add some description
This commit is contained in:
jacksu
@ -24,9 +24,7 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
@ -42,15 +40,40 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[[165349.2 136897.8 471784.1 'New York']\n",
|
||||
" [162597.7 151377.59 443898.53 'California']\n",
|
||||
" [153441.51 101145.55 407934.54 'Florida']\n",
|
||||
" [144372.41 118671.85 383199.62 'New York']\n",
|
||||
" [142107.34 91391.77 366168.42 'Florida']\n",
|
||||
" [131876.9 99814.71 362861.36 'New York']\n",
|
||||
" [134615.46 147198.87 127716.82 'California']\n",
|
||||
" [130298.13 145530.06 323876.68 'Florida']\n",
|
||||
" [120542.52 148718.95 311613.29 'New York']\n",
|
||||
" [123334.88 108679.17 304981.62 'California']]\n",
|
||||
"[192261.83 191792.06 191050.39 182901.99 166187.94 156991.12 156122.51\n",
|
||||
" 155752.6 152211.77 149759.96 146121.95 144259.4 141585.52 134307.35\n",
|
||||
" 132602.65 129917.04 126992.93 125370.37 124266.9 122776.86 118474.03\n",
|
||||
" 111313.02 110352.25 108733.99 108552.04 107404.34 105733.54 105008.31\n",
|
||||
" 103282.38 101004.64 99937.59 97483.56 97427.84 96778.92 96712.8\n",
|
||||
" 96479.51 90708.19 89949.14 81229.06 81005.76 78239.91 77798.83\n",
|
||||
" 71498.49 69758.98 65200.33 64926.08 49490.75 42559.73 35673.41\n",
|
||||
" 14681.4 ]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"dataset = pd.read_csv('../datasets/50_Startups.csv')\n",
|
||||
"X = dataset.iloc[ : , :-1].values\n",
|
||||
"Y = dataset.iloc[ : , 4 ].values"
|
||||
"Y = dataset.iloc[ : , 4 ].values\n",
|
||||
"print(X[:10])\n",
|
||||
"print(Y)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -62,35 +85,82 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"outputs": [],
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"labelencoder:\n",
|
||||
"[[165349.2 136897.8 471784.1 2]\n",
|
||||
" [162597.7 151377.59 443898.53 0]\n",
|
||||
" [153441.51 101145.55 407934.54 1]\n",
|
||||
" [144372.41 118671.85 383199.62 2]\n",
|
||||
" [142107.34 91391.77 366168.42 1]\n",
|
||||
" [131876.9 99814.71 362861.36 2]\n",
|
||||
" [134615.46 147198.87 127716.82 0]\n",
|
||||
" [130298.13 145530.06 323876.68 1]\n",
|
||||
" [120542.52 148718.95 311613.29 2]\n",
|
||||
" [123334.88 108679.17 304981.62 0]]\n",
|
||||
"onehot:\n",
|
||||
"[[0.0000000e+00 0.0000000e+00 1.0000000e+00 1.6534920e+05 1.3689780e+05\n",
|
||||
" 4.7178410e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.6259770e+05 1.5137759e+05\n",
|
||||
" 4.4389853e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05\n",
|
||||
" 4.0793454e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.4437241e+05 1.1867185e+05\n",
|
||||
" 3.8319962e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04\n",
|
||||
" 3.6616842e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.3187690e+05 9.9814710e+04\n",
|
||||
" 3.6286136e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.3461546e+05 1.4719887e+05\n",
|
||||
" 1.2771682e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.3029813e+05 1.4553006e+05\n",
|
||||
" 3.2387668e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.2054252e+05 1.4871895e+05\n",
|
||||
" 3.1161329e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.2333488e+05 1.0867917e+05\n",
|
||||
" 3.0498162e+05]]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
|
||||
"labelencoder = LabelEncoder()\n",
|
||||
"X[: , 3] = labelencoder.fit_transform(X[ : , 3])\n",
|
||||
"print(\"labelencoder:\")\n",
|
||||
"print(X[:10])\n",
|
||||
"onehotencoder = OneHotEncoder(categorical_features = [3])\n",
|
||||
"X = onehotencoder.fit_transform(X).toarray()"
|
||||
"X = onehotencoder.fit_transform(X).toarray()\n",
|
||||
"print(\"onehot:\")\n",
|
||||
"print(X[:10])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**躲避虚拟变量陷阱**"
|
||||
"**躲避虚拟变量陷阱**\n",
|
||||
"\n",
|
||||
"在回归预测中我们需要所有的数据都是numeric的，但是会有一些非numeric的数据，比如国家，省，部门，性别。这时候我们需要设置虚拟变量（Dummy variable）。做法是将此变量中的每一个值，衍生成为新的变量，是设为1，否设为0.举个例子，“性别”这个变量,我们可以虚拟出“男”和”女”两虚拟变量，男性的话“男”值为1，”女”值为,；女性的话“男”值为0，”女”值为1。\n",
|
||||
"\n",
|
||||
"但是要注意，这时候虚拟变量陷阱就出现了。就拿性别来说，其实一个虚拟变量就够了，比如 1 的时候是“男”， 0 的时候是”非男”，即为女。如果设置两个虚拟变量“男”和“女”，语义上来说没有问题，可以理解，但是在回归预测中会多出一个变量，多出的这个变量将会对回归预测结果产生影响。一般来说，如果虚拟变量要比实际变量的种类少一个。 \n",
|
||||
"\n",
|
||||
"在多重线性回归中，变量不是越多越好，而是选择适合的变量。这样才会对结果准确预测。如果category类的特征都放进去，拟合的时候，所有权重的计算，都可以有两种方法实现，一种是提高某个category的w，一种是降低其他category的w，这两种效果是等效的，也就是发生了共线性,虚拟变量系数相加和为1，出现完全共线陷阱。\n",
|
||||
"\n",
|
||||
"**但是下面测试尽然和想法不一致。。。**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X = X[: , 1:]"
|
||||
