CS5228kaggle

[train]To reproduce our results, please use Train_catboost.ipynb!
[data]In the code, we also use datasets that processed by ourselves, which are Xtrain_pre3.0.csv and Xtest_pre.csv.
[processor] These two pre-processed datasets are generated from data_preprocessor1.0.py.
[report] You can read Report_GIT.pdf for analysis

Name		Name	Last commit message	Last commit date
Latest commit History 23 Commits
DisbursementDatesFreq.npy		DisbursementDatesFreq.npy
DisbursementDatesIndex.npy		DisbursementDatesIndex.npy
FranchiseCodesIdx.npy		FranchiseCodesIdx.npy
NAICS_to_NoEmp.csv		NAICS_to_NoEmp.csv
NewExists_to_DisbursementDates.csv		NewExists_to_DisbursementDates.csv
README.md		README.md
Report_GIT.pdf		Report_GIT.pdf
To_BankStates.csv		To_BankStates.csv
Train_catboost.ipynb		Train_catboost.ipynb
Train_catboost_originaldata.ipynb		Train_catboost_originaldata.ipynb
Xtrain.csv		Xtrain.csv
Xtrain_pre.csv		Xtrain_pre.csv
Xtrain_pre1.0.csv		Xtrain_pre1.0.csv
Xtrain_pre2.0.csv		Xtrain_pre2.0.csv
Ytrain.csv		Ytrain.csv
data_preprocess.py		data_preprocess.py
data_preprocess_1.ipynb		data_preprocess_1.ipynb
data_preprocess_2.ipynb		data_preprocess_2.ipynb
data_preprocess_3.ipynb		data_preprocess_3.ipynb
data_preprocess_4.ipynb		data_preprocess_4.ipynb
data_preprocessor1.0.py		data_preprocessor1.0.py
familiar_bank.npy		familiar_bank.npy
familiar_date.npy		familiar_date.npy
familiar_name.npy		familiar_name.npy
model_comparism.xlsx		model_comparism.xlsx
sample_output.csv		sample_output.csv
term_blackList.npy		term_blackList.npy
train_process.ipynb		train_process.ipynb
utils.py		utils.py

Provide feedback