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

Update Day 1_Data_Preprocessing.ipynb

Browse Source
This commit is contained in:
yx-xyc
2021-01-14 11:03:32 +08:00
parent 13020158fe
commit 61ed111ec8
1 changed files with 9 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
Code/Day 1_Data_Preprocessing.ipynb
View File

@ -41,23 +41,10 @@
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout",
"output_type": "stream", "output_type": "stream",
"name": "stdout",
"text": [ "text": [
"Step 2: Importing dataset\n", "Step 2: Importing dataset\nX\n[['France' 44.0 72000.0]\n ['Spain' 27.0 48000.0]\n ['Germany' 30.0 54000.0]\n ['Spain' 38.0 61000.0]\n ['Germany' 40.0 nan]\n ['France' 35.0 58000.0]\n ['Spain' nan 52000.0]\n ['France' 48.0 79000.0]\n ['Germany' 50.0 83000.0]\n ['France' 37.0 67000.0]]\nY\n['No' 'Yes' 'No' 'No' 'Yes' 'Yes' 'No' 'Yes' 'No' 'Yes']\n"
"X\n",
"[['France' 44.0 72000.0]\n",
" ['Spain' 27.0 48000.0]\n",
" ['Germany' 30.0 54000.0]\n",
" ['Spain' 38.0 61000.0]\n",
" ['Germany' 40.0 nan]\n",
" ['France' 35.0 58000.0]\n",
" ['Spain' nan 52000.0]\n",
" ['France' 48.0 79000.0]\n",
" ['Germany' 50.0 83000.0]\n",
" ['France' 37.0 67000.0]]\n",
"Y\n",
"['No' 'Yes' 'No' 'No' 'Yes' 'Yes' 'No' 'Yes' 'No' 'Yes']\n"
] ]
} }
], ],
@ -109,12 +96,12 @@
} }
], ],
"source": [ "source": [
"# If you use the newest version of sklearn, use the lines of code commented out", "# If you use the newest version of sklearn, use the lines of code commented out\n",
"# from sklearn.impute import SimpleImputer", "from sklearn.impute import SimpleImputer\n",
"# imputer = SimpleImputer(missing_values=\"NaN\", strategy=\"mean\")", "imputer = SimpleImputer(missing_values=np.nan, strategy=\"mean\")\n",
"from sklearn.preprocessing import Imputer\n", "#from sklearn.preprocessing import Imputer\n",
"# axis=0表示按列进行\n", "# axis=0表示按列进行\n",
"imputer = Imputer(missing_values = \"NaN\", strategy = \"mean\", axis = 0)\n", "#imputer = Imputer(missing_values = \"NaN\", strategy = \"mean\", axis = 0)\n",
"imputer = imputer.fit(X[ : , 1:3])\n", "imputer = imputer.fit(X[ : , 1:3])\n",
"X[ : , 1:3] = imputer.transform(X[ : , 1:3])\n", "X[ : , 1:3] = imputer.transform(X[ : , 1:3])\n",
"print(\"---------------------\")\n", "print(\"---------------------\")\n",
@ -329,9 +316,9 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.5" "version": "3.8.3-final"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 2
} }