What's happening? What's new? What can I do? Find answers to these questions in the blog.
What can data about vehicle accidents tell us? I recently was able to take data from the New York Police Department that spanned 2013-2015, refine it and upload it into Watson Analytics to see what I could learn about accidents and the injuries and deaths they cause. I was especially interested in discerning the latent patterns. Before we get started The real-world data set I used is courtesy of NYPD Motor Vehicle Collisions open data and based on motor vehicle accidents in the New York area. This data set was later merged with hourly weather data based on latitude and longitude and time of accident. The data was shaped and customized by removing all rows where “Borough” was blank and “Contributing Factor (for Vehicle 1)” was either blank or unspecified, because my plan was to analyze only those accidents that had information about the borough and the contributing factor for the primary vehicle. This calculation was also created: # Persons killed or injured = Persons Killed + Persons Injured It begins with a simple question The question I asked Watson Analytics was “I want to understand accidents by borough.” As you can see here, Manhattan was the most accident prone area for the three-year period I was analyzing, while Staten Island the least. Looking at those accidents over the years, I immediately realize that not only has there been a steady increase in accidents for all boroughs, but also that the increase is pretty steep for Brooklyn and Queens (compared to the others). When I replaced year with quarters, we see the same pattern of gradual increase in accidents as the quarters progressed. Essentially, accidents are increasing by the day! More accidents do not necessarily mean more injuries or deaths But not every accident results in an injury or a fatality! It’s really interesting when I made that distinction. So, although Manhattan had the most number of accidents, Brooklyn and Queens had more injuries and deaths due to them. Further, it’s clear that a passenger vehicle resulted in a majority of those accidents that led to injuries or deaths. If I want to bolster the value of my analysis, the transactional data can be augmented with relevant contextual data. In this case, that could be the make and model of the specific vehicle used, highway information, demographic details of the driver and other related data. Digging deeper for validation and new factors not easily seen Although a few important characteristics were easy to spot, the questions remained about what drove injuries or deaths during an accident. So, I turned to another aspect of Watson Analytics, the simplified predictive model that can be used to: Validate existing understanding, knowledge or gut feel Discover novel factors that are not obvious when you first examine data. Contributing factors (for the primary vehicle involved in the accident) seems to be the most important driver of injuries or deaths in an accident and its combination with Boroughs seemed to have the most significant bearing. I can not only see all the factor combinations ranked in order of their bearing to the target but I can also drill down into each one of them to learn more. Interestingly, weather plays a pivotal role too. Delving deeper and looking at the top 5 Contributing Factors across the three Boroughs (with the highest injuries and deaths from accidents), it’s evident that Driver inattention/distraction tops the list followed by Failure to Yield Right-of-Way. This is ironic given that either can be avoided and yet it ended up taking so many lives from accidents in New York boroughs in the last three years! But this is good insight because it makes it possible to fine-tune existing policies and focus areas with more education on the topic along with higher penalties for distracted or inattentive driving. An analyst, an office manager or any other regular user with the dataset can arrive at these insights within moments. No pre-requisite understanding of statistics required. How’s the weather there? Based on what I learnt from the predictive insight, I decided to learn more about the 66% impact that the combination of Wind Direction and Weather Conditions had on injuries/deaths resulting from an accident. Although, it might be common sense that higher the wind speed, the higher the chances of accidents (and hence more chances of injuries or deaths), it is nice to have statistical proof that specific wind direction could a bearing on high injury or deaths during an accident. The NYPD can use these insights to monitor and control such situations with alerts and real-time dashboards. Displaying what I’ve learned With Watson Analytics, I brought my insights together in easy-to-build, interactive displays. The daily view of both accidents and injuries or deaths resulting can be filtered to show any month we want. We can further break down Injuries and deaths into cyclists, pedestrians and motorists to understand them individually by region, time and other factors, to yield actionable insights. For example, my displays show that pedestrians in all boroughs run a higher risk of an accident related injury than cyclists. Try Watson Analytics If you haven’t used Watson Analytics yet, today’s a great day to try it. Visit www.watsonanalytics.com for more details.
