What is Mural and how do you use it? Great question! Mural is a virtual collaboration whiteboard you can use anytime and anywhere. It is the perfect platform for CANA’s virtual team members who are located throughout the United States and Canada. With such a widespread group, finding communication and collaboration solutions is key to our success. Adding markers to a map image in Mural Mural is able to import website links, documents, photos, and graphics. Mural is one of CANA’s project management “go to” tools for collaborating on-line with clients and the CANA team. Our project managers can create templates to design, plan, and execute tasks for a project based on multiple contributors’ input, synthesize the collected data, and reach a decision faster than using other traditional techniques. Mural has proven to be outstanding for virtual collaboration and getting every person on the same page. A recent example of a CANA project use case Originally, CANA selected this platform to plan and execute the Future Unmanned Logistics Systems (ULS) Energy Logistics Enabling Distributed Operations (FUELED Ops) Virtual Demonstration Day and Design Think Workshop. We needed an on-line platform to collaboratively and simultaneously capture multiple users’ inputs into event design, planning, and coordination. We used Mural to visually map out and plan the event. This gave the planning team a visual representation of the event and kept all of the key information in one place. Mural Collaborative Planning Boards This dashboard had 16 different planning boards, and one of these included a storyboard used to plan out the narrative for the virtual event. As a virtual team, it was very important to put together the client’s vision in a way they could readily understand. It increased client confidence that the event would be successful, and their story clearly and accurately conveyed, to the event’s audience. Mural Storyboard Session This is the storyboard mural board the FUELED Ops team used for the event’s dry run. This event showcased the market research and modeling and simulation and provided an unmanned system demonstration for the FUELED Ops Program’s Year 1 efforts. In addition, during the event, CANA held brainstorming sessions to bring concepts into reality. The Mural board display below was an activity we conducted to come up with a common operational view. The board on the left shows the ideas for the “game pieces” and what we thought the operational concept should look like. The final result, on the right, is a 3D island model and includes game pieces created by CANA’s Graphics Artist. The team was able to use the game pieces and copy and paste them into the island visual to create several operating concepts. This provided an exciting and interactive experience to the FUELED Ops participants. Operational View (OV1) Mural Brainstorming Session Exercise CANA also hosted the FUELED Ops Design Thinking Workshop after the virtual demonstration. The information from the event will feed into the FUELED Ops Program Year 2 efforts. CANA was excited to host this event, having understood the challenges of how to achieve the best results in a virtual environment. Below are the morning and afternoon session activity boards used to diverge and converge on the future of unmanned logistics systems in the military. CANA Design Think Mural Canvases A few examples of CANA operations use cases CANA Lessons Learned Mural A great feature of Mural is that it is completely customizable, and a team can create the board in a way that will work for them. Two great CANA examples are our lessons learned activities and the on-boarding of new employees. We conduct lessons learned activities on Mural to have meaningful conversations in a judgment-free, neutral zone. As a team, we are constantly looking for ways to improve our communication, and Mural allows us to create a space for everyone to add their thoughts and have open discussions. The tool also has a voting feature that allows us to vote on important issues and prioritize them. New Team CANA Member Onboarding Another example is the CANA new employee on-boarding Mural board. We created this board to conduct an easy first-day orientation with documents, presentations, files, and more to help our newest employees understand what to expect for the first day, week, and month. Mural makes it easy to customize these boards for each employee - we can publish a template and customize it specifically to the individual. CANA’s newest Hiring Our Heroes Corporate Fellow, Neil Young, recently used our on-boarding Mural board, and he commented, “[c]ompleting my onboarding using Mural has been extremely helpful, especially with having diagrams, training, contact information, documents, and the ability to collaborate on tasks in real-time.” Mural works well for CANA, could it work well for you? Mural has helped our virtual company collaborate with, and understand one another, in a way much like being in person. It's a very diverse tool kit full of unique features that fit our specific needs, and it works well for CANA. We continue to build new use cases every week using this tool. Does your company use Mural? If so, we would love to hear how you are using the platform! #agilebusiness #mural #canaadvisors #teambuilding #collaboration #communication

In this post, I take a look at bicycle traffic patterns in Seattle, Washington, in light of the ongoing COVID-19 pandemic. Also, given very recent events and the timing of this article’s publication, I take the opportunity to include updated data for June, which presents bicycle traffic patterns affected by the recent social protests in addition to the pandemic. The data supporting this analysis was sourced from the Seattle Department of Transportation Bike Counters webpage, which registers daily bicycle traffic at 12 locations throughout the city. The original analysis was inspired by an R for Data Science Tidy Tuesday community event on GitHub; I highly recommend checking out the Tidy Tuesday repository for interesting, quick, data challenges. Seattle Bike Traffic Overview First, let’s take a look at an overview of tracked Seattle bike traffic over time. A few high-volume crossings (e.g., BGT North of NE 70th and the Elliot Bay Trail) stand out as well as some gaps in the bike counter data. We lost access to