machine-learning

(★ 3,496)

:earth_americas: machine learning tutorials (mainly in Python3)

파일 탐색기

최종 버전 다운로드 (.zip)

- - diff_in_diff.html
  - diff_in_diff.ipynb
  - inverse_propensity_weighting.html
  - inverse_propensity_weighting.ipynb
  - matching.html
  - matching.ipynb
- - mostwinningabtestresultsareillusory_0.pdf
  - puzzlingOutcomesInControlledExperiments.pdf
- - ab_test_regression.html
  - ab_test_regression.ipynb
  - quantile_regression.html
  - quantile_regression.ipynb
- frequentist_ab_test.html
- frequentist_ab_test.ipynb
- gsp_ad_auction.html
- gsp_ad_auction.ipynb
- - apriori_stage1.png
  - beverage_preference.png
  - binary_data.png
  - conf_pruned.png
  - data.png
  - rules.png
  - rules_pruned.png
- - apriori.html
  - apriori.R
  - apriori.Rmd
  - titanic.raw.rdata
- apriori.html
- apriori.ipynb
- Association Rule Mining-Applications in Various Areas.pdf
- ch6.pdf
- - PySpark_Cheat_Sheet_Python.pdf
  - PySpark_SQL_Cheat_Sheet_Python.pdf
- - h2o_api_walkthrough.html
  - h2o_api_walkthrough.ipynb
  - h2o_explainers.py
- - window_query.png
- - get_data.py
  - sparkml.json
- .gitignore
- local_hadoop.md
- spark_crime.html
- spark_crime.ipynb
- spark_installation.md
- spark_partitions.html
- spark_partitions.ipynb
- spark_pca.html
- spark_pca.ipynb
- - GMM.html
  - GMM.ipynb
  - guassians.pdf
- - feature_extraction.py
  - tfidf.html
  - tfidf.ipynb
- - .gitignore
  - LDA.html
  - LDA.ipynb
- .gitignore
- kmeans.html
- kmeans.ipynb
- - clustering.html
  - clustering.Rmd
  - clustering_functions.R
  - kmeanspp.R
- - text_similarity.html
  - text_similarity.R
  - text_similarity.Rmd
- - news.csv
  - tf_idf.html
  - tf_idf.R
  - tf_idf.Rmd
- - LDA.html
  - LDA.R
  - LDA.Rmd
  - LDA_functions.R
- - data_science_is_software.html
  - data_science_is_software.ipynb
- - __init__.py
- - __init__.py
  - test_example.py
- .gitignore
- - contrastive_learning_notes.html
  - contrastive_learning_notes.ipynb
  - sentence_transformer.html
  - sentence_transformer.ipynb
- - gnn_node_classification_intro.html
  - gnn_node_classification_intro.ipynb
- - conv1.png
  - conv2.png
  - conv3.png
  - conv4.png
  - conv5.png
  - conv6.png
  - convolution.gif
  - dropout.png
  - layer_size.png
  - mnist.png
  - neural_net.jpeg
  - neuron_model.jpeg
  - pool1.jpeg
  - regularizations.png
  - softmax1.png
  - softmax2.png
  - softmax3.png
- - t10k-images-idx3-ubyte.gz
  - t10k-labels-idx1-ubyte.gz
  - train-images-idx3-ubyte.gz
  - train-labels-idx1-ubyte.gz
- - .gitignore
  - fasttext.html
  - fasttext.ipynb
  - nsw.html
  - nsw.ipynb
  - product_quantization.html
  - product_quantization.ipynb
- - tensorflow_notes_02_TensorFlow_Ops.pdf
  - tensorflow_notes_04_how_to_structure_your_model_in_tensorflow.pdf
  - vecDerivs.pdf
- - question_answer.html
  - question_answer.ipynb
- - 1_pytorch_rnn.html
  - 1_pytorch_rnn.ipynb
  - 1_tensorflow_rnn.html
  - 1_tensorflow_rnn.ipynb
  - 2_tensorflow_lstm.html
  - 2_tensorflow_lstm.ipynb
  - dataloader.py
- - 1_torch_seq2seq_intro.html
  - 1_torch_seq2seq_intro.ipynb
  - 2_torch_seq2seq_attention.html
  - 2_torch_seq2seq_attention.ipynb
  - huggingface_torch_transformer.html
  - huggingface_torch_transformer.ipynb
  - torch_transformer.html
  - torch_transformer.ipynb
- - .gitignore
  - bpe.html
  - bpe.ipynb
- - .gitignore
  - deep_learning_learning_to_rank.html
  - deep_learning_learning_to_rank.ipynb
  - deep_learning_tabular.html
  - deep_learning_tabular.ipynb
  - features_config.yaml
- - .gitignore
  - word2vec Explained- Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method.pdf
