diff --git a/Code/Day 3_Multiple_Linear_Regression.ipynb b/Code/Day 3_Multiple_Linear_Regression.ipynb index 3efd4f6..90888bd 100644 --- a/Code/Day 3_Multiple_Linear_Regression.ipynb +++ b/Code/Day 3_Multiple_Linear_Regression.ipynb @@ -40,40 +40,44 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 33, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "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" + "[[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['New York' 'California' 'Florida' 'New York' 'Florida' 'New York'\n 'California' 'Florida' 'New York' 'California' 'Florida' 'California'\n 'Florida' 'California' 'Florida' 'New York' 'California' 'New York'\n 'Florida' 'New York' 'California' 'New York' 'Florida' 'Florida'\n 'New York' 'California' 'Florida' 'New York' 'Florida' 'New York'\n 'Florida' 'New York' 'California' 'Florida' 'California' 'New York'\n 'Florida' 'California' 'New York' 'California' 'California' 'Florida'\n 'California' 'New York' 'California' 'New York' 'Florida' 'California'\n 'New York' 'California']\n" ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " R&D Spend Administration Marketing Spend State Profit\n", + "0 165349.20 136897.80 471784.10 New York 192261.83\n", + "1 162597.70 151377.59 443898.53 California 191792.06\n", + "2 153441.51 101145.55 407934.54 Florida 191050.39\n", + "3 144372.41 118671.85 383199.62 New York 182901.99\n", + "4 142107.34 91391.77 366168.42 Florida 166187.94" + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
R&D SpendAdministrationMarketing SpendStateProfit
0165349.20136897.80471784.10New York192261.83
1162597.70151377.59443898.53California191792.06
2153441.51101145.55407934.54Florida191050.39
3144372.41118671.85383199.62New York182901.99
4142107.3491391.77366168.42Florida166187.94
\n
" + }, + "metadata": {}, + "execution_count": 33 } ], "source": [ "dataset = pd.read_csv('../datasets/50_Startups.csv')\n", "X = dataset.iloc[ : , :-1].values\n", "Y = dataset.iloc[ : , 4 ].values\n", + "Z = dataset.iloc[ : , 3 ].values\n", + "print(\"X:\")\n", "print(X[:10])\n", - "print(Y)" + "print(Y)\n", + "print(\"Y:\")\n", + "print(Z)\n", + "dataset.head(5)" ] }, { @@ -85,56 +89,31 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 35, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "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" + "[[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']]\nlabelencoder:\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]]\nonehot:\n[[0.0 0.0 1.0 165349.2 136897.8 471784.1]\n [1.0 0.0 0.0 162597.7 151377.59 443898.53]\n [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 0.0 1.0 144372.41 118671.85 383199.62]\n [0.0 1.0 0.0 142107.34 91391.77 366168.42]\n [0.0 0.0 1.0 131876.9 99814.71 362861.36]\n [1.0 0.0 0.0 134615.46 147198.87 127716.82]\n [0.0 1.0 0.0 130298.13 145530.06 323876.68]\n [0.0 0.0 1.0 120542.52 148718.95 311613.29]\n [1.0 0.0 0.0 123334.88 108679.17 304981.62]]\n" ] } ], "source": [ "from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n", + "from sklearn.compose import ColumnTransformer \n", "labelencoder = LabelEncoder()\n", + "print(X[:10])\n", + "#print(X[: , 3])\n", "X[: , 3] = labelencoder.fit_transform(X[ : , 3])\n", + "#print(X[: , 3])\n", "print(\"labelencoder:\")\n", "print(X[:10])\n", - "onehotencoder = OneHotEncoder(categorical_features = [3])\n", - "X = onehotencoder.fit_transform(X).toarray()\n", + "ct = ColumnTransformer([(\"\", OneHotEncoder(), [3])], remainder = 'passthrough')\n", + "X = ct.fit_transform(X)\n", + "#onehotencoder = OneHotEncoder(categorical_features = [3])\n", + "#X = onehotencoder.fit_transform(X).toarray()\n", "print(\"onehot:\")\n", "print(X[:10])" ] @@ -156,13 +135,30 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 27, "metadata": {}, "outputs": [], "source": [ "X1 = X[: , 1:]" ] }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "[[0.0 1.0 165349.2 136897.8 471784.1]\n [0.0 0.0 162597.7 151377.59 443898.53]\n [1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 1.0 144372.41 118671.85 383199.62]\n [1.0 0.0 142107.34 91391.77 366168.42]\n [0.0 1.0 131876.9 99814.71 362861.36]\n [0.0 0.0 134615.46 147198.87 127716.82]\n [1.0 0.0 130298.13 145530.06 323876.68]\n [0.0 1.0 120542.52 