0. 핵심개념 및 사이킷런 알고리즘 API 링크
sklearn.neighbors.KNeighborsClassifier
sklearn.neighbors.KNeighborsRegressor
Part1. 분류(Classification)
1. 분석 데이터 준비
import warnings
warnings.filterwarnings("ignore")
import pandas as pd
data1=pd.read_csv('breast-cancer-wisconsin.csv', encoding='utf-8')
X=data1[data1.columns[1:10]]
y=data1[["Class"]]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X, y, stratify=y, random_state=42)
from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaler.fit(X_train)
X_scaled_train=scaler.transform(X_train)
X_scaled_test=scaler.transform(X_test)2. 기본모델 적용
from sklearn.neighbors import KNeighborsClassifier
model=KNeighborsClassifier()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.984375
from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)
훈련데이터 오차행렬:
[[331 2]
[ 6 173]]
from sklearn.metrics import classification_report
cfreport_train=classification_report(y_train, pred_train)
print("분류예측 레포트:\n", cfreport_train)
분류예측 레포트:
precision recall f1-score support
0 0.98 0.99 0.99 333
1 0.99 0.97 0.98 179
accuracy 0.98 512
macro avg 0.99 0.98 0.98 512
weighted avg 0.98 0.98 0.98 512
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.9532163742690059
confusion_test=confusion_matrix(y_test, pred_test)
print("테스트데이터 오차행렬:\n", confusion_test)
테스트데이터 오차행렬:
[[106 5]
[ 3 57]]
from sklearn.metrics import classification_report
cfreport_test=classification_report(y_test, pred_test)
print("분류예측 레포트:\n", cfreport_test)
분류예측 레포트:
precision recall f1-score support
0 0.97 0.95 0.96 111
1 0.92 0.95 0.93 60
accuracy 0.95 171
macro avg 0.95 0.95 0.95 171
weighted avg 0.95 0.95 0.95 171
3. Grid Search
param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(KNeighborsClassifier(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=KNeighborsClassifier(),
param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11]})
print("Best Parameter: {}".format(grid_search.best_params_))
print("Best Score: {:.4f}".format(grid_search.best_score_))
print("TestSet Score: {:.4f}".format(grid_search.score(X_scaled_test, y_test)))
Best Parameter: {'n_neighbors': 3}
Best Score: 0.9824
TestSet Score: 0.95324. Random Search
from scipy.stats import randint
param_distribs = {'n_neighbors': randint(low=1, high=20)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(KNeighborsClassifier(),
param_distributions=param_distribs, n_iter=20, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=KNeighborsClassifier(), n_iter=50,
param_distributions={'n_neighbors': <scipy.stats._distn_infrastructure.rv_frozen object at 0x00000177EC257250>})
print("Best Parameter: {}".format(random_search.best_params_))
print("Best Score: {:.4f}".format(random_search.best_score_))
print("TestSet Score: {:.4f}".format(random_search.score(X_scaled_test, y_test)))
Best Parameter: {'n_neighbors': 3}
Best Score: 0.9824
TestSet Score: 0.9532Part2. 회귀(Regression)
1. 분석 데이터 준비
data2=pd.read_csv('house_price.csv', encoding='utf-8')
X=data2[data2.columns[1:5]]
y=data2[["house_value"]]
data2.head()
housing_age income bedrooms households rooms house_value
0 23 6.7770 0.141112 2.442244 8.103960 500000
1 49 6.0199 0.160984 2.726688 5.752412 500000
2 35 5.1155 0.249061 1.902676 3.888078 500000
3 32 4.7109 0.231383 1.913669 4.508393 500000
4 21 4.5625 0.255583 3.092664 4.667954 500000
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X, y, random_state=42)
from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaler.fit(X_train)
X_scaled_train=scaler.transform(X_train)
X_scaled_test=scaler.transform(X_test)2. 기본모델 적용
from sklearn.neighbors import KNeighborsRegressor
model=KNeighborsRegressor()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)
0.6804607237174459
pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)
0.5541889571372401
# RMSE (Root Mean Squared Error)
import numpy as np
from sklearn.metrics import mean_squared_error
MSE_train = mean_squared_error(y_train, pred_train)
MSE_test = mean_squared_error(y_test, pred_test)
print("훈련 데이터 RMSE:", np.sqrt(MSE_train))
print("테스트 데이터 RMSE:", np.sqrt(MSE_test))
훈련 데이터 RMSE: 53952.69804097723
테스트 데이터 RMSE: 63831.916629647733. Grid Search
param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(KNeighborsRegressor(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)
GridSearchCV(cv=5, estimator=KNeighborsRegressor(),
param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11]})
print("Best Parameter: {}".format(grid_search.best_params_))
print("Best Score: {:.4f}".format(grid_search.best_score_))
print("TestSet Score: {:.4f}".format(grid_search.score(X_scaled_test, y_test)))
Best Parameter: {'n_neighbors': 11}
Best Score: 0.5638
TestSet Score: 0.5880
4. Random Search
param_distribs = {'n_neighbors': randint(low=1, high=20)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(KNeighborsRegressor(),
param_distributions=param_distribs, n_iter=50, cv=5)
random_search.fit(X_scaled_train, y_train)
RandomizedSearchCV(cv=5, estimator=KNeighborsRegressor(), n_iter=50,
param_distributions={'n_neighbors': <scipy.stats._distn_infrastructure.rv_frozen object at 0x00000177EC2A3700>})
print("Best Parameter: {}".format(random_search.best_params_))
print("Best Score: {:.4f}".format(random_search.best_score_))
print("TestSet Score: {:.4f}".format(random_search.score(X_scaled_test, y_test)))
Best Parameter: {'n_neighbors': 19}
Best Score: 0.5777
TestSet Score: 0.6004