238281 is not greater than the previous one 1278101.8469238281. Dropping point (x=1278101.8469238281, y=PermissionError: [WinError 5] Access is denied

    Besides, I'm wondering if such runtime warning is normal.

    deepsense.neptune.client_library.threads.channel_values_thread WARNING channel_values_thread.py:389 - _validate() X-coordinate 1278101.8469238281 is not greater than the previous one 1278101.8469238281. Dropping point (x=1278101.8469238281, y= new_handle = steal_handle(parent_pid, pipe_handle) ) for channel stderr. X-coordinates must be strictly increasing for each channel.

    This warning came out every second. Should it be like this?

    Could you please tell me why there is such error?

    opened by MRrollingJerry 4
  • Notebook Updated ?

    Notebook Updated ?

    Hello,

    Thank you for sharing your project, it is interesting ! I have a question regarding the different notebook where there are some preprocessing (cleaning) and creation of new features (hand craft and aggregating). I think the notebook are not updated if we compare to the code. For instance, if we look at the application data, we see 5 cleaning in the code, but in the notebook only two are available. It is forecast to update them ? It is more easy to understand all the data engineering with a notebook than a complete code.

    opened by Shiro-LK 2
  • Add some logger info while reading data

    Add some logger info while reading data

    Pull Request template to Home Credit Default Risk Open Solution

    Code contributions

    Major - and most appreciated - contribution is pull request with feature or bug fix. Each pull request initiates discussion about your code contribution.

    Each pull request should be provided with minimal description about its contents.

    Thanks!

    Jakub & Kamil,

    core contributors to the minerva.ml

    opened by pranayaryal 2
  • KeyError: 'NAME_EDUCATION_TYPE_CODE_GENDER_AMT_CREDIT_min' while running the code

    KeyError: 'NAME_EDUCATION_TYPE_CODE_GENDER_AMT_CREDIT_min' while running the code

    Solution Version: solution 5 | sunflowerย ๐ŸŒป Command used to run the code: neptune run --config configs/neptune.yaml main.py train_evaluate_predict_cv --pipeline_name lightGBM

    Error Message: KeyError: 'NAME_EDUCATION_TYPE_CODE_GENDER_AMT_CREDIT_min' The pops up in the feature_extraction.py file, under the GroupbyAggregateDiffs class and _add_diff_features method. While iterating through self.groupby_aggregations, using this line of code for groupby_cols, specs in self.groupby_aggregations:, the contents of this - self.groupby_aggregations are:

