python training 資料準備 (以DataFrame匯入) KNN

# 一開始先被好資料(df格式)

# 決定切割欄位

cols = ["x1","x2","x3","x4"]

x = np.array(df[cols])

y = np.array(df["y"])

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=88)

#使用KNN演算法

from sklearn.neighbors import KNeighborsClassifier

#從k=1開始測試

knn = KNeighborsClassifier(n_neighbors=1)

knn.fit(X_train,y_train)

pred = knn.predict(X_test)

#使用決策樹

from sklearn import tree

clf = tree.DecisionTreeClassifier()

clf = clf.fit(X_train,y_train)

tree.plot_tree(clf)

#pred = clf.predict(X_test)

#測試資料與預測資料比較

from sklearn.metrics import classification_report,confusion_matrix

print(confusion_matrix(y_test,pred))

print(classification_report(y_test,pred))