Linear Regression : Logistic Regression [Iris] (3)

0. Dataset

# 데이터 불러오기
import seaborn as sns # seaborn을 불러오고 SNS로 축약
iris = sns.load_dataset('iris')  # iris라는 변수명으로 Iris data를 download

X = iris.drop('species', axis=1) # 'species'열을 drop하고 input X를 정의
y = iris['species']

# y data를 범주형으로 변환
from sklearn.preprocessing import LabelEncoder    # LabelEncoder() method를 불러옴
classle = LabelEncoder()
y = classle.fit_transform(iris['species'].values) # species 열의 문자열을 categorical 값으로 전환

# 전체 data를 training set과 test set으로 split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,
                                                    random_state=1, stratify=y)

 

1.Data Normalization

# 표준화
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)

 

2. Inference

# Logistic regression
from sklearn.linear_model import LogisticRegression
Logit = LogisticRegression(C=200, random_state=11)  # C = 1/λ. 디폴트: L2, Auto.  
l_1=Logit.fit(X_train_std, y_train)
y_train_pred = Logit.predict(X_train_std)
y_test_pred = Logit.predict(X_test_std)

 

3. Score

# Accuracy score
from sklearn.metrics import accuracy_score
print(accuracy_score(y_train,y_train_pred))  
print(accuracy_score(y_test,y_test_pred))

# Confusion matrix
from sklearn.metrics import confusion_matrix
print(confusion_matrix(y_test, y_test_pred))  # Confusion matrix