{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "

\n", " \n", " \"Skills\n", " \n", "

\n", "\n", "\n", "# Simple Linear Regression\n", "\n", "\n", "Estimated time needed: **15** minutes\n", " \n", "\n", "## Objectives\n", "\n", "After completing this lab you will be able to:\n", "\n", "* Use scikit-learn to implement simple Linear Regression\n", "* Create a model, train it, test it and use the model\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Importing Needed packages\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import pylab as pl\n", "import numpy as np\n", "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Downloading Data\n", "To download the data, we will use !wget to download it from IBM Object Storage.\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2025-10-20 11:52:27-- https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%202/data/FuelConsumptionCo2.csv\n", "Resolving cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud (cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud)... 169.63.118.104, 169.63.118.104\n", "Connecting to cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud (cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud)|169.63.118.104|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 72629 (71K) [text/csv]\n", "Saving to: ‘FuelConsumption.csv’\n", "\n", "FuelConsumption.csv 100%[===================>] 70.93K --.-KB/s in 0.004s \n", "\n", "2025-10-20 11:52:27 (16.8 MB/s) - ‘FuelConsumption.csv’ saved [72629/72629]\n", "\n" ] } ], "source": [ "!wget -O FuelConsumption.csv https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%202/data/FuelConsumptionCo2.csv" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In case you're working **locally** uncomment the below line. \n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "#!curl https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-ML0101EN-SkillsNetwork/labs/Module%202/data/FuelConsumptionCo2.csv -o FuelConsumptionCo2.csv" ] }, { "cell_type": "markdown", "metadata": { "jp-MarkdownHeadingCollapsed": true, "tags": [] }, "source": [ "\n", "## Understanding the Data\n", "\n", "### `FuelConsumption.csv`:\n", "We have downloaded a fuel consumption dataset, **`FuelConsumption.csv`**, which contains model-specific fuel consumption ratings and estimated carbon dioxide emissions for new light-duty vehicles for retail sale in Canada. [Dataset source](http://open.canada.ca/data/en/dataset/98f1a129-f628-4ce4-b24d-6f16bf24dd64)\n", "\n", "- **MODELYEAR** e.g. 2014\n", "- **MAKE** e.g. Acura\n", "- **MODEL** e.g. ILX\n", "- **VEHICLE CLASS** e.g. SUV\n", "- **ENGINE SIZE** e.g. 4.7\n", "- **CYLINDERS** e.g 6\n", "- **TRANSMISSION** e.g. A6\n", "- **FUEL CONSUMPTION in CITY(L/100 km)** e.g. 9.9\n", "- **FUEL CONSUMPTION in HWY (L/100 km)** e.g. 8.9\n", "- **FUEL CONSUMPTION COMB (L/100 km)** e.g. 9.2\n", "- **CO2 EMISSIONS (g/km)** e.g. 182 --> low --> 0\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Reading the data in\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "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", " \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", "
MODELYEARMAKEMODELVEHICLECLASSENGINESIZECYLINDERSTRANSMISSIONFUELTYPEFUELCONSUMPTION_CITYFUELCONSUMPTION_HWYFUELCONSUMPTION_COMBFUELCONSUMPTION_COMB_MPGCO2EMISSIONS
02014ACURAILXCOMPACT2.04AS5Z9.96.78.533196
12014ACURAILXCOMPACT2.44M6Z11.27.79.629221
22014ACURAILX HYBRIDCOMPACT1.54AV7Z6.05.85.948136
32014ACURAMDX 4WDSUV - SMALL3.56AS6Z12.79.111.125255
42014ACURARDX AWDSUV - SMALL3.56AS6Z12.18.710.627244
\n", "
" ], "text/plain": [ " MODELYEAR MAKE MODEL VEHICLECLASS ENGINESIZE CYLINDERS \\\n", "0 2014 ACURA ILX COMPACT 2.0 4 \n", "1 2014 ACURA ILX COMPACT 2.4 4 \n", "2 2014 ACURA ILX HYBRID COMPACT 1.5 4 \n", "3 2014 ACURA MDX 4WD SUV - SMALL 3.5 6 \n", "4 2014 ACURA RDX AWD SUV - SMALL 3.5 6 \n", "\n", " TRANSMISSION FUELTYPE FUELCONSUMPTION_CITY FUELCONSUMPTION_HWY \\\n", "0 AS5 Z 9.9 6.7 \n", "1 M6 Z 11.2 7.7 \n", "2 AV7 Z 6.0 5.8 \n", "3 AS6 Z 12.7 9.1 \n", "4 AS6 Z 12.1 8.7 \n", "\n", " FUELCONSUMPTION_COMB FUELCONSUMPTION_COMB_MPG CO2EMISSIONS \n", "0 8.5 33 196 \n", "1 9.6 29 221 \n", "2 5.9 48 136 \n", "3 11.1 25 255 \n", "4 10.6 27 244 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(\"FuelConsumption.csv\")\n", "\n", "# take a look at the dataset\n", "df.head()\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "### Data Exploration\n", "Let's first have a descriptive exploration on our data.\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "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", " \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", "