the X39th Ave NE Greenway counter in mid-2018 with no visible return. There is also clear seasonality to this data, as might be expected given Seattle’s rainy winters. Using NOAA weather files for the area, we can take a quick look at the relationship between the number of bicyclists on the road and area precipitation. We consider a “rainy” day to be one with at least 0.5 inches of precipitation. We can see a relationship between precipitation and bike count as well as a relationship between temperature and bike count. Bicyclist counts are noticeably higher on sunny, dry days than cold, wet ones. In Seattle, rainy day bicyclists are likely regular commuters. Next, let’s look into the hourly bike traffic patterns at different crossings to get a sense of their usage. Note: This graphic was inspired by a live screencast by David Robinson. Check out his YouTube channel for more Tidy Tuesday analyses. Many bike crossings show clear commuter patterns on the weekdays, with ridership hitting its highest counts around 9 am and again at 5 pm on Monday through Friday. For most crossing locations, weekend traffic peaks around noon. COVID-19 and Bike Traffic Seattle was the first major U.S. city to be affected by COVID-19 starting in February, 2020. How have the imposed social distancing practices impacted overall transportation trends over the past months? First, let’s look at the overall growth in COVID -19 cases compared to daily bike traffic. With pandemic isolation practices in place, there appears to be a cyclist traffic peak in April and early May. In late May and June, we start to see a decrease in these cyclists as businesses begin to reopen. How, then, has the pandemic impacted commuter patterns? As the pandemic worsens, we see a loss of commuting structure to the bicyclists’ movements over the course of the day. By April, the transportation pattern differs significantly from previous years, with counts peaking in the afternoon. Finally, let’s look at these cycling patterns broken out by counter location for the month of April, in comparison with average April ridership patterns from 2014 through 2019. These quick snapshots of Seattle’s bike lane traffic show a changing picture of transportation in the midst of a pandemic. As social distancing practices make public transit or ride-hailing inadvisable modes of transportation, many people turn to biking for both necessary transportation and leisure activity. Local Social Protest Activities and Bike Traffic Seattle was also the site of some of the nation's largest organized social protests in response to the May 25th death of George Floyd. Notably, the Capitol Hill Organized Protest (CHOP) created and occupied an autonomous zone for several weeks in June within Seattle’s Capitol Hill neighborhood. One of the bike counters we studied in this analysis, the Broadway Cycle Track N of E Union Street, is located on the edge of this zone, providing a unique look at movement during this time. As the community responds after the death of George Floyd on May 25, 2020, we see a sharp drop in cyclist movement near this counter. When the autonomous zone is established on June 8, 2020, movement falls close to zero. Unfortunately, we can’t see the full picture with regards to pedestrian data at this location and time. However, the bike data shows a clear change in movement patterns and gives an indication of the major impacts of this event. In Summary Events of the past several months have been unprecedented in scale and scope, with tangible effects on the micro- and macro- level. Changes at each level may provide valuable insight into the impact of events throughout the world. How have COVID-19 and social protests impacted transportation patterns in your neighborhood? Have you seen follow on effects outside your community? Share your comments below or in the CANA Forum.

This January, several team members from CANA Advisors attended the RStudio Conference, both in person in San Francisco and remotely! At CANA, the R language is a part of our daily analytics practice, from quick turn analyses to high impact applications build in R Shiny. The RStudio Conference provides a great opportunity to learn about the latest trends in the language and connect with others in the community. Here are a few takeaways from CANA Senior Operations Research Analyst, Lucia Darrow, who attended the conference in San Francisco: Virtual Attendance As a fully remote team, CANA Advisors is accustomed to making the most of virtual meetings and seminars to share knowledge and build community. This conference was the first time several teammates attended talks online simultaneously, coordinating to make sure we covered all the topic areas of interest. The conference organizers allowed virtual attendees to ask questions in the main queue and participate in talks as if they were in the room. It was awesome to feel as if the other R users on our team were attending the conference with me, catching the talks I wasn’t able to attend! With more and more conferences offering virtual attendance as an option, this mode of concurrent virtual attendance is definitely something to consider. Trends and Best Practices Two trends that seemed to be of growing interest among intermediate and advanced users are custom R packages and taking R into production. With a slew of new tools and packages to make package creation easier, the use of internal or project specific packages has increased drastically. Formalization of shiny applications into production grade apps was a continuing theme this year. New packages like golem show promise in making this process more attainable for R programmers lacking traditional web experience. At CANA, we are always looking for best practices to improve our R products and streamline the connection to other tools. I enjoyed several talks in the Programming track which elucidated topics like parallel computing and asynchronous processing with R. As R is a single-threaded language, these methods become increasingly important for processes with longer run time. R Community and RLadies In keeping with their commitment to the open source community, RStudio announced their new status as a Public Benefit Corporation. Diversity and inclusivity were promoted throughout the conference, including a RLadies meetup event hosted by RLadies SF! This was a great opportunity to connect with other chapters and share tips and tricks for building local programming communities. Interested in learning more? Many of these talks are available online. Check out https://resources.rstudio.com/rstudio-conf-2020 to experience the conference. To view CANA’s take on the 2019 RStudio Conference, check out Lucia’s blog post from last year's event. #TeamCANA #CANAAdvisors #Logistics #Analytics #RStudio #Conference #SanFrancisco #OperationsResearch #Analyst

