1+ {
2+ "nbformat" : 4 ,
3+ "nbformat_minor" : 0 ,
4+ "metadata" : {
5+ "colab" : {
6+ "name" : " Multiple Linear Regression"
7+ "provenance" : []
8+ },
9+ "kernelspec" : {
10+ "name" : " python3"
11+ "display_name" : " Python 3"
12+ }
13+ },
14+ "cells" : [
15+ {
16+ "cell_type" : " markdown"
17+ "metadata" : {
18+ "id" : " CazISR8X_HUG"
19+ },
20+ "source" : [
21+ " # Multiple Linear Regression"
22+ ]
23+ },
24+ {
25+ "cell_type" : " markdown"
26+ "metadata" : {
27+ "id" : " pOyqYHTk_Q57"
28+ },
29+ "source" : [
30+ " ## Importing the libraries"
31+ ]
32+ },
33+ {
34+ "cell_type" : " code"
35+ "metadata" : {
36+ "id" : " T_YHJjnD_Tja"
37+ },
38+ "source" : [
39+ " import numpy as np\n "
40+ " import matplotlib.pyplot as plt\n "
41+ " import pandas as pd"
42+ ],
43+ "execution_count" : 2 ,
44+ "outputs" : []
45+ },
46+ {
47+ "cell_type" : " markdown"
48+ "metadata" : {
49+ "id" : " vgC61-ah_WIz"
50+ },
51+ "source" : [
52+ " ## Importing the dataset"
53+ ]
54+ },
55+ {
56+ "cell_type" : " code"
57+ "metadata" : {
58+ "id" : " UrxyEKGn_ez7"
59+ },
60+ "source" : [
61+ " dataset = pd.read_csv('50_Startups.csv')\n "
62+ " X = dataset.iloc[:, :-1].values\n "
63+ " y = dataset.iloc[:, -1].values"
64+ ],
65+ "execution_count" : 3 ,
66+ "outputs" : []
67+ },
68+ {
69+ "cell_type" : " code"
70+ "metadata" : {
71+ "id" : " GOB3QhV9B5kD"
72+ "outputId" : " eecdc574-cedd-4140-985d-60b93e6a7efe"
73+ "colab" : {
74+ "base_uri" : " https://localhost:8080/"
75+ "height" : 857
76+ }
77+ },
78+ "source" : [
79+ " print(X)"
80+ ],
81+ "execution_count" : 4 ,
82+ "outputs" : [
83+ {
84+ "output_type" : " stream"
85+ "text" : [
86+ " [[165349.2 136897.8 471784.1 'New York']\n "
87+ " [162597.7 151377.59 443898.53 'California']\n "
88+ " [153441.51 101145.55 407934.54 'Florida']\n "
89+ " [144372.41 118671.85 383199.62 'New York']\n "
90+ " [142107.34 91391.77 366168.42 'Florida']\n "
91+ " [131876.9 99814.71 362861.36 'New York']\n "
92+ " [134615.46 147198.87 127716.82 'California']\n "
93+ " [130298.13 145530.06 323876.68 'Florida']\n "
94+ " [120542.52 148718.95 311613.29 'New York']\n "
95+ " [123334.88 108679.17 304981.62 'California']\n "
96+ " [101913.08 110594.11 229160.95 'Florida']\n "
97+ " [100671.96 91790.61 249744.55 'California']\n "
98+ " [93863.75 127320.38 249839.44 'Florida']\n "
99+ " [91992.39 135495.07 252664.93 'California']\n "
100+ " [119943.24 156547.42 256512.92 'Florida']\n "
101+ " [114523.61 122616.84 261776.23 'New York']\n "
102+ " [78013.11 121597.55 264346.06 'California']\n "
103+ " [94657.16 145077.58 282574.31 'New York']\n "
104+ " [91749.16 114175.79 294919.57 'Florida']\n "
105+ " [86419.7 153514.11 0.0 'New York']\n "
106+ " [76253.86 113867.3 298664.47 'California']\n "
107+ " [78389.47 153773.43 299737.29 'New York']\n "
108+ " [73994.56 122782.75 303319.26 'Florida']\n "
109+ " [67532.53 105751.03 304768.73 'Florida']\n "
110+ " [77044.01 99281.34 140574.81 'New York']\n "
111+ " [64664.71 139553.16 137962.62 'California']\n "
112+ " [75328.87 144135.98 134050.07 'Florida']\n "
113+ " [72107.6 127864.55 353183.81 'New York']\n "
114+ " [66051.52 182645.56 118148.2 'Florida']\n "
115+ " [65605.48 153032.06 107138.38 'New York']\n "
116+ " [61994.48 115641.28 91131.24 'Florida']\n "
117+ " [61136.38 152701.92 88218.23 'New York']\n "
118+ " [63408.86 129219.61 46085.25 'California']\n "
119+ " [55493.95 103057.49 214634.81 'Florida']\n "
120+ " [46426.07 157693.92 210797.67 'California']\n "