The new IBM Watson Analytics user interface has been redesigned and focused around interacting with data – adding data, discovering insights and displaying your findings. The IBM Design Thinking process was used to support and focus the new design on the user’s analytical journey. The result? A powerful, intuitive and easy-to-use, self-service data analytics and visualization platform. This blog provides a quick overview of the main features in the new Watson Analytics user interface. For more details, check out these other resources: Watson Analytics New User Experience Frequently Asked Question Watson Analytics new experience arrives! Now what? For a quick tour of the new Watson Analytics, check out this video: New Home page It’s all about the three D’s - Data, Discover and Display. The new Watson Analytics Home page organizes your content and workflow into these three key areas. Data – Import, manage and refine your data. Quickly launch new data explorations. Discover – Explore your data by asking natural language questions, using the suggested starting points or building your own visualizations. Organize your discoveries and visualizations into Discovery sets. Display – Use visualizations from your Discovery sets to build your own custom data stories with dashboards and infographics. Plus, there’s also IBM Watson Analytics for Social Media, the new Expert Storybooks and the new Analytics Exchange. Navigating the new user experience Use the new navigation menu to switch between your open assets and get back to the Home page. Watson Analytics for Social Media and the new Analytics Exchange are also accessed from this menu. Hover over an item in the list and click the X to close that item. An asterisk symbol (*) next to an item in the list means that the item hasn’t been saved yet. TIP: Click on the IBM Watson Analytics logo as a shortcut back to the Home page from a Refine, Discovery, or Display item. Asking questions across all of your data The ability to ask natural language questions and get automatic insights has been expanded throughout Watson Analytics, improving the overall analytical guidance and journey. In addition to asking questions about a specific data set, you can now ask a question across all of your data sets. The Data and Discover tabs both include a dedicated question box for this feature. The suggested starting points are ranked by relevance, indicate which data set was matched and include thumbnail images that represent the visualizations for that related analysis. Of course, you can also click an individual data set and ask a question just about that specific data set too. Data … is where it all starts Got data? The Data tab is the starting place for most of your projects; where you import, manage, access and shape your data. Import your data from any of the available data sources or formats and then quickly launch into exploring and visualizing the data. Getting your data into Watson Analytics is quick and easy using the New data button. Add sample data, retrieve files from local or online storage sites like Box, connect to a database or extract social media data. Easily manage all of the data that you’ve imported into Watson Analytics by renaming, deleting, and moving the assets. Create and arrange folders to better organize your assets. Take existing data and replace it completely or refine it with the built-in data preparation refinement features. When you’re ready to explore and visualize your data, one click on a data set is all it takes to get you to the Discover process. Discover … insights from your data The Discover tab gives you multiple powerful paths to explore and visualize your data. Discover insights by typing in questions in natural language Use the suggested starting points Build your own visualization from scratch Use predictive analysis to see what drives a certain target field Use the insights from the cognitive side panel TIP: For users of Watson Analytics classic, the new Discover tab combines the previous features of Explore and Predict into a new, single location. Start out by asking questions about your data and use the suggested starting points or “insights” … or build your own visualization. The visualizations you discover and create are saved in a collection called a ‘Discovery Set’. Discovery Sets organize multiple visualizations for the same data set into a tabbed workspace. The cognitive Discoveries panel on right side provides additional insights that are relevant to the current fields you are visualizing. After creating your Discovery Sets, you can then use the visualizations from them to build dashboards and infographics in Display. Display … and share your data story After discovering the insights in your data, use Display to build and communicate your data story to others by creating dashboards and infographics based on the discoveries you’ve found in your data. Simply browse through your discoveries and selectively drag the visualizations you want onto the dashboard canvas. You can edit the columns and visualization types for a discovery right within Display. You can also set filters globally across all tabs, or per tab. Share the results: When you’ve finished building a display, you can share it by email, download, link or social media. Watson Analytics for