At CANA Advisors, we use R daily, for everything from exploratory analysis, to generating publication-quality documents with R Markdown and interactive web apps with Shiny. In January, I made the trek down to Austin, TX to attend the RStudio conference. This was the largest RStudio conference to date, buzzing with nearly 2,000 attendees. Here a few reflections from those two enlightening days. R in Production: Not only possible, but easy! The first keynote speaker, Joe Cheng, broke down how the RStudio team is working to make R in production effortless for R programmers with little to no experience in web development. New tools like Shiny load test, plot caching, and async are now available to supplement old standbys RStudio Connect and Profvis. Throughout his presentation, Cheng stressed the importance of addressing the cultural and organizational barriers to scaling R. The ability to swiftly take analysis from an exploration in R to production presents a new role for data scientists, one that must be taken mindfully, respecting and relying on the expertise of IT and engineering teammates. The theme of production carried throughout the conference, with several presentations on the topic. Of note was a presentation from a team at T-Mobile, who shared a familiar story with the audience: presenting a Shiny application to high-level leadership gave credibility to their project, sparked interest, and eventually earned them additional resources to continue their work. From there, their engineering and data science teams worked together to put a Keras model into production, which is now responding to customer requests in real time. This is one of the most robust R models I’ve seen in terms of scale— seeing how they overcame technical and cultural barriers to create a fast, compact app was incredibly valuable. Defining Data Science In the second keynote talk of the conference, Felienne Herman, shared her joys and challenges in studying how people learn programming languages. Although this may be changing for the next generation, the majority of practicing data scientists do not have a shared memory of what it looks like to learn the tools of our trade. In part, this may be because data science programs didn’t exist until a few years ago, but the issue is even more fundamental. The view that learning how to code is exploratory, done individually with great struggle, is very common, because that is how so many of us learned how to code. What if, as with math or reading, there is worth in structured education for this line of work? Data science is supposedly the “sexiest job of the 21st century.” Despite all of the hype surrounding this career, amongst the analytics community, there is little consensus on what actually defines a data scientist, apart from a high salary. As operations research (OR) analysts, we see great overlap between our two disciplines. OR can certainly be considered a necessary predecessor of data science. While at the RStudio conference, I was surprised to see how many presenters and conference attendees, from a variety of disciplines, identified as data scientists. To an extent, it feels as if “data scientist” is an attribute that we can append to those that have mastered modern analytics techniques, whether they be biologists, geographers, or operations research analysts. Angela Bassa gave an inspiring talk about growing data science teams and taking advantage of the unique strengths individuals may bring to an organization. A panel discussion with industry leaders also addressed this topic with a conversation about how to manage a diverse set of team members. Strength in Community As with most R events, Hadley Wickham opened the conference with a Code of Conduct, reinforcing the importance of inclusivity and diversity. The “Pacman Rule” of always leaving space for a new face to join a conversation was honored throughout the conference. On the final evening, I connected with other RLadies at a social event. I picked up great tips on successful events from folks at different chapters from around the globe to take back to my own chapter. This event continued a theme of openness and inclusivity felt throughout the conference. PC: JD Long Interested in learning more? Many of these talks are available online. Check out https://resources.rstudio.com/rstudio-conf-2019 to experience the conference. #RStudio #shiny #RLadies

Analytics is a rapidly evolving discipline. Staying up to date with the latest methods and software can be a daunting task to undertake alone. Local meetups provide access to a community of professionals with similar goals. In particular, Meetup.com is one site that supports self-organizing groups, which generate events based on a common interest. In the tech space, these can range from networking events to book clubs and hackathons. In the D.C. area alone, there are over 100 meetup groups related to analytics and data science. In this post, three CANA team members, Lucia, Walt, and Jerome, discuss how they use meetups to learn, network, and give back to their communities. Lucia Darrow | I use meetups primarily to learn. One of my favorite data science meetups in the Vancouver area hosts monthly briefs based on the online competition website Kaggle. Local teams present a Kaggle competition, share their approach, and then explain the methods of the highest-ranking teams. These presentations give me a chance to think about how to handle diverse problems, often with different data types than I work with in my day-to-day tasks. The combination of algorithms crafted by the winning teams are fascinating! One of my top takeaways is the relative success a simple method can have against these highly complex solutions. Another way I use meetups is to connect with other women and gender minorities in tech, through groups like RLadies and PyLadies, that aim to give