Question

如果您能告诉我如何绘制类重量的验证曲线，我将不胜感激。事实上，我厌倦了以下代码来完成这项任务：

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split, StratifiedKFold, validation_curve, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
import numpy as np
import matplotlib.pyplot as plt

def plot_validation_curve(param_range, train_scores, test_scores, title, alpha=0.1):
    train_mean = np.mean(train_scores, axis=1)
    train_std = np.std(train_scores, axis=1)
    test_mean = np.mean(test_scores, axis=1)
    test_std = np.std(test_scores, axis=1)
    plt.plot(param_range, train_mean, label='train score', color='blue', marker='o')
    plt.fill_between(param_range, train_mean + train_std,
                     train_mean - train_std, color='blue', alpha=alpha)
    plt.plot(param_range, test_mean, label='test score', color='red', marker='o')
    plt.fill_between(param_range, test_mean + test_std, test_mean - test_std, color='red', alpha=alpha)
    plt.title(title)
    plt.grid(ls='--')
    plt.xlabel('Parameter value')
    plt.ylabel('F-measure')
    plt.legend(loc='best')
    plt.show()

if __name__ == '__main__':
    X, y = make_classification(n_classes=2, class_sep=2, weights=[0.9, 0.1], n_informative=3, n_redundant=1, flip_y=0,
                               n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10)

    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
    st = StandardScaler()

    rg = LogisticRegression(class_weight={0: 1, 1: 6.5}, random_state=42, solver='saga', max_iter=100, n_jobs=-1)

    param_grid = {'clf__C': [0.001, 0.01, 0.1],
                  'clf__class_weight': [{0: 1, 1: 6}, {0: 1, 1: 5.5}]}

    pipeline = Pipeline(steps=[('scaler', st),
                               ('clf', rg)])

    cv = StratifiedKFold(n_splits=5, random_state=42)
    rg_cv = GridSearchCV(pipeline, param_grid, cv=cv, scoring='f1')
    rg_cv.fit(X_train, y_train)

    plt.figure(figsize=(9, 6))

    param_range2 = [{0: 1, 1: 6}, {0: 1, 1: 4}, {0: 1, 1: 5.5}]

    train_scores, test_scores = validation_curve(
        estimator=rg_cv.best_estimator_, X=X_train, y=y_train, param_name="clf__class_weight", param_range=param_range2,
        cv=cv, scoring="f1", n_jobs=-1)

    plot_validation_curve(param_range2, train_scores, test_scores, title="Validation Curve for class_weight", alpha=0.1)

但是，会报告此错误，该错误与最后一行中的param_range2有关：

TypeError: float() argument must be a string or a number, not 'dict'

提前致谢。

致以最诚挚的问候，

Answer 1

您必须决定要在x轴上绘制的内容。您可以对不同的类权重进行参数扫描。由于您将第一堂课的重量固定为1并且仅修改了第2班的重量，因此我决定将分数与第二类的重量进行对比。

然后我按照升序对绘图函数中的权重进行排序，以便获得连接良好的线条。

def plot_validation_curve(param_range, train_scores, test_scores, title, alpha=0.1):
    param_range = [x[1] for x in param_range] 
    sort_idx = np.argsort(param_range)
    param_range=np.array(param_range)[sort_idx]
    train_mean = np.mean(train_scores, axis=1)[sort_idx]
    train_std = np.std(train_scores, axis=1)[sort_idx]
    test_mean = np.mean(test_scores, axis=1)[sort_idx]
    test_std = np.std(test_scores, axis=1)[sort_idx]
    plt.plot(param_range, train_mean, label='train score', color='blue', marker='o')
    plt.fill_between(param_range, train_mean + train_std,
                     train_mean - train_std, color='blue', alpha=alpha)
    plt.plot(param_range, test_mean, label='test score', color='red', marker='o')
    plt.fill_between(param_range, test_mean + test_std, test_mean - test_std, color='red', alpha=alpha)
    plt.title(title)
    plt.grid(ls='--')
    plt.xlabel('Weight of class 2')
    plt.ylabel('Average values and standard deviation for F1-Score')
    plt.legend(loc='best')
    plt.show()

这导致以下图表

绘制sklearn中类权重的曲线验证曲线

1 个答案: