If you need to adjust the size of your visualizations to match the options in the questions, use the \u201cFormat\u201d-> \u201cCell size\u201d options. For example, \u201cCtrl+Shift+B\u201d on a Windows computer will make the visualization bigger, and \u201cCtrl+Up\u201d will make it taller.<\/li>\n<\/ul>\n\n\n\nAttachments:<\/p>\n\n\n\n
\nDiabetes2.csv (dataset downloaded from Kaggle):<\/li>\n\n\n\n Pima Indians Diabetes Database<\/u><\/a>\u00a0\u00a0<\/a><\/li>\n<\/ul>\n\n\n\nFor this assignment, follow these steps:<\/p>\n\n\n\n
\nDownload the Pima Indians Diabetes dataset<\/li>\n\n\n\n Perform exploratory data analysis (EDA) of the data in Tableau<\/li>\n\n\n\n Perform clustering analysis of the data in Tableau<\/li>\n\n\n\n Perform distribution analysis of the data in Tableau<\/li>\n<\/ol>\n\n\n\nDownload the diabetes dataset<\/strong><\/strong><\/p>\n\n\n\n\nClick to access the Pima Indians Diabetes Database<\/u><\/a>. You may need to sign in or register if you don\u2019t already have an account on Kaggle. Click the \u201cDownload\u201d button on the linked page above to download the dataset.<\/li>\n<\/ol>\n\n\n\n\nYou can scroll down on this web page to learn more about this dataset, including its original publication date and what the fields mean.<\/li>\n\n\n\n When you download the data, it will save it as a .zip file, likely named something like “archive.zip\u201d (a standard download protocol for Kaggle).<\/li>\n<\/ol>\n\n\n\nAlt text: standard download<\/p>\n\n\n\n
\nDouble-click on the \u201carchive\u201d file. It should open to a screen like the one below (this is from a Windows machine; if you are on a Mac, it may vary slightly). You will see that there is one file there (named diabetes.csv, highlighted with a green arrow below). If you click on the \u201cExtract all\u201d option, it will extract all the files (in this case, just the one diabetes.csv file). Save the file in a location of your choice, where it will be easy to find in order to connect with Tableau.<\/li>\n<\/ol>\n\n\n\nOpen the dataset on your computer. It\u2019s a .csv file, so it should open in Microsoft Excel, and it should look like the table below. Verify that you have these exact numbers showing up in your downloaded file:<\/p>\n\n\n\nPerform Exploratory Data Analysis (EDA) with Tableau<\/strong><\/strong><\/p>\n\n\n\n\nOpen the dataset in Tableau. Since this is a .csv file, and not an Excel file, you need to connect to a \u201cmore\u201d kind of data (see image below):<\/li>\n<\/ol>\n\n\n\nAlt text: Data file<\/p>\n\n\n\n
\nWhen you open the file in Tableau, you should see something like this:<\/li>\n<\/ol>\n\n\n\nAlt text: Tableau file<\/p>\n\n\n\n
\nBefore we do any multidimensional clustering, it\u2019s always a good idea to get an overview of each of the data fields:There are 768 data rows here, each corresponding to a different member of the Pima Indian Tribe. The table contains each member\u2019s number of pregnancies, blood glucose, blood pressure, and other health measurements. All the way to the right, the table also contains an outcome variable:0 if the tribe member was not diagnosed with diabetes<\/li><\/ol>1 if the tribe member was diagnosed with diabetes<\/li><\/ol><\/li><\/ol>\n\nFor example, let\u2019s look at the Outcome for the first member. This person has had six pregnancies with a glucose reading of 148. If we scroll all the way to the right, we see the age listed as 50 and the Outcome listed as 1. This means this tribe member was diagnosed with diabetes.<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n\n\n\nQuestion 1: Understanding the Data<\/strong><\/p>\n\n\n\nIn the diabetes dataset, Row 8 contains a tribe member who reported ten pregnancies. Which other data fields correspond with this person?<\/p>\n\n\n\n
\nGlucose of 115, BMI 35.3, Outcome: No Diabetes<\/li>\n\n\n\n Glucose of 115, BMI 35.3, Outcome: Diabetes<\/li>\n\n\n\n Glucose of 168, BMI 38.0, Outcome: Diabetes<\/li>\n\n\n\n Glucose of 168, BMI 38.0, Outcome: No Diabetes<\/li>\n\n\n\n Glucose of 139, BMI 27.1, Outcome: No Diabetes<\/li>\n\n\n\n None of these<\/li>\n<\/ol>\n\n\n\nQuestion 1 Answer:<\/strong> <\/td> A. Glucose of 115, BMI 35.3, Outcome: No Diabetes<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n\nLet\u2019s explore the Pima Indians Diabetes Database a little bit more. Anytime you get a new dataset, it\u2019s a good idea to run some general descriptives to see what the data look like. One of the major tools we use is a histogram<\/em>.<\/li>\n<\/ol>\n\n\n\nMake a histogram of the age. On a new worksheet (below, Sheet 1), we first pull the Age to the Rows, and then, in the \u201cShow Me\u201d tab, we select the histog<\/p>\n\n\n\nAlt text: histogram<\/p>\n\n\n\n
