Silver bullet

보호되어 있는 글입니다.

보호되어 있는 글입니다.

RandomForest 모델 활용 : 감성분류import numpy as npimport pandas as pd# AI-HUB 감성 대화 말뭉치 활용하여 만든 데이터 읽어오기final_data = pd.read_csv('https://github.com/ohgzone/file1/raw/main/aihub_coupus.csv')# 총 51,630건final_data.info()# boolean indexing# 영문, 숫자, 특수문자 제거final_data[final_data['문장'].str.contains('[^가-힣 ]')]# '문장' 컬럼의 내용중에 영문, 특수문자 있는지 확인 : 영문과 특수문자 존재 확인final_data[final_data['문장'].str.contains('[^가-힣 ]')]..

import reimport matplotlib.pyplot as pltimport tensorflow as tffrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Dense, LSTM, Bidirectional, Embedding, Activationfrom tensorflow.keras.optimizers import Adamfrom tensorflow.keras.preprocessing.text import Tokenizerfrom tensorflow.keras.preprocessing.sequence import pad_sequencesfrom tensorflow.keras.utils import to_..

IMDB_movie_review  영화평 Text 분류 - Sentiment AnalysisIMDB (Internet Movie Database, https://www.imdb.com/) Dataset각 25,000 개의 training/testing set 으로 구성된 IMDB 영화관람평“imdb_reviews” – encoding 되어있지 않은 string 형태의 datalabel : positive, negative binary classification import tensorflow as tffrom tensorflow.keras.layers import Dense, LSTM, Embedding, Dropout, Bidirectionalfrom tensorflow.keras.models impo..

import numpy as npimport matplotlib.pyplot as pltimport tensorflow as tfprint(tf.__version__)mnist = tf.keras.datasets.fashion_mnist(training_images, training_labels), (test_images, test_labels) = mnist.load_data()plt.imshow(training_images[0])plt.show()training_images = training_images / 255.0test_images = test_images / 255.0model = tf.keras.models.Sequential([tf.keras.layers.Flatten(), ..

유방암 데이터 셋 사용import numpy as npimport pandas as pdimport matplotlib.pyplot as pltfrom sklearn.datasets import load_breast_cancerfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom lightgbm import LGBMClassifierimport warningswarnings.filterwarnings('ignore')cancer = load_breast_cancer()X_train, X_test, y_train, y_test = train_test_split( can..

Object Detection & Recognition- 이미지 속에 담긴 사물의 위치와 종류를 알아내는 기술- 입력 이미지에서 후보 영역을 추출한 후 CNN을 적용하여 해당 영역에 무엇이 있는지 예측5-1. (Advanced) Keras CNN + BN & DataAugment (99.X%)MNIST with Keras CNN + BN & DataAugment (99.X%)import tensorflow as tffrom tensorflow.keras import datasets, utilsfrom tensorflow.keras import models, layers, activations, initializers, losses, optimizers, metricsimport numpy as npimp..