Improve notebook

2_knn/knn_classification.ipynb

@@ -80,7 +80,7 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "# data generation\n",
+    "# data generation (FIXME: feature name not good)\n",
     "np.random.seed(314)\n",
     "data_size_1 = 300\n",
     "x1_1 = np.random.normal(loc=5.0, scale=1.0, size=data_size_1)\n",
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -147,6 +147,7 @@
     "\n",
     "def knn_vote(ys):\n",
     "    vote_dict = {}\n",
+    "    \n",
     "    for y in ys:\n",
     "        if y not in vote_dict.keys():\n",
     "            vote_dict[y] = 1\n",
@@ -166,13 +167,14 @@
     "    \n",
     "\n",
     "#a = knn_predict(x_train[0], x_train, y_train)\n",
+    "\n",
     "y_train_est = [knn_predict(x_train[i], x_train, y_train) for i in range(len(x_train))]\n",
     "print(y_train_est)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -194,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -224,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -278,7 +280,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -298,6 +300,8 @@
     "# knn classifier\n",
     "clf = KNN(k=3)\n",
     "train_acc = clf.fit(x_train, y_train).score() * 100.0\n",
+    "\n",
+    "y_test_pred = clf.predict(x_test)\n",
     "test_acc = clf.score(y_test, y_test_pred) * 100.0\n",
     "\n",
     "print('train accuracy: %f %%' % train_acc)\n",
@@ -313,7 +317,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -342,7 +346,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -371,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -387,7 +391,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {

3_kmeans/README.md

@@ -1,3 +1,7 @@
+## 内容
+
+增加一个Bag of Words的说明和例子程序 （https://blog.csdn.net/wsj998689aa/article/details/47089153）
+
 
 
 ## References

4_logistic_regression/PCA.ipynb

@@ -24,7 +24,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,

5_nn/1-Perceptron.ipynb

@@ -119,17 +119,22 @@
     "\n",
     "\n",
     "算法\n",
-    "```\n",
+    "\n",
+    "\n",
     "输入：T={(x1,y1),(x2,y2)...(xN,yN)}（其中xi∈X=Rn，yi∈Y={-1, +1}，i=1,2...N，学习速率为η）\n",
+    "\n",
     "输出：w, b;感知机模型f(x)=sign(w·x+b)\n",
-    "(1) 初始化w0,b0\n",
-    "(2) 在训练数据集中选取（xi, yi）\n",
-    "(3) 如果yi(w * xi+b)≤0\n",
-    "           w = w + ηyixi\n",
-    "           b = b + ηyi\n",
-    "(4) 如果所有的样本都正确分类，或者迭代次数超过设定值，则终止\n",
-    "(5) 否则，跳转至（2）\n",
-    "```\n",
+    "\n",
+    "1. 初始化$w_0$,$b_0$\n",
+    "2. 在训练数据集中选取$(x_i, y_i）$\n",
+    "3. 如果$y_i(w * x_i+b)≤0$\n",
+    "           \n",
+    "    $w = w + η y_i x_i$\n",
+    "    \n",
+    "    $b = b + η y_i$\n",
+    "\n",
+    "4. 如果所有的样本都正确分类，或者迭代次数超过设定值，则终止\n",
+    "5. 否则，跳转至（2）\n",
     "\n"
    ]
   },
@@ -142,7 +147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {
     "lines_to_end_of_cell_marker": 2
    },
@@ -151,13 +156,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "update weight and bias:  1.0 2.5 0.5\n",
-      "update weight and bias:  -2.5 1.0 0.0\n",
-      "update weight and bias:  -1.5 3.5 0.5\n",
-      "update weight and bias:  -5.0 2.0 0.0\n",
-      "update weight and bias:  -4.0 4.5 0.5\n",
-      "w =  [-4.0, 4.5]\n",
-      "b =  0.5\n",
+      "update weight and bias:  1.0 3.0 0.5\n",
+      "update weight and bias:  -2.5 1.5 0.0\n",
+      "w =  [-2.5, 1.5]\n",
+      "b =  0.0\n",
       "ground_truth:  [1, 1, 1, 1, -1, -1, -1, -1]\n",
       "predicted:     [1, 1, 1, 1, -1, -1, -1, -1]\n"
      ]
@@ -248,7 +250,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,