Skip to content

Commit 6beadca

Browse files
hyunjoonbokhyunjoonbok
authored
Update README.md
1 parent 3e01003 commit 6beadca

File tree

1 file changed

+45
-40
lines changed

1 file changed

+45
-40
lines changed

‎README.md‎

Lines changed: 45 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -32,12 +32,47 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
3232
# Projects
3333

3434
### 2020 Edition
35-
#### [GameTitle-Recommender with Market-Basket-Analysis (1)](https://github.com/hyunjoonbok/R-projects/blob/master/Title_Recommender_with_market_basket_analysis/Market_Basket_Analysis_with_recommender%20(1)%20-%20Data%20Preparation.R)
35+
36+
#### [Google-play App Review Sentiment Analysis with BERT](https://github.com/hyunjoonbok/Python-Projects/blob/master/Pytorch/(Pytorch)%20Sentiment%20Analysis%20with%20Transformer%20BERT.ipynb):
37+
<p>
38+
3-way polarity (positive, neutral, negative) sentiment analysis system for Google-Play App reviews. Use Pytorch to get review in JSON, data-preprocess, Create pytorch dataloader , train/evaluate the model. Evaluate the errors and testing on the raw text data in the end.
39+
</p>
40+
Mar 5, 2020
41+
42+
#### [Credit Card Fraud Detection using Keras (Imbalanced response)](https://github.com/hyunjoonbok/Python-Projects/blob/master/tensorflow/Credit%20Card%20Fraud%20Dectection%20using%20Keras%20(Imbalanced%20response).ipynb)
3643
<p>
37-
A End-to-End recommendation system model building using the game title from data wragling, to building an algorithm and deplying to Shiny WebApp. A full comprehension of recommender algorithm could be gained and can be applied to any real-world data.
44+
Buiding a Fraud Detection model using a sample Credit Card transaction data from Kaggle. The data is highly imbalanced, so it shows how to adjust sampling to solve the problem. Then we check important metrics needed to be evalulated (fp/tp/precision/recall, etc)
3845
</p>
39-
Reference: [Diego Usai's Website](https://diegousai.io/categories/multi-article-studies/)
40-
May 17, 2020
46+
Reference: [Kaggle CreditCard data](https://www.kaggle.com/mlg-ulb/creditcardfraud/)
47+
May 20, 2020
48+
49+
50+
#### [(Kaggle) Handwritten_Image_Classification (Grapheme language)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Pytorch/%5BKaggle%5D%20(Pytorch)%20Handwritten_Image_Classification%20(Grapheme%20language).ipynb):
51+
<p>
52+
Pytorch version of builing a CNN model to classify a image of a langauge. Complete model building from loading/defining/transforming data to create and train model. From [Bengali.AI Handwritten Grapheme Classification](https://www.kaggle.com/c/bengaliai-cv19) in Kaggle.
53+
</p>
54+
Jan 4, 2020
55+
56+
57+
#### [(Kaggle) M5_Forecasting](https://github.com/hyunjoonbok/Python-Projects/blob/master/Kaggle/%5BKaggle%5D%20M5_Forecasting.ipynb):
58+
<p>
59+
From Walmart sales data, forecast daily sales for the next 28 days. The data, covers stores in three US States (California, Texas, and Wisconsin) and includes item level, department, product categories, and store details. Pre-process (Feature Enginenering / Hyperparameter Optimization) given data and used LGB/XGB ensemble to generate a final submission. From [M5 Forecasting - Accuracy](https://www.kaggle.com/c/m5-forecasting-accuracy/overview) in Kaggle.
60+
</p>
61+
Mar 24, 2020
62+
63+
64+
#### [(Kaggle) NCAAW® 2020 ML Competition](https://github.com/hyunjoonbok/Python-Projects/blob/master/Kaggle/%5BKaggle%5D%20NCAAW20.ipynb):
65+
<p>
66+
To forecast the outcomes of March-Madness during rest of 2020's NCAAW games. Covers all team-by-team season games results data. Pre-processing of tabular data and ensemble of LGB/XGB generates a final submission. From [Google Cloud & NCAA® ML Competition 2020-NCAAW](https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-womens-tournament/overview) in Kaggle. *Update: this competition was cancelled in Mar.2020 due to the COVID-19.*
67+
</p>
68+
Feb 27, 2020
69+
70+
71+
#### [Text Classification_final (Language Model)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/(Fast.ai)%20Neural%20Net%20Tabular%20data.ipynb):
72+
<p>
73+
2-way polarity (positive, negative) classification system for tweets. Using Fast.ai framework to fine-tune a language model and build a classification model with close to 80% accuracy.
74+
</p>
75+
Feb 21, 2020
4176