Social Media Looking to better understand topic trends and gain insights from social media? You can try IBM Watson Analytics for Social Media for free for 10 days. Open Watson Analytics for Social Media from the navigation menu. Take the pulse of your audience and gain greater visibility into a topic or market by spotting trends and discovering new insights in data across multiple social channels. Watson Analytics for Social Media provides guided data exploration, automated predictive analytics and automatic dashboard creation for exceptionally insightful discoveries, all on the cloud. Expert Storybooks Looking for your own personal analytics mentor to help guide you through the analytics journey end to end? Import your data into an Expert Storybook and see how these guided analytic templates can help. Expert Storybooks combine visualizations, insights and navigation into one package that ‘walks’ you through your data for a specific industry, domain or business problem. You can find an existing Storybook on IBM Analytics Exchange and apply it to your own data. Already an analytics expert and want to build your own Expert Storybook? That’s possible too! All you need is a collection of visualizations and insights that could apply to other data sets for the same industry, domain or business problem. Use the storybook editor to build and publish your own Expert Storybook to share as a template with other Watson Analytics users. Analytics Exchange The Analytics Exchange offers a marketplace for Expert Storybooks and additional public data sets that can both be imported directly into Watson Analytics. Open Analytics Exchange right from the Watson Analytics main menu. Browse and select a storybook template that you can then import and use with your own data. Looking for more data? Browse and load publicly available data directly into Watson Analytics from a wide range of data categories. Use this data to augment or support your own data analysis, to explore data from an interesting domain, or as sample data to learn more about Watson Analytics. Looking for community support and help? Documentation and community pages are just a click away in the Help menu. You can also check out the updated tutorial: Getting Started Tutorial for IBM Watson Analytics For more information about Watson Analytics, visit www.watsonanalytics.com. And, if you haven't tried Watson Analytics yet, you can now register for the free edition and get a free 30-day trial of Watson Analytics Professional. See the different editions of Watson Analytics summarized in this video:
The start of the college football season in the US is only 3 ½ months away. And with it comes the perennial argument over the best college football conference, which can get pretty heated. Looking at data with Watson Analytics offers some insights into which conference is the best by the numbers. By collective wins, the SEC is supreme followed closely by the Big 10 conference. Let’s take a look at total offense. Again, the SEC wins out with, collectively, the top performing offenses in college football. Finally, let’s look at points against per game.
One of the great capabilities of Watson Analytics is the ability to quickly explore your data and automatically create compelling visualizations. And you can do this in 4 steps. (If you haven’t already signed up for Watson Analytics, you can do so here for free.) 1. Upload the data you want to explore by clicking the Add button. 2. Click the data set and select Explore from the Start from Scratch dropdown menu. 3. Type what you’d like to see. 4. Select the tile you’d like to see, and voila, there is your visualization. From here you can continue to explore your data by clicking on one of the interesting findings in the ribbon along the top. Or simply start over and type another question. With Watson Analytics, you can be confident you’re getting your point across with brilliant visualizations created from answers to your questions. If you haven’t used Watson Analytics yet, today’s a great day to sign up for your free account. Want more from Watson Analytics? Consider subscribing to the Professional Edition. Learn more in this video.
You might have noticed some changes in Watson Analytics these last few days. We’ve made some updates that we hope will make your data journey more straightforward, so that you can start solving your business problems even faster. The first change you’re likely to notice is what happens after you’ve uploaded a data set. When you click your data set, Watson Analytics will almost immediately present you with a number of interesting insights to get you started right away. If you want to know the most interesting things about your data, this is a great starting point. Or you can just type in your own question if you’ve got something else burning on your mind. If you’re keen to understand some of the hidden patterns and relationships in your data or create some stunning dashboards, infographs and stories, all of those capabilities are still possible from this same window. Simply select the relevant feature from the Create your own dropdown: It’s that simple. The first step in your data journey just got easier. If you haven’t used Watson Analytics yet, today’s a great day to start by visiting www.watsonanalytics.com