PythonとScikit-learnで学ぶ基本的な分類モデル

from sklearn.model_selection import train_test_split

X = iris.data  # 特徴量
y = iris.target  # ラベル

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

model_lr = LogisticRegression()
model_lr.fit(X_train, y_train)  # モデルの訓練
predictions_lr = model_lr.predict(X_test)  # テストデータの予測

accuracy_lr = accuracy_score(y_test, predictions_lr)  # 正確度の計算
print(f"Logistic Regression Accuracy: {accuracy_lr}")

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification

# デモデータの生成
X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1)
model = LogisticRegression()
model.fit(X, y)

# 決定境界のプロット
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
                     np.arange(y_min, y_max, 0.01))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)

plt.contourf(xx, yy, Z, alpha=0.4)
plt.scatter(X[:, 0], X[:, 1], c=y, s=20, edgecolor='k')
plt.title('Decision Boundary')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.show()

from sklearn.svm import SVC

model_svc = SVC()
model_svc.fit(X_train, y_train)
predictions_svc = model_svc.predict(X_test)

accuracy_svc = accuracy_score(y_test, predictions_svc)
print(f"SVM Accuracy: {accuracy_svc}")

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs

# トイデータセットの生成
X, y = make_blobs(n_samples=40, centers=2, random_state=6)

# SVCモデルの訓練
clf = svm.SVC(kernel='linear', C=1000)
clf.fit(X, y)

# プロット用のグリッドを生成
xx = np.linspace(0, 8, 10)
yy = np.linspace(-7, 1, 10)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
Z = clf.decision_function(xy).reshape(XX.shape)

# プロットの設定
plt.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1], alpha=0.5, linestyles=['--', '-', '--'])
plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1], s=100,
            facecolors='none', edgecolors='k')
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Paired, edgecolors='k')

plt.show()

from sklearn.tree import DecisionTreeClassifier

model_dt = DecisionTreeClassifier()
model_dt.fit(X_train, y_train)
predictions_dt = model_dt.predict(X_test)

accuracy_dt = accuracy_score(y_test, predictions_dt)
print(f"Decision Tree Accuracy: {accuracy_dt}")

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier, plot_tree
import matplotlib.pyplot as plt

# データのロード
iris = load_iris()
X, y = iris.data, iris.target

# 決定木モデルの訓練
model = DecisionTreeClassifier()
model.fit(X, y)

# 決定木の視覚化
plt.figure(figsize=(20,10))
plot_tree(model, filled=True, feature_names=iris.feature_names, class_names=iris.target_names, rounded=True)
plt.show()

from sklearn.ensemble import RandomForestClassifier

model_rf = RandomForestClassifier()
model_rf.fit(X_train, y_train)
predictions_rf = model_rf.predict(X_test)

accuracy_rf = accuracy_score(y_test, predictions_rf)
print(f"Random Forest Accuracy: {accuracy_rf}")