4277

4378
<hr>
@@ -53,20 +88,12 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
5388
Finding a customer who's income level. Simple ML Classification problem tackled with Fast.ai API. Executable to almost all types of tabular data to naively achieve a good baseline model in a few lines of code. Also, collaborative filtering is when you're tasked to predict how much a user is going to like a certain item. Here I looked at "MovieLens" dataset to predict the rating a user would give a particular movie (from 0 to 5)
5489
</p>
5590
May 10, 2018
56-
57-
58-
### [(Kaggle) M5_Forecasting](https://github.com/hyunjoonbok/Python-Projects/blob/master/Kaggle/%5BKaggle%5D%20M5_Forecasting.ipynb):
59-
<p>
60-
From Walmart sales data, forecast daily sales for the next 28 days. The data, covers stores in three US States (California, Texas, and Wisconsin) and includes item level, department, product categories, and store details. Pre-process (Feature Enginenering / Hyperparameter Optimization) given data and used LGB/XGB ensemble to generate a final submission. From [M5 Forecasting - Accuracy](https://www.kaggle.com/c/m5-forecasting-accuracy/overview) in Kaggle.
61-
</p>
62-
Mar 24, 2020
63-
64-
65-
### [(Kaggle) NCAAW® 2020 ML Competition](https://github.com/hyunjoonbok/Python-Projects/blob/master/Kaggle/%5BKaggle%5D%20NCAAW20.ipynb):
91+
92+
### [(Kaggle) Handwritten_Image_Classification (Grapheme language)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/%5BKaggle%5D%20(Fast.ai)%20Handwritten_Image_Classification%20(Grapheme%20language).ipynb):
6693
<p>
67-
To forecast the outcomes of March-Madness during rest of 2020's NCAAW games. Covers all team-by-team season games results data. Pre-processing of tabular data and ensemble of LGB/XGB generates a final submission. From [Google Cloud & NCAA® ML Competition 2020-NCAAW](https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-womens-tournament/overview) in Kaggle. *Update: this competition was cancelled in Mar.2020 due to the COVID-19.*
94+
Use Fast.ai to build a CNN model to classify a image of a langauge. From [Bengali.AI Handwritten Grapheme Classification](https://www.kaggle.com/c/bengaliai-cv19) in Kaggle. Includes Load image / Genearte custom loss function / Train & Test data using Fast.ai.
6895
</p>
69-
Feb 6, 2020
96+
Jan 3, 2020
7097

7198

7299
### [(Kaggle) NY Taxi Trip Duration](https://github.com/hyunjoonbok/Python-Projects/blob/master/Kaggle/%5BKaggle%5D%20NY%20Taxi%20Data.ipynb):
@@ -100,19 +127,14 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
100127
June 30, 2019
101128

