Practical Machine Learning


KYKim-PyTorch

002_autograd_and_Variable

SHKim-PyTorch

012_Lec_001_RNN_basic

TodayCode

kaggle - NLP2-2of3
NLP2-2of3.ipynb
kaggle - Bike Sharing Demand with random forest
bikesharingdemand.ipynb
kaggle - Bike Sharing Demand with linear regression, ridge regularization, lasso regularization, ensemble
kaggle - Bag Of Word Meets Bags Of Popcorn
BagOfWordMeetsBagsOfPopcorn
nlp perceptron
google colabotory
googleColaboratory2. using keras in colaboratory
deal with range data, one hot encoding
google machine learning course 001 - pandas

TensorFlow

01_Variables_Constant_Placeholders
02_Graph_and_Session
03_Tensor_Manipulation
tf.get_variable(), tf.variable_scope(), tf.name_scope()

Kidel - TensorFlow

Keywords:
- TensorFlow CNN
- MNIST dataset
- Visualize CNN filter weights
- Visualize CNN feature map processed by above filters
- How to create new filter, bias, conv layer, fc layer

ynml-machine learning and deep learning

003. basic of "GET request"
004. using basic of BeautifulSoup
005. collect currency data and news data by using beautifulsoup
006. login by using "requests library"
007. install phantomjs and selenium, configure ubuntu environment
008. using phantomjs and selenium, login, bring email data
009. xml, collecting weather data
010. Basic of JSON and parsing
011. Basic of CSV(comma separated values)
012. Basic of Excel
013. Additional contents of web scrapping
014. Basic of scikit-learn and simply applying svm
015. Basic flow of machine learning with scikit-learn
016. Arguments of fit() of scikit-learn
017. Configuring process and memory of docker virtual machine
018. Natural language processing 1
019. Natural language processing 2
020. Classifier(svm, random forest, etc)
021. Q and A
022. Dealing with mushroom data, converting character data into number, one-hot-encoding
023. Installing Tensorflow and Keras
024. Basic of applying deep learning methodology with Keras
025. Configuring KoNLPy
026. Analyzing frequency of shown words in text
027. Word2Vec
028. Classifying text by Bayes classifier
029. Classifying text data into class by MLP(multi layer perceptron), Converting text data into vector
030. Creating sentence with markov chain
031. Creating sentence with LSTM and RNN
032. Converting image into vector by hash function
033. Converting colored image to vector, Using CNN model
034. Converting image to vector and increasing quantity of data by processing some techniques like rotating

cwlee-tensorflow

002. build predicting model
003. evaluate and save model
004. restore checkpoint(weight data of model)
005. using tensorboard
011. Word2Vec (1)


msa-applying tensorflow

013. chatbot
013-003. create train data for chatbot
013-004. using Char-CNN for Intent
013-006. qna bot built with seq2seq2 with attention

shkim-deep learning with tensorflow

001-Lab_Install_TensorFlow_Basic_operation
002-lab. lineaar regression with tensorflow
003-lec. gradient descent algorithm for linear regression
003-lab. linear regression, loss function, gradient descent
004-lec. linear regression with multiple variables
004-002-lab. slicing, using loaded csv file as data, queue runners, batch, reader
005-001-lec. hypothesis function of logistic regression(classification)
005-002-lec. hypothesis function of logistic regression(classification), loss function of logistic regression(classification)
006-lec-001. multinomial classification(A,B,C)
006-lec-002. softmax function for multinomial classification
006-lab-001. softmax function for multinomial classification by tf
006-lab-002. one hot encoding, fancy softmax classification
007-lec-001. learning rate, preprocess data, overfitting, regularization
007-lec-002. training dataset, test dataset, validation dataset, online learing
007-lab-001. learning rate, linear regression with not normalized data, linear regression with normalized data by MinMaxScaler()
007-lab-002. mnist dataset
008-lab. manipulate tensor
009-lec-001. resolve xor question by deep learning
009-lec-002. forwarpropagaion and backpropagation in deep neural net
009-lab-001. xor by none nn, xor by nn, wide and deep nn
009-lab-002. tensorboard
010-lec-001. hidden layer, deep nn, issue of backpropagation with sigmoid, vanishing gradient, sigmoid and relu
010-lec-002. initialize weight, RBM, xavier initialization, he initialization
010-lec-003. dropout, ensemble
010-lec-004. stack nn module
010-lab. nn, relu, xavier, dropout, adam optimizer
011-lec-001. basic of cnn
011-lec-002. max pooling
011-lec-003. application using cnn
011-lab-001. cnn by tensorflow
011-lab-002. mnist 99% with cnn
011-lab-003. build cnn class, use tf.layers, implement ensemble
012-lab-001. basic rnn with tf
012-lab-003. rnn for long sentence
012-lab-004. stack layer for rnn with softmax layer

flearning-data science

001-001. what is data analysis, law of large numbers
001-002. reason we use python, pandas, pivot_table(), dataframe.plot("title")
001-003. scipy, numpy, pandas, matplotlib
002-001. run sh file, update conda
003_001_numpy_array
003_002_indexing_with_numpy_array,_mask_aka_boolean_array,_indexing_with_mask_aka_boolean_array
003_004_analyze_movieLens_1m_data_by_numpy,_how_to_use_np.loadtxt_np.mean_np.unique
004_001_pandas,_series,_dataframe
004_002_indexing_on_dataframe,_row_data,_column_data,_loc,_iloc
004_003_pd.date_range,_df.dropna,_df.fillna,_df.isnull,_pd.to_datetime
004-004. df["one"] and df.loc["b"], axis=0, axis=1, skipna, df.corr(), df.cov(), df.sort_index(), df.sort_values(), df.apply()
004-005. lending club loan" data by pandas, pd.read_csv(), df.to_csv()
005-001. matplotlib, magic command, plot(), plot(kind="bar"), hist(), scatter()
005-002. advanced features of matplotlib
005-003. analyze and visualize "game of thrones" dataset by matplotlib and pandas
005-004. seaborn, bokeh, polium
006-001. merge series, merge dataframe
006-002. layered index
006-003. manipulate dataframe
006-004. groupby()

golbin-tensorflow

004-003. neural network basic - word2vec
005-001. how to save variables
005-002. how to configure vairables to use tensorboard
009-001. GAN1
010-001. rnn, mnist
010-002. rnn, train words, predict last character
010-003. seq2seq, translator
010-004-001. chat.py
010-004-002. model.py
010-004-003. train.py
010-004-004. config.py
010-004-005. dialog.py

Keess324-Image classification when image has multiple labels

1. Analyze dataset
2. SIFT Key Point Detection, SIFT Feature Engineering, ORB Key Point Detection
3. Metrics for multi label image classification: Exact Match Ratio, Hamming Loss, Godbole et Measure
4. Use CNN
5. Use XGBoost

Environment Setup

https://youngminpark2559.github.io/prac_ml/env/nlp/001