study 100-Days-Of-ML-Code first day

Code/Day 1_Data_Preprocessing.ipynb

@@ -11,6 +11,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "搭建anaconda环境，参考 https://zhuanlan.zhihu.com/p/33358809\n",
+    "\n",
     "## 第一步：导入需要的库\n",
     "这两个是我们每次都需要导入的库。NumPy包含数学计算函数。Pandas用于导入和管理数据集。"
    ]
@@ -18,9 +20,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
+   "metadata": {},
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
     "import numpy as np\n",
@@ -63,7 +63,9 @@
    ],
    "source": [
     "dataset = pd.read_csv('../datasets/Data.csv')\n",
+    "# 不包括最后一列的所有列\n",
     "X = dataset.iloc[ : , :-1].values\n",
+    "#取最后一列\n",
     "Y = dataset.iloc[ : , 3].values\n",
     "print(\"Step 2: Importing dataset\")\n",
     "print(\"X\")\n",
@@ -108,6 +110,7 @@
    ],
    "source": [
     "from sklearn.preprocessing import Imputer\n",
+    "# axis=0表示按列进行\n",
     "imputer = Imputer(missing_values = \"NaN\", strategy = \"mean\", axis = 0)\n",
     "imputer = imputer.fit(X[ : , 1:3])\n",
     "X[ : , 1:3] = imputer.transform(X[ : , 1:3])\n",
@@ -323,7 +326,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.2"
+   "version": "3.6.5"
   }
  },
  "nbformat": 4,