    [(['NAME_EDUCATION_TYPE', 'CODE_GENDER'], [('AMT_CREDIT', 'min'), ('AMT_CREDIT', 'mean'), ('AMT_CREDIT', 'max'), ('AMT_CREDIT', 'sum'), ('AMT_CREDIT', 'var'), ('AMT_ANNUITY', 'min'), ('AMT_ANNUITY', 'mean'), ('AMT_ANNUITY', 'max'), ('AMT_ANNUITY', 'sum'), ('AMT_ANNUITY', 'var'), ('AMT_INCOME_TOTAL', 'min'), ('AMT_INCOME_TOTAL', 'mean'), ('AMT_INCOME_TOTAL', 'max'), ('AMT_INCOME_TOTAL', 'sum'), ('AMT_INCOME_TOTAL', 'var'), ('AMT_GOODS_PRICE', 'min'), ('AMT_GOODS_PRICE', 'mean'), ('AMT_GOODS_PRICE', 'max'), ('AMT_GOODS_PRICE', 'sum'), ('AMT_GOODS_PRICE', 'var'), ('EXT_SOURCE_1', 'min'), ('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_1', 'max'), ('EXT_SOURCE_1', 'sum'), ('EXT_SOURCE_1', 'var'), ('EXT_SOURCE_2', 'min'), ('EXT_SOURCE_2', 'mean'), ('EXT_SOURCE_2', 'max'), ('EXT_SOURCE_2', 'sum'), ('EXT_SOURCE_2', 'var'), ('EXT_SOURCE_3', 'min'), ('EXT_SOURCE_3', 'mean'), ('EXT_SOURCE_3', 'max'), ('EXT_SOURCE_3', 'sum'), ('EXT_SOURCE_3', 'var'), ('OWN_CAR_AGE', 'min'), ('OWN_CAR_AGE', 'mean'), ('OWN_CAR_AGE', 'max'), ('OWN_CAR_AGE', 'sum'), ('OWN_CAR_AGE', 'var'), ('REGION_POPULATION_RELATIVE', 'min'), ('REGION_POPULATION_RELATIVE', 'mean'), ('REGION_POPULATION_RELATIVE', 'max'), ('REGION_POPULATION_RELATIVE', 'sum'), ('REGION_POPULATION_RELATIVE', 'var'), ('DAYS_REGISTRATION', 'min'), ('DAYS_REGISTRATION', 'mean'), ('DAYS_REGISTRATION', 'max'), ('DAYS_REGISTRATION', 'sum'), ('DAYS_REGISTRATION', 'var'), ('CNT_CHILDREN', 'min'), ('CNT_CHILDREN', 'mean'), ('CNT_CHILDREN', 'max'), ('CNT_CHILDREN', 'sum'), ('CNT_CHILDREN', 'var'), ('CNT_FAM_MEMBERS', 'min'), ('CNT_FAM_MEMBERS', 'mean'), ('CNT_FAM_MEMBERS', 'max'), ('CNT_FAM_MEMBERS', 'sum'), ('CNT_FAM_MEMBERS', 'var'), ('DAYS_ID_PUBLISH', 'min'), ('DAYS_ID_PUBLISH', 'mean'), ('DAYS_ID_PUBLISH', 'max'), ('DAYS_ID_PUBLISH', 'sum'), ('DAYS_ID_PUBLISH', 'var'), ('DAYS_BIRTH', 'min'), ('DAYS_BIRTH', 'mean'), ('DAYS_BIRTH', 'max'), ('DAYS_BIRTH', 'sum'), ('DAYS_BIRTH', 'var'), ('DAYS_EMPLOYED', 'min'), ('DAYS_EMPLOYED', 'mean'), ('DAYS_EMPLOYED', 'max'), ('DAYS_EMPLOYED', 'sum'), ('DAYS_EMPLOYED', 'var')]), (['NAME_FAMILY_STATUS', 'NAME_EDUCATION_TYPE'], [('AMT_CREDIT', 'min'), ('AMT_CREDIT', 'mean'), ('AMT_CREDIT', 'max'), ('AMT_CREDIT', 'sum'), ('AMT_CREDIT', 'var'), ('AMT_ANNUITY', 'min'), ('AMT_ANNUITY', 'mean'), ('AMT_ANNUITY', 'max'), ('AMT_ANNUITY', 'sum'), ('AMT_ANNUITY', 'var'), ('AMT_INCOME_TOTAL', 'min'), ('AMT_INCOME_TOTAL', 'mean'), ('AMT_INCOME_TOTAL', 'max'), ('AMT_INCOME_TOTAL', 