Note that when it makes the histogram, under the Data tab, you can see a new variable under Tables called \u201cAge (bin).\u201d This is the histogram bin for your Age variable.<\/p>\n\n\n\n
If we look at Sheet 1, we can see that most of our data points report an Age of between 20 and 30. We also have a few people in their 40s and 50s, and many fewer older people.<\/p>\n\n\n\n
\nTableau does the best it can to guess at \u201cgood\u201d bin sizes for your dataset, but it doesn\u2019t always guess exactly the way a human would like. Go to the right of the green oval under the Data -> Tables -> Age (bin), pull that menu down, and select Edit to see the exact bin sizes Tableau is suggesting here.<\/li>\n<\/ol>\n\n\n\nAlt text: Data tables<\/p>\n\n\n\n
We can see here that Tableau is suggesting we group people in age groups of 4.69 years, and that our first bin is suggested to start at age 18.76. So the first bin will contain ages 21, 22, and 23. The second bin, due to rounding issues, contains ages 24, 25, 26, 27, and 28! Let\u2019s update the bins so that they are of bin size 5, so that our yearly increments go in nice, round age buckets.<\/p>\n\n\n\nAlt text: Edit bins<\/p>\n\n\n\n
If we update the bin size to 5, we can now see that the histogram has adjusted slightly. The first bin contains ages 20, 21, 22, 23 and 24. The second bin contains ages 25, 26, 27, 28, and 29. The histogram is \u201csmoother\u201d in the jump between the 35\u201340 and 40\u201345 age bins.<\/p>\n\n\n\nSometimes, the axis labels aren\u2019t obvious. To be sure of which bin you are viewing, you can click on a bin, and it will display the information.<\/p>\n\n\n\n
Below, we have clicked on one of the bars and learned it is the bin for ages 35 (and contains ages 35, 36, 37, 38, and 39 but not age 40). If you are curious, you can right-click on the bin and choose \u201cView Data\u201d and then \u201cFull Data\u201d to see the exact data points which make up that bar.<\/p>\n\n\n\nAlt text: histogram<\/p>\n\n\n\n
\nOn a new sheet in Tableau, make a histogram of the BMI variable. Adjust the bin sizes so that they are size 5.<\/li>\n<\/ol>\n\n\n\nIn your BMI histogram, what values are in the most frequent bin?<\/p>\n\n\n\n
\n30\u201334.9<\/li>\n\n\n\n 30\u201335<\/li>\n\n\n\n 30.40, 135<\/li>\n\n\n\n 30.40\u201333.30<\/li>\n\n\n\n none of these<\/li>\n<\/ol>\n\n\n\nQuestion 2 Answer:<\/strong> <\/td> B. 30\u201335<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nQuestion 3: Understanding Questionable Values<\/strong><\/p>\n\n\n\nIn your BMI histogram, are there any values that make you question the data and wonder if those should be filtered out?<\/p>\n\n\n\n
\nYes; the data looks normally distributed, like a bell curve, and this is not expected for these sorts of measurements<\/li>\n\n\n\n Yes; there are too many counts of a BMI of 40 and higher, which is much larger than expected<\/li>\n\n\n\n Yes; there are 11 counts of a BMI of 0, which is probably not an accurate measure<\/li>\n\n\n\n No; the data looks normally distributed, like a bell curve, and this is expected for these sorts of measurements<\/li>\n<\/ol>\n\n\n\nQuestion 3 Answer:<\/strong> <\/td> C.Yes; there are 11 counts of a BMI of 0, which is probably not an accurate measure<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nOn a new sheet in Tableau, make a histogram of the Glucose variable. Adjust the bin sizes so they are size 10. (Don\u2019t filter out any Glucose measurements at this point.)<\/p>\n\n\n\nQuestion 4: Understanding the most frequent bins<\/strong><\/p>\n\n\n\nIn your Glucose histogram, what values are in the most frequent bin?<\/p>\n\n\n\n
