This is an open solution to the Home Credit Default Risk challenge 🏡

Last update: Dec 27, 2022

Overview

Home Credit Default Risk: Open Solution

This is an open solution to the Home Credit Default Risk challenge 🏡 .

More competitions 🎇

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

Our goals

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

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.
Encourage more Kagglers to start working on this competition.
Deliver open source solution with no strings attached. Code is available on our GitHub repository 💻 . This solution should establish solid benchmark, as well as provide good base for your custom ideas and experiments. We care about clean code 😃
We are opening our experiments as well: everybody can have live preview on our experiments, parameters, code, etc. Check: Home Credit Default Risk 📈 and screens below.

Train and 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 🐍 .

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

Check Kaggle forum and participate in the discussions.
Check our Wiki pages 🏡 , where we document our work. See solutions below:

link to code	name	CV	LB	link to description
solution 1	chestnut 🌰	?	0.742	LightGBM and basic features
solution 2	seedling 🌱	?	0.747	Sklearn and XGBoost algorithms and groupby features
solution 3	blossom 🌼	0.7840	0.790	LightGBM on selected features
solution 4	tulip 🌷	0.7905	0.801	LightGBM with smarter features
solution 5	sunflower 🌻	0.7950	0.804	LightGBM clean dynamic features
solution 6	four leaf clover 🍀	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)

Clone repository and install requirements (use Python3.5)

pip3 install -r requirements.txt

Register to the neptune.ml (if you wish to use it)
Run experiment based on LightGBM:

🔱

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

🐍

python main.py -- train_evaluate_predict_cv --pipeline_name lightGBM

Installation (step by step)

Step by step installation 🖥️

Hyperparameter Tuning

Various options of hyperparameter tuning are available

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:

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

User support

There are several ways to seek help:

Kaggle discussion is our primary way of communication.
Read project's Wiki, where we publish descriptions about the code, pipelines and supporting tools such as neptune.ml.
Submit an issue directly in this repo.

Comments

ModuleNotFoundError: No module named 'deepsense'
There are two things that will make the processing of your issue faster:

Make sure that you are using the latest version of the code,

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

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

Make sure that you are using the latest version of the code,
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?

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

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 ?

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

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

Solution Version: solution 5 | sunflower 🌻 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

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

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

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

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

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)

solution-6(Aug 30, 2018)

Source code(tar.gz)
Source code(zip)
solution-5(Jul 18, 2018)

Description: https://github.com/neptune-ml/open-solution-home-credit/wiki/LightGBM-clean-dynamic-features
Source code(tar.gz)
Source code(zip)
solution-4(Jul 10, 2018)

Description: https://github.com/neptune-ml/open-solution-home-credit/wiki/LightGBM-with-smarter-features
Source code(tar.gz)
Source code(zip)
solution-3(Jul 3, 2018)

Description: https://github.com/neptune-ml/open-solution-home-credit/wiki/LightGBM-on-selected-features
Source code(tar.gz)
Source code(zip)
solution-2(Jun 19, 2018)

Description: https://github.com/neptune-ml/open-solution-home-credit/wiki/Sklearn-and-XGBoost-algorithms-and-groupby-features
Source code(tar.gz)
Source code(zip)
solution-1(Jul 18, 2018)

Description: https://github.com/neptune-ml/open-solution-home-credit/wiki/LightGBM-and-basic-features
Source code(tar.gz)
Source code(zip)

Owner

minerva.ml

GitHub Repository https://www.kaggle.com/c/home-credit-default-risk

This is an open solution to the Home Credit Default Risk challenge 🏡

Related tags

Overview

Home Credit Default Risk: Open Solution

More competitions 🎇

Our goals

Disclaimer

Note

How to start?

Learn about our solutions

Start experimenting with ready-to-use code

Installation (fast track)

Installation (step by step)

Hyperparameter Tuning

Get involved

User support

Comments

Pull Request template to Home Credit Default Risk Open Solution

Code contributions

Pull Request template to Home Credit Default Risk Open Solution

Code contributions

Pull Request template to Home Credit Default Risk Open Solution

Code contributions

Releases(solution-6)

solution-6(Aug 30, 2018)

solution-5(Jul 18, 2018)

solution-4(Jul 10, 2018)

solution-3(Jul 3, 2018)

solution-2(Jun 19, 2018)

solution-1(Jul 18, 2018)

Owner

minerva.ml

LieTransformer: Equivariant Self-Attention for Lie Groups

A TensorFlow implementation of DeepMind's WaveNet paper

Differentiable molecular simulation of proteins with a coarse-grained potential

Cross-platform CLI tool to generate your Github profile's stats and summary.

SAFL: A Self-Attention Scene Text Recognizer with Focal Loss

working repo for my xumx-sliCQ submissions to the ISMIR 2021 MDX

Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)

SAAVN - Sound Adversarial Audio-Visual Navigation,ICLR2022 (In PyTorch)

A curated list of neural rendering resources.

Fully-automated scripts for collecting AI-related papers

AWS documentation corpus for zero-shot open-book question answering.

ELSED: Enhanced Line SEgment Drawing

code associated with ACL 2021 DExperts paper

Complementary Patch for Weakly Supervised Semantic Segmentation, ICCV21 (poster)

Python implementation of Lightning-rod Agent, the Stack4Things board-side probe

Flower classification model that classifies flowers in 10 classes made using transfer learning (~85% accuracy).

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

PyMove is a Python library to simplify queries and visualization of trajectories and other spatial-temporal data

PEPit is a package enabling computer-assisted worst-case analyses of first-order optimization methods.

Official Code for "Non-deep Networks"