使用scikit-learn中的heart数据，分别采用决策树和随机森林训练心脏病预测模型，注意恰当使用参数寻优的思想。将代码、分类结果以及决策树模型的可视化图片粘贴至空白处。

首先，我们需要安装必要的库，包括`pandas`, `numpy`, `matplotlib`, `seaborn`, 和 `sklearn`。然后我们可以按照以下步骤使用scikit-learn中的heart数据集来构建决策树和随机森林模型：

# 导入所需的库
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_heart
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix

# 加载心脏数据集
heart = load_heart()
X = heart.data
y = heart.target

# 数据预处理（例如：归一化、特征选择等）
# 这里假设我们已经处理好数据

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 参数网格搜索（对于决策树和随机森林）
param_grid_tree = {
    'criterion': ['gini', 'entropy'],
    'max_depth': range(1, 11),
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4]
}

grid_tree = GridSearchCV(DecisionTreeClassifier(), param_grid_tree, cv=5)
grid_tree.fit(X_train, y_train)

param_grid_forest = {
    'n_estimators': [50, 100, 200],
    'max_depth': range(1, 11),
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4]
}

grid_forest = GridSearchCV(RandomForestClassifier(), param_grid_forest, cv=5)
grid_forest.fit(X_train, y_train)

# 训练模型
tree_model = grid_tree.best_estimator_
forest_model = grid_forest.best_estimator_

# 预测
y_pred_tree = tree_model.predict(X_test)
y_pred_forest = forest_model.predict(X_test)

# 评估
print("Decision Tree Model:")
print(classification_report(y_test, y_pred_tree))
print(confusion_matrix(y_test, y_pred_tree))

print("\nRandom Forest Model:")
print(classification_report(y_test, y_pred_forest))
print(confusion_matrix(y_test, y_pred_forest))

# 可视化决策树
plt.figure(figsize=(12, 8))
tree_dot_data = tree_model.export_graphviz(
    out_file=None,
    feature_names=heart.feature_names,
    class_names=heart.target_names,
    filled=True,
    rounded=True,
    special_characters=True
)
graphviz.Source(tree_dot_data).render("decision_tree.dot")
plt.imshow(plt.imread("decision_tree.dot.png"))
plt.title("Decision Tree Visualization")

# 对于随机森林，Scikit-Learn默认不会提供可视化的工具，你可以考虑使用第三方库如`plotly`或`eli5`。