1. Cluster(클러스터) 유사한 특성을 가진 객체들의 집합 고객 분류, 유전자 분석, 이미지 분할 import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.datasets import make_blobs # X는 2차원으로 된 데이터 프레임 # y는 데이터 답을 만들어줌 X, y = make_blobs(n_samples=100, centers=3, random_state=10) # n_samples = 샘플을 몇개를 만들지 # centers = 몇가지의 클래스를 만들지, 군집데이터를 만들기 때문에 class가 아닌 centers라고 작성함 X # 결과값 => # arr..

1. AirQualityUCI 데이터셋 import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt air_df = pd.read_csv('/content/drive/MyDrive/KDT v2/머신러닝과 딥러닝/ data/AirQualityUCI.csv') air_df air_df.info() # 결과값 => # # Column Non-Null Count Dtype # --- ------ -------------- ----- # 0 Date 9357 non-null object # 1 Time 9357 non-null object # 2 CO(GT) 9357 non-null fl..

1. Credit 데이터셋 import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt credit_df = pd.read_csv('/content/drive/MyDrive/KDT v2/머신러닝과 딥러닝/ data/credit.csv') credit_df # 컬럼의 최대치를 50으로 설정 pd.set_option('display.max_columns', 50) # 정보 확인 credit_df.info() # # Column Non-Null Count Dtype # --- ------ -------------- ----- # 0 ID 12500 non-null object # 1 ..

1. 호텔 데이터셋 import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt hotel_df = pd.read_csv('/content/drive/MyDrive/KDT v2/머신러닝과 딥러닝/ data/hotel.csv') hotel_df pd.set_option('display.max_columns', 60) hotel_df.head() hotel_df.info() 0 hotel 119390 non-null object 1 is_canceled 119390 non-null int64 2 lead_time 119390 non-null int64 3 arrival_date_ye..

from sklearn.datasets import load_digits digits = load_digits() digits.keys() # 출력값 => dict_keys(['data', 'target', 'frame', 'feature_names', 'target_names', 'images', 'DESCR']) data = digits['data'] data.shape # 출력값 => (1797, 64) target = digits['target'] target.shape # 출력값 => (1797,) target # 출력값 => array([0, 1, 2, ..., 8, 9, 8]) import matplotlib.pyplot as plt fig, axes = plt.subplots(2, 5, f..

import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns hr_df = pd.read_csv('/content/drive/MyDrive/KDT v2/머신러닝과 딥러닝/ data/hr.csv') hr_df.head() hr_df.info() # 결과값 => # 0 employee_id 54808 non-null int64 # employee_id: 임의의 직원 아이디 # 1 department 54808 non-null object # department: 부서 # 2 region 54808 non-null object # region: 지역 # 3 education 52399..