"X1 = X[: , 1:]"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -102,11 +172,58 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 39,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[[0.0000000e+00 1.0000000e+00 0.0000000e+00 6.6051520e+04 1.8264556e+05\n",
|
||||
" 1.1814820e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.0067196e+05 9.1790610e+04\n",
|
||||
" 2.4974455e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.0191308e+05 1.1059411e+05\n",
|
||||
" 2.2916095e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 2.7892920e+04 8.4710770e+04\n",
|
||||
" 1.6447071e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05\n",
|
||||
" 4.0793454e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 7.2107600e+04 1.2786455e+05\n",
|
||||
" 3.5318381e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 2.0229590e+04 6.5947930e+04\n",
|
||||
" 1.8526510e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 6.1136380e+04 1.5270192e+05\n",
|
||||
" 8.8218230e+04]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 7.3994560e+04 1.2278275e+05\n",
|
||||
" 3.0331926e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04\n",
|
||||
" 3.6616842e+05]]\n",
|
||||
"[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n",
|
||||
" 97483.56 110352.25 166187.94]\n",
|
||||
"[[1.0000000e+00 0.0000000e+00 6.6051520e+04 1.8264556e+05 1.1814820e+05]\n",
|
||||
" [0.0000000e+00 0.0000000e+00 1.0067196e+05 9.1790610e+04 2.4974455e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 1.0191308e+05 1.1059411e+05 2.2916095e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 2.7892920e+04 8.4710770e+04 1.6447071e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05 4.0793454e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 7.2107600e+04 1.2786455e+05 3.5318381e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 2.0229590e+04 6.5947930e+04 1.8526510e+05]\n",
|
||||
" [0.0000000e+00 1.0000000e+00 6.1136380e+04 1.5270192e+05 8.8218230e+04]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 7.3994560e+04 1.2278275e+05 3.0331926e+05]\n",
|
||||
" [1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04 3.6616842e+05]]\n",
|
||||
"[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n",
|
||||
" 97483.56 110352.25 166187.94]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0)"
|
||||
"X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0)\n",
|
||||
"X1_train, X1_test, Y1_train, Y1_test = train_test_split(X1, Y, test_size = 0.2, random_state = 0)\n",
|
||||
"print(X_test)\n",
|
||||
"print(Y_test)\n",
|
||||
"print(X1_test)\n",
|
||||
"print(Y1_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -118,7 +235,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -127,7 +244,7 @@
|
||||
"LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -135,52 +252,64 @@
|
||||
"source": [
|
||||
"from sklearn.linear_model import LinearRegression\n",
|
||||
"regressor = LinearRegression()\n",
|
||||
"regressor.fit(X_train, Y_train)"
|
||||
"regressor.fit(X_train, Y_train)\n",
|
||||
"regressor1 = LinearRegression()\n",
|
||||
"regressor1.fit(X1_train, Y1_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 第3步：在测试集上预测结果"
|
||||
"## 第3步：在测试集上预测结果¶"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
},
|
||||
"execution_count": 41,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"y_pred = regressor.predict(X_test)"
|
||||
"y_pred = regressor.predict(X_test)\n",
|
||||
"y1_pred = regressor1.predict(X1_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 42,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[ 103015.20159796 132582.27760815 132447.73845175 71976.09851258\n",
|
||||
" 178537.48221056 116161.24230166 67851.69209676 98791.73374687\n",
|
||||
" 113969.43533013 167921.06569551]\n"
|
||||
"[103015.20159796 132582.27760815 132447.73845173 71976.09851258\n",
|
||||
" 178537.48221051 116161.24230163 67851.69209676 98791.73374689\n",
|
||||
" 113969.43533011 167921.06569547]\n",
|
||||
"[103015.20159795 132582.27760817 132447.73845176 71976.09851257\n",
|
||||
" 178537.48221058 116161.24230165 67851.69209675 98791.73374686\n",
|
||||
" 113969.43533013 167921.06569553]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(y_pred)"
|
||||
"print(y_pred)\n",
|
||||
"print(y1_pred)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<b>完整的项目请前往Github项目<a href=\"https://github.com/MachineLearning100/100-Days-Of-ML-Code\">100-Days-Of-ML-Code</a>查看。有任何的建议或者意见欢迎在issue中提出~</b>"
|
||||
"**完整的项目请前往Github项目100-Days-Of-ML-Code查看。有任何的建议或者意见欢迎在issue中提出~**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -199,7 +328,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.2"
|
||||
"version": "3.6.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user