  - word2vec_detailed.html
  - word2vec_detailed.ipynb
  - word2vec_workflow.py
- .gitignore
- cnn_image_tensorflow.html
- cnn_image_tensorflow.ipynb
- nn_tensorflow.html
- nn_tensorflow.ipynb
- softmax.html
- softmax.ipynb
- softmax.py
- softmax_tensorflow.html
- softmax_tensorflow.ipynb
- - decomposed.png
  - objective1.png
  - objective2.png
  - pca_versus_svd.png
  - svd.png
  - SVx_plot.png
  - transformed_plot.png
  - USVx_plot.png
  - Vx_plot.png
- - mining-massive-dataset-ch11.pdf
  - SVD-Tutorial-[Kirk-Baker].pdf
  - understanding_complex_datasets_data_mining_with_matrix_decompositions.pdf
- PCA.html
- PCA.ipynb
- svd.html
- svd.ipynb
- - ga.cpython-35.pyc
- - __init__.py
  - tspga.py
- ga.html
- ga.ipynb
- ga.py
- TSP_berlin52.txt
- TSP_berlin52_opt.txt
- - 2_layer_rnn.png
- - explainer.py
  - resnet_cam.html
  - resnet_cam.ipynb
- - .gitignore
  - keras_pretrained_embedding.html
  - keras_pretrained_embedding.ipynb
  - keras_subword_tokenization.html
  - keras_subword_tokenization.ipynb
  - word2vec_text_classification.html
  - word2vec_text_classification.ipynb
- cnn_image_keras.html
- cnn_image_keras.ipynb
- Keras_Cheat_Sheet_Python.pdf
- nn_keras_basics.html
- nn_keras_basics.ipynb
- nn_keras_hyperparameter_tuning.html
- nn_keras_hyperparameter_tuning.ipynb
- rnn_language_model_basic_keras.html
- rnn_language_model_basic_keras.ipynb
- - gradient_descent.R
  - linear_regession.R
  - LMPlot.R
- housing.txt
- linear_regession.html
- linear_regession.Rmd
- - aws_s3.html
  - aws_s3.ipynb
- - .dockerignore
  - .gitignore
  - deployment.yaml
  - Dockerfile
  - README.md
  - service.yaml
  - tree_model_deployment.html
  - tree_model_deployment.ipynb
- - .gitignore
  - gbt_inference.html
  - gbt_inference.ipynb
  - model.json
  - xgboost.onnx
- - llm_batch_inference_ray_vllm.html
  - llm_batch_inference_ray_vllm.ipynb
- - README.md
  - response_knowledge_distillation.html
  - response_knowledge_distillation.ipynb
  - text_classification_onnxruntime.html
  - text_classification_onnxruntime.ipynb
- - auc.html
  - auc.ipynb
  - HR.csv
- - .gitignore
  - imbalanced_metrics.html
  - imbalanced_metrics.ipynb
- - hyperband.png
  - hyperparameter_search.png
  - kfolds.png
  - linear_regression.png
  - normal_random_sample.png
  - refit.png
  - search_comparison.png
  - two_normal_sample.png
- - .gitignore
  - partial_dependence.html
  - partial_dependence.ipynb
  - partial_dependence.py
- - deeplearning_prob_calibration.html
  - deeplearning_prob_calibration.ipynb
  - prob_calibration.html
  - prob_calibration.ipynb
- - tips_and_tricks.html
  - tips_and_tricks.ipynb
- .gitignore
- collinearity.html
- collinearity.ipynb
- kl_divergence.html
- kl_divergence.ipynb
- model_selection.html
- model_selection.ipynb
- ray_tune_hyperband.html
- ray_tune_hyperband.ipynb
- - max_influence.html
  - max_influence.ipynb
- .gitignore
- networkx.html
- networkx.ipynb
- page_rank.html
- page_rank.ipynb
- Synthetic Social Network.pkl
- - formats.cpython-35.pyc
  - formats.cpython-36.pyc
  - formats.cpython-37.pyc
  - notebook_format.cpython-35.pyc
- custom1.css
- custom2.css
- formats.py
- plot.json
- ortools.html
- ortools.ipynb
- - .gitignore
  - pytorch_quora_insincere.html
  - pytorch_quora_insincere.ipynb
  - README.md
- - .gitignore
  - README.md
  - rossman_data_prep.html
  - rossman_data_prep.ipynb
  - rossman_deep_learning.html
  - rossman_deep_learning.ipynb
  - rossman_gbt.html
  - rossman_gbt.ipynb
- - basic_data_structure.html
  - basic_data_structure.ipynb
  - README.md
  - recursion.html
  - recursion.ipynb