MODELYEARENGINESIZECYLINDERSFUELCONSUMPTION_CITYFUELCONSUMPTION_HWYFUELCONSUMPTION_COMBFUELCONSUMPTION_COMB_MPGCO2EMISSIONS
count1067.01067.0000001067.0000001067.0000001067.0000001067.0000001067.0000001067.000000
mean2014.03.3462985.79475213.2965329.47460211.58088126.441425256.228679
std0.01.4158951.7974474.1012532.7945103.4855957.46870263.372304
min2014.01.0000003.0000004.6000004.9000004.70000011.000000108.000000
25%2014.02.0000004.00000010.2500007.5000009.00000021.000000207.000000
50%2014.03.4000006.00000012.6000008.80000010.90000026.000000251.000000
75%2014.04.3000008.00000015.55000010.85000013.35000031.000000294.000000
max2014.08.40000012.00000030.20000020.50000025.80000060.000000488.000000
\n", "
" ], "text/plain": [ " MODELYEAR ENGINESIZE CYLINDERS FUELCONSUMPTION_CITY \\\n", "count 1067.0 1067.000000 1067.000000 1067.000000 \n", "mean 2014.0 3.346298 5.794752 13.296532 \n", "std 0.0 1.415895 1.797447 4.101253 \n", "min 2014.0 1.000000 3.000000 4.600000 \n", "25% 2014.0 2.000000 4.000000 10.250000 \n", "50% 2014.0 3.400000 6.000000 12.600000 \n", "75% 2014.0 4.300000 8.000000 15.550000 \n", "max 2014.0 8.400000 12.000000 30.200000 \n", "\n", " FUELCONSUMPTION_HWY FUELCONSUMPTION_COMB FUELCONSUMPTION_COMB_MPG \\\n", "count 1067.000000 1067.000000 1067.000000 \n", "mean 9.474602 11.580881 26.441425 \n", "std 2.794510 3.485595 7.468702 \n", "min 4.900000 4.700000 11.000000 \n", "25% 7.500000 9.000000 21.000000 \n", "50% 8.800000 10.900000 26.000000 \n", "75% 10.850000 13.350000 31.000000 \n", "max 20.500000 25.800000 60.000000 \n", "\n", " CO2EMISSIONS \n", "count 1067.000000 \n", "mean 256.228679 \n", "std 63.372304 \n", "min 108.000000 \n", "25% 207.000000 \n", "50% 251.000000 \n", "75% 294.000000 \n", "max 488.000000 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# summarize the data\n", "df.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's select some features to explore more.\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ENGINESIZECYLINDERSFUELCONSUMPTION_COMBCO2EMISSIONS
02.048.5196
12.449.6221
21.545.9136
33.5611.1255
43.5610.6244
53.5610.0230
63.5610.1232
73.7611.1255
83.7611.6267
\n", "
" ], "text/plain": [ " ENGINESIZE CYLINDERS FUELCONSUMPTION_COMB CO2EMISSIONS\n", "0 2.0 4 8.5 196\n", "1 2.4 4 9.6 221\n", "2 1.5 4 5.9 136\n", "3 3.5 6 11.1 255\n", "4 3.5 6 10.6 244\n", "5 3.5 6 10.0 230\n", "6 3.5 6 10.1 232\n", "7 3.7 6 11.1 255\n", "8 3.7 6 11.6 267" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cdf = df[['ENGINESIZE','CYLINDERS','FUELCONSUMPTION_COMB','CO2EMISSIONS']]\n", "cdf.head(9)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can plot each of these features:\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "viz = cdf[['CYLINDERS','ENGINESIZE','CO2EMISSIONS','FUELCONSUMPTION_COMB']]\n", "viz.hist()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now, let's plot each of these features against the Emission, to see how linear their relationship is:\n" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "tags": [] }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(cdf.FUELCONSUMPTION_COMB, cdf.CO2EMISSIONS, color='blue')\n", "plt.xlabel(\"FUELCONSUMPTION_COMB\")\n", "plt.ylabel(\"Emission\")\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "tags": [] }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(cdf.ENGINESIZE, cdf.CO2EMISSIONS, color='blue')\n", "plt.xlabel(\"Engine size\")\n", "plt.ylabel(\"Emission\")\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "## Practice\n", "Plot __CYLINDER__ vs the Emission, to see how linear is their relationship is:\n" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(cdf.CYLINDERS, cdf.CO2EMISSIONS, color='blue')\n", "plt.xlabel(\"Cylinders\")\n", "plt.ylabel(\"Emission\")\n", "plt.show()\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