121+ " [46014.02 85047.44 205517.64 'New York']\n "
122+ " [28663.76 127056.21 201126.82 'Florida']\n "
123+ " [44069.95 51283.14 197029.42 'California']\n "
124+ " [20229.59 65947.93 185265.1 'New York']\n "
125+ " [38558.51 82982.09 174999.3 'California']\n "
126+ " [28754.33 118546.05 172795.67 'California']\n "
127+ " [27892.92 84710.77 164470.71 'Florida']\n "
128+ " [23640.93 96189.63 148001.11 'California']\n "
129+ " [15505.73 127382.3 35534.17 'New York']\n "
130+ " [22177.74 154806.14 28334.72 'California']\n "
131+ " [1000.23 124153.04 1903.93 'New York']\n "
132+ " [1315.46 115816.21 297114.46 'Florida']\n "
133+ " [0.0 135426.92 0.0 'California']\n "
134+ " [542.05 51743.15 0.0 'New York']\n "
135+ " [0.0 116983.8 45173.06 'California']]\n "
136+ ],
137+ "name" : " stdout"
138+ }
139+ ]
140+ },
141+ {
142+ "cell_type" : " markdown"
143+ "metadata" : {
144+ "id" : " VadrvE7s_lS9"
145+ },
146+ "source" : [
147+ " ## Encoding categorical data"
148+ ]
149+ },
150+ {
151+ "cell_type" : " code"
152+ "metadata" : {
153+ "id" : " wV3fD1mbAvsh"
154+ },
155+ "source" : [
156+ " from sklearn.compose import ColumnTransformer\n "
157+ " from sklearn.preprocessing import OneHotEncoder\n "
158+ " ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')\n "
159+ " X = np.array(ct.fit_transform(X))"
160+ ],
161+ "execution_count" : 5 ,
162+ "outputs" : []
163+ },
164+ {
165+ "cell_type" : " code"
166+ "metadata" : {
167+ "id" : " 4ym3HdYeCGYG"
168+ "outputId" : " 75d3a14b-9bbd-4e62-a40b-63a6eeafca2a"
169+ "colab" : {
170+ "base_uri" : " https://localhost:8080/"
171+ "height" : 857
172+ }
173+ },
174+ "source" : [
175+ " print(X)"
176+ ],
177+ "execution_count" : 7 ,
178+ "outputs" : [
179+ {
180+ "output_type" : " stream"
181+ "text" : [
182+ " [[0.0 0.0 1.0 165349.2 136897.8 471784.1]\n "
183+ " [1.0 0.0 0.0 162597.7 151377.59 443898.53]\n "
184+ " [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n "
185+ " [0.0 0.0 1.0 144372.41 118671.85 383199.62]\n "
186+ " [0.0 1.0 0.0 142107.34 91391.77 366168.42]\n "
187+ " [0.0 0.0 1.0 131876.9 99814.71 362861.36]\n "
188+ " [1.0 0.0 0.0 134615.46 147198.87 127716.82]\n "
189+ " [0.0 1.0 0.0 130298.13 145530.06 323876.68]\n "
190+ " [0.0 0.0 1.0 120542.52 148718.95 311613.29]\n "
191+ " [1.0 0.0 0.0 123334.88 108679.17 304981.62]\n "
192+ " [0.0 1.0 0.0 101913.08 110594.11 229160.95]\n "
193+ " [1.0 0.0 0.0 100671.96 91790.61 249744.55]\n "
194+ " [0.0 1.0 0.0 93863.75 127320.38 249839.44]\n "
195+ " [1.0 0.0 0.0 91992.39 135495.07 252664.93]\n "
196+ " [0.0 1.0 0.0 119943.24 156547.42 256512.92]\n "
197+ " [0.0 0.0 1.0 114523.61 122616.84 261776.23]\n "
198+ " [1.0 0.0 0.0 78013.11 121597.55 264346.06]\n "
199+ " [0.0 0.0 1.0 94657.16 145077.58 282574.31]\n "
200+ " [0.0 1.0 0.0 91749.16 114175.79 294919.57]\n "
201+ " [0.0 0.0 1.0 86419.7 153514.11 0.0]\n "
202+ " [1.0 0.0 0.0 76253.86 113867.3 298664.47]\n "
203+ " [0.0 0.0 1.0 78389.47 153773.43 299737.29]\n "
204+ " [0.0 1.0 0.0 73994.56 122782.75 303319.26]\n "
205+ " [0.0 1.0 0.0 67532.53 105751.03 304768.73]\n "
206+ " [0.0 0.0 1.0 77044.01 99281.34 140574.81]\n "
207+ " [1.0 0.0 0.0 64664.71 139553.16 137962.62]\n "
208+ " [0.0 1.0 0.0 75328.87 144135.98 134050.07]\n "
209+ " [0.0 0.0 1.0 72107.6 127864.55 353183.81]\n "
210+ " [0.0 1.0 0.0 66051.52 182645.56 118148.2]\n "
211+ " [0.0 0.0 1.0 65605.48 153032.06 107138.38]\n "
212+ " [0.0 1.0 0.0 61994.48 115641.28 91131.24]\n "
213+ " [0.0 0.0 1.0 61136.38 152701.92 88218.23]\n "