'sum'), ('AMT_INCOME_TOTAL', 'var'), ('AMT_GOODS_PRICE', 'min'), ('AMT_GOODS_PRICE', 'mean'), ('AMT_GOODS_PRICE', 'max'), ('AMT_GOODS_PRICE', 'sum'), ('AMT_GOODS_PRICE', 'var'), ('EXT_SOURCE_1', 'min'), ('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_1', 'max'), ('EXT_SOURCE_1', 'sum'), ('EXT_SOURCE_1', 'var'), ('EXT_SOURCE_2', 'min'), ('EXT_SOURCE_2', 'mean'), ('EXT_SOURCE_2', 'max'), ('EXT_SOURCE_2', 'sum'), ('EXT_SOURCE_2', 'var'), ('EXT_SOURCE_3', 'min'), ('EXT_SOURCE_3', 'mean'), ('EXT_SOURCE_3', 'max'), ('EXT_SOURCE_3', 'sum'), ('EXT_SOURCE_3', 'var'), ('OWN_CAR_AGE', 'min'), ('OWN_CAR_AGE', 'mean'), ('OWN_CAR_AGE', 'max'), ('OWN_CAR_AGE', 'sum'), ('OWN_CAR_AGE', 'var'), ('REGION_POPULATION_RELATIVE', 'min'), ('REGION_POPULATION_RELATIVE', 'mean'), ('REGION_POPULATION_RELATIVE', 'max'), ('REGION_POPULATION_RELATIVE', 'sum'), ('REGION_POPULATION_RELATIVE', 'var'), ('DAYS_REGISTRATION', 'min'), ('DAYS_REGISTRATION', 'mean'), ('DAYS_REGISTRATION', 'max'), ('DAYS_REGISTRATION', 'sum'), ('DAYS_REGISTRATION', 'var'), ('CNT_CHILDREN', 'min'), ('CNT_CHILDREN', 'mean'), ('CNT_CHILDREN', 'max'), ('CNT_CHILDREN', 'sum'), ('CNT_CHILDREN', 'var'), ('CNT_FAM_MEMBERS', 'min'), ('CNT_FAM_MEMBERS', 'mean'), ('CNT_FAM_MEMBERS', 'max'), ('CNT_FAM_MEMBERS', 'sum'), ('CNT_FAM_MEMBERS', 'var'), ('DAYS_ID_PUBLISH', 'min'), ('DAYS_ID_PUBLISH', 'mean'), ('DAYS_ID_PUBLISH', 'max'), ('DAYS_ID_PUBLISH', 'sum'), ('DAYS_ID_PUBLISH', 'var'), ('DAYS_BIRTH', 'min'), ('DAYS_BIRTH', 'mean'), ('DAYS_BIRTH', 'max'), ('DAYS_BIRTH', 'sum'), ('DAYS_BIRTH', 'var'), ('DAYS_EMPLOYED', 'min'), ('DAYS_EMPLOYED', 'mean'), ('DAYS_EMPLOYED', 'max'), ('DAYS_EMPLOYED', 'sum'), ('DAYS_EMPLOYED', 'var')]), (['NAME_FAMILY_STATUS', 'CODE_GENDER'], [('AMT_CREDIT', 'min'), ('AMT_CREDIT', 'mean'), ('AMT_CREDIT', 'max'), ('AMT_CREDIT', 'sum'), ('AMT_CREDIT', 'var'), ('AMT_ANNUITY', 'min'), ('AMT_ANNUITY', 'mean'), ('AMT_ANNUITY', 'max'), ('AMT_ANNUITY', 'sum'), ('AMT_ANNUITY', 'var'), ('AMT_INCOME_TOTAL', 'min'), ('AMT_INCOME_TOTAL', 'mean'), ('AMT_INCOME_TOTAL', 'max'), ('AMT_INCOME_TOTAL', 'sum'), ('AMT_INCOME_TOTAL', 'var'), ('AMT_GOODS_PRICE', 'min'), ('AMT_GOODS_PRICE', 'mean'), ('AMT_GOODS_PRICE', 'max'), ('AMT_GOODS_PRICE', 'sum'), ('AMT_GOODS_PRICE', 'var'), ('EXT_SOURCE_1', 'min'), ('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_1', 'max'), ('EXT_SOURCE_1', 'sum'), ('EXT_SOURCE_1', 'var'), ('EXT_SOURCE_2', 'min'), ('EXT_SOURCE_2', 'mean'), ('EXT_SOURCE_2', 'max'), ('EXT_SOURCE_2', 