{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4.2 分类函数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.2.1 MLPClassifier\n",
    "\n",
    "MLPClassifier（hidden_layer_sizes =（100，），activation ='relu'，solver ='adam'，alpha = 0.0001，batch_size ='auto'，learning_rate ='constant'，learning_rate_init = 0.001，power_t = 0.5，max_iter = 200，shuffle = True，random_state = None，tol = 0.0001，verbose = False，warm_start = False，momentum = 0.9，nesterovs_momentum = True，early_stopping = False，validation_fraction = 0.1，beta_1 = 0.9，beta_2 = 0.999，epsilon = 1e-08 ）\n",
    "\n",
    "参数解释(Parameters):\n",
    "\n",
    "    hidden_layer_sizes : tuple, length = n_layers - 2, default (100,)            #第i个元素表示第i个隐藏层中的神经元数量\n",
    "    activation : {‘identity’, ‘logistic’, ‘tanh’, ‘relu’}, default ‘relu’   #隐藏层的激活函数\n",
    "    solver : {‘lbfgs’, ‘sgd’, ‘adam’}, default ‘adam’                 #权重优化的求解器\n",
    "    learning_rate : {‘constant’, ‘invscaling’, ‘adaptive’}, default ‘constant’#学习率\n",
    "    max_iter：int，optional，default 200                               #最大迭代次数\n",
    "    early_stopping : bool, default False                               #当验证评分没有改善时，是否使用提前停止来终止培训\n",
    "\n",
    "属性(Attributes):\n",
    "    \n",
    "    classes_ : array or list of array of shape (n_classes,)  #每个输出的类标签\n",
    "    loss_ : float                             #使用损失函数计算的当前损失\n",
    "    coefs_ : list, length n_layers - 1               #列表中的第i个元素表示对应于层i的权重矩阵\n",
    "    intercepts_ : list, length n_layers - 1            #列表中的第i个元素表示对应于层i + 1的偏置矢量\n",
    "    n_iter_ : int,                             #求解器运行的迭代次数\n",
    "    n_layers_ : int                            #层数\n",
    "    n_outputs_ : int                           #输出个数\n",
    "    out_activation_ : string                      #输出激活功能的名称\n",
    "    \n",
    "方法(Methods)：\n",
    "\n",
    "    fit（X，y）\t            #使模型适合数据矩阵X和目标y。\n",
    "    get_params（[deep]）\t        #获取此估算工具的参数。\n",
    "    predict（X）\t             #预测使用多层感知器分类器\n",
    "    predict_log_proba（X）\t     #返回概率估计的对数。\n",
    "    predict_proba（X）\t       #概率估计。\n",
    "    score（X，y [，sample_weight]）\t#返回给定测试数据和标签的平均准确度。\n",
    "    set_params（** PARAMS）\t     #设置此估算器的参数。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4.2.2 SVC\n",
    "\n",
    "SVC(C=1.0, kernel='rbf', degree=3, gamma='auto', coef0=0.0, shrinking=True, probability=False, tol=0.001, cache_size=200, class_weight=None, verbose=False, max_iter=-1, decision_function_shape='ovr', random_state=None)\n",
    "\n",
    "参数解释(Parameters):\n",
    "\n",
    "    C : float, optional (default=1.0)         # 惩罚参数C.\n",
    "    kernel : string, optional (default=’rbf’)  # 指定要在算法中使用的内核类型\n",
    "    degree : int, optional (default=3)        # 多项式核函数的次数（'poly'）被所有其他内核忽略\n",
    "    gamma : float, optional (default=’auto’)   # 'rbf'，'poly'和'sigmoid'的核系数\n",
    "    \n",
    "属性(Attributes):\n",
    "\n",
    "    support_ : array-like, shape = [n_SV]              # 支持向量指数\n",
    "    support_vectors_：array-like，shape = [n_SV，n_features] # 支持向量\n",
    "    n_support_：array-like，dtype = int32，shape = [n_class] # 每个类的支持向量数。\n",
    "    dual_coef_：array，shape = [n_class-1，n_SV]         # 决策函数中支持向量的系数\n",
    "    coef_：array，shape = [n_class-1，n_features]        # 赋予特征的权重（原始问题中的系数）这仅适用于线性内核\n",
    "    intercept_：array，shape = [n_class *（n_class-1）/ 2]  # 决策函数中的常量\n",
    "    \n",
    "方法(Methods)：\n",
    "\n",
    "    decision_function（X）\t     #样品X到分离超平面的距离。\n",
    "    fit（X，y [，sample_weight]）\t#根据给定的训练数据拟合SVM模型。\n",
    "    get_params（[deep]）\t       #获取此估算工具的参数。\n",
    "    predict（X）\t             #对X中的样本进行分类。\n",
    "    score（X，y [，sample_weight]）\t#返回给定测试数据和标签的平均准确度。\n",
    "    set_params（** PARAMS）\t     #设置此估算器的参数。"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}