minorities a voice in tech communities. RLadies is an organization promoting gender diversity in the R community with meetup groups in 131 cities worldwide. You can check out a map of current locations here. For me, this group provides a bridge to the larger R community and connection to wide range of experienced R users. Hadley Wickham speaking at an RLadies Meetup, August 2018 Walt DeGrange | One of the great things about living in the Research Triangle is the abundance of tech companies. SAS, RedHat, Lenovo, Cisco, IBM, and many more call the Triangle home. It also has three major universities with the University of North Carolina, Duke, and NC State and lots of smaller schools. Given this abundance of analytics, the area boasts many Meetup.com groups. There are groups for languages like Python, R, SAS, and Julia and techniques such as machine learning and AI. There are even groups specific to certain genders like the R-Ladies RTP. In May 2018, the Research Triangle Analytics group ask me to speak. The venue was the SAS Training Center in Cary, NC. The facility was state-of-the-art and had more screens than I had ever seen in one room. I shared three stories from my past that focused on challenges in implementing analytics solutions. There was an excellent discussion after my presentation and several analysts shared their personal experiences. "I love interacting with this diverse group of analytical professionals. The meetups give someone that works at home an opportunity to interact and share in person with other analysts. It also allows me to see what cutting edge in other industries. The cost of getting started is a little time to log into Meetup.com and search for analytics. As an additional bonus, many of the meetings are sponsored by organizations that supply pizza for the evening gatherings." - Walt DeGrange Jerome Dixon I I use meetups to learn, network, and collaborate where it fits with like projects or technologies I’m interested in. My focus is machine learning, becoming a better programmer, and keeping up with the myriad of tools and techniques constantly getting introduced into the data science and technology space. One of the benefits to living in Richmond are the tech companies that sponsor meetups and examples of the use cases that they have actually put into production. I’ve seen amazing presentations by CapitalOne for how they use machine learning and hints into their data engineering infrastructure. I’ve sat through a very novel idea and use case for Tableau Server as basically an extract, transform, and load (ETL) tool by CarMax. Ippon has hosted some great meetups with how they are using Apache Spark as well as some best practices for their IT project management. Below picture is from NVIDIA’s Data Scientist, May Casterline, on the work they are doing with image processing, deep learning networks, and GPU dataframes. Leading edge technology! And when I get stuck - PyRVA (python user group), RVA R User’s Group (R statistical programming language), RVA Linux User Group (Linux, Amazon Web Services), and Docker Richmond meetup group (for containerization). Great opportunities for both support and networking with Richmond’s local meetup community. I am very fortunate and grateful for the city I live. If you are lucky enough to be located in a great meetup community - please leverage! *CANA Advisors is a veteran and woman owned leading logistics and analytics agency based out of Gainesville VA USA. For more information about CANA Advisors and its world class team visit canaadvisors.com #techmeetup #meetupcom #kaggle #RLadies #PyLadies #python #R #NVIDIA

One of our DoD clients inquired on where they could apply machine learning to improve their repair processes. What makes this process challenging is that repair personnel maintain a list of parts required to do a specific repair task. If for example, your car needs an oil change, then the list of parts for the maintenance would include one oil filter and a few quarts of oil. If the list of parts were always the same, then determining the list would be trivial. Unfortunately, there is always the possibility of performing scheduled maintenance and finding other parts that require repair. Also, there is the additional complexity of having parts replaced by newer parts. When you scale this up to a fleet of thousands of vehicles and tens of thousands of repairs per year, determining the required part list from maintenance personnel experience alone is a daunting task. We recommended an innovative approach using natural language processing (NLP) for creating a Bill of Material (BOM). What is a Bill of Material (BOM)? A Bill of Material (BOM) is a breakdown of items with associated configuration data needed to repair a subassembly or component of a larger system. Usually, these are broken up into a manufacturing domain and a supply chain domain, but there may be additional domains depending on the complexity of the part and the processes needed to repair or procure. Figure 1: The BOM connects the critical domains for a system's supportability Oleg Shilovitsky has written several blog posts and presentations on the challenges of BOM management. His presentation provides a backdrop on the issues that make BOM management challenging. http://beyondplm.com/2016/03/08/pi-munich-presentation-develop-single-bom-strategy-3/ What drives our analysis? Operational requirements drive how many vehicles are ‘Awaiting Repair’. Accurate onhand inventory (BOM Forecast) and ‘Repair Rate’ drive the number of ‘Repaired Vehicles’ delivered. Figure 2 is a high-level depiction of our repair process. Figure 2: High-Level Repair Process We first match the number of ‘Repaired Vehicles’ to the ‘Repair Type’ performed over a set period of time. Our set period of time is typically the previous repair schedule. After we match the repair types completed to the number of issues per vehicle, we then calculate the frequencies of the parts ordered. Our final step is to divide the frequency counts by the number of vehicles per period to get a Replacement Rate (RR) per individual part. This RR with a part number now becomes our forecasted Bill of Material (BOM). Natural Language Processing (NLP) Refresher A term document matrix is a way of representing the words in the text as a table (or matrix) of numbers. The analysis uses the rows