import 구문
1 2 3 4 5 6 | import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import cross_val_score, train_test_split
|
jupyter notebook에서 파일에 바로 내용을 써 넣어서 채우고 싶을 때
1 2 3 4 5 6 | %%writefile test2
1,2,3,4,5
2,3,4,5,6
7,8,9,0,1
|
그래프 한글폰트 설정
1 2 3 4 5 6 7 8 9 10 11 12 13 14 | import matplotlib.font_manager
if platform.system() == 'Windows':
path = "c:\Windows\Fonts\malgun.ttf"
font_name = matplotlib.font_manager.FontProperties(fname=path).get_name()
plt.rc('font', family=font_name)
elif platform.system() == 'Darwin':
rc('font', family='AppleGothic')
elif platform.system() == 'Linux':
rc('font', family='NanumBarunGothic')
|
datetime 데이터 분해하는 코드
1 2 3 4 5 6 7 8 | train["d-year"] = train["datetime"].dt.year
train["d-month"] = train["datetime"].dt.month
train["d-day"] = train["datetime"].dt.day
train["d-hour"] = train["datetime"].dt.hour
train["d-minute"] = train["datetime"].dt.minute
train["d-second"] = train["datetime"].dt.second
train[["datetime", "d-year", "d-month", "d-day", "d-hour", "d-minute", "d-second"]].head()
|
zip파일 압축풀기
1 2 3 4 | local_zip = './data/cats_and_dogs_filtered.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('./data')
zip_ref.close()
|
폴더 없으면 폴더 만들기. 그리고 wget
1 2 3 4 5 6 | if not os.path.exists("./data"):
os.makedirs("./data")
if not os.path.exists("./data/cats_and_dogs_filtered.zip"):
!wget --no-check-certificate \
https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip \
-O ./data/cats_and_dogs_filtered.zip
|
csv 파일 읽기
1 2 3 4 5 6 | import pandas as pd
df_train = pd.read_csv('data/ratings_train.txt', delimiter='\t', keep_default_na=False)
df_test = pd.read_csv('data/ratings_test.txt', delimiter='\t', keep_default_na=False)
df_train.head()
|
학습 데이터, 테스트 데이터로 분리하기
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | import numpy as np
from sklearn.model_selection import train_test_split
X = [[0,1],[2,3],[4,5],[6,7],[8,9]]
Y = [0,1,2,3,4]
X_train, X_test = train_test_split(X, test_size=0.2, random_state=123)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.33, random_state=321)
|
|
