关于sklearn的部分教程

import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
X, y = load_digits(return_X_y=True)
plt.imshow(X[0].reshape(8, 8), cmap='gray')# 下面完成灰度图的绘制
# 灰度显示图像
plt.axis('off')# 关闭坐标轴
print('The digit in the image is {}'.format(y[0]))# 格式化打印

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
#设置stratify参数，可以处理数据不平衡问题
#设置stratify=y时，我们发现每次划分后，测试集和训练集中的类标签比例同原始的样本中类标签的比例相同

from sklearn.linear_model import LogisticRegression# 求出Logistic回归的精确度得分
clf = LogisticRegression(solver='lbfgs', multi_class='ovr', max_iter=5000, random_state=42)
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)
print('Accuracy score of the {} is {:.2f}'.format(clf.__class__.__name__, accuracy))

from sklearn.datasets import load_breast_cancer
X_breast, y_breast = load_breast_cancer(return_X_y=True)
from sklearn.model_selection import train_test_split
X_breast_train, X_breast_test, y_breast_train, y_breast_test = train_test_split(X_breast, y_breast, stratify=y_breast, random_state=0, test_size=0.3)
from sklearn.ensemble import GradientBoostingClassifier
clf = GradientBoostingClassifier(n_estimators=100, random_state=0)
clf.fit(X_breast_train, y_breast_train)
y_pred = clf.predict(X_breast_test)
from sklearn.metrics import balanced_accuracy_score
accuracy = balanced_accuracy_score(y_breast_test, y_pred)
print('Accuracy score of the {} is {:.2f}'.format(clf.__class__.__name__, accuracy))
#观察未标准化的迭代次数
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(solver='lbfgs', multi_class='auto', max_iter=5000, random_state=42)
clf.fit(X_train, y_train)
print('{} required {} iterations to be fitted'.format(clf.__class__.__name__, clf.n_iter_[0]))

from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
clf = LogisticRegression(solver='lbfgs', multi_class='auto', max_iter=1000, random_state=42)
clf.fit(X_train_scaled, y_train)
accuracy = clf.score(X_test_scaled, y_test)
print('Accuracy score of the {} is {:.2f}'.format(clf.__class__.__name__, accuracy))
print('{} required {} iterations to be fitted'.format(clf.__class__.__name__, clf.n_iter_[0]))

from sklearn.pipeline import Pipeline
pipe = Pipeline(steps=[('scaler', MinMaxScaler()),
                       ('clf', LogisticRegression(solver='lbfgs', multi_class='auto', random_state=42))])
pipe.fit(X_train, y_train)
accuracy = pipe.score(X_test, y_test)
print('Accuracy score of the {} is {:.2f}'.format(pipe.__class__.__name__, accuracy))
pipe.get_params()#检查管道的所有参数