machine learning

from sklearn.datasets import load_iris

iris_dataset = load_iris()

 

print("iris_dataset의 키 : {}".format(iris_dataset.keys()))

print("타깃의 이름 : ", iris_dataset['feature_names'])

print("data type : ", type(iris_dataset['data']))

print("size of data : ", iris_dataset['data'].shape)

print("data : \n", iris_dataset['data'][:3])

print("target의 크기 : ", iris_dataset['target'].shape)

print("target : ", iris_dataset['target'])

print("target name : ", iris_dataset['target_names'])

 

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], random_state=0)

print("X_train :", X_train.shape)

print("X_test : ", X_teset.shape)

print("y_train: ", y_train.shape)

print("y_test : ", y_test.shape)

 

iris_dataframe = pd.DataFrame(X_train, columns=iris_dataset.feature_names)

 

pd.plotting.scatter_matrix(iris_dataframe. c=y_train, figsize(15,15), marker='o', hist_kwds={'bins':20}, s=60, alpha=.8, cmap=mglearn.cm3)

 

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(ne_neighbors=1)

knn.fit(X_train, y_train)

X_new = np.arrary([[5,2,9,1,0,2]])

prediction = knn.predict(X_new)

print("예측 : ", prediction)

y_pred = knn.predcit(X_test)

print("예측값 : ", y_pred)

print("정확 : {:.2f}", format(knn.score(X_test, y_test))