andre/100-Days-Of-ML-Code
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
jacksu
2018-11-17 16:16:57 +08:00
parent 17b48a0738
commit 32a06daeb1
1 changed files with 27 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
Code/Day 1_Data_Preprocessing.ipynb
View File

@ -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": {
"collapsed": true
},
"metadata": {},
"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",
@ -138,25 +141,25 @@
"---------------------\n",
"Step 4: Encoding categorical data\n",
"X\n",
"[[ 1.00000000e+00 0.00000000e+00 0.00000000e+00 4.40000000e+01\n",
"[[1.00000000e+00 0.00000000e+00 0.00000000e+00 4.40000000e+01\n",
" 7.20000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 2.70000000e+01\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 2.70000000e+01\n",
" 4.80000000e+04]\n",
" [ 0.00000000e+00 1.00000000e+00 0.00000000e+00 3.00000000e+01\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 3.00000000e+01\n",
" 5.40000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 3.80000000e+01\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 3.80000000e+01\n",
" 6.10000000e+04]\n",
" [ 0.00000000e+00 1.00000000e+00 0.00000000e+00 4.00000000e+01\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 4.00000000e+01\n",
" 6.37777778e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 3.50000000e+01\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 3.50000000e+01\n",
" 5.80000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 3.87777778e+01\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 3.87777778e+01\n",
" 5.20000000e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 4.80000000e+01\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 4.80000000e+01\n",
" 7.90000000e+04]\n",
" [ 0.00000000e+00 1.00000000e+00 0.00000000e+00 5.00000000e+01\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 5.00000000e+01\n",
" 8.30000000e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 3.70000000e+01\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 3.70000000e+01\n",
" 6.70000000e+04]]\n",
"Y\n",
"[0 1 0 0 1 1 0 1 0 1]\n"
@ -323,7 +326,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.2"
"version": "3.6.5"
}
},
"nbformat": 4,