Youtubeでビデオ・レッスン（13/16）モデルの評価と選択 | 交差検証、さまざまな評価基準

Jupyter Notebookなどで、コードを実装して実際に確かめてみましょう。

Jetson Nanoでjupyter-notebookを使う場合
mglearnは入ってないのでインストールしておきます
＄sudo pip3 install mglearn

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_moons

moons = make_moons(n_samples=200,noise=0.2,random_state=0)
x = moons[0]
y = moons[1]

from matplotlib.colors import ListedColormap

def plot_decision_boundary(model,x,y,margin=0.3):
    _x1 = np.linspace(x[:,0].min()-margin,x[:,0].max()+margin,100)
    _x2 = np.linspace(x[:,1].min()-margin,x[:,1].max()+margin,100)
    x1,x2 = np.meshgrid(_x1,_x2)
    x_new = np.c_[x1.ravel(),x2.ravel()]
    y_pred = model.predict(x_new).reshape(x1.shape)
    custom_cmap = ListedColormap(['mediumblue','orangered'])
    plt.contourf(x1,x2,y_pred,alpha=0.3,cmap=custom_cmap)

def plot_dataset(x,y):
    plt.plot(x[:,0][y==0],x[:,1][y==0],'bo',ms=15)
    plt.plot(x[:,0][y==1],x[:,1][y==1],'r^',ms=15)
    plt.xlabel("$x_0$",fontsize=30)
    plt.ylabel("$x_1$",fontsize=30,rotation=0)

plt.figure(figsize=(12,8))
plot_dataset(x,y)
plt.show()

-----------------------------------------------------
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=0)

log_reg = LogisticRegression().fit(x_train,y_train)
tree_clf = DecisionTreeClassifier().fit(x_train,y_train)

print(log_reg.score(x_test,y_test))
print(tree_clf.score(x_test,y_test))

-----------------------------------------------------
from sklearn.model_selection import KFold,cross_val_score

kfold = KFold(n_splits=5,shuffle=True,random_state=0)

log_reg_score = cross_val_score(log_reg,x,y,cv=kfold)
tree_clf_score = cross_val_score(tree_clf,x,y,cv=kfold)

print(log_reg_score)
print(tree_clf_score)

print(log_reg_score.mean())
print(tree_clf_score.mean())

-----------------------------------------------------
from sklearn.metrics import confusion_matrix

y_pred_log_reg = log_reg.predict(x_test)
y_pred_tree_clf = tree_clf.predict(x_test)

cm_log_reg = confusion_matrix(y_test,y_pred_log_reg)
cm_tree_clf = confusion_matrix(y_test,y_pred_tree_clf)

print(cm_log_reg)
print(cm_tree_clf)

-----------------------------------------------------
from sklearn.metrics import precision_score,recall_score,f1_score

print("precision log_reg:\n",precision_score(y_test,y_pred_log_reg))
print("\n")
print("precision tree_clf:\n",precision_score(y_test,y_pred_tree_clf))

print("recall log_reg:\n",recall_score(y_test,y_pred_log_reg))
print("\n")
print("recall tree_clf:\n",recall_score(y_test,y_pred_tree_clf))

print("f1 log_reg:\n",f1_score(y_test,y_pred_log_reg))
print("\n")
print("f1 tree_clf:\n",f1_score(y_test,y_pred_tree_clf))

-----------------------------------------------------
from sklearn.metrics import precision_recall_curve

precision,recall,threshold = precision_recall_curve(y_test,y_pred_tree_clf)

plt.figure(figsize=(12,8))
plt.plot(precision,recall)
plt.xlabel("precision")
plt.ylabel("recall")
plt.show()

precision,recall,threshold = precision_recall_curve(y_test,y_pred_log_reg)

plt.figure(figsize=(12,8))
plt.plot(precision,recall)
plt.xlabel("precision")
plt.ylabel("recall")
plt.show()

-----------------------------------------------------
from mglearn.datasets import make_wave

x,y = make_wave(n_samples=100)

plt.figure(figsize=(12,8))
plt.scatter(x,y)
plt.xlabel("x")
plt.ylabel("y")
plt.show()

from sklearn.linear_model import LinearRegression

x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=0)
lin_reg = LinearRegression().fit(x_train,y_train)

print(lin_reg.score(x_test,y_test))

from sklearn.metrics import mean_squared_error

y_pred = lin_reg.predict(x_test)

mse = mean_squared_error(y_test,y_pred)
mse

rmse = np.sqrt(mse)
rmse

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

import numpy as np

import matplotlib.pyplot as plt

from sklearn.datasets import make_moons

moons = make_moons(n_samples=200,noise=0.2,random_state=0)

x = moons[0]

y = moons[1]

from matplotlib.colors import ListedColormap

def plot_decision_boundary(model,x,y,margin=0.3):

