Hello, Can someone help me do data analysis exercise? Please see the requirement attached. I am looking for high quality work.

SAP Lumira desktop (SAP Predictive Analytics) DATA ANALYSIS EXERCISE 2 ADVANCED DATA VISUALIZATION USING SAP LUMIRA DESKTOP Acknowledgment: This exercise is adapted from the work of Nitin Kal (University of Southern California) and Nancy Jones (San Diego State University). I would like to thank Nitin and Nancy for their valuable contribution. You need to submit the following files via blackboard: The completed answer sheet: Answer each question and provide a screenshot of the results that support your answer. The SAP Predictive Analytics file (the file extension is .lums) OBJECTIVE Use advanced data visualization to discover trends in data sets. ACTIVITIES Import and prepare data Join data from several files into one dataset Perform data cleansing Perform data harmonization Create data visualizations Nitin Kal & Nancy Jones 2016 -1- SAP Lumira desktop (SAP Predictive Analytics) SOFTWARE PREREQUISITES Microsoft Excel 2010 or newer SAP Predictive Analytics 2.4 (PA) UCC PRODUCTS REQUIRED None DATA REQUIRED GBI data files are available in the folder GBI_Data_Files_E9_1 SCENARIO We have noted some interesting and potentially informative trends in the 2007 - 2011 sales data at Global Bike Inc. We would like to explore these trends using data visualizations. Data trends can be used to make informed business decisions and plan our strategy for marketing, product development, customer service etc. The multidimensional data for Global Bike Inc. can be modeled as a star schema as shown in Figure 1. Nitin Kal & Nancy Jones 2016 -2- SAP Lumira desktop (SAP Predictive Analytics) PRODUCT DIM PK ProductDimKey Material FACT TABLE TIME DIM PK TimeDimKey Calendar Year Calendar Month Calendar Year/month PK,FK1 PK,FK2 PK,FK3 PK,FK4 TimeDimKey UnitDimKey CustomerDimKey ProductDimKey CUSTOMER DIM PK CustomerDimKey Customer Sales Quantity Revenue Discount Net Sales Cost of Goods Manufactured UNIT DIM PK UnitDimKey Base Unit of Measure Currency Key Figure 1: GBI Star Schema The fact table consists of five key figures - Sales Quantity, Revenue, Discount, Net Sales and Cost of Goods Manufactured. These facts can be analyzed against four dimensions - Time, Product, Customer and Unit. These dimensions have attributes as shown above. TECHNIQUES FOR ADVANCED DATA VISUALIZATION The human visual system has evolved to be particularly good at recognizing patterns. Data visualization has become a standard analytical tool which capitalizes on the ability of humans to recognize patterns within massive quantities of multi-dimensional data generated by business information systems. Many scientific studies have led to the creation of visualization models that utilize human perception and cognition. When the number of dimensions is small, we can use standard graphing techniques for visualization e.g. bar charts, line charts, histograms, pie charts and scatter plots. Nitin Kal & Nancy Jones 2016 -3- SAP Lumira desktop (SAP Predictive Analytics) When the number of dimensions is large, there are several novel techniques for visualizing such data. They are categorized into the following major areas 1 - For more information on these visualization techniques, please refer to the journal reference in the footnote. A. Pixel-oriented Techniques a. Space filling curves b. Recursive pattern c. Snake-Spiral d. Circle segments B. Geometric Projection Techniques a. Parallel coordinates b. Scatter plot matrix c. Hyperbox d. Trellis display e. Self-organizing maps C. Icon-based Techniques a. Star glyphs b. Color icons c. Stick figures d. Chernoff faces D. Hierarchical and Graph-based Techniques a. Dimensional stacking b. Cone trees c. Mosaic plots d. Fractal foam ADVANCED DATA VISUALIZATION FOR GLOBAL BIKE INC. 1. Launch SAP Predictive Analytics using Start All Programs SAP Business Intelligence SAP Predictive Analytics or by clicking on the shortcut icon on your desktop. Choose Expert Analytics on the main menu. Click on Expert Analytics again when you get to the Welcome screen. 1 Keim D. A., Kriegel H.-P. Visualization Techniques for Mining Large Databases: A Comparison , Transactions on Knowledge and Data Engineering, Vol. 8, No. 6, Dec. 1996, pp. 923-938. Nitin Kal & Nancy Jones 2016 -4- SAP Lumira desktop (SAP Predictive Analytics) 2. Acquiring GBI data a. Click File New b. In the New Dataset window, choose Microsoft Excel. Next c. Browse for the Sales Transactions file (in the GBI Data Files folder provided by your instructor) d. You should see a preview of the data being acquired. This is where you can select/deselect fields for importing. Import all fields. e. Click Create 3. Interface a. Click on the Prepare view b. See Figure 2 for the SAP Predictive Analysis interface. Explore the various panels and tools. Nitin Kal & Nancy Jones 2016 -5- SAP Lumira desktop (SAP Predictive Analytics) Figure 2 4. Look at the status bar at the bottom of the window, to see that there are 48,384 sales entries. 