of the matrix to represent the text responses, and the columns of the matrix to represent the words from the text. Once in a term document matrix format, we can apply various text-mining algorithms. Figure 3 provides an example of this process. Figure 3: NLP Bag of Words Part numbers or National Item Identification Numbers (NIINs) can be represented as words or character vectors for text mining analysis. By representing this as a text mining problem, we gain efficiencies in computer memory utilization in addition to additional analysis methods. Job Order Number (JON) refers to the type of repair action and the required parts and procedures required for repairs. Control Order Number (CON) refers to the higher level JON that a major repair action falls under. CONs and JONs will be our “bags” for collecting words (NIINs). Figure 4 shows a high-level view of how JONs (sentences) are made up of NIINs (words). Figure 4: Parts Data in Array Format BOM Building Example We use R to create the required data structure and perform the frequency analysis. We format our issue data into a list array by Repair Type: Figure 5: Issue Data in List Array Data Structure Figure 6: Issue Data – expanded We then convert our list array to a document term matrix, count frequencies, and calculate the individual Replacement Rates. Figure 7: Final BOM BOM Building Made Easy Here we have shown a relatively easy, data driven approach to developing a BOM. Our goal is to reduce the workload of the repair personnel to perform BOM maintenance and create a more proactive approach to BOM management. By also monitoring repair rate trends from period to period, maintainer or senior management can identify missed configuration changes or possible changes to local repair procedures. These techniques can be applied to the manufacturing side as well. This article was written and developed by the creative team of analysts at CANA LLC #NLP #DoD #BOM #billofmaterial #naturallanguageprocessing #JON #jobordernumber

CANA Advisors through its CANA Foundation – supports our people and offers opportunities to ‘give back’ in many ways. One specific form of support this past 2017 holiday season was to give our team members company time to spend “volunteering in their local community.” To quote our company’s Founder and President, Rob Cranston, the CANA Foundation “provides the CANA family of employees an opportunity to connect with and give back to community areas we feel passionate and care about.” Below are a few stories of how our team members chose to ‘give back’ using this time. Bicycles for Monterey Principal Operations Research Analyst Harrison Schramm used his volunteer time in support of a project with Monterey County Behavioral and Mental Health – procuring and providing bicycles for kids in need. This project started several years ago in a casual conversation between Harrison and the Project’s leader. She knew that Harrison was in to riding bicycles and wondered if he could help build a few. One thing led to another, and he ended up with a wrench in his hand the week before Christmas 2016. Clinicians in contact with families provide a list with information such as age, height, and gender. An anonymous donor contributes money. Harrison and a few others convert the money into age appropriate bicycles. The clinicians then pick up the bicycles and deliver them to the families. The process is ‘double blind’ in the sense that the providers and recipients of the bicycles will never be introduced. Harrison completing the 2017 Bicycle Build: Six bikes and one Scooter. “That doesn’t stop me from wondering, though” Harrison said. “Sometimes, I’ll be out on the Rec-trail, see a kid coming and wonder ‘did I build that bike?’” The bicycles are all brand-new, and a helmet is provided with each. “A bicycle isn’t just a toy for a kid on the [Monterey] Peninsula. It’s exercise, it’s a way to get to school and work, it’s a way to put everything behind you – if only for a few minutes.” Harrison says that he prefers to get the bicycles un-built from stores if he can, because he can fit more in his car that way. Kitsilano Neighborhood House Operations Research Analyst Lucia Darrow spent her volunteer hours at the Kitsilano (“Kits”) Neighborhood House, helping out with the Kits Club after-school childcare program. The Kits House develops programs to meet the needs of the community, ranging from childcare and senior living options to hosting farmers markets and ESL circles for newcomers to the city. Through volunteering with the Kits House and assisting with special events, Lucia says she enjoys connecting with the community and learning about the rich history of Vancouver’s Westside. Lucia on the steps of the Kitsilano Neighborhood House. Samaritan’s Purse Operation Christmas Child Norm Reitter, our Director of Analytics, spent an afternoon at a Samaritan's Purse run "Operation Christmas Child" gift distribution center where he inspected and enhanced gift boxes that were collected from many donation sources. These boxes were then routed through the Denver, Colorado distribution center and shipped to children in need who would not otherwise get Christmas gifts. Operation Christmas Child counts on thousands of volunteers to collect and process millions of shoebox gifts every year. Samaritan's Purse provides this approach so that kids get meaningful and useful Christmas gifts. Norm and Annalisa were busy inspecting donations, adding age appropriate items to gift boxes, and packing the gift boxes into larger containers for shipping. Norm said that seeing all the donations and knowing the positive impact on each child that would receive a gift box made this a very meaningful experience for him and Annalisa. Norm and Annalisa at their local Colorado Operation Christmas Child gift distribution centers. In Closing CANA Foundation has enjoyed a wonderful inaugural year of growth and giving back to our communities. We are excited to continue our upward momentum and build upon that success. In 2018, we will continue to create more opportunities for our team to participate, facilitate our team’s ideas to give back, and continue to develop meaningful relationships with other organizations. Onward and upward!! #CANAFoundation #CANAAdvisors #givingback #charity #community #support #bicycles #Kitsilano #KitsHouse #Samaratin #operationChristmasChild