214+ " [1.0 0.0 0.0 63408.86 129219.61 46085.25]\n "
215+ " [0.0 1.0 0.0 55493.95 103057.49 214634.81]\n "
216+ " [1.0 0.0 0.0 46426.07 157693.92 210797.67]\n "
217+ " [0.0 0.0 1.0 46014.02 85047.44 205517.64]\n "
218+ " [0.0 1.0 0.0 28663.76 127056.21 201126.82]\n "
219+ " [1.0 0.0 0.0 44069.95 51283.14 197029.42]\n "
220+ " [0.0 0.0 1.0 20229.59 65947.93 185265.1]\n "
221+ " [1.0 0.0 0.0 38558.51 82982.09 174999.3]\n "
222+ " [1.0 0.0 0.0 28754.33 118546.05 172795.67]\n "
223+ " [0.0 1.0 0.0 27892.92 84710.77 164470.71]\n "
224+ " [1.0 0.0 0.0 23640.93 96189.63 148001.11]\n "
225+ " [0.0 0.0 1.0 15505.73 127382.3 35534.17]\n "
226+ " [1.0 0.0 0.0 22177.74 154806.14 28334.72]\n "
227+ " [0.0 0.0 1.0 1000.23 124153.04 1903.93]\n "
228+ " [0.0 1.0 0.0 1315.46 115816.21 297114.46]\n "
229+ " [1.0 0.0 0.0 0.0 135426.92 0.0]\n "
230+ " [0.0 0.0 1.0 542.05 51743.15 0.0]\n "
231+ " [1.0 0.0 0.0 0.0 116983.8 45173.06]]\n "
232+ ],
233+ "name" : " stdout"
234+ }
235+ ]
236+ },
237+ {
238+ "cell_type" : " markdown"
239+ "metadata" : {
240+ "id" : " WemVnqgeA70k"
241+ },
242+ "source" : [
243+ " ## Splitting the dataset into the Training set and Test set"
244+ ]
245+ },
246+ {
247+ "cell_type" : " code"
248+ "metadata" : {
249+ "id" : " Kb_v_ae-A-20"
250+ },
251+ "source" : [
252+ " from sklearn.model_selection import train_test_split\n "
253+ " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"
254+ ],
255+ "execution_count" : 8 ,
256+ "outputs" : []
257+ },
258+ {
259+ "cell_type" : " markdown"
260+ "metadata" : {
261+ "id" : " k-McZVsQBINc"
262+ },
263+ "source" : [
264+ " ## Training the Multiple Linear Regression model on the Training set"
265+ ]
266+ },
267+ {
268+ "cell_type" : " code"
269+ "metadata" : {
270+ "id" : " ywPjx0L1BMiD"
271+ "outputId" : " 721b8613-3990-468d-c2f0-c828fb4f3b7a"
272+ "colab" : {
273+ "base_uri" : " https://localhost:8080/"
274+ "height" : 34
275+ }
276+ },
277+ "source" : [
278+ " from sklearn.linear_model import LinearRegression\n "
279+ " regressor = LinearRegression()\n "
280+ " regressor.fit(X_train, y_train)"
281+ ],
282+ "execution_count" : 9 ,
283+ "outputs" : [
284+ {
285+ "output_type" : " execute_result"
286+ "data" : {
287+ "text/plain" : [
288+ " LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
289+ ]
290+ },
291+ "metadata" : {
292+ "tags" : []
293+ },
294+ "execution_count" : 9
295+ }
296+ ]
297+ },
298+ {
299+ "cell_type" : " markdown"
300+ "metadata" : {
301+ "id" : " xNkXL1YQBiBT"
302+ },
303+ "source" : [
304+ " ## Predicting the Test set results"
305+ ]
306+ },
307+ {
308+ "cell_type" : " code"
309+ "metadata" : {
310+ "id" : " TQKmwvtdBkyb"
311+ "outputId" : " 71d3e9ba-a6ef-4e16-9805-664f2a1b777e"
312+ "colab" : {
313+ "base_uri" : " https://localhost:8080/"
314+ "height" : 185
315+ }
316+ },
317+ "source" : [
318+ " y_pred = regressor.predict(X_test)\n "
319+ " np.set_printoptions(precision=2)\n "
320+ " print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))"
321+ ],
322+ "execution_count" : 10 ,
323+ "outputs" : [
324+ {
325+ "output_type" : " stream"
326+ "text" : [
327+ " [[103015.2 103282.38]\n "
328+ " [132582.28 144259.4 ]\n "
329+ " [132447.74 146121.95]\n "
330+ " [ 71976.1 77798.83]\n "
331+ " [178537.48 191050.39]\n "
332+ " [116161.24 105008.31]\n "
333+ " [ 67851.69 81229.06]\n "
334+ " [ 98791.73 97483.56]\n "
335+ " [113969.44 110352.25]\n "
336+ " [167921.07 166187.94]]\n "
337+ ],
338+ "name" : " stdout"
339+ }
340+ ]
341+ }
342+ ]
343+ }
0 commit comments