102129

103-
### [(Kaggle) Handwritten_Image_Classification (Grapheme language)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/%5BKaggle%5D%20(Fast.ai)%20Handwritten_Image_Classification%20(Grapheme%20language).ipynb):
104-
<p>
105-
Use Fast.ai to build a CNN model to classify a image of a langauge. From [Bengali.AI Handwritten Grapheme Classification](https://www.kaggle.com/c/bengaliai-cv19) in Kaggle. Includes Load image / Genearte custom loss function / Train & Test data using Fast.ai.
106-
</p>
107-
Jan 3, 2020
108-
109130
### [Simple CNN data Augmentation](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/(Fast.ai)%20Simple%20CNN%20data%20Augmentation.ipynb):
110131
<p>
111132
Image-Augmentation on CNN model is one of the most important feature engineering steps. Here I looked at how image tranformation can be done with a built-in. Wider range of selection are availalbe in [fast.ai-vision-transform](https://docs.fast.ai/vision.transform.html) except the ones shown.
112133
*Things to add*: How ["Albumentation"](https://github.com/albumentations-team/albumentations) library can be used within Fast.ai framework.
113134
</p>
114135
Nov 12, 2019
115136

137+
116138
### [(Kaggle) MNIST Digit Recognizer](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/%5BKaggle%5D%20(Fast.ai)%20MNIST%20Digit%20Recognizer%20Kaggle.ipynb):
117139
<p>
118140
Kaggle version of MNIST. Use Fast.ai and transfer learning to solve.
@@ -144,11 +166,6 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
144166
- ## NLP/TextClassification
145167
Library / Tools: Pytorch, transformers, fast.ai, tqdm, pandas, numpy, pygments, google_play_scraper, albumentations, joblib, xgboost, lightgbm, scikit-learn, optuna, Seaborn, Matplotlib
146168

147-
### [Text Classification_final (Language Model)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Fast.ai/(Fast.ai)%20Neural%20Net%20Tabular%20data.ipynb):
148-
<p>
149-
2-way polarity (positive, negative) classification system for tweets. Using Fast.ai framework to fine-tune a language model and build a classification model with close to 80% accuracy.
150-
</p>
151-
Feb 21, 2020
152169

153170
### [BERT-base: classify twitter sentiment](https://github.com/hyunjoonbok/Python-Projects/blob/master/Pytorch/(Pytorch)%20(2)%20BERT-base%20to%20Classify%20Twitter%20NLP.ipynb):
154171
<p>
@@ -162,18 +179,6 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
162179
</p>
163180
December 7, 2019
164181

165-
### [Google-play App Review Sentiment Analysis with BERT](https://github.com/hyunjoonbok/Python-Projects/blob/master/Pytorch/(Pytorch)%20Sentiment%20Analysis%20with%20Transformer%20BERT.ipynb):
166-
<p>
167-
3-way polarity (positive, neutral, negative) sentiment analysis system for Google-Play App reviews. Use Pytorch to get review in JSON, data-preprocess, Create pytorch dataloader , train/evaluate the model. Evaluate the errors and testing on the raw text data in the end.
168-
</p>
169-
Mar 5, 2020
170-
171-
### [(Kaggle) Handwritten_Image_Classification (Grapheme language)](https://github.com/hyunjoonbok/Python-Projects/blob/master/Pytorch/%5BKaggle%5D%20(Pytorch)%20Handwritten_Image_Classification%20(Grapheme%20language).ipynb):
172-
<p>
173-
Pytorch version of builing a CNN model to classify a image of a langauge. Complete model building from loading/defining/transforming data to create and train model. From [Bengali.AI Handwritten Grapheme Classification](https://www.kaggle.com/c/bengaliai-cv19) in Kaggle.
174-
</p>
175-
Jan 4, 2020
176-
177182

178183
<hr>
179184

@@ -184,7 +189,7 @@ Below examples include the intense usage of industry-hot frameworks (i.e. Pytorc
184189
<p>
185190
Use of Python language to pull data directly from ELK stack. Origianlly came in to JSON format, convert it to Dataframe and do simple EDA / Visualization.
186191
</p>
187-
December 28, 2019
192+
December 12, 2019
188193

189194

190195
<hr>

0 commit comments

Comments
 (0)