'sum'), ('EXT_SOURCE_2', 'var'), ('EXT_SOURCE_3', 'min'), ('EXT_SOURCE_3', 'mean'), ('EXT_SOURCE_3', 'max'), ('EXT_SOURCE_3', 'sum'), ('EXT_SOURCE_3', 'var'), ('OWN_CAR_AGE', 'min'), ('OWN_CAR_AGE', 'mean'), ('OWN_CAR_AGE', 'max'), ('OWN_CAR_AGE', 'sum'), ('OWN_CAR_AGE', 'var'), ('REGION_POPULATION_RELATIVE', 'min'), ('REGION_POPULATION_RELATIVE', 'mean'), ('REGION_POPULATION_RELATIVE', 'max'), ('REGION_POPULATION_RELATIVE', 'sum'), ('REGION_POPULATION_RELATIVE', 'var'), ('DAYS_REGISTRATION', 'min'), ('DAYS_REGISTRATION', 'mean'), ('DAYS_REGISTRATION', 'max'), ('DAYS_REGISTRATION', 'sum'), ('DAYS_REGISTRATION', 'var'), ('CNT_CHILDREN', 'min'), ('CNT_CHILDREN', 'mean'), ('CNT_CHILDREN', 'max'), ('CNT_CHILDREN', 'sum'), ('CNT_CHILDREN', 'var'), ('CNT_FAM_MEMBERS', 'min'), ('CNT_FAM_MEMBERS', 'mean'), ('CNT_FAM_MEMBERS', 'max'), ('CNT_FAM_MEMBERS', 'sum'), ('CNT_FAM_MEMBERS', 'var'), ('DAYS_ID_PUBLISH', 'min'), ('DAYS_ID_PUBLISH', 'mean'), ('DAYS_ID_PUBLISH', 'max'), ('DAYS_ID_PUBLISH', 'sum'), ('DAYS_ID_PUBLISH', 'var'), ('DAYS_BIRTH', 'min'), ('DAYS_BIRTH', 'mean'), ('DAYS_BIRTH', 'max'), ('DAYS_BIRTH', 'sum'), ('DAYS_BIRTH', 'var'), ('DAYS_EMPLOYED', 'min'), ('DAYS_EMPLOYED', 'mean'), ('DAYS_EMPLOYED', 'max'), ('DAYS_EMPLOYED', 'sum'), ('DAYS_EMPLOYED', 'var')]), (['CODE_GENDER', 'ORGANIZATION_TYPE'], [('AMT_ANNUITY', 'mean'), ('AMT_INCOME_TOTAL', 'mean'), ('DAYS_REGISTRATION', 'mean'), ('EXT_SOURCE_1', 'mean')]), (['CODE_GENDER', 'REG_CITY_NOT_WORK_CITY'], [('AMT_ANNUITY', 'mean'), ('CNT_CHILDREN', 'mean'), ('DAYS_ID_PUBLISH', 'mean')]), (['CODE_GENDER', 'NAME_EDUCATION_TYPE', 'OCCUPATION_TYPE', 'REG_CITY_NOT_WORK_CITY'], [('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_2', 'mean')]), (['NAME_EDUCATION_TYPE', 'OCCUPATION_TYPE'], [('AMT_CREDIT', 'mean'), ('AMT_REQ_CREDIT_BUREAU_YEAR', 'mean'), ('APARTMENTS_AVG', 'mean'), ('BASEMENTAREA_AVG', 'mean'), ('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_2', 'mean'), ('EXT_SOURCE_3', 'mean'), ('NONLIVINGAREA_AVG', 'mean'), ('OWN_CAR_AGE', 'mean'), ('YEARS_BUILD_AVG', 'mean')]), (['NAME_EDUCATION_TYPE', 'OCCUPATION_TYPE', 'REG_CITY_NOT_WORK_CITY'], [('ELEVATORS_AVG', 'mean'), ('EXT_SOURCE_1', 'mean')]), (['OCCUPATION_TYPE'], [('AMT_ANNUITY', 'mean'), ('CNT_CHILDREN', 'mean'), ('CNT_FAM_MEMBERS', 'mean'), ('DAYS_BIRTH', 'mean'), ('DAYS_EMPLOYED', 'mean'), ('DAYS_ID_PUBLISH', 'mean'), ('DAYS_REGISTRATION', 'mean'), ('EXT_SOURCE_1', 'mean'), ('EXT_SOURCE_2', 'mean'), ('EXT_SOURCE_3', 'mean')])]