_x1 = np.linspace(x[:,0].min()-margin,x[:,0].max()+margin,100)

_x2 = np.linspace(x[:,1].min()-margin,x[:,1].max()+margin,100)

x1,x2 = np.meshgrid(_x1,_x2)

x_new = np.c_[x1.ravel(),x2.ravel()]

y_pred = model.predict(x_new).reshape(x1.shape)

custom_cmap = ListedColormap(['mediumblue','orangered'])

plt.contourf(x1,x2,y_pred,alpha=0.3,cmap=custom_cmap)

def plot_dataset(x,y):

plt.plot(x[:,0][y==0],x[:,1][y==0],'bo',ms=15)

plt.plot(x[:,0][y==1],x[:,1][y==1],'r^',ms=15)

plt.xlabel("$x_0$",fontsize=30)

plt.ylabel("$x_1$",fontsize=30,rotation=0)

plt.figure(figsize=(12,8))

plot_dataset(x,y)

plt.show()

-----------------------------------------------------

from sklearn.linear_model import LogisticRegression

from sklearn.tree import DecisionTreeClassifier

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=0)

log_reg = LogisticRegression().fit(x_train,y_train)

tree_clf = DecisionTreeClassifier().fit(x_train,y_train)

print(log_reg.score(x_test,y_test))

print(tree_clf.score(x_test,y_test))

-----------------------------------------------------

from sklearn.model_selection import KFold,cross_val_score

kfold = KFold(n_splits=5,shuffle=True,random_state=0)

log_reg_score = cross_val_score(log_reg,x,y,cv=kfold)

tree_clf_score = cross_val_score(tree_clf,x,y,cv=kfold)

print(log_reg_score)

print(tree_clf_score)

print(log_reg_score.mean())

print(tree_clf_score.mean())

-----------------------------------------------------

from sklearn.metrics import confusion_matrix

y_pred_log_reg = log_reg.predict(x_test)

y_pred_tree_clf = tree_clf.predict(x_test)

cm_log_reg = confusion_matrix(y_test,y_pred_log_reg)

cm_tree_clf = confusion_matrix(y_test,y_pred_tree_clf)

print(cm_log_reg)

print(cm_tree_clf)

-----------------------------------------------------

from sklearn.metrics import precision_score,recall_score,f1_score

print("precision log_reg:\n",precision_score(y_test,y_pred_log_reg))

print("\n")

print("precision tree_clf:\n",precision_score(y_test,y_pred_tree_clf))

print("recall log_reg:\n",recall_score(y_test,y_pred_log_reg))

print("\n")

print("recall tree_clf:\n",recall_score(y_test,y_pred_tree_clf))

print("f1 log_reg:\n",f1_score(y_test,y_pred_log_reg))

print("\n")

print("f1 tree_clf:\n",f1_score(y_test,y_pred_tree_clf))

-----------------------------------------------------

from sklearn.metrics import precision_recall_curve

precision,recall,threshold = precision_recall_curve(y_test,y_pred_tree_clf)

plt.figure(figsize=(12,8))

plt.plot(precision,recall)

plt.xlabel("precision")

plt.ylabel("recall")

plt.show()

precision,recall,threshold = precision_recall_curve(y_test,y_pred_log_reg)

plt.figure(figsize=(12,8))

plt.plot(precision,recall)

plt.xlabel("precision")

plt.ylabel("recall")

plt.show()

-----------------------------------------------------

from mglearn.datasets import make_wave

x,y = make_wave(n_samples=100)

plt.figure(figsize=(12,8))

plt.scatter(x,y)

plt.xlabel("x")

plt.ylabel("y")

plt.show()

from sklearn.linear_model import LinearRegression

x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=0)

lin_reg = LinearRegression().fit(x_train,y_train)

print(lin_reg.score(x_test,y_test))

from sklearn.metrics import mean_squared_error

y_pred = lin_reg.predict(x_test)

mse = mean_squared_error(y_test,y_pred)

mse

rmse = np.sqrt(mse)

rmse

FRONT

地図と画像のサイト

Youtubeでビデオ・レッスン（13/16）モデルの評価と選択 | 交差検証、さまざまな評価基準

Be the first to comment

Leave a Reply コメントをキャンセル