Notebook:

• capstone_project_v0_data_prep.ipynb
• capstone_project_v1_data_exploratory.ipynb
• capstone_project_v2_features_engineering.ipynb
• capstone_project_v3_apply_model_m1_DecisionTree_with_norm.ipynb
• capstone_project_v3_apply_model_m1_DecisionTree_without_norm.ipynb
• capstone_project_v3_apply_model_m2_Methods_Comparison.ipynb
• capstone_project_v4_apply_model_optimal.ipynb

Note: As long as the previous steps have been executed, the subsequent step should run without any issue (Run v0, v1, and v2 first to get the imput dataset for v3). In each Notebook, the procedures are decribed with the comments and the parameters are self-explanatory.

Software:

Jupyter Notebook 3.6.0 |Anaconda custom (x86_64)| (default, Dec 23 2016, 13:19:00) [GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.57)]

• numpy version: 1.13.1
• pandas version: 0.20.3
• sklearn version: 0.19.0
• matplotlib version: 2.0.2
• seaborn version: 0.7.1

Data:

https://www.kaggle.com/c/instacart-market-basket-analysis/data

Associated Kaggle Competition:

https://www.kaggle.com/c/instacart-market-basket-analysis

Knowledge Pool

The study has been greatly motivated by the fruitful discussion on its original Kaggle competition. If the modified snippet is implemented in the project, the citation is explicitly mentioned in the notebook.

101317

access hdf5 file

http://pandas.pydata.org/pandas-docs/version/0.20/io.html#io-hdf5

100917

tips to go further

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/35048

slide for general tips on competitions

http://people.inf.ethz.ch/jaggim/meetup/slides/ML-meetup-9-vonRohr-kaggle.pdf

100717 Next stage: from Bronze to Silver in 3 days...

F1-optimize discussion and reference post

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/37016

100617 LB 0.3805009, Python Edition(鯤)

implement XGBoost

inspired by R script

https://www.kaggle.com/nickycan/lb-0-3805009-python-edition

Kaggle instacart related discussion

Experience sharing to 0.4 (InfiniteWing)

https://www.kaggle.com/infinitewing/experience-sharing-to-0-4

Faron: F1-Score Expectation Maximization in O(n²)

https://www.kaggle.com/mmueller/f1-score-expectation-maximization-in-o-n/code

script from sh1ng

https://github.com/sh1ng/imba

kaggle competition

Instacart Market Basket Analysis

https://www.kaggle.com/c/instacart-market-basket-analysis/

discussion

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion

solutions in summary

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/38130

2nd place:

https://github.com/KazukiOnodera/Instacart

3rd place: Deep Learning Method

https://github.com/sjvasquez/instacart-basket-prediction

6th place: Feature Selection Overview

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/38112

9th place: Script Provided!

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/38100

100th: SQL feature engineering + XGBoost (.4026 private LB, 1/2 of #100 solution)

https://www.kaggle.com/c/instacart-market-basket-analysis/discussion/38105