MathLab/skills/mathlab/scripts/compile_day.py

#!/usr/bin/env python3
"""编译单日课程（周六 10:00 批处理）"""

import argparse
import os
import sys
from pathlib import Path
from jinja2 import Template
import yaml

# 添加项目根目录到路径
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent.parent
sys.path.insert(0, str(PROJECT_ROOT))

def load_config() -> dict:
    """加载配置"""
    config_path = PROJECT_ROOT / "skills" / "mathlab" / "config.yaml"
    with open(config_path, "r", encoding="utf-8") as f:
        return yaml.safe_load(f)

def generate_symbol_decoder(topic: str) -> str:
    """生成符号解码字典（示例：感知机）"""
    return r"""
    <div class="symbol-map">
        <strong>$w$</strong> → <code>self.weights</code> (权重向量，shape: [d])
    </div>
    <div class="symbol-map">
        <strong>$b$</strong> → <code>self.bias</code> (偏置标量，shape: [])
    </div>
    <div class="symbol-map">
        <strong>$x$</strong> → <code>input_tensor</code> (输入样本，shape: [d])
    </div>
    <div class="symbol-map">
        <strong>$y$</strong> → <code>label</code> (标签，值域：{-1, +1})
    </div>
    <div class="symbol-map">
        <strong>$\sign(\cdot)$</strong> → <code>np.sign()</code> (符号函数)
    </div>
    <div class="symbol-map">
        <strong>$\xi$</strong> → <code>margin</code> (间隔，用于更新步长)
    </div>
"""

def generate_math_derivation(topic: str) -> str:
    """生成数学推导（示例：感知机）"""
    return r"""
### 感知机预测函数

$$f(x) = w \cdot x + b$$

其中 $\cdot$ 表示向量点积。

### 损失函数（ hinge loss 的简化形式）

$$L(w, b) = -\sum_{x_i \in M} y_i (w \cdot x_i + b)$$

$M$ 是误分类点集合。

### 梯度下降更新规则

$$w \leftarrow w + \eta \cdot y_i \cdot x_i$$

$$b \leftarrow b + \eta \cdot y_i$$

其中 $\eta$ 是学习率。
"""

def generate_html(day: int, topic: str, config: dict) -> str:
    """生成课程 HTML"""
    template_path = PROJECT_ROOT / "skills" / "mathlab" / "templates" / "course_template.html"
    
    with open(template_path, "r", encoding="utf-8") as f:
        template_content = f.read()
    
    template = Template(template_content)
    
    html_content = template.render(
        day=day,
        topic=topic,
        technical_debt="之前的算法无法处理线性不可分数据，导致泛化能力差。感知机通过引入决策边界，将分类问题转化为优化问题。",
        visual_intuition="想象一条直线（或超平面）将两类点分开。权重向量 $w$ 决定直线的方向，偏置 $b$ 决定直线的位置。",
        bilibili_keyword="感知机 直观解释",
        symbol_decoder=generate_symbol_decoder(topic),
        math_derivation=generate_math_derivation(topic),
        optimization_bottleneck=r"全量梯度下降需要遍历所有样本，复杂度 $O(N \cdot d)$。现代框架使用 mini-batch SGD 加速。",
        oj_mission="实现感知机的 forward 和 update 函数，在 XOR 数据集上验证无法收敛（线性不可分）。",
        katex_css="https://cdn.jsdelivr.net/npm/katex@0.16.9/dist/katex.min.css",
        katex_js="https://cdn.jsdelivr.net/npm/katex@0.16.9/dist/katex.min.js"
    )
    
    return html_content

def generate_exercise(day: int, topic: str) -> str:
    """生成练习题"""
    return f'''"""
Day {day} - {topic} 练习

任务：实现 {topic} 的核心算法
"""

import numpy as np
import matplotlib.pyplot as plt


class {topic.replace(" ", "_").lower()}:
    """{topic} 类"""
    
    def __init__(self, learning_rate: float = 0.01):
        self.learning_rate = learning_rate
        self.weights = None
        self.bias = None
    
    def forward(self, X: np.ndarray) -> np.ndarray:
        """前向传播
        
        Args:
            X: 输入数据，shape: [n_samples, n_features]
            