5. So far we have acquired Transactional data for GBI. We would like to acquire master data as well. Master data will help describe fields such as Product in more detail. For example, in addition to Product number, we might like to know its color, price, description etc. These attributes are usually available in the material master data in SAP ERP. a. Click on Combine - Merge (at the upper right) b. Click Add New Dataset c. Choose MS Excel d. Browse for the file Material.xlsx file e. Create f. You will now see the master data; e.g., Product Category, Components, color etc... for 28 materials. Nitin Kal & Nancy Jones 2016 -6- SAP Lumira desktop (SAP Predictive Analytics) 6. Merging data a. In the Current Dataset list, choose (highlight) Product b. In the Lookup Dataset list, choose (highlight) Material c. Click Merge d. The two data sets are merged (joined on the common attribute) e. Now Add the Customer data and Merge. Be sure to start from the Sales Transaction sheet before doing the merge, (using customer field in both the datasets). If you have trouble merging the data, this is probably due to a data type mismatch. Edit the Excel file for Customer. Change the data type for which there is mismatch. Reacquire it. Then try to merge. f. Now Add the Product Category data and Merge (product category in both) g. Now Add the Sales Organization data and Merge (Sales organization in both) h. Now Add the Month data and Merge i. You notice that there is more than one column called Language Key in your new spreadsheet. Delete (click on cog wheel) all but one of them so that you are left with only one Language Key column. 7. We have acquired and merged sales transaction data with master data. 8. Save as a file name of your choice. 9. We are now ready to manipulate and visualize this data 10. Since the values in Customer, OrderNumber, OrderItem etc. are numeric, PA has incorrectly identified them as measures (in the left panel). a. Click on the cog wheel for each errant measure. Remove. b. Delete all measures except - Discount, Revenue , Sales Price, SalesQuantity, and Transfer Price 11. We will now add Net Sales as a new calculated measure a. Click on the Grid icon in the toolbar b. Click on Calculation New Calculated Dimension. c. Attribute name: Net Sales. Nitin Kal & Nancy Jones 2016 -7- SAP Lumira desktop (SAP Predictive Analytics) d. In the Formula area enter the formula {Revenue} - {Discount}. You can do this by double clicking on each attribute and entering the operand in between them rather than typing them out. e. Click OK f. A new attribute (and a column) is created. g. Click on the cog wheel for Net Sales and Create a Measure. h. You should now see Net Sales as a measure (rename it to Net Sales, if different) 12. In the dimensions list on the left, you see that several dimension have a globe icon with a question mark. This implies that there is a geographic hierarchy possible for that attribute. We will use these hierarchies and we will also do some data cleansing. a. Click on the cog wheel for Country. Select Create a Geographic Hierarchy by Names b. In the Geographic Data window, choose Country as Country, City as Location. c. Click Confirm d. You see US/Palo Alto was Not Found. Click Done e. The data set now contains four new Geographic Hierarchy aware columns - SubRegion, Country, City, Region f. Delete the SubRegion column g. Click on City column in the Grid, then unresolved (in the Manipulation Panel, to the right of the grid). In the Replace tab, Replace: Palo Alto. Click Apply. h. Click on Region column, then unresolved. In the Replace tab, Replace: California. Apply. i. Click on Country (Geography) column, then unresolved. In the Replace tab, Replace: United States. Apply. 13. The data is now cleansed and ready for Visualization, click on Visualize a. Several charting options are available for visualization - bars, lines, pies, geographic, scatter/bubble, maps, radar, tag cloud etc. b. Using the appropriate charting technique, answer the following questions. Hints are provided for each question. Nitin Kal & Nancy Jones 2016 -8- SAP Lumira desktop (SAP Predictive Analytics) Hint: Use a column chart. From Measures, drag Revenue into Y Axis, from Dimensions, drag Year into X Axis. In Y axis, use the cog wheel for Revenue to Sort it in descending. Question 1: What Year had the highest revenue? What was the revenue? Hint: Click Create new Visualization (click + at the bottom). Use a column chart. Y Axis - Revenue, X Axis - Product, Product Description. Sort Revenue in descending. Question 2: What material (with name) had the highest revenue? What was the revenue? Hint: Use a line chart. Y Axis - Revenue, X Axis - Year, Legend Color - Country (use Country from the attribute list) Question 