从sklearn导入良性恶性肿瘤数据，划分测试与训练集，分别用logistic回归与SVM分类器完成分类任务，建立评价指标（评价侧重癌症病人是否能正确识别出来），记录参数调整过程和结果，评价两种分类器对该任务的完成程度

好的，让我来回答您的问题。

首先，我会从sklearn中导入良性恶性肿瘤数据集，并将其划分为训练集和测试集。以下是代码示例：

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

# 导入数据集
cancer = load_breast_cancer()

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, test_size=0.2, random_state=42)

接下来，我会使用logistic回归和SVM分类器完成分类任务。以下是代码示例：

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC

# 创建logistic回归分类器
logistic = LogisticRegression()

# 训练模型
logistic.fit(X_train, y_train)

# 创建SVM分类器
svm = SVC()

# 训练模型
svm.fit(X_train, y_train)

然后，我会建立评价指标，侧重于癌症病人是否能被正确识别出来。以下是代码示例：

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

# 预测测试集结果
logistic_pred = logistic.predict(X_test)
svm_pred = svm.predict(X_test)

# 计算评价指标
logistic_accuracy = accuracy_score(y_test, logistic_pred)
svm_accuracy = accuracy_score(y_test, svm_pred)

logistic_precision = precision_score(y_test, logistic_pred)
svm_precision = precision_score(y_test, svm_pred)

logistic_recall = recall_score(y_test, logistic_pred)
svm_recall = recall_score(y_test, svm_pred)

logistic_f1 = f1_score(y_test, logistic_pred)
svm_f1 = f1_score(y_test, svm_pred)

接着，我会记录参数调整过程和结果。以下是代码示例：

# 调整logistic回归分类器参数
logistic = LogisticRegression(C=100)

# 训练模型
logistic.fit(X_train, y_train)

# 调整SVM分类器参数
svm = SVC(C=100, kernel='poly')

# 训练模型
svm.fit(X_train, y_train)

最后，我会评价两种分类器对该任务的完成程度。以下是代码示例：

print("Logistic Regression:")
print("Accuracy: {:.2f}".format(logistic_accuracy))
print("Precision: {:.2f}".format(logistic_precision))
print("Recall: {:.2f}".format(logistic_recall))
print("F1 Score: {:.2f}".format(logistic_f1))

print("\nSVM:")
print("Accuracy: {:.2f}".format(svm_accuracy))
print("Precision: {:.2f}".format(svm_precision))
print("Recall: {:.2f}".format(svm_recall))
print("F1 Score: {:.2f}".format(svm_f1))

通过比较两种分类器的评价指标，我们可以得出结论，哪种分类器对该任务的完成程度更好。