  - search_sort.html
  - search_sort.ipynb
  - tree.html
  - tree.ipynb
- - cohort.html
  - cohort.ipynb
  - relay-foods.csv
  - stack_unstack.png
- - .gitignore
  - cython.html
  - cython.ipynb
  - helloworld.c
  - helloworld.cpython-35m-darwin.so
  - helloworld.pyx
  - kiel2012_cython.pdf
  - pairwise1.c
  - pairwise1.cpython-35m-darwin.so
  - pairwise1.pyx
  - pairwise2.c
  - pairwise2.cpython-35m-darwin.so
  - pairwise2.pyx
  - pairwise3.c
  - pairwise3.pyx
  - setup.py
  - setup_parallel.py
- - decorators.html
  - decorators.ipynb
  - display_info.log
  - log_timing.py
- - async_multi_thread.png
  - async_single_thread.png
  - sync_multi_thread.png
  - sync_single_thread.png
- - iterator.html
  - iterator.ipynb
- - categorical.png
  - pandas.html
  - pandas.ipynb
- - pivot_table.html
  - pivot_table.ipynb
  - sales-funnel.xlsx
- - 1_data_structure.html
  - 1_data_structure.ipynb
  - 2_strings_and_text.html
  - 2_strings_and_text.ipynb
- class.html
- class.ipynb
- factory_pattern.html
- factory_pattern.ipynb
- logging.html
- logging.ipynb
- parallel.html
- parallel.ipynb
- test.py
- unicode.md
- - movielens.cpython-35.pyc
- - .gitignore
  - ann_benchmarks.html
  - ann_benchmarks.ipynb
- - .gitignore
  - calibrated_reco.html
  - calibrated_reco.ipynb
- - lsh_text.html
  - lsh_text.ipynb
- - factorization_machine.html
  - factorization_machine.ipynb
  - sms.tsv
- - interactions.png
  - matrix_factorization.png
- - .gitignore
  - max_inner_product.html
  - max_inner_product.ipynb
- - BPR- Bayesian personalized ranking from implicit feedback.pdf
  - Collaborative Filtering for Implicit Feedback Datasets.pdf
  - Learning to Rank Recommendations with the k-Order Statistic Loss.pdf
  - Rendle2010FM.pdf
  - The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries.pdf
  - WSABIE- Scaling Up To Large Vocabulary Image Annotation.pdf
  - XboxInnerProduct.pdf
- .gitignore
- 1_ALSWR.html
- 1_ALSWR.ipynb
- 2_implicit.html
- 2_implicit.ipynb
- 4_bpr.html
- 4_bpr.ipynb
- 5_warp.html
- 5_warp.ipynb
- - bias_variance.png
  - Bias_vs_Variance_inforgraphics.png
  - estimating_coefficients.png
  - lasso_ridge_coefficients.png
- regularization.html
- regularization.ipynb
- - ab_vs_bandit.png
  - epsilon_greedy.png
- - bandits.pdf
- multi_armed_bandits.html
- multi_armed_bandits.ipynb
- - doc_len_comparison.png
  - tf_comparison.png
- bm25_intro.html
- bm25_intro.ipynb
- - basics.html
  - basics.ipynb
  - sms.tsv
- - bernoulli.txt
  - multinomial.txt
  - naive_bayes.html
  - naive_bayes.ipynb
  - Text Classification using Naive Bayes.pdf
- chisquare.html
- chisquare.ipynb
- logistic.html
- logistic.ipynb
- - ads.csv
- - fft.html
  - fft.ipynb
- - time_series_cv.png
- 1_exponential_smoothing.html
- 1_exponential_smoothing.ipynb
- 3_supervised_time_series.html
- 3_supervised_time_series.ipynb
- - tree.cpython-35.pyc
  - tree.cpython-36.pyc
- - a gentle introduction to gradient boosting.pdf
  - gbm.html
  - gbm.ipynb
  - gradient_boosting.pdf
- - leafwise.png
  - levelwise.png
  - monotonic_node.png
  - monotonic_tree.png
  - onehot_encoding.png
- .gitignore
- decision_tree.html
- decision_tree.ipynb
- lightgbm.html
- lightgbm.ipynb
- monotonic.html
- monotonic.ipynb
- random_forest.html
- random_forest.ipynb
- tree.dot
- tree.py
- winequality-white.csv
- xgboost.html
- xgboost.ipynb
- - HR.csv
  - HR_unknown.csv
- - unbalanced.R
  - unbalanced_functions.R
- unbalanced.html
- unbalanced.Rmd
.gitignore
changelog.md
contributors.md
convert_to_html.py
convert_to_knowledge_repo.py
LICENSE
README.md
requirements.txt