    I am assuming that this is where it is combining 'NAME_EDUCATION_TYPE', 'CODE_GENDER', 'AMT_CREDIT', 'min' and the key is missing. I tried to isolate the error message, but the code base is quite large. I figured a community based approach to resolve the bug might be ideal.

    opened by KartikKannapur 2
  • ValueError: No transformer cached credit_card_balance_cleaning_fold_1

    ValueError: No transformer cached credit_card_balance_cleaning_fold_1

    When I run "python main.py -- train_evaluate_predict_cv --pipeline_name XGBoost", I got this error in the title. However, I can run the lightGBM pipeline successfully.

    opened by liyinxiao 1
  • Ming zhang

    Ming zhang

    Pull Request template to Home Credit Default Risk Open Solution

    Code contributions

    Major - and most appreciated - contribution is pull request with feature or bug fix. Each pull request initiates discussion about your code contribution.

    Each pull request should be provided with minimal description about its contents.

    Thanks!

    Jakub & Kamil,

    core contributors to the minerva.ml

    opened by Bowen-Guo 1
  • Update models.py - Neural Network framework

    Update models.py - Neural Network framework

    Added a general framework for a Keras-based neural network (#136)

    Pull Request template to Home Credit Default Risk Open Solution

    Code contributions

    Major - and most appreciated - contribution is pull request with feature or bug fix. Each pull request initiates discussion about your code contribution.

    Each pull request should be provided with minimal description about its contents.

    Thanks!

    Jakub & Kamil,

    core contributors to the minerva.ml

    opened by yotamco100 1
  • CV improved LB not

    CV improved LB not

    Hi guys,

    i have extracted some more features from bureau file, it improved CV from .7950 to 0.7974 ( std 0.0024) but LB drop from .804 to .802. has anyone experienced this before ? i dont use any TARGET related features, and dont think it is overfitting.

    opened by davutpolat 1
  • Best configurations and models used

    Best configurations and models used

    Hello, I would like to use your pipeline described as 'solution 6,' but I don't get which models were used for the 1st level as oof-predictions.

    Also, I would like to know which configurations were used for the 1st level and the 2nd level respectively. In the config file, there are two configuration files (neptune_stacking.yaml and neptune.yaml) and I'm confused which one was used for each level.

    Could you let me know the models and the configurations used for the 1st and the 2nd layer respectively?

    Thank you!!

    opened by kssteven418 0
Releases(solution-6)
Owner
minerva.ml
minerva.ml
GitHub Repository https://www.kaggle.com/c/home-credit-default-risk
Yolov5-lite - Minimal PyTorch implementation of YOLOv5

Yolov5-Lite: Minimal YOLOv5 + Deep Sort Overview This repo is a shortened versio

Kadir Nar 57 Nov 28, 2022
[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation

SelectionGAN for Guided Image-to-Image Translation CVPR Paper | Extended Paper | Guided-I2I-Translation-Papers Citation If you use this code for your

Hao Tang 424 Dec 02, 2022
Weakly Supervised Segmentation by Tensorflow.

Weakly Supervised Segmentation by Tensorflow. Implements semantic segmentation in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).

