로지스틱 회귀

시그모이드 함수

소프트맥스 함수

시그모이드 함수 예제

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

###### 생선별 Weight, Length, Diagonal, Height, Width 정보입니다 ######
bream_smelt_data = [[ 242.    ,   25.4   ,   30.    ,   11.52  ,    4.02  ],
       [ 290.    ,   26.3   ,   31.2   ,   12.48  ,    4.3056],
       [ 340.    ,   26.5   ,   31.1   ,   12.3778,    4.6961],
       [ 363.    ,   29.    ,   33.5   ,   12.73  ,    4.4555],
       [ 430.    ,   29.    ,   34.    ,   12.444 ,    5.134 ],
       [ 450.    ,   29.7   ,   34.7   ,   13.6024,    4.9274],
       [ 500.    ,   29.7   ,   34.5   ,   14.1795,    5.2785],
       [ 390.    ,   30.    ,   35.    ,   12.67  ,    4.69  ],
       [ 450.    ,   30.    ,   35.1   ,   14.0049,    4.8438],
       [ 500.    ,   30.7   ,   36.2   ,   14.2266,    4.9594],
       [ 475.    ,   31.    ,   36.2   ,   14.2628,    5.1042],
       [ 500.    ,   31.    ,   36.2   ,   14.3714,    4.8146],
       [ 500.    ,   31.5   ,   36.4   ,   13.7592,    4.368 ],
       [ 340.    ,   32.    ,   37.3   ,   13.9129,    5.0728],
       [ 600.    ,   32.    ,   37.2   ,   14.9544,    5.1708],
       [ 600.    ,   32.    ,   37.2   ,   15.438 ,    5.58  ],
       [ 700.    ,   33.    ,   38.3   ,   14.8604,    5.2854],
       [ 700.    ,   33.    ,   38.5   ,   14.938 ,    5.1975],
       [ 610.    ,   33.5   ,   38.6   ,   15.633 ,    5.1338],
       [ 650.    ,   33.5   ,   38.7   ,   14.4738,    5.7276],
       [ 575.    ,   34.    ,   39.5   ,   15.1285,    5.5695],
       [ 685.    ,   34.    ,   39.2   ,   15.9936,    5.3704],
       [ 620.    ,   34.5   ,   39.7   ,   15.5227,    5.2801],
       [ 680.    ,   35.    ,   40.6   ,   15.4686,    6.1306],
       [ 700.    ,   35.    ,   40.5   ,   16.2405,    5.589 ],
       [ 725.    ,   35.    ,   40.9   ,   16.36  ,    6.0532],
       [ 720.    ,   35.    ,   40.6   ,   16.3618,    6.09  ],
       [ 714.    ,   36.    ,   41.5   ,   16.517 ,    5.8515],
       [ 850.    ,   36.    ,   41.6   ,   16.8896,    6.1984],
       [1000.    ,   37.    ,   42.6   ,   18.957 ,    6.603 ],
       [ 920.    ,   38.5   ,   44.1   ,   18.0369,    6.3063],
       [ 955.    ,   38.5   ,   44.    ,   18.084 ,    6.292 ],
       [ 925.    ,   39.5   ,   45.3   ,   18.7542,    6.7497],
       [ 975.    ,   41.    ,   45.9   ,   18.6354,    6.7473],
       [ 950.    ,   41.    ,   46.5   ,   17.6235,    6.3705],
       [   6.7   ,    9.8   ,   10.8   ,    1.7388,    1.0476],
       [   7.5   ,   10.5   ,   11.6   ,    1.972 ,    1.16  ],
       [   7.    ,   10.6   ,   11.6   ,    1.7284,    1.1484],
       [   9.7   ,   11.    ,   12.    ,    2.196 ,    1.38  ],
       [   9.8   ,   11.2   ,   12.4   ,    2.0832,    1.2772],
       [   8.7   ,   11.3   ,   12.6   ,    1.9782,    1.2852],
       [  10.    ,   11.8   ,   13.1   ,    2.2139,    1.2838],
       [   9.9   ,   11.8   ,   13.1   ,    2.2139,    1.1659],
       [   9.8   ,   12.    ,   13.2   ,    2.2044,    1.1484],
       [  12.2   ,   12.2   ,   13.4   ,    2.0904,    1.3936],
       [  13.4   ,   12.4   ,   13.5   ,    2.43  ,    1.269 ],
       [  12.2   ,   13.    ,   13.8   ,    2.277 ,    1.2558],
       [  19.7   ,   14.3   ,   15.2   ,    2.8728,    2.0672],
       [  19.9   ,   15.    ,   16.2   ,    2.9322,    1.8792]]

bream_smelt_target = ['Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream',
       'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream',
       'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream',
       'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream',
       'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream', 'Bream',
       'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt',
       'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt', 'Smelt']

train_input , test_input , train_target , test_target = train_test_split(bream_smelt_data , bream_smelt_target , random_state = 10)

ss = StandardScaler()
ss.fit(train_input)
train_scaled = ss.transform(train_input)
test_scaled = ss.transform(test_input)

lr = LogisticRegression()
lr.fit(train_scaled , train_target)

print(lr.predict(test_scaled[0:5]))
print(lr.predict_proba(test_scaled[0:5]))
print(lr.classes_)

소프트맥스 함수 예제