breast cancer - KNN

from sklearn.datasets import load_breast_cancer

from sklearn.neighbors import KNeighborsClassifier

from sklearn.model_selection import train_test_split

my_data = load_breast_cancer()

print(my_data)


print(my_data.keys())

print("資料筆數:")
print(my_data.data.shape)
print("\n")

print("第一筆的資料內容:")

print(my_data.data[0])
print("\n")

print("第一筆的分類目標:")
print(my_data.target[0])
print("\n")

print("預測目標的名稱種類，分別是惡性腫瘤及良性腫瘤:")
print(my_data.target_names)
print("\n")


train_x, test_x, train_y, test_y = train_test_split(my_data.data,my_data.target,test_size=0.2,random_state=18,shuffle=True)

print("原始資料的維度大小:", my_data.data.shape)
print("訓練集的維度大小:", train_x.shape)
print("測試集的維度大小:", test_x.shape)

#my_model = KNeighborsClassifier()
my_model = KNeighborsClassifier(n_neighbors=6)

my_model.fit(train_x, train_y)

test_score = my_model.score(test_x,test_y)
print("模型評估完測試集的準確度為:", test_score)

波士頓房價_線性迴歸

from sklearn.datasets import load_boston

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import mean_squared_error

my_data = load_boston()

#print(my_data)

print(my_data.keys())

print("資料比數:")
print(my_data.data.shape)
print("\n")

print("資料的欄位名稱，分別是:")
print(my_data.feature_names)
print("\n")

print("第一筆的資料內容:")
print(my_data.data[0])
print("\n")

print("第一筆的預測目標:")
print(my_data.target[0])
print("\n")



train_x, test_x, train_y, test_y, = train_test_split(my_data.data, my_data.target, test_size=0.2, random_state=43, shuffle=True)

print("原始資料集的維度大小:", my_data.data.shape)
print("訓練集的維度大小:", train_x.shape)
print("測試集的維度大小:", test_x.shape)

my_model = LinearRegression()

my_model.fit(train_x, train_y)

pred = my_model.predict(test_x)

score = mean_squared_error(test_y, pred)

print("模型評估完測試集的MSE:", score)


train_x_f1=train_x[:,[4]]
test_x_f1=test_x[:,[4]]

model_f1=LinearRegression()
model_f1.fit(train_x_f1,train_y)

pred=model_f1.predict(test_x_f1)

score=mean_squared_error(test_y,pred)
print("模型評估完測試集的誤差:" ,score)