Click here for the solution\n", "\n", "```python \n", "plt.scatter(cdf.CYLINDERS, cdf.CO2EMISSIONS, color='blue')\n", "plt.xlabel(\"Cylinders\")\n", "plt.ylabel(\"Emission\")\n", "plt.show()\n", "\n", "```\n", "\n", "
\n" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "#### Creating train and test dataset\n", "Train/Test Split involves splitting the dataset into training and testing sets that are mutually exclusive. After which, you train with the training set and test with the testing set. \n", "This will provide a more accurate evaluation on out-of-sample accuracy because the testing dataset is not part of the dataset that have been used to train the model. Therefore, it gives us a better understanding of how well our model generalizes on new data.\n", "\n", "This means that we know the outcome of each data point in the testing dataset, making it great to test with! Since this data has not been used to train the model, the model has no knowledge of the outcome of these data points. So, in essence, it is truly an out-of-sample testing.\n", "\n", "Let's split our dataset into train and test sets. 80% of the entire dataset will be used for training and 20% for testing. We create a mask to select random rows using __np.random.rand()__ function: \n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "msk = np.random.rand(len(df)) < 0.8\n", "train = cdf[msk]\n", "test = cdf[~msk]" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "### Simple Regression Model\n", "Linear Regression fits a linear model with coefficients B = (B1, ..., Bn) to minimize the 'residual sum of squares' between the actual value y in the dataset, and the predicted value yhat using linear approximation. \n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Train data distribution\n" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS, color='blue')\n", "plt.xlabel(\"Engine size\")\n", "plt.ylabel(\"Emission\")\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Modeling\n", "Using sklearn package to model data.\n" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Coefficients: [[38.66591065]]\n", "Intercept: [126.72971482]\n" ] } ], "source": [ "from sklearn import linear_model\n", "regr = linear_model.LinearRegression()\n", "train_x = np.asanyarray(train[['ENGINESIZE']])\n", "train_y = np.asanyarray(train[['CO2EMISSIONS']])\n", "regr.fit(train_x, train_y)\n", "# The coefficients\n", "print ('Coefficients: ', regr.coef_)\n", "print ('Intercept: ',regr.intercept_)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As mentioned before, __Coefficient__ and __Intercept__ in the simple linear regression, are the parameters of the fit line. \n", "Given that it is a simple linear regression, with only 2 parameters, and knowing that the parameters are the intercept and slope of the line, sklearn can estimate them directly from our data. \n", "Notice that all of the data must be available to traverse and calculate the parameters.\n" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "#### Plot outputs\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can plot the fit line over the data:\n" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0, 0.5, 'Emission')" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(train.ENGINESIZE, train.CO2EMISSIONS, color='blue')\n", "plt.plot(train_x, regr.coef_[0][0]*train_x + regr.intercept_[0], '-r')\n", "plt.xlabel(\"Engine size\")\n", "plt.ylabel(\"Emission\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Evaluation\n", "We compare the actual values and predicted values to calculate the accuracy of a regression model. Evaluation metrics provide a key role in the development of a model, as it provides insight to areas that require improvement.\n", "\n", "There are different model evaluation metrics, lets use MSE here to calculate the accuracy of our model based on the test set: \n", "* Mean Absolute Error: It is the mean of the absolute value of the errors. This is the easiest of the metrics to understand since it’s just average error.