        Returns:
            预测结果，shape: [n_samples]
        """
        # TODO: 实现 f(x) = sign(w · x + b)
        raise NotImplementedError
    
    def compute_loss(self, X: np.ndarray, y: np.ndarray) -> float:
        """计算损失"""
        # TODO: 实现损失函数
        raise NotImplementedError
    
    def update(self, X_i: np.ndarray, y_i: int):
        """更新参数
        
        Args:
            X_i: 单个样本，shape: [n_features]
            y_i: 标签，值域 {-1, +1}
        """
        # TODO: 实现梯度下降更新
        raise NotImplementedError
    
    def fit(self, X: np.ndarray, y: np.ndarray, max_iter: int = 100):
        """训练模型"""
        # TODO: 实现训练循环
        raise NotImplementedError


def plot_concept():
    """可视化概念"""
    # 生成二维数据
    np.random.seed(42)
    X = np.random.randn(100, 2)
    y = np.sign(X[:, 0] + X[:, 1] - 0.5) * 1
    
    # 绘制散点图
    plt.figure(figsize=(8, 6))
    scatter = plt.scatter(X[:, 0], X[:, 1], c=y, cmap="bwr", s=100, edgecolors="black")
    plt.xlabel("x1")
    plt.ylabel("x2")
    plt.title("Day {day} - {topic} 可视化")
    plt.colorbar(scatter)
    plt.grid(True, alpha=0.3)
    plt.savefig("./plots/day{day}_concept.png", dpi=150)
    print(f"✅ 可视化已保存：plots/day{day}_concept.png")


if __name__ == "__main__":
    plot_concept()
'''

def generate_test(day: int, topic: str) -> str:
    """生成测试用例"""
    return f'''"""
Day {day} - {topic} 测试用例
"""

import numpy as np
import sys
sys.path.append("../exercises")

# TODO: 导入对应的类
# from day{day}_task import *


def test_forward_shape():
    """测试前向传播输出形状"""
    # TODO: 实现测试
    assert True


def test_loss_computation():
    """测试损失计算"""
    # TODO: 实现测试
    assert True


def test_update_rule():
    """测试参数更新规则"""
    # TODO: 实现测试
    assert True


def test_convergence():
    """测试收敛性"""
    # TODO: 实现测试
    assert True
'''

def main():
    parser = argparse.ArgumentParser(description="编译单日课程")
    parser.add_argument("--day", type=int, required=True, help="天数 (1-7)")
    parser.add_argument("--topic", type=str, required=True, help="主题名称")
    args = parser.parse_args()
    
    config = load_config()
    
    # 创建 staging 目录
    staging_dir = PROJECT_ROOT / config["output"]["staging"]
    staging_dir.mkdir(exist_ok=True)
    
    exercises_dir = staging_dir / "exercises"
    tests_dir = staging_dir / "tests"
    exercises_dir.mkdir(exist_ok=True)
    tests_dir.mkdir(exist_ok=True)
    
    # 生成 HTML
    html_content = generate_html(args.day, args.topic, config)
    html_path = staging_dir / f"course_day{args.day}.html"
    with open(html_path, "w", encoding="utf-8") as f:
        f.write(html_content)
    print(f"✅ 生成课程 HTML: {html_path}")
    
    # 生成练习题
    exercise_content = generate_exercise(args.day, args.topic)
    exercise_path = exercises_dir / f"day{args.day}_task.py"
    with open(exercise_path, "w", encoding="utf-8") as f:
        f.write(exercise_content)
    print(f"✅ 生成练习题：{exercise_path}")
    
    # 生成测试
    test_content = generate_test(args.day, args.topic)
    test_path = tests_dir / f"test_day{args.day}.py"
    with open(test_path, "w", encoding="utf-8") as f:
        f.write(test_content)
    print(f"✅ 生成测试用例：{test_path}")
    
    print(f"\n🎉 Day {args.day} 编译完成！文件已保存到 staging/")

if __name__ == "__main__":
    main()