\n100 through 107, including 100 and 107<\/li>\n\n\n\n 100 through 109, including 100 and 109<\/li>\n\n\n\n 100 through 110, including 100 and 110<\/li>\n\n\n\n 110 through 120, including 110 and 120<\/li>\n\n\n\n 120 through 129, including 120 and 129<\/li>\n<\/ol>\n\n\n\nQuestion 4 Answer:<\/strong> <\/td> <\/strong><\/td> <\/strong><\/td>B.<\/strong><\/strong><\/td>100 through 109, including 100 and 109<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nQuestion 5 \u2013 Understanding the bin values and counts<\/strong><\/p>\n\n\n\nThe most frequent Glucose measurement is about 100. What is the second<\/strong> most frequent Glucose measurement?<\/p>\n\n\n\n\nbin 100, count 117<\/li>\n\n\n\n bin 110, count 94<\/li>\n\n\n\n bin 110, count 105<\/li>\n\n\n\n bin 120, count 102<\/li>\n<\/ol>\n\n\n\nQuestion 5 Answer:<\/strong> <\/td> D.<\/strong> <\/strong>bin 120, count 102<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nQuestion 6: Understanding the shape of the data<\/strong><\/p>\n\n\n\nIn your Glucose histogram, how would you describe the overall shape of this data?<\/p>\n\n\n\n
\nThe average\/median is about 100, and symmetric. It\u2019s not skewed at all.<\/li>\n\n\n\n The average\/median is about 100, and it\u2019s skewed to the right.<\/li>\n\n\n\n The average\/median is about 100, and it\u2019s skewed to the left.<\/li>\n\n\n\n It is bimodal: there are two distinct centers of glucose measurements, probably one for diabetes diagnoses and one for non-diabetes diagnoses.<\/li>\n\n\n\n None of these<\/li>\n<\/ol>\n\n\n\nQuestion 6 Answer:<\/strong> <\/td> B.The average\/median is about 100, and it\u2019s skewed to the right.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nQuestion 7: Understanding the Descriptives of the Data<\/strong><\/p>\n\n\n\nIn your Insulin histogram, how would you describe the overall descriptives of this data?<\/p>\n\n\n\n
\nZero insulin is meaningless, so there must be some mistakes.<\/li>\n\n\n\n This data is normally distributed and follows a bell curve symmetric shape.<\/li>\n\n\n\n This data is bimodal. We can see two distinct populations: those with diabetes and those without.<\/li>\n\n\n\n The most frequent amount of insulin is between 0 and 49, but a few people report large levels of insulin, at 400 units or above.<\/li>\n\n\n\n None of these<\/li>\n<\/ol>\n\n\n\nQuestion 7 Answer:<\/strong> <\/td> D.The most frequent amount of insulin is between 0 and 49, but a few people report large levels of insulin, at 400 units or above.<\/strong><\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nIn your Insulin histogram, drag Outcome to the Color under Marks. Remember that Outcome=0 means No Diabetes, and Outcome=1 means Diabetes. Now go to the leftmost bin, right-click on it to View Data, and then look at the Full Data. How would you describe the data points in this bin? Check all that apply.Question 8: Two-Dimensional Descriptives of the Data<\/strong><\/p>\n\n\n\nHow would you describe the data points in the leftmost bin in terms of insulin and outcome?<\/p>\n\n\n\n
\nThe most frequent amount of insulin is 0, but there are some values here between 0 and 49.<\/li>\n\n\n\n All the Insulin values here are 0.<\/li>\n\n\n\n All the Outcome values here are 0 (no Diabetes).<\/li>\n\n\n\n The values here average to 25.<\/li>\n\n\n\n This contains only values from people with No Diabetes as their Outcome. If you have diabetes, you need insulin.<\/li>\n\n\n\n None of these<\/li>\n<\/ol>\n\n\n\nQuestion 8 Answer:<\/strong> <\/td>The most frequent amount of insulin is 0, but there are some values here between 0 and 49.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nNow, let\u2019s look at the Outcome variable. We could make a histogram of this binary variable, but that\u2019s not very satisfying. Let\u2019s recode it to be a text variable. Instead of having to remember \u201c0 means No Diabetes,\u201d wouldn\u2019t it be easier to just have the words \u201cNo Diabetes\u201d showing on the screen?<\/p>\n\n\n\nFill it out as follows: You want to create a new field called \u201cOutcome_Text,\u201d and we want it to be \u201cDiabetes\u201d if the Outcome variable was a 1, 0 otherwise, and \u201cNA\u201d if, for some weird reason, the Outcome variable was neither a 1 nor a 0.<\/p>\n\n\n\n
If you want to copy and paste the formula with all the glorious brackets and parentheses, here it is:<\/p>\n\n\n\n
IF ([Outcome]=1)<\/p>\n\n\n\n
THEN “Diabetes”<\/p>\n\n\n\n
ELSEIF ([Outcome]=0)<\/p>\n\n\n\n
THEN “No Diabetes”<\/p>\n\n\n\n
ELSE “NA”<\/p>\n\n\n\nAlt text: copy and paste formula<\/p>\n\n\n\n