CHENG-YOU LU 52 Dec 27, 2022
Spontaneous Facial Micro Expression Recognition using 3D Spatio-Temporal Convolutional Neural Networks

Spontaneous Facial Micro Expression Recognition using 3D Spatio-Temporal Convolutional Neural Networks Abstract Facial expression recognition in video

Bogireddy Sai Prasanna Teja Reddy 103 Dec 29, 2022
Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Paper | Blog OFA is a unified multimodal pretrained model that unifies modalities (i.e., cross-modality, vision, language) and tasks (e.g., image gene

OFA Sys 1.4k Jan 08, 2023
Python implementation of Lightning-rod Agent, the Stack4Things board-side probe

Iotronic Lightning-rod Agent Python implementation of Lightning-rod Agent, the Stack4Things board-side probe. Free software: Apache 2.0 license Websit

2 May 19, 2022
Learning hierarchical attention for weakly-supervised chest X-ray abnormality localization and diagnosis

Hierarchical Attention Mining (HAM) for weakly-supervised abnormality localization This is the official PyTorch implementation for the HAM method. Pap

Xi Ouyang 22 Jan 02, 2023
Romanian Automatic Speech Recognition from the ROBIN project

RobinASR This repository contains Robin's Automatic Speech Recognition (RobinASR) for the Romanian language based on the DeepSpeech2 architecture, tog

RACAI 10 Jan 01, 2023
H&M Fashion Image similarity search with Weaviate and DocArray

H&M Fashion Image similarity search with Weaviate and DocArray This example shows how to do image similarity search using DocArray and Weaviate as Doc

Laura Ham 18 Aug 11, 2022
MINOS: Multimodal Indoor Simulator

MINOS Simulator MINOS is a simulator designed to support the development of multisensory models for goal-directed navigation in complex indoor environ

194 Dec 27, 2022
Repo for code associated with Modeling the Mitral Valve.

Project Title Mitral Valve Getting Started Repo for code associated with Modeling the Mitral Valve. See https://arxiv.org/abs/1902.00018 for preprint,

Alex Kaiser 1 May 17, 2022
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

NNI Doc | ็ฎ€ไฝ“ไธญๆ–‡ NNI (Neural Network Intelligence) is a lightweight but powerful toolkit to help users automate Feature Engineering, Neural Architecture

Microsoft 12.4k Dec 31, 2022
A PoC Corporation Relationship Knowledge Graph System on top of Nebula Graph.

Corp-Rel is a PoC of Corpartion Relationship Knowledge Graph System. It's built on top of the Open Source Graph Database: Nebula Graph with a dataset

Wey Gu 20 Dec 11, 2022
A bare-bones Python library for quality diversity optimization.

pyribs Website Source PyPI Conda CI/CD Docs Docs Status Twitter pyribs.org GitHub docs.pyribs.org A bare-bones Python library for quality diversity op

ICAROS 127 Jan 06, 2023
A Sign Language detection project using Mediapipe landmark detection and Tensorflow LSTM's

sign-language-detection A Sign Language detection project using Mediapipe landmark detection and Tensorflow LSTM. The project is built for a vocabular

Hashim 4 Feb 06, 2022
Cross View SLAM

Cross View SLAM This is the associated code and dataset repository for our paper I. D. Miller et al., "Any Way You Look at It: Semantic Crossview Loca

Ian D. Miller 99 Dec 09, 2022
ECCV2020 paper: Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards. Code and Data.

This repo contains some of the codes for the following paper Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards. Code

Xuewen Yang 56 Dec 08, 2022
Download from Onlyfans.com.

OnlySave: Onlyfans downloader Getting Started: Download the setup executable from the latest release. Install and run. Only works on Windows currently

4 May 30, 2022
Data and code from COVID-19 machine learning paper

Machine learning approaches for localized lockdown, subnotification analysis and cases forecasting in Sรฃo Paulo state counties during COVID-19 pandemi

Sara Malvar 4 Dec 22, 2022
Keras like implementation of Deep Learning architectures from scratch using numpy.

Mini-Keras Keras like implementation of Deep Learning architectures from scratch using numpy. How to contribute? The project contains implementations

MANU S PILLAI 5 Oct 10, 2021