from sklearn.datasets import make_classification, load_breast_cancer,load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import GridSearchCV

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import sklearn.metrics as metrics
import seaborn as sns

import matplotlib
matplotlib.rcParams["font.family"]="Malgun Gothic"
matplotlib.rcParams["axes.unicode_minus"]= False

import warnings
warnings.simplefilter('ignore')

출처 : https://drive.google.com/uc?id=1M-rZSCsgOylvAq82HwPdmn2MikZeDQ9a

iris = load_iris() # 프랑스의 국화 붖꽃
iris.keys()

[OUT]:

dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename'])

iris['data'] # 특성데이터

[OUT]:

array([[5.1, 3.5, 1.4, 0.2],
       [4.9, 3. , 1.4, 0.2],
       [4.7, 3.2, 1.3, 0.2],
       [4.6, 3.1, 1.5, 0.2],
       [5. , 3.6, 1.4, 0.2],
       [5.4, 3.9, 1.7, 0.4],
       [4.6, 3.4, 1.4, 0.3],
       [5. , 3.4, 1.5, 0.2],
       [4.4, 2.9, 1.4, 0.2],
       [4.9, 3.1, 1.5, 0.1],
       [5.4, 3.7, 1.5, 0.2],
       [4.8, 3.4, 1.6, 0.2],
       [4.8, 3. , 1.4, 0.1],
       [4.3, 3. , 1.1, 0.1],
       [5.8, 4. , 1.2, 0.2],
       [5.7, 4.4, 1.5, 0.4],
       [5.4, 3.9, 1.3, 0.4],
       [5.1, 3.5, 1.4, 0.3],
       [5.7, 3.8, 1.7, 0.3],
       [5.1, 3.8, 1.5, 0.3],
  # ...
  # 중략
  # ...
       [5.9, 3. , 5.1, 1.8]])

iris['target'] # 라벨(종분류)

[OUT]:

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

iris['feature_names']

[OUT]:

['sepal length (cm)',
 'sepal width (cm)',
 'petal length (cm)',
 'petal width (cm)']

iris['target_names']

[OUT]:

array(['setosa', 'versicolor', 'virginica'], dtype='<U10')

iris_df = pd.DataFrame(iris.data)
iris_df.columns = iris['feature_names']
iris_df['specis']  = iris.target
iris_df

iris_df.corr()

시각화

sns.heatmap(iris_df.corr(),annot=True,cmap='Reds',vmin=1,vmax=1 )
plt.show()

sns.pairplot(data = iris_df, hue='specis')
plt.show()

plt.xticks(rotation=45)
sns.boxplot(data=iris_df[iris['feature_names']])
plt.show()

iris_df.boxplot(rot=45)
plt.show()

data set 설정

x_data = iris_df.iloc[:,:-1]
y_data = iris_df.iloc[:,-1]
x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.2,
                                                    random_state=1,stratify=y_data)
# 다중분류 시 multi_class : 'multinomial' 로 꼭 주기 (auto로 되어있지만 오류 날때를 대비)
model_logi = LogisticRegression(multi_class='multinomial')
model_logi.fit(x_train,y_train)

[OUT]:

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=100,
                   multi_class='multinomial', n_jobs=None, penalty='l2',
                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,
                   warm_start=False)

model_logi.score(x_test,y_test) # f1 score아닌 정확도

[OUT]:

0.9666666666666667

model_logi.coef_ # 12개 왜?

[OUT]:

array([[-0.51418077,  0.77926692, -2.38300365, -0.96097857],
       [ 0.30080885, -0.27663283, -0.15953256, -0.76810102],
       [ 0.21337192, -0.50263409,  2.54253621,  1.72907959]])

model_logi.intercept_ # 3개 왜?

[OUT]:

array([ 10.43736141,   2.92425059, -13.361612  ])

다중분류

- w의 개수 : 피쳐의 개수 * 분류의 개수
ws1x1 + ws2x2 + ws3x3 + ws4x4 + bs
wvs1x1 + wvs2x2 + wvs3x3 + wvs4x4 + bvs
wvc1x1 + wvc2x2 + wvc3x3 + wvc4x4 + bvc

#1

(np.matmul(x_test.values,model_logi.coef_.T) + model_logi.intercept_).argmax(axis=1)

[OUT]:

array([2, 0, 1, 0, 0, 0, 2, 2, 2, 1, 0, 1, 2, 1, 2, 0, 2, 1, 1, 2, 1, 1,
       0, 0, 2, 1, 0, 0, 1, 1], dtype=int64)

#2

model_logi.predict_proba(x_test).argmax(axis=1)

[OUT]:

array([2, 0, 1, 0, 0, 0, 2, 2, 2, 1, 0, 1, 2, 1, 2, 0, 2, 1, 1, 2, 1, 1,
       0, 0, 2, 1, 0, 0, 1, 1], dtype=int64)

#3

y_predict =  model_logi.predict(x_test)
y_predict

[OUT]:

array([2, 0, 1, 0, 0, 0, 2, 2, 2, 1, 0, 1, 2, 1, 2, 0, 2, 1, 1, 2, 1, 1,
       0, 0, 2, 1, 0, 0, 1, 1])

연습문제

[5.2,3.5,1.5,0.2]를 예측하시오

Solution

#1

model_logi.predict_proba([[5.2,3.5,1.5,0.2]]).argmax(axis=1)

[OUT]:

array([0], dtype=int64)

#2

model_logi.predict([[5.2,3.5,1.5,0.2]])

[OUT]:

array([0])

Confusion Matrix, f1 score

cm = metrics.confusion_matrix(y_test,y_predict)
sns.heatmap(cm, annot=True, cmap='Reds',
           xticklabels=['setosa로 예측', 'versicolor로 예측', 'virginica로 예측'],
            yticklabels=iris['target_names'])
plt.show()

metrics.f1_score(y_test, y_predict, average='macro')

[OUT]:

0.9665831244778613

review
- 다중분류 시 multi_class : 'multinomial' -> LogisticRegression(multi_class='multinomial')