\nLet\u2019s check that it coded correctly:\n\nHow many Outcome=0 do we have? Let\u2019s look at a histogram of the original Outcome variable. Looks like we have 500 in the Outcome=0 bin and 268 in the Outcome=1 bin. (Those of you who are following along at home on your calculators will notice this is about 65% No Diabetes, 35% Diabetes.)<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n\n\n\nAlt text: copy and paste formula<\/p>\n\n\n\n
\n\u00a0Let\u2019s check that it coded correctly:<\/li>\n<\/ol>\n\n\n\nHow many Outcome=0 do we have? Let\u2019s look at a histogram of the original Outcome variable. Looks like we have 500 in the Outcome=0 bin and 268 in the Outcome=1 bin. (Those of you who are following along at home on your calculators will notice this is about 65% No Diabetes, 35% Di<\/p>\n\n\n\nAlt text: outcome<\/p>\n\n\n\n
\nHow does our Outcome_Text = \u201cNo Diabetes\u201d or \u201cDiabetes\u201d stack up against our original binary variable? Let\u2019s drag the Outcome_Text to the Color and also\u00a0to the Rows.<\/li>\n<\/ol>\n\n\n\nAlt text: outcome<\/p>\n\n\n\n
\n\u00a0We can see success! The orange bar is marked \u201cNo Diabetes\u201d in the legend, and it is showing on the left (per the binary Outcome variable = 0), while the blue bar is marked \u201cDiabetes\u201d in the legend and is showing on the right (per the binary Outcome variable = 1).<\/li>\n<\/ol>\n\n\n\nWe are studying this dataset to try to understand diabetes in the Pima Indian tribe. We have a dataset which contains about 35% diabetes diagnoses.<\/p>\n\n\n\n
Which research statement(s) does this data look like it might be able to answer? Check all that apply.<\/p>\n\n\n\n
\nWhy do people with zero insulin recorded still have a diabetes diagnosis?<\/li>\n\n\n\n What aspects of the modern diet cause diabetes?<\/li>\n\n\n\n For the Pima Indian population listed in this dataset, are there any relationships between diabetes, age, and BMI which might be interesting?<\/li>\n\n\n\n For the Pima Indian population listed in this dataset, are there any relationships between glucose, insulin, and diabetes diagnosis which might be interesting?<\/li>\n\n\n\n For the Pima Indian population listed in this dataset, are there any relationships between household income, gender, and diabetes diagnosis which might be interesting?<\/li>\n\n\n\n This is not enough data to ask anything; we really need to go to the CDC and get millions of rows of data.<\/li>\n\n\n\n None of these<\/li>\n<\/ol>\n\n\n\nQuestion 9 Answer:<\/strong> <\/td><\/strong>Why do people with zero insulin recorded still have a diabetes diagnosis?<\/strong><\/strong><\/strong>
![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-1.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-2.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-3.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-4.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-5.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-6.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-7.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-8.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-9.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-10.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-11.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-12.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-13.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-14.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-15.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-16.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-17.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-18.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-19.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-20.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-21.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-22.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-23.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-24.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-25.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-26.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-27.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-28.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-29.png\")
<\/a><\/figure>\n\n\n\n![\"\"](\"https:\/\/myassignmenthelp.info\/assignments\/wp-content\/uploads\/2025\/05\/image-30.png\")
<\/a><\/figure>\n\n\n\n