3: Are the historical (year by year) revenue trends for the US and DE (Germany) similar or dissimilar? Hint: Use a Column chart. Y Axis - Revenue, X Axis - Customer, Customer Description, Trellis: Rows - Year Question 4: Did GBI ever gain or lose a customer? Explain Hint: Use a heat map. Area Color - Revenue, Area Name - Month and Month Name, Area Name 2 - Year Question 5: Is there seasonality in revenue during the year? If so, what month has the highest revenue? Is the seasonality similar from year to year? Hint: Use a Column chart. Y Axis -Revenue, X Axis - Customer and Product. Filter the Year (in Dimensions to 2011). Now add descriptions for the customer and product to the X-Axis. Nitin Kal & Nancy Jones 2016 -9- SAP Lumira desktop (SAP Predictive Analytics) Question 6: In 2011, for what Material did the highest Revenue from a single customer occur? Hint: Use a heat map. Measure (Area Color) - Revenue, Attributes: Area Name - Year, Area Name 2 - Product. Question 7: Are there any products that show dramatic change in revenue over time (years)? Does it have similar change by country? Hint: Use a line chart. Y Axis - Revenue, X Axis - Month, Legend Color - Product and Product Description. In the resulting line chart, select the tallest peak by selecting its color in the Product legend, then exclude. Be sure you are not deleting any months (check the filters above the chart). Repeat to eliminate more peaks. As you zero into the products that have low seasonality, the one with the lowest seasonality (relatively flat line) will appear. Question 8: Is there any material that does not display significant seasonality? Hint: Use a Column Chart. Measures: Y-axis: Revenue. Dimensions: X-axis: Customer. For the Measure Revenue add a calculation (use the cog wheel) to your Revenue measure - Percentage. Delete the Revenue measure, leaving the Percentage Revenue in place. Question 9: What customer has the highest percentage contribution to revenues? What has been the trend of that customer's percentage contribution over the years? Hint: Use a Geo Choropleth chart to display revenue. Measures - Revenue, Geography -Region. Question 10: Which region has the highest revenue? 14. Save and close. Nitin Kal & Nancy Jones 2016 - 10 - DATA ANALYSIS CASE 1 APPLYING PIVOT TABLES FOR ANALYSIS Acknowledgment: This exercise is adapted from the work of Nitin Kal (University of Southern California) and Nancy Jones (San Diego State University). I would like to thank Nitin and Nancy for their valuable contribution. OBJECTIVE Use Microsoft Excel Pivot Tables for analysis. ACTIVITIES Create a pivot table Create crosstabs Filter, sort, rank Aggregate data Create charts as needed SOFTWARE PREREQUISITES Microsoft Excel 2010 or higher UCC PRODUCTS REQUIRED None DATA REQUIRED GBI dataset is available in GBI_E5_2.xlsx SCENARIO You are an accountant working for a company called Global Bike Inc. You have been assigned to assist the strategic planning team with profitability analysis in the wholesale division of the company. (The internet sales will be handled by a different team.) Your IT team has pulled transactional data from 2011 through 2014 for you to analyze. The data are stored in an Excel file called GBI_E5_2.xlsx. There are 36,968 lines of data in the spreadsheet. QUESTIONS Use Excel Pivot tables to answer the questions for the case assignment in BBL. DATA ANALYSIS CASE 2 APPLYING PIVOT TABLES FOR ANALYSIS Acknowledgment: This exercise is adapted from the work of Nitin Kal (University of Southern California) and Nancy Jones (San Diego State University). I would like to thank Nitin and Nancy for their valuable contribution. OBJECTIVE Slice and dice a data set using SAP Predictive Analytics and Lumira for data exploration and discovery. ACTIVITIES Import a spreadsheet to Predictive Analytics (PA) Filter, sort, and rank data Aggregate data Create charts as needed SOFTWARE PREREQUISITES Microsoft Excel 2010 or higher UCC PRODUCTS REQUIRED SAP Predictive Analytics 2.X DATA REQUIRED GBI dataset is available in GBI_E5_2.xlsx SCENARIO You are an accountant working for a company called Global Bike Inc. You have been assigned to assist the strategic planning team with profitability analysis in the wholesale division of the company. (The internet sales will be handled by a different team.) Your IT team has pulled transactional data from 2011 through 2014 for you to analyze. The data are stored in an Excel file called GBI_E5_2.xlsx. There are 36,968 lines of data in the spreadsheet. Everyone on the team agrees that you are the best person to do the initial exploration of the data set. Although you are free to do your own analysis, at the very least, you need to answer the questions in the following section so that you can report back to the team. QUESTIONS Use the Expert Analytics component of SAP Predictive Analytics to answer the questions for the case assignment in BBL