캐글 스터디 커리큘럼

<이유한님> 캐글 스터디 커리큘럼

공부한 자료는 깃허브에 업로드하였습니다.
Andy-SKlee

목차

1. Binary classification : Tabular data
   1.1 level. Titanic: Machine Learning from Disaster
   1.2 level. Porto Seguro’s Safe Driver Prediction
   1.3 level. Home Credit Default Risk
   
2. Multi-class classification : Tabular data
   2.1 level. Costa Rican Household Poverty Level Prediction
3. Binary classification : Image classification
   3.1 level. Statoil/C-CORE Iceberg Classifier Challenge
4. Multi-class classification : Image classification
   4.1 level. TensorFlow Speech Recognition Challenge
5. Regression : Tabular data
   5.1 level. New York City Taxi Trip Duration
   5.2 level. Zillow Prize: Zillow’s Home Value Prediction (Zestimate)
6. Object segmentation : Deep learning
   6.1 level. 2018 Data Science Bowl
7. Natural language processing : classification, regression
   7.1 level. Spooky Author Identification
   7.2 level. Mercari Price Suggestion Challenge
   7.3 level. Toxic Comment Classification Challenge
8. Other dataset : anomaly detection, visualization
   8.1 level. Credit Card Fraud Detection
   8.2 level. Kaggle Machine Learning & Data Science Survey 2017

---

1. Binary classification : Tabular data

Titanic Machine Learning from Disaster

• 타이타닉 튜토리얼 - Exploratory data analysis, visualization, machine learning
• EDA To Prediction(DieTanic)
• Titanic Top 4% with ensemble modeling
• Introduction to Ensembling/Stacking in Python

Porto Seguro Safe Driver Prediction

• Data Preparation & ExplorationPorto
• Interactive Porto Insights - A Plot.ly Tutorial
• XGBoost CV (LB .284)
• Seguro Exploratory Analysis and Prediction

Home Credit Default Risk

• Introduction: Home Credit Default Risk Competition
• Introduction to Manual Feature Engineering
• Stacking Test-Sklearn, XGBoost, CatBoost, LightGBM
• LightGBM 7th place solution

2. Multi-class classification : Tabular data

Costa Rican Household Poverty Level Prediction

• A Complete Introduction and Walkthrough
• 3250feats->532 feats using shap[LB: 0.436]
• XGBoost

3. Binary classification : Image classification

Statoil C CORE Iceberg Classifier Challenge

• Keras Model for Beginners (0.210 on LB)+EDA+R&D
• Transfer Learning with VGG-16 CNN+AUG LB 0.1712
• Submarineering.EVEN BETTER PUBLIC SCORE until now.
• Keras+TF LB 0.18

4. Multi-class classification : Image classification

TensorFlow Speech Recognition Challenge

• Speech representation and data exploration
• Light-Weight CNN LB 0.74
• WavCeption V1: a 1-D Inception approach (LB 0.76)

5. Regression : Tabular data

New York City Taxi Trip Duration

• Dynamics of New York city - Animation
• EDA + Baseline Model
• Beat the benchmark!

Zillow Prize Zillow Home Value Prediction Zestimate

• Simple Exploration Notebook - Zillow Prize
• Simple XGBoost Starter (~0.0655)
• Zillow EDA On Missing Values & Multicollinearity
• XGBoost, LightGBM, and OLS and NN

6. Object segmentation : Deep learning

2018 Data Science Bowl

• Teaching notebook for total imaging newbies
• Keras U-Net starter - LB 0.277
• Nuclei Overview to Submission

7. Natural language processing : classification, regression

Spooky Author Identification

• Spooky NLP and Topic Modelling tutorial
• Approaching (Almost) Any NLP Problem on Kaggle
• Simple Feature Engg Notebook - Spooky Author

Mercari Price Suggestion Challenge

• Mercari Interactive EDA + Topic Modelling
• A simple nn solution with Keras (~0.48611 PL)
• Ridge (LB 0.41943)
• LGB and FM (18th Place - 0.40604)

Toxic Comment Classification Challenge

• (For Beginners) Tackling Toxic Using Keras
• Stop the S@#$ - Toxic Comments EDA
• Logistic regression with words and char n-grams
• Classifying multi-label comments (0.9741 lb)

8. Other dataset : anomaly detection, visualization

Credit Card Fraud Detection

• In depth skewed data classif. (93% recall acc now)
• Anomaly Detection - Credit Card Fraud Analysis
• Semi-Supervised Anomaly Detection Survey

Kaggle Machine Learning and Data Science Survey 2017

• Novice to Grandmaster
• What do Kagglers say about Data Science ?
• PLOTLY TUTORIAL - 1