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/ethen8181/machine-learning

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd machine-learning

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Docker

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.

⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.

docker build -f model_deployment/fastapi_kubernetes/Dockerfile -t machine-learning .

Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.

docker run -p 8080:80 machine-learning

빌드된 이미지를 실제 컨테이너로 실행합니다.

✅ 터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.

3. CMake

보통

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
CMake 빌드 설정을 생성하는 도구입니다.
C/C++ 컴파일러 Windows는 Visual Studio(Community 무료), macOS는 Xcode Command Line Tools, Linux는 gcc/g++ 패키지가 필요합니다.

cd model_deployment/gbt_inference/gbt_inference

이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.

mkdir build && cd build

빌드 결과물을 담을 폴더를 만들고 그 안으로 이동합니다.

cmake ..

소스코드를 분석해 빌드 설정 파일을 생성합니다 (build 폴더 안에서 실행해야 함).

make

생성된 빌드 설정을 바탕으로 실제 컴파일을 진행해 실행 파일을 만듭니다.

✅ build 폴더 안에 실행 파일이 생성됐는지 확인하고, 직접 실행해보세요 (예: ./build/앱이름).

4. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

- Vanilla RNN - Tensorflow. [[nbviewer](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/deep_learning/rnn/1_tensorflow_rnn.ipynb)][[html](http://ethen8181.github.io/machine-learning/deep_learning/rnn/1_tensorflow_rnn.html)]

이 명령어를 터미널에 그대로 입력해 실행하세요.

- Long Short Term Memory (LSTM) - Tensorflow. [[nbviewer](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/deep_learning/rnn/2_tensorflow_lstm.ipynb)][[html](http://ethen8181.github.io/machine-learning/deep_learning/rnn/2_tensorflow_lstm.html)]

이 명령어를 터미널에 그대로 입력해 실행하세요.

- RNN, LSTM - PyTorch hello world. [[nbviewer](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/deep_learning/rnn/1_pytorch_rnn.ipynb)][[html](http://ethen8181.github.io/machine-learning/deep_learning/rnn/1_pytorch_rnn.html)]

이 명령어를 터미널에 그대로 입력해 실행하세요.

- Seq2Seq for German to English Machine Translation - PyTorch. Includes quick intro to torchtext [[nbviewer](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/deep_learning/seq2seq/1_torch_seq2seq_intro.ipynb)][[html](http://ethen8181.github.io/machine-learning/deep_learning/seq2seq/1_torch_seq2seq_intro.html)]

이 명령어를 터미널에 그대로 입력해 실행하세요.

- Seq2Seq with Attention for German to English Machine Translation - PyTorch. [[nbviewer](http://nbviewer.jupyter.org/github/ethen8181/machine-learning/blob/master/deep_learning/seq2seq/2_torch_seq2seq_attention.ipynb)][[html](http://ethen8181.github.io/machine-learning/deep_learning/seq2seq/2_torch_seq2seq_attention.html)]

이 명령어를 터미널에 그대로 입력해 실행하세요.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)