k近傍法（k-nn）

# ライブラリの読み込み
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

# irisデータの読み込み
df = sns.load_dataset("iris")

# 説明変数と目的変数に分ける
df_x = df.drop('species', axis=1)
df_y = df['species']

#学習データをテストデータを分割
train_x, test_x, train_y, test_y = train_test_split(df_x, df_y, test_size=0.5)

#モデル学習
model = KNeighborsClassifier()
model.fit(train_x, train_y)

# 予測値を算出
pred_y = model.predict(test_x)

# 正解率を表示
print(model.score(test_x, test_y))

# 混合行列を算出
print(confusion_matrix(pred_y, test_y))

# ライブラリの読み込み
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

# irisデータの読み込み
df = sns.load_dataset("iris")

# 説明変数と目的変数に分ける
df_x = df.drop('species', axis=1)
df_y = df['species']

#学習データをテストデータを分割
train_x, test_x, train_y, test_y = train_test_split(df_x, df_y, test_size=0.5)

#モデル学習
model = KNeighborsClassifier(n_neighbors=50)
model.fit(train_x, train_y)

# 予測値を算出
pred_y = model.predict(test_x)

# 正解率を表示
print(model.score(test_x, test_y))

# 混合行列を算出
print(confusion_matrix(pred_y, test_y))