A few months after graduating with an advanced engineering degree, I find myself back in the classroom, this time for my first class of beginner French. All about me I hear snippets of broken French from my Canadian classmates: phrases, simple sentences and questions. I know three words, which I can pronounce in a distinctly American way: bonjour, merci, and croissant. The “beginner” level of French language for Canadians, it turns out, is a little different from the “beginner” level for an American. I reassure myself that I’m a fast learner and struggle through the first class. After years of focus in one area of work, it’s natural to grow confident in your carefully crafted method of learning and doing. Once varied problems start to take on familiar forms, and it becomes easier to prescribe a certain solution. Stepping into French, I realized my tried and true approaches to learning were not going to prove effective. Several months later, here are some lessons I learned. Failing: Fast and often. I find the most difficult part of language acquisition is not grammar or syntax, but the inevitability of mistakes. Regarding mistakes as taboo creates a major roadblock to personal improvement. The same holds true with solving a difficult analytics problem. Instead, sharing in-progress or flawed work with colleagues helps to break through the small failures and clear a path to a robust solution. Out with the old and in with the new – Suppressing instinct and embracing a new technique. As with many language learners, my first instinct when I don’t know a word is to simply throw in the word from another language. Similarly, we tend to retain old sentence structures, until the structures of the new language become natural. R users can understand how this relates to learning the dplyr workflow or transitioning to functional programming. While these changes feel like a major paradigm shift at first, the impact on future work can prove invaluable. Analytics MacGyver. Asking someone about their aunt’s profession can sound something more like “What does your mother’s sister do in life?” coming from a novice speaker. This roundabout method may sound silly, but is arguably better for the learning process than simply inserting words in English. Analytics professionals must also be bricoleurs, utilizing many resources, tools, and experts to make complex and unfamiliar problems tractable. Diving in and staying in. Immersion and persistence are key to language acquisition. In analytics, methods are rapidly changing and improving. Attempting to become proficient in every new technology can be tempting, but dedicating time to one technology allows for quicker mastery. Abstraction and derivation of meaning. In the early stages of learning, every interaction with a new language can feel like a game of abstraction, as we try to translate back to our mother tongue. As sentences become phrases, then complex sentence structures, the problem becomes a greater puzzle. Here is where I’d argue that many analytics professionals would find joy in the challenge of language acquisition - the feeling of successfully working through a verbal puzzle and constructing a response, hopefully more expressive than oui or non. #learningFrench #strategy #Analytics #LuciaDarrow #R

Over the past year, "fake news" has become a topic of particular interest for politicians, news media, social media companies, and... data scientists. As this type of news clutter becomes more prevalent, individuals and organizations are working to leverage computing power to help social media users discern the "fake" from the legitimate. In this article, we take a look at some basic natural language processing (NLP) ideas to better understand how algorithms can help make this distinction. Natural Language Processing: A Brief Introduction Text Preprocessing: Arguably the most important step to text mining is preparing the data for analysis. In NLP, this involves actions such as tokenizing words, removing distinctions between upper and lower case words, stemming (extracting the root of words), and removing stop words (common words in a language that don't carry meaning-- think: the, and, is). An example of tokenization and stemming is shown below in Figure 1. Bag of Words: This model is useful in finding topics in text by focusing on word frequency. Bag of words can be supplemented with word vectors, which add meaning to NLP representations by capturing the relationship between words. Text as a Graph: Graph-based approaches consider words as nodes and focus on associations to draw more complex and contextually rich meaning from text data. Named Entity Recognition (NER): This method can be used to extract types of words, such as names, organizations, etc. Many NER libraries are online for public use. Sentiment Analysis: Otherwise known as "opinion mining," this technique provides a gauge of the author's feeling towards a subject, and strength. Do fake news outlets produce more opinionated articles? # Tokenization and Stemming Example headline <- "The Onion Reports: Harry Potter Books Spark Rise in Satanism Among Children" tokenize_word_stems(headline) ## [[1]] ## [1] "the" "onion" "report" "harri" "potter" "book" ## [7] "spark" "rise" "in" "satan" "among" "children" Figure 1. Tokenization and Stemming Example How Are Data Scientists Framing the Problem? While popular browser extensions use crowdsourcing to classify sites that publish fabrications, researchers are reframing the problem of fake news. In order to fit a model, an understanding of the most influential features that differ between fake and legitimate is helpful. Regardless of whether the fake news is created by provocateurs, bots, or satire, we know it will have a few things in common: a questionable source, content out of line with legitimate news, and an inflammatory nature. Current research in the area takes advantage of these truths and applies approaches spanning from naive Bayes classifiers to random forest models. Researchers at Stanford are investigating the importance of stance, a potential red-flag trait of misleading articles. Stance detection assesses the degree of agreement between two texts, in this case: the headline and the article. Another popular approach is the use of fact-checking pipelines to compare an article's content to known truths or an online search of a subject. As the complexity of fake news adapts to modern modes of media consumption, research in this space will expand. Image classification is a likely next step, albeit one that poses a major scalability challenge. Interested in learning more or building your own fake news classifier? Check out these resources: Python's Natural Language Processing Toolkit R's NLP Package Python's SpaCy for NER #fakenews #science #NER #NLP #NaturalLanguageProcessing #tokenization #stemming #datascience #LuciaDarrow