148718.95 311613.29]\n [0.0 0.0 123334.88 108679.17 304981.62]\n [1.0 0.0 101913.08 110594.11 229160.95]\n [0.0 0.0 100671.96 91790.61 249744.55]\n [1.0 0.0 93863.75 127320.38 249839.44]\n [0.0 0.0 91992.39 135495.07 252664.93]\n [1.0 0.0 119943.24 156547.42 256512.92]\n [0.0 1.0 114523.61 122616.84 261776.23]\n [0.0 0.0 78013.11 121597.55 264346.06]\n [0.0 1.0 94657.16 145077.58 282574.31]\n [1.0 0.0 91749.16 114175.79 294919.57]\n [0.0 1.0 86419.7 153514.11 0.0]\n [0.0 0.0 76253.86 113867.3 298664.47]\n [0.0 1.0 78389.47 153773.43 299737.29]\n [1.0 0.0 73994.56 122782.75 303319.26]\n [1.0 0.0 67532.53 105751.03 304768.73]\n [0.0 1.0 77044.01 99281.34 140574.81]\n [0.0 0.0 64664.71 139553.16 137962.62]\n [1.0 0.0 75328.87 144135.98 134050.07]\n [0.0 1.0 72107.6 127864.55 353183.81]\n [1.0 0.0 66051.52 182645.56 118148.2]\n [0.0 1.0 65605.48 153032.06 107138.38]\n [1.0 0.0 61994.48 115641.28 91131.24]\n [0.0 1.0 61136.38 152701.92 88218.23]\n [0.0 0.0 63408.86 129219.61 46085.25]\n [1.0 0.0 55493.95 103057.49 214634.81]\n [0.0 0.0 46426.07 157693.92 210797.67]\n [0.0 1.0 46014.02 85047.44 205517.64]\n [1.0 0.0 28663.76 127056.21 201126.82]\n [0.0 0.0 44069.95 51283.14 197029.42]\n [0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 0.0 38558.51 82982.09 174999.3]\n [0.0 0.0 28754.33 118546.05 172795.67]\n [1.0 0.0 27892.92 84710.77 164470.71]\n [0.0 0.0 23640.93 96189.63 148001.11]\n [0.0 1.0 15505.73 127382.3 35534.17]\n [0.0 0.0 22177.74 154806.14 28334.72]\n [0.0 1.0 1000.23 124153.04 1903.93]\n [1.0 0.0 1315.46 115816.21 297114.46]\n [0.0 0.0 0.0 135426.92 0.0]\n [0.0 1.0 542.05 51743.15 0.0]\n [0.0 0.0 0.0 116983.8 45173.06]]\n" + ] + } + ], + "source": [ + "print(X1)" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -172,47 +168,14 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 29, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "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" + "[[0.0 1.0 0.0 66051.52 182645.56 118148.2]\n [1.0 0.0 0.0 100671.96 91790.61 249744.55]\n [0.0 1.0 0.0 101913.08 110594.11 229160.95]\n [0.0 1.0 0.0 27892.92 84710.77 164470.71]\n [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 0.0 1.0 72107.6 127864.55 353183.81]\n [0.0 0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 0.0 1.0 61136.38 152701.92 88218.23]\n [0.0 1.0 0.0 73994.56 122782.75 303319.26]\n [0.0 1.0 0.0 142107.34 91391.77 366168.42]]\n[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n 97483.56 110352.25 166187.94]\n[[1.0 0.0 66051.52 182645.56 118148.2]\n [0.0 0.0 100671.96 91790.61 249744.55]\n [1.0 0.0 101913.08 110594.11 229160.95]\n [1.0 0.0 27892.92 84710.77 164470.71]\n [1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 1.0 72107.6 127864.55 353183.81]\n [0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 1.0 61136.38 152701.92 88218.23]\n [1.0 0.0 73994.56 122782.75 303319.26]\n [1.0 0.0 142107.34 91391.77 366168.42]]\n[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n 97483.56 110352.25 166187.94]\n" ] } ], @@ -235,18 +198,18 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 30, "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ - "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)" + "LinearRegression()" ] }, - "execution_count": 40, "metadata": {}, - "output_type": "execute_result" + "execution_count": 30 } ], "source": [ @@ -266,7 +229,7 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 31, "metadata": {}, "outputs": [], "source": [ @@ -276,19 +239,14 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 32, "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "[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" + "[103015.20159796 132582.27760816 132447.73845174 71976.09851258\n 178537.48221055 116161.24230166 67851.69209676 98791.73374686\n 113969.43533013 167921.06569551]\n[103015.20159796 132582.27760815 132447.73845175 71976.09851258\n 178537.48221056 116161.24230166 67851.69209676 98791.73374687\n 113969.43533013 167921.06569551]\n" ] } ], @@ -303,13 +261,6 @@ "source": [ "**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": { @@ -328,9 +279,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.8.3-final" } }, "nbformat": 4, "nbformat_minor": 2 -} +} \ No newline at end of file