Assignment – Preprocessing Data for scikit-learn Very often, we’re tasked with taking data in one form and transforming it for easier downstream analysis. In this assignment, you’ll use what you’ve learned in the course to prepare data for predictive analysis in Project 4. Mushrooms Dataset. A famous—if slightly moldy—dataset about mushrooms can be found in the UCI repository here: https://archive.ics.uci.edu/ml/datasets/Mushroom. The fact that this is such a well-known dataset in the data science community has made it a good dataset to use for comparative benchmarking. For example, if someone was working to build a better decision tree algorithm (or other predictive classifier) to analyze categorical data, this dataset could be useful. In Project 4, we’ll use scikit-learn to answer the question, “Which other attribute or attributes are the best predictors of whether a particular mushroom is poisonous or edible?” Your assignment is to • • • • • • First study the dataset and the associated description of the data (i.e. “data dictionary”). You may need to look around a bit, but it’s there! Create a pandas DataFrame with a subset of the columns in the dataset. You should include the column that indicates edible or poisonous, the column that includes odor, and at least one other column of your choosing. Add meaningful names for each column. Replace the codes used in the data with numeric values—for example, in the first “target” column, “e” might become 0 and “p” might become 1. This is because your downstream processing in Project 4 using scikit-learn requires that values be stored as numerics. Perform exploratory data analysis: show the distribution of data for each of the columns you selected, and show scatterplots for edible/poisonous vs. odor as well as the other column that you selected. Include some text describing your preliminary conclusions about whether either of the other columns could be helpful in predicting if a specific mushroom is edible or poisonous. Your deliverable is a Jupyter Notebook that performs these transformation and exploratory data analysis tasks. If you are working in a group, you also have the option of replacing the mushroom dataset in the assignment with a different data set that your group members might find more interesting. You should post the Jupyter Notebook (.ipynb) file in your GitHub repository, and provide the appropriate URL to your GitHub repository in your assignment link. You should also have the original data file accessible through your code—for example, read directly from the UCI repository or stored in a GitHub repository. IS 362 Assignment – Preprocessing Data for scikit-learn Page 1 of 1 Chapter 10 – System Architecture Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part.     Provide a checklist of issues to consider when selecting a system architecture Trace the evolution of system architecture from mainframes to current designs Explain client/server architecture, including tiers, cost-benefit issues, and performance Compare in-house ecommerce development with packaged solutions and service providers Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 2     Discuss the impact of cloud computing and Web 2.0 Define network topology, including hierarchical, bus, ring, star, and mesh models Describe wireless networking, including wireless standards, topologies, and trends Describe the system design specification Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 3  Issues that influence the architecture choice ◦ ◦ ◦ ◦ ◦ ◦ ◦ ◦ ◦ Corporate organization and culture Enterprise resource planning (ERP) Initial and total cost of ownership (TCO) Scalability Web integration Legacy system interface requirements Processing options Security issues Corporate portals Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 4  Corporate Organization and Culture ◦ A successful system performs well in a company’s organization and culture  Enterprise resource planning (ERP) ◦ Objective – To establish a company-wide strategy for using IT that includes a specific architecture, standards for data, processing, network, and user interface design FIGURE 10-1 Oracle offers ERP solutions as a cloud-based service. Source: Oracle Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 5 ◦ Companies are extending internal ERP systems to their suppliers and customers, using supply chain management (SCM)  Initial Cost and TCO ◦ TCO includes tangible purchases, fees, and contracts called hard costs ◦ TCO analysis answers questions about the validity, effectiveness, and new trends in systems planning  May affect the initial cost and TCO for a proposed system Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 6  Scalability (Extensibility) ◦ A system’s ability to expand, change, or downsize easily to meet the changing needs of a business enterprise  Web Integration ◦ A web-centric architecture enables a company to integrate new applications into its ecommerce strategy  Legacy Systems ◦ A new system might have to interface with legacy systems  Involves analysis of data formats and compatibility Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 7  Processing Options ◦ Systems can process data online or in batches  Security Issues ◦ Analysts must consider security issues and how the company will address them  Corporate Portals ◦ Provide access for customers, employees, suppliers, and the public ◦ A well-designed portal can:  Integrate with various other systems  Provide a consistent look and feel across organizational divisions Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 8  Functions of a business information system ◦ Manage applications that perform the processing logic ◦ Handle data storage and access ◦ Provide an interface that allows users to interact with the system  While planning system design: ◦ Determine where the functions will be carried out ◦ Identify the advantages and disadvantages of each design approach Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 9  Mainframe Architecture ◦ Server: A computer that supplies data, processing services or other support to one or more computers called clients ◦ Earliest servers - Mainframe computers  All data input and output occurred at a central location ◦ Advances in technology enabled installation of terminals at remote locations FIGURE 10-3 In a centralized design, the remote user’s keystrokes are transmitted to the mainframe, which responds by sending screen output back to the user’s screen. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 10  Impact of the Personal Computer ◦ Individuals could work in stand-alone mode  The workstation performed all the functions of a server ◦ Lesser IT assistance resulted in increased productivity in certain tasks  Absence of a central storage location raised concerns about data security, integrity, and consistency  Network Evolution ◦ Local area network (LAN): Allows sharing of data and hardware resources ◦ Wide area network (WAN): Spans long distances and can connect LANs that are continents apart Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 11 FIGURE 10-4 A LAN allows sharing of data and hardware, such as printers and scanners. FIGURE 10-5 A WAN can connect many LANs and link users who are continents apart. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 12  Client/Server Architecture ◦ Includes systems that divide processing between one or more networked clients and a central server  Client handles the entire user interface  Server stores data and provides data access and database management functions FIGURE 10-6 In a client/server design, data is stored and usually processed on the server. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 13 FIGURE 10-7 Comparison of the characteristics of client/server and mainframe systems. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 14  The Client’s Role ◦ Client/server relationship must specify how the processing will be divided between the client and the server ◦ Fat client (thick client) design: Locates all or most of the application processing logic at the client ◦ Thin client design: Locates all or most of the processing logic at the server  Provides better performance as the program code resides on the server Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 15  Client/Server Tiers ◦ Two-tier design  User interface resides on the client  Data resides on the server  Application logic can run either on the server or on the client, or be divided between the client and the server ◦ Three-tier (n-tier) design  User interface runs on the client  Data is stored on the server  Has a middle layer between the client and server  Processes the client requests and translates them into data access commands  Considered an application server Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 16 FIGURE 10-8 Characteristics of two-tier versus three-tier client/server design. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 17 FIGURE 10-9 The location of the data, the application logic, and the user interface depend on the type of architecture. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 18  Middleware ◦ Enables communication between the tiers ◦ Referred to as glueware  Used to connect two or more software components in a federated system architecture ◦ Integrates legacy systems and Web-based and/or cloud applications ◦ Represents the slash in the term client/server  Cost-Benefit Issues ◦ Client/server systems offer the best combination of features to meet information system requirements Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 19  Enable firms to scale the system according to the environment  Enable transfer of applications from expensive mainframes to less-expensive client platforms  Reduce workload and improve response times  Performance Issues ◦ Knee of the curve  Response time to requests increases significantly as the system nears its capacity ◦ Client should contact the server only when necessary in a client/server system ◦ Distributed database management system (DDBMS) helps improve client/server performance Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 20  In an Internet-based architecture, the entire user interface is provided by the web server in the form of HTML documents ◦ Shifting the responsibility for the interface from the client to the server simplifies data transmission and results in lower hardware cost and complexity Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 21  Cloud Computing ◦ The concept envisions a cloud of remote computers providing a total online software and data environment that is hosted by third parties ◦ Eliminates compatibility issues and provides scaling on demand FIGURE 10-10 Cloud computing Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 22  Web 2.0 ◦ Second generation of the web  Enables people to collaborate, interact, and share information more dynamically ◦ Considered a step towards the semantic web ◦ Wiki: Web-based repository of information  Run by social collaboration ◦ Users collaborate and add new layers of information to the Internet operating system Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 23  In-House Solutions ◦ Benefits  A unique website, with a look and feel consistent with the company’s other marketing efforts  Complete control over the organization of the site  A scalable structure to handle increases in sales and product offerings in the future  More flexibility to modify and manage the site  The opportunity to integrate the firm’s web-based business systems with its other information systems Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 24 FIGURE 10-11 Guidelines for companies developing ecommerce strategies. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 25  Packaged Solutions ◦ Viable alternative for medium- to large-sized firms ◦ Less complex than an in-house effort  Service Providers ◦ Application service provider (ASP) - Provides applications or access to applications by charging a fee  Many ASPs offer full-scale Internet business services for companies that decide to outsource functions Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 26  Online Processing ◦ Online systems handle transactions when and where they occur  Output is provided directly to users ◦ Avoids delays and allows a constant dialog between the user and the system ◦ Can be used with file-oriented systems Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 27 FIGURE 10-13 When a customer requests a balance, the ATM system verifies the account number, submits the query, retrieves the current balance, and displays the balance on the ATM screen. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 28  Batch Processing: Still With Us After All These Years ◦ Data is managed in groups ◦ Advantages  Tasks can be planned and run on a predetermined schedule without user involvement  Programs that require major network resources can run when costs and impact on other traffic will be lowest  Well-suited to address security, audit, and privacy concerns Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 29  Real-World Examples ◦ Point of Sale (POS) terminals FIGURE 10-14 Many retailers use a combination of online and batch processing. When a salesperson enters the sale on the POS terminal, the online system retrieves data from the item file, updates the quantity in stock, and produces a sales transaction record. At the end of the day, a batch processing program produces a daily sales report and updates the accounting system. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 30  The Open Systems Interconnection (OSI) Model ◦ Describes how data moves from an application on one computer to an application on another networked computer ◦ Provides physical design standards that assure seamless network connectivity, regardless of the specific hardware environment Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 31  Network Topology ◦ Topology - Physical or logical view of the network  Physical topology: Actual network cabling and connections  Logical topology: Describes the way the components interact ◦ Hierarchical network  Departmental servers control lower levels of processing and network devices ◦ Bus network  A single communication path connects the central server, departmental servers, workstations, and peripheral devices Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 32 ◦ Ring network  Resembles a circle where the data flows in only one direction from one device to the next ◦ Star network  Has a central networking device called a switch which manages the network and acts as a communications conduit for all network traffic ◦ Mesh network  Each node connects to every other node Figure 10-15 Although these computers form a physical circle, the physical layout has no bearing on the network topology, which might be a bus, ring, star, or other logical design. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 33 FIGURE 10-16 A hierarchical network with a single server that controls the network. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 34 FIGURE 10-18 A ring network with a set of computers that send and receive data flowing in one direction. FIGURE 10-17 A bus network with all devices connected to a single communication path. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 35 FIGURE 10-19 A typical star network with a switch, departmental server, and connected computers, and workstations. FIGURE 10-20 A mesh network is used in situations where a high degree of redundancy is needed, such as military applications. The redundant design provides alternate data paths, but is expensive to install and maintain. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 36  Network Devices ◦ LANs or WANs can be interconnected using routers  Router: Connects network segments, determines the most efficient data path, and guides the flow of data  Proxy server: Provides Internet connectivity for internal LAN users  Modeling Tools ◦ Microsoft Visio – Used to represent the physical structure and network components of a system ◦ Creatly.com - Offer network diagram drawing capabilities that are completely web-based Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 37 FIGURE 10-21 Routers can be used to create gateways between different network topologies and large, dissimilar networks such as the Internet. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 38 FIGURE 10-22 Creatly is a web-based software application for creating network diagrams. Source : © 2008-2015 Cinergix Pty. Ltd. Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 39  Wireless Network Standards ◦ IEEE 802.11 is a family of standards developed by the Institute of Electrical and Electronics Engineers (IEEE) for wireless LANs ◦ Current wireless networks are based on variations of the original 802.11 standard  802.11g and 802.11n offered increased bandwidth and were widely accepted by the IT industry  Current standards, such as 802.11ac, use multiple input/multiple output (MIMO) technology to boost performance Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 40  Wireless Network Topologies ◦ Network topologies available for IEEE 802.11 WLANs  The Basic Service Set (BSS) or the infrastructure mode  Contains a central wireless device called an access point or wireless access point (WAP) to serve all wireless clients  Extended Service Set (ESS)  Comprises two or more Basic Service Set networks  Wireless access can be expanded over a larger area Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 41  Wireless Trends ◦ Wi-Fi Alliance  A non-profit international association that certifies interoperability of wireless network products based on IEEE 802.11 specifications  Products that meet the requirements are certified as Wi-Fi (wireless fidelity) compatible  Disadvantage - Wireless transmissions are less secure ◦ Bluetooth is used for short-distance wireless communication ◦ IEEE works on 802.16 standards or Wi-MAX  Wi-MAX: Broadband wireless communications protocols for MANs (metropolitan area networks) Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 42   System architecture marks the end of the systems design phase of the SDLC Final activities in the systems design phase ◦ Preparing a system design specification ◦ Obtaining user approval ◦ Delivering a presentation to management Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 43  System Design Specification ◦ Document that presents the complete design for a new information system  Contains detailed costs, staffing, and scheduling for completing the next SDLC phase ◦ Used as a baseline to measure the operational system Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 44 ◦ Sections in a system design specification       Management summary System components System environment Implementation requirements Time and cost estimates Additional material Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 45  User Approval ◦ Users must review and approve the interface design, report and menu designs, data entry screens, source documents, and other areas of the system that affect them  Ensures that approvals are obtained as and when required  Keeps the users involved with the system’s development  Provides feedback that can be used to guide efforts ◦ System design specification should be reviewed by other IT department members as well Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 46  Presentations ◦ Provide an opportunity to explain the system, answer questions, consider comments, and secure final approval  The first presentation is to the systems analysts, programmers, and technical support staff members who will be involved in future project phases or operational support for the system  Next presentation is to the department managers and users from departments affected by the system  Final presentation is delivered to management ◦ Management will reach a decision based on the presentation Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 47   An information system combines hardware, software, data, procedures, and people into a system architecture Before selecting an architecture, the analyst must consider enterprise resource planning, initial cost and TCO, scalability, Web integration, legacy interface requirements, processing options, security issues, and corporate portals Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 48   ERP establishes an enterprise-wide strategy for IT resources and specific standards for data, processing, network, and user interface design A system architecture requires servers and clients ◦ Client/server architecture divides processing between one or more clients and a central server  A thick client design places all or most of the application processing logic at the client Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 49     A thin client design places all or most of the processing logic at the server Client/server designs can be two- or threetier The Internet has had an enormous impact on system architecture The most prevalent processing method today is online processing Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 50    Networks allow the sharing of hardware, software, and data resources in order to reduce expenses and provide more capability to users The way a network is configured is called the network topology The system design specification presents the complete systems design for an information system and is the basis for the presentations that complete the systems design phase Copyright ©2017 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part. 51
Purchase answer to see full attachment