CANA Attends Key Events By Will Berry Pentagon Energy Expo The Pentagon Energy Expo took place over two busy days in September, one sunny and one rainy. Regardless of the weather, the courtyard of the Pentagon was the ideal setting for over a hundred exhibitors ringing the central courtyard walking path to demonstrate emerging technology capabilities that will help preserve U.S. military dominance in future contested logistics environments. The Expo was hosted by a number of Department of Defense sponsors including the individual Service branches, and the Office of the Under Secretary of Defense (OUSD), Under Secretary of Defense for Acquisition and Sustainment (OUSD(A&S)), Operational Energy Capability Improvement Fund (OECIF), and the Operational Energy Prototype Fund (OEPF). These sponsors had the opportunity to view a variety of cutting edge technology, including vehicle electrification, installation energy resilience, batteries, energy storage, energy distribution, power generation, software, and cybersecurity. One of the standout exhibits was the eTHOR, a project funded by OECIF, sponsored by National Information Warfare Center-Pacific (NIWC PAC), and project-managed by CANA. eTHOR will provide a network of electric vehicles capable of storage, transport, delivery, and exportation of energy in a contested environment. In addition, the system is an agile 5G network infrastructure, deploying and extending 5G’s low latency, high bandwidth capabilities to the expeditionary force enabling unmanned systems, artificial intelligence, and all domain command and control. The goal of the system is to increase the efficiency of energy logistics in a contested environment and provide sufficient network communications to enable the future force. A tag line of the Expo was, “[e]nergy is the key enabler that will keep the Joint Forces in the fight to achieve decisive victory.” With that in mind, the eTHOR exhibit showcased electric vehicle technology and exportable energy all-in-one by having a DANNAR Mobile Power Station (MPS) at the eTHOR booth. It was a unique visual draw that brought hundreds of visitors to the exhibit. Amongst those visitors was Deputy Defense Secretary Kathleen H. Hicks, resulting in a special opportunity to directly share the significant energy plus 5G communications capabilities the eTHOR system will bring to bear. In regards to the Expo, Deputy Defense Secretary Hicks was quoted that energy innovation, "...has to do with national security and what it takes to have the capabilities we need for the warfighter today and going forward.” Well said, we believe, and the eTHOR project is excited to deliver. Unmanned Systems West The Unmanned Systems West Conference took place late September in San Diego, CA, and was a fascinating forum of presentations, analysis and discussion. It focused on how the military, government, technology industry, and academics can work together to develop capabilities that advance Unmanned Systems (UxS) capabilities to benefit the warfighter on land, sea and air. The conference was billed as an opportunity to further dialogue on tactical and technical priorities and the challenges of autonomy and artificial intelligence and to shine a light on ongoing research and innovation that will help integrate both UxS and robotic capabilities. It was successfully achieved on all fronts. Over the two day conference, there were a number of common themes woven through the presentations and panel discussions, including the need for increased collaborative research on design to decrease prototyping systems costs and to increase design speed. Ideas, such as low-cost platform sharing based on common vehicle chassis, were recognized as a tactic to accelerate change; otherwise we risk losing from an acquisition perspective. While there were many different perspectives offered by the presenters and panelists, the iterative design notion – to collaborate, develop, test, fail fast, and evolve – was a common theme that encapsulated the pathway to effectively meet requirements and achieve success. On Day One, the conference was capstoned with a special presentation by one of our partners, NavalX So Cal Tech Bridge Director, Captain Ben Cohen, USMC, who discussed industry innovation needs and requirements. Attendees were enlightened to Capt Cohen’s unique perspective as a Marine Corps warfighter and as the new Director of the NavalX So Cal Tech Bridge. Amongst other things, Capt Cohen discussed bringing warfighters into the academic/industry ecosystem by highlighting the need to focus capabilities on the diverse pool of end users first, with the technology to follow. By focusing on the end user first, the culture of the warfighter is taken into account, which is paramount because, as Capt Cohen stated, “...culture eats strategy for lunch.” #innovation #warfighter #autonomy #5G #connected

