Apache-Airflow Setting in Windows11 (WSL 2)
Step 1. Create a virtual environment Install pip and virtualenv package 12$ sudo apt install python3-pip$ sudo pip3 install virtualenv Create a virtual environment in c:\airflow-test folder 123456
Step 1. Create a virtual environment Install pip and virtualenv package 12$ sudo apt install python3-pip$ sudo pip3 install virtualenv Create a virtual environment in c:\airflow-test folder 123456
Step 1. Enable WSL-related features by DISM Run Windows Terminal as administrator Enable Microsoft-Windows-Subsystem-Linux Features 1$ dism.exe /online /enable-feature /featurename:Microsoft-Win
LSTM(Long Short-Term Memory) When the sentence is long, the learning ability of RNN is poor. LSTM is designed to keep short-term memory long. 1234567891011from tensorflow.keras.datasets import imdbfr
Text Normalization: Pre-processing text for use as input data Cleansing 텍스트 분석에 방해되는 불필요한 문자 및 기호를 사전에 제거 ex) HTML, XML 태그 제거 Tokenization Sentence Tokenization- 문장, 마침표, 개행문자 등 문장 마지막을 뜻하는 기호를 따라
Sequential data meaningful in order such as text data, time series data Requires the function to remember previously entered data Text data text mining (representatively, sentimental analysis) natura
Prepare Fashion Mnist Data12345678from tensorflow import kerasfrom sklearn.model_selection import train_test_split(train_input, train_target), (test_input, test_target) =\ keras.datasets.fashion_mnis
CNN(Convolution Neural Network) Neural network operations can also be applied to two-dimensional arrays by CNN. Neuron in CNN is called filter or kernel. 12from tensorflow import keraskeras.layers.Co
Pipeline : 데이터 누수(Data Leakge) 방지를 위한 모델링 기법 Pycaret, MLOps (Pipeline 형태로 구축) 머신러닝 코드의 자동화 및 운영 가능 기존 방식 데이터 불러오기 -> 데이터 전처리 -> 특성 공학 -> 데이터셋 분리 -> 모델링 -> 평가 파이프라인 방식 데이터 불러오기 ->
Create DNN Model12345678910from tensorflow import kerasfrom sklearn.model_selection import train_test_split(train_input, train_target), (test_input, test_target) = \ keras.datasets.fashion_mnist.lo
Prepare Dataset123from tensorflow import keras(train_input, train_target), (test_input, test_target) = keras.datasets.fashion_mnist.load_data() 1234567from sklearn.model_selection import train_test_