Skip to content

Commit

Permalink
Add files via upload
Browse files Browse the repository at this point in the history
  • Loading branch information
@mkumakech
mkumakech authored Oct 31, 2021
1 parent a52459b commit 6c89f1a
Showing 1 changed file with 1 addition and 0 deletions.
1 change: 1 addition & 0 deletions mlr.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"cells":[{"metadata":{},"cell_type":"markdown","source":"<h2> Multiple Linear Regression Machine Learning Model Example</h2>"},{"metadata":{},"cell_type":"markdown","source":"<b> by Michael Kumakech</b>"},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport pandas as pd\nimport pylab as pl\nimport numpy as np\n%matplotlib inline","execution_count":1,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<b> Download the data set</b>"},{"metadata":{"trusted":true},"cell_type":"code","source":"!wget -O FuelConsumption.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/FuelConsumptionCo2.csv","execution_count":2,"outputs":[{"output_type":"stream","text":"--2021-10-31 08:24:50-- https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/FuelConsumptionCo2.csv\nResolving s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)... 67.228.254.196\nConnecting to s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)|67.228.254.196|:443... connected.\nHTTP request sent, awaiting response... 200 OK\nLength: 72629 (71K) [text/csv]\nSaving to: ‘FuelConsumption.csv’\n\nFuelConsumption.csv 100%[===================>] 70.93K 452KB/s in 0.2s \n\n2021-10-31 08:24:51 (452 KB/s) - ‘FuelConsumption.csv’ saved [72629/72629]\n\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df =pd.read_csv(\"FuelConsumption.csv\")\ndf.head()","execution_count":3,"outputs":[{"output_type":"execute_result","execution_count":3,"data":{"text/plain":" MODELYEAR MAKE MODEL VEHICLECLASS ENGINESIZE CYLINDERS \\\n0 2014 ACURA ILX COMPACT 2.0 4 \n1 2014 ACURA ILX COMPACT 2.4 4 \n2 2014 ACURA ILX HYBRID COMPACT 1.5 4 \n3 2014 ACURA MDX 4WD SUV - SMALL 3.5 6 \n4 2014 ACURA RDX AWD SUV - SMALL 3.5 6 \n\n TRANSMISSION FUELTYPE FUELCONSUMPTION_CITY FUELCONSUMPTION_HWY \\\n0 AS5 Z 9.9 6.7 \n1 M6 Z 11.2 7.7 \n2 AV7 Z 6.0 5.8 \n3 AS6 Z 12.7 9.1 \n4 AS6 Z 12.1 8.7 \n\n FUELCONSUMPTION_COMB FUELCONSUMPTION_COMB_MPG CO2EMISSIONS \n0 8.5 33 196 \n1 9.6 29 221 \n2 5.9 48 136 \n3 11.1 25 255 \n4 10.6 27 244 ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>MODELYEAR</th>\n <th>MAKE</th>\n <th>MODEL</th>\n <th>VEHICLECLASS</th>\n <th>ENGINESIZE</th>\n <th>CYLINDERS</th>\n <th>TRANSMISSION</th>\n <th>FUELTYPE</th>\n <th>FUELCONSUMPTION_CITY</th>\n <th>FUELCONSUMPTION_HWY</th>\n <th>FUELCONSUMPTION_COMB</th>\n <th>FUELCONSUMPTION_COMB_MPG</th>\n <th>CO2EMISSIONS</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>2014</td>\n <td>ACURA</td>\n <td>ILX</td>\n <td>COMPACT</td>\n <td>2.0</td>\n <td>4</td>\n <td>AS5</td>\n <td>Z</td>\n <td>9.9</td>\n <td>6.7</td>\n <td>8.5</td>\n <td>33</td>\n <td>196</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2014</td>\n <td>ACURA</td>\n <td>ILX</td>\n <td>COMPACT</td>\n <td>2.4</td>\n <td>4</td>\n <td>M6</td>\n <td>Z</td>\n <td>11.2</td>\n <td>7.7</td>\n <td>9.6</td>\n <td>29</td>\n <td>221</td>\n </tr>\n <tr>\n <th>2</th>\n <td>2014</td>\n <td>ACURA</td>\n <td>ILX HYBRID</td>\n <td>COMPACT</td>\n <td>1.5</td>\n <td>4</td>\n <td>AV7</td>\n <td>Z</td>\n <td>6.0</td>\n <td>5.8</td>\n <td>5.9</td>\n <td>48</td>\n <td>136</td>\n </tr>\n <tr>\n <th>3</th>\n <td>2014</td>\n <td>ACURA</td>\n <td>MDX 4WD</td>\n <td>SUV - SMALL</td>\n <td>3.5</td>\n <td>6</td>\n <td>AS6</td>\n <td>Z</td>\n <td>12.7</td>\n <td>9.1</td>\n <td>11.1</td>\n <td>25</td>\n <td>255</td>\n </tr>\n <tr>\n <th>4</th>\n <td>2014</td>\n <td>ACURA</td>\n <td>RDX AWD</td>\n <td>SUV - SMALL</td>\n <td>3.5</td>\n <td>6</td>\n <td>AS6</td>\n <td>Z</td>\n <td>12.1</td>\n <td>8.7</td>\n <td>10.6</td>\n <td>27</td>\n <td>244</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"cdf = df[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_CITY','FUELCONSUMPTION_HWY','FUELCONSUMPTION_COMB','CO2EMISSIONS']]\ncdf.head()","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":" ENGINESIZE CYLINDERS FUELCONSUMPTION_CITY FUELCONSUMPTION_HWY \\\n0 2.0 4 9.9 6.7 \n1 2.4 4 11.2 7.7 \n2 1.5 4 6.0 5.8 \n3 3.5 6 12.7 9.1 \n4 3.5 6 12.1 8.7 \n\n FUELCONSUMPTION_COMB CO2EMISSIONS \n0 8.5 196 \n1 9.6 221 \n2 5.9 136 \n3 11.1 255 \n4 10.6 244 ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>ENGINESIZE</th>\n <th>CYLINDERS</th>\n <th>FUELCONSUMPTION_CITY</th>\n <th>FUELCONSUMPTION_HWY</th>\n <th>FUELCONSUMPTION_COMB</th>\n <th>CO2EMISSIONS</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>2.0</td>\n <td>4</td>\n <td>9.9</td>\n <td>6.7</td>\n <td>8.5</td>\n <td>196</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2.4</td>\n <td>4</td>\n <td>11.2</td>\n <td>7.7</td>\n <td>9.6</td>\n <td>221</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1.5</td>\n <td>4</td>\n <td>6.0</td>\n <td>5.8</td>\n <td>5.9</td>\n <td>136</td>\n </tr>\n <tr>\n <th>3</th>\n <td>3.5</td>\n <td>6</td>\n <td>12.7</td>\n <td>9.1</td>\n <td>11.1</td>\n <td>255</td>\n </tr>\n <tr>\n <th>4</th>\n <td>3.5</td>\n <td>6</td>\n <td>12.1</td>\n <td>8.7</td>\n <td>10.6</td>\n <td>244</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nfrom sklearn import linear_model\nregr = linear_model.LinearRegression()","execution_count":5,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Train the model\nmsk = np.random.rand(len(df)) < 0.8\ntrain = cdf[msk]\ntest = cdf[~msk]","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = np.asanyarray(train[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB',]])\ny = np.asanyarray(train[['CO2EMISSIONS']])\nregr.fit (x, y)\n# The coefficients\nprint ('Coefficients: ', regr.coef_)\nprint ('Intercept: ',regr.intercept_)","execution_count":8,"outputs":[{"output_type":"stream","text":"Coefficients: [[ 9.72636039 7.40132059 10.11607914]]\nIntercept: [63.76087285]\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"<h2> CO2EMISSIONS =63.76087285 + 9.72636039*ENGINESIZE + 7.40132059*CYLINDERS + 10.11607914*FUELCONSUMPTION_COMB </h2>"},{"metadata":{},"cell_type":"markdown","source":"<h2> EVALUATION OF THE MODEL</H2>"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_hat= regr.predict(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])\nx = np.asanyarray(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB']])\ny = np.asanyarray(test[['CO2EMISSIONS']])\nprint(\"Residual sum of squares: %.2f\"\n % np.mean((y_hat - y) ** 2))\n\n# Explained variance score: 1 is perfect prediction\nprint('R-squared: %.2f' % regr.score(x, y))","execution_count":10,"outputs":[{"output_type":"stream","text":"Residual sum of squares: 511.69\nR-squared: 0.86\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = np.asanyarray(train[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB', 'FUELCONSUMPTION_CITY','FUELCONSUMPTION_HWY']])\ny = np.asanyarray(train[['CO2EMISSIONS']])\nregr.fit (x, y)\n# The coefficients\nprint ('Coefficients: ', regr.coef_)\nprint ('Intercept: ',regr.intercept_)","execution_count":11,"outputs":[{"output_type":"stream","text":"Coefficients: [[ 9.85937206 6.94821804 20.09961581 -4.35506941 -6.00944907]]\nIntercept: [65.19404913]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_hat= regr.predict(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB','FUELCONSUMPTION_CITY','FUELCONSUMPTION_HWY']])\nx = np.asanyarray(test[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB', 'FUELCONSUMPTION_CITY','FUELCONSUMPTION_HWY']])\ny = np.asanyarray(test[['CO2EMISSIONS']])\nprint(\"Residual sum of squares: %.2f\"\n % np.mean((y_hat - y) ** 2))\n\n# Explained variance score: 1 is perfect prediction\nprint('R-squared: %.2f' % regr.score(x, y))","execution_count":12,"outputs":[{"output_type":"stream","text":"Residual sum of squares: 513.62\nR-squared: 0.86\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.6.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":5}

0 comments on commit 6c89f1a

Please sign in to comment.