Exploratory Seminar #33 - Exploratory v6.4 Introduction

I have presented the newly released Exploratory v6.4's new features and enhancements on 2/10 (Wed), 2021.

Exploratory v6.4 New Feature Highlights:

- Dashboard - Drag & Drop to Resize
- Time Series Data Clustering
- Time Series Forecasting (Prophet) - Quarterly / Monthly Seasonality
- Snowflake Data Source Support
- Improvements on ODBC Data Source
- Chart: Rename on Y-Axis Column Names

Exploratory: https://exploratory.io/

Follow us at @ExploratoryData (https://twitter.com/ExploratoryData) !!

Transcript

1. EXPLORATORY Online Seminar #33 Exploratory v6.4
2. Kan Nishida CEO/co-founder Exploratory Summary In Spring 2016, launched Exploratory, Inc. to democratize Data Science. Prior to Exploratory, Kan was a director of product development at Oracle leading teams to build various Data Science products in areas including Machine Learning, BI, Data Visualization, Mobile Analytics, Big Data, etc. While at Oracle, Kan also provided training and consulting services to help organizations transform with data. @KanAugust Speaker
3. 3 Data Science is not just for Engineers and Statisticians. Exploratory makes it possible for Everyone to do Data Science. The Third Wave
4. 4 Questions Communication Data Access Data Wrangling Visualization Analytics (Statistics / Machine Learning) Data Analysis Data Science Workflow
5. 5 Questions Communication (Dashboard, Note, Slides) Data Access Data Wrangling Visualization Analytics (Statistics / Machine Learning) Data Analysis ExploratoryɹModern & Simple UI
6. EXPLORATORY Online Seminar #33 Exploratory v6.4
7. • Summary View • Analytics • Visualization with Chart • Data Wrangling • Reporting - Dashboard • Data Source Areas of New Features / Enhancements
8. • t Test • ANOVA • Wilcoxson Summary View
9. • Time Series Clustering • Time Series Forecasting with Prophet - Monthly, Quarterly Seasonality Support • Prediction with Survival Models • Sample Size Setting Analytics
10. Time Series Clustering
11. Dynamic Time Warping is used to compare the similarity or calculate the distance between two time series data with different length and speed. Dynamic Time Warping
12. If we apply the one-to-one match, shown in the top, the mapping is not perfectly synced up and the tail of the blue curve is being left out.
13. DTW creates one-to-many matches so that the peaks and bottoms with the same pattern are perfectly matched, and there is no left out for both curves(shown in the bottom top).
14. Calculating Distance in a Naive Way • Calculate the distance on each date and time point. • But, when the two lines have a lag the distance can be over- calculated.
15. Create one-to-many matches so that the total distance can be minimized between the two time series data. Calculating Distance with Dynamic Time Warping (DTW)
16. Time Series Clustering
17. Prophet - Quarterly / Monthly Seasonality
18. Prediction with Survival Models - Survival Random Forest / Cox Regression Now, you can predict the probability of survival for each individual by using the model - Survival Random Forest and Cox Regression - you have created under the Analytics view.
19. Step 1: Build a Prediction Model with Survival Algorithms
20. Step 2: Select ‘Predict with Model (Analytics View)’ from the Step menu
21. Step 3: Select the model and set the Survival Time for Prediction
22. Marketing Mixed Model - Decay Effect
23. Sample Size Setting You can set the sample size easier now. You no longer need to open the property dialog!
24. • Renaming the Column Names for Y-Axis • Summarize Table / Table: Column Header Formatting • Table: Text Wrapping and Width Adjustment • Auto Scaling for Numeric Columns at X-Axis Visualization with Charts
25. Renaming the Column Names for Y-Axis
26. Summarize Table: Column Header Formatting
27. Table: Column Header Formatting
28. Table: Text Wrapping and Width Adjustment
29. Table: Text Wrapping and Width Adjustment
30. Auto Scaling for Numeric Columns at X-Axis
31. You can change it to ‘As Number’ to make all the unique values have their own bars.
32. When you assign Numeric column it will automatically ‘categorize (or bin)’ the values into 5 groups.
33. This auto-categorizing is convenient especially when you assign numeric