"Can I view that in Excel?" The capabilities of R programming are expanding. Fast. From publication-quality graphics with ggplot2 to the capability to handle large scale computing with Apache Spark, the analytics community embraces R as a core environment. At CANA Advisors, we use the latest developments in order to deliver the fastest, most adaptable solutions. For clients, results need to be in a form that is easy to process by any member of their team-- with little to no learning curve. As analytics professionals, how can we ensure the best of both worlds? That is, state of the art solutions that produce results in the familiar form clients seek. In this post, I'll go over one such method: using R programming to export the results of a Shiny analysis to Microsoft Excel. For those not familiar with Shiny, it is a package to create interactive, aesthetically pleasing web apps with all the statistical capability of the R programming language. This brief tutorial will utilize the Shiny and XLConnect packages in R. The Method In this example, we'll be working with the iris data set [1], which contains information about the dimensions of different instances of various iris flower species. For the purpose of this tutorial, we'll assume we already have a functioning Shiny app and the data structures we are interested in saving. In this case, the data we'd like to store is reactive in nature. This means, it will change with user inputs. You can recognize calls to reactive expressions in the code below by their distinctive form expression(). To export a worksheet: 1. Lay the groundwork: Create the download button, workbook, and worksheets. 2. Assign the data frames to the worksheets. 3. Save and download. The Result The above process will take us from a shiny app like this: To an excel file like this: The Implementation # Load the shiny and XLConnect packages library(shiny); library(XLConnect) # Create and label the download button that will appear in the shiny app renderUI({ downloadButton("downloadExcel", "Download") }) output$downloadFile <- downloadHandler(filename = "Iris_data.xlsx", content = function(file) # Name the file fname <- paste(file, "xlsx", sep = ".") # Create and assign names to the blank workbook and worksheets wb <- loadWorkbook(fname, create = TRUE) createSheet(wb, name = "Sepal Data") createSheet(wb, name = "Petal Data") # Write the reactive datasets to the appropriate worksheets writeWorksheet(wb, sepal(), sheet = "Sepal Data") writeWorksheet(wb, petal(), sheet = "Petal Data") # Save and prepare for download saveWorkbook(wb) file.rename(fname, file) }) To learn more about any of the features discussed above, use the ?topic feature in R. A more comprehensive overview of shiny is provided by RStudio here. Lucia Darrow is an valued Operation Research Analyst at CANA Advisors to read more R articles by her and other members of the CANA Team visit the CANA Blog. [1] In R, type ?iris to learn more than you would ever want to know about it. #R #Rstudio #shiny #XLConnect #ShinnyApps #codeexample #RStudio #programming #graphics #ggplot2 #LuciaDarrow

It is somewhat difficult to convey the spirit of Camp PARC to someone unfamiliar with it. When describing the communal shower house and lack of air conditioning, the squeaky beds and sharing a cabin with up to 35 other people, plus whatever wildlife critters invite themselves in for the night, most people don't match my enthusiasm. It’s hard to put into words an experience so fulfilling, self-validating, yet humbling. A person so innocent, one who is open to your kindness, seeks nothing, yet is overwhelmed by your compassion and companionship, is someone truly worth meeting and making smile. Through Camp PARC we have 100+ of those people. One of the core values of CANA Advisors is to balance work and life through flexible working hours, encouraging each of us to pursue passions and focus on our personal goals. In July I chose to invest my time at Laurel Hill State Park in Somerset, Pennsylvania and volunteer for a local non-profit organization - Camp PARC. 2016 was my tenth year of service with the organization. Camp PARC is a privately funded service organization "[that] creates recreational and social opportunities for children and adults with mental and developmental disabilities (Down Syndrome, Fetal Alcohol Syndrome, severe autism, etc.) through its residential summer camp." With a mission to provide summer camp experiences to these special needs "campers," Camp PARC hosts three (3) unique weeks of camp: 7-day Main Camp is for anyone over 18 and has been the traditional format of the camp for over 50 years. 5-day Adult Mini Camp for those over 18 who cannot, or may not want to, keep up with the faster paced week-long camp 4-day Youth Mini Week for the younger crowd to experience their first time away from home overnight and start building new relationships. This year, a total of 130 campers attended our camp season. To add additional awe to the very special mission of Camp PARC, the camp is run ENTIRELY by volunteers and donations. From the cooks to the Directors, dishwashers to the very important nurses, and everyone in between, hundreds of people flock to this camp annually to lend a hand. The most important people, though, are the junior staff. These positions are filled by local young adults (ages 13-21) who volunteer a week (or three!!) of their summer to be paired with 1 - 2 campers. They provide 24-hour care for the duration of the camp session. Junior staff are responsible for serving campers food, keeping them safe, and ensuring all their needs are met, while also encouraging them to participate in activities, go outside of their comfort zone, and have fun. For a teenager who is just coming into their own as well, the interactions between junior counselor and camper is something very special. Day-to-day camp activities are organized and executed by the Senior Staff (this where I fit in!). We are adults over 21 and most of us have previously served as a junior counselor during our high school years. Even as jobs and families force us away from Western PA, several of our staff make the journey annually, traveling from Texas, Missouri, Alabama, Virginia, and all across Pennsylvania. In 2014 & 2015, I traveled in from Afghanistan because this camp is that special. Koa Beam, another CANA Advisors team member, was gracious enough to volunteer one morning and experienced first-hand the spirit of Camp PARC. "I just thought it was a great thing and seeing the kids you guys help out with is a daunting task, but so needed. My hat goes off to the people who volunteer a portion of their summer to go help-out. I just hope that my small contribution of time put a smile on at least one or two kids' faces and that they enjoyed my time there as well. It couldn't have been a nicer day." How many of us miss out on these kinds of people, opportunities, and smiles? It is amazing what happens when we put down our phones, walk away from our computers, and live in life’s beautiful and inspiring moments. Somehow, our ships sail straighter when we invest in others and balance ourselves. For more information about Camp PARC, please visit their website: http://campparc.org/ #camp #PARC #CANAAdvisors #volunteers #community #kindness #team #summer #connection