\n", "\n", "* Mean Squared Error (MSE): Mean Squared Error (MSE) is the mean of the squared error. It’s more popular than Mean Absolute Error because the focus is geared more towards large errors. This is due to the squared term exponentially increasing larger errors in comparison to smaller ones.\n", "\n", "* Root Mean Squared Error (RMSE). \n", "\n", "* R-squared is not an error, but rather a popular metric to measure the performance of your regression model. It represents how close the data points are to the fitted regression line. The higher the R-squared value, the better the model fits your data. The best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse).\n" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mean absolute error: 25.41\n", "Residual sum of squares (MSE): 1073.69\n", "R2-score: 0.76\n" ] } ], "source": [ "from sklearn.metrics import r2_score\n", "\n", "test_x = np.asanyarray(test[['ENGINESIZE']])\n", "test_y = np.asanyarray(test[['CO2EMISSIONS']])\n", "test_y_ = regr.predict(test_x)\n", "\n", "print(\"Mean absolute error: %.2f\" % np.mean(np.absolute(test_y_ - test_y)))\n", "print(\"Residual sum of squares (MSE): %.2f\" % np.mean((test_y_ - test_y) ** 2))\n", "print(\"R2-score: %.2f\" % r2_score(test_y , test_y_) )" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Exercise\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Lets see what the evaluation metrics are if we trained a regression model using the `FUELCONSUMPTION_COMB` feature.\n", "\n", "Start by selecting `FUELCONSUMPTION_COMB` as the train_x data from the `train` dataframe, then select `FUELCONSUMPTION_COMB` as the test_x data from the `test` dataframe\n" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "train_x = train_x = train[[\"FUELCONSUMPTION_COMB\"]]\n", "\n", "test_x = test_x = test[[\"FUELCONSUMPTION_COMB\"]]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now train a Linear Regression Model using the `train_x` you created and the `train_y` created previously\n" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "LinearRegression()" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "regr = linear_model.LinearRegression()\n", "\n", "regr.fit(train_x, train_y)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
Click here for the solution\n", "\n", "```python \n", "regr = linear_model.LinearRegression()\n", "\n", "regr.fit(train_x, train_y)\n", "\n", "```\n", "\n", "
\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Find the predictions using the model's `predict` function and the `test_x` data\n" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "predictions = regr.predict(test_x)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
Click here for the solution\n", "\n", "```python \n", "predictions = regr.predict(test_x)\n", "\n", "```\n", "\n", "
\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Finally use the `predictions` and the `test_y` data and find the Mean Absolute Error value using the `np.absolute` and `np.mean` function like done previously\n" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mean Absolute Error: 21.49\n" ] } ], "source": [ "print(\"Mean Absolute Error: %.2f\" % np.mean(np.absolute(predictions - test_y)))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
Click here for the solution\n", "\n", "```python \n", "print(\"Mean Absolute Error: %.2f\" % np.mean(np.absolute(predictions - test_y)))\n", "\n", "```\n", "\n", "
\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can see that the MAE is much worse when we train using `ENGINESIZE` than `FUELCONSUMPTION_COMB`\n" ] }, { "cell_type": "markdown", "metadata": { "tags": [] }, "source": [ "### Thank you for completing this lab!\n", "\n", "\n", "## Author\n", "\n", "Saeed Aghabozorgi\n", "\n", "\n", "### Other Contributors\n", "\n", "Joseph Santarcangelo\n", "\n", "Azim Hirjani\n", "\n", "##

© IBM Corporation. All rights reserved.

\n", "\n", "\n", "\n", "\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python", "language": "python", "name": "conda-env-python-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.12" }, "prev_pub_hash": "20d6dc1d9e74df451be22381c972d7921c93657bea402a00c749dca52bb85996" }, "nbformat": 4, "nbformat_minor": 4 }