๋ณธ๋ฌธ ๋ฐ”๋กœ๊ฐ€๊ธฐ

728x90

์•Œ๊ณ ๋ฆฌ์ฆ˜

10/11 ํ™” 1. ๋จธ์‹ ๋Ÿฌ๋‹ ์ž‘์—… ์ˆœ์„œ ๋ฐ ํ•™์Šต ๋ฐฉ๋ฒ• ๋ณ„ ๋Œ€ํ‘œ์ ์ธ ์•Œ๊ณ ๋ฆฌ์ฆ˜๋“ค 2. GridSearchCV ๊ต์ฐจ ๊ฒ€์ฆ๊ณผ ์ตœ์  ํ•˜์ดํผ ํŒŒ๋ผ๋ฏธํ„ฐ ํŠœ๋‹์„ ํ•œ ๋ฒˆ์— from sklearn.model_selection import GridSearchCV X_train, X_test, y_train, y_test = train_test_split(iris_data.data, iris_data.target, test_size = 0.2, random_state = 121) dtree = DecisionTreeClassifier() # max_depth = ๊ฒฐ์ • ํŠธ๋ฆฌ์˜ ์ตœ๋Œ€ ๊นŠ์ด, min_samples_splits = ์ž์‹ ๊ทœ์น™ ๋…ธ๋“œ๋ฅผ ๋ถ„ํ• ํ•ด ๋งŒ๋“ค๊ธฐ ์œ„ํ•œ ์ตœ์†Œํ•œ์˜ ์ƒ˜ํ”Œ ๋ฐ์ดํ„ฐ ๊ฐœ์ˆ˜ parameters = {'max_depth':[1,.. ๋”๋ณด๊ธฐ
7/16 ํ† _์ฝ”๋”ฉ ํ…Œ์ŠคํŠธ ์—ฐ์Šต(Python) 1. .sort() ๋ฉ”์„œ๋“œ, sorted() ํ•จ์ˆ˜ - .sort() ๋ฉ”์„œ๋“œ : ๋ฉ”๋ชจ๋ฆฌ ๊ณต๊ฐ„ ์ ˆ์•ฝ์„ ์œ„ํ•ด ์‹œํ€€์Šค๋ฅผ ์ œ์ž๋ฆฌ์—์„œ ์ˆ˜์ •ํ•˜์—ฌ ํšจ์œจ์  ์ •๋ ฌ๋œ ์‹œํ€€์Šค๋ฅผ ๋ฐ˜ํ™˜ํ•˜์ง€ ์•Š์Œ key์™€ reverse ๋‘ ๊ฐœ์˜ ์ธ์ž๋ฅผ ๋ฐ›์Œ (reverse=True) ๋‚ด๋ฆผ์ฐจ์ˆœ ์ •๋ ฌ - sorted() ํ•จ์ˆ˜ : sort() ๋ฉ”์„œ๋“œ์™€ ๋‹ค๋ฅด๊ฒŒ ์ •๋ ฌ๋œ ๊ฐ์ฒด๋ฅผ ๋ฐ˜ํ™˜ํ•จ iterable ๊ฐ์ฒด, key, reverse์˜ ์ธ์ž๋ฅผ ๋ฐ›์Œ c = [5, 4, 3, 2, 1] print(f'sorted ํ•จ์ˆ˜: {sorted(c)}', f'์›๋ณธ: {c}', sep='\n') c.sort() print(f'sort ๋ฉ”์„œ๋“œ: {c}') 2. %d %f %s %x %o ํฌ๋งทํŒ… num_1 = 15 num_2 = 3.0 str_1 = 'abc' print('์ˆซ์ž .. ๋”๋ณด๊ธฐ
3/24 ๋ชฉ ๋ชฉ์š”์ผ! ๊ธฐ์ˆ ํ†ต๊ณ„๋ฅผ ์ด์–ด์„œ ๋ฐฐ์šด๋‹ค. ๊ธฐ์ˆ ํ†ต๊ณ„๊ฐ€ ๋๋‚˜๋ฉด ์ถ”๋ฆฌํ†ต๊ณ„(ํ†ต๊ณ„๋ถ„์„. ์ถ”์ธก. ์ „์ˆ˜์กฐ์‚ฌ, ๋ชจ์ง‘๋‹จ)๊ฐ€ ์ˆ˜์ˆœ์ด์ง€๋งŒ ๋ฉ€์บ ์—์„œ ๋ฐฐ์šฐ์ง€๋Š” ์•Š๋Š”๋‹ค! 1์ฐจ์› ๋ฐ์ดํ„ฐ์˜ ํŠน์ง• ํŒŒ์•… - ์ˆ˜์น˜์ง€ํ‘œ → ๋Œ€ํ‘œ๊ฐ’ : ํ‰๊ท , ์ค‘์œ„๊ฐ’, ์ตœ๋Œ€/์ตœ์†Œ๊ฐ’, ํŽธ์ฐจ, ๋ถ„์‚ฐ, ํ‘œ์ค€ํŽธ์ฐจ... - ์‹œ์ž‘์  ํ‘œํ˜„ → ๋„์ˆ˜๋ถ„ํฌํ‘œ, Histogram, Box plot 2์ฐจ์› ๋ฐ์ดํ„ฐ์˜ ํŠน์ง• ํŒŒ์•… - ์ˆ˜์น˜์ง€ํ‘œ → ๊ณต๋ถ„์‚ฐ, ์ƒ๊ด€๊ณ„์ˆ˜ - ์‹œ์ž‘์  ํ‘œํ˜„ → Scatter 2์ฐจ์› ๋ฐ์ดํ„ฐ์˜ ์ˆ˜์น˜์ง€ํ‘œ → ๊ณต๋ถ„์‚ฐ, ์ƒ๊ด€๊ณ„์ˆ˜ 1. ๊ณต๋ถ„์‚ฐ(covariance) : ๋‘ ํ™•๋ฅ ๋ณ€์ˆ˜ ์‚ฌ์ด์˜ ์ƒ๊ด€ ์ •๋„ import numpy as np import pandas as pd df = pd.read_csv('./data/student_scores_em.csv', index_col='stu.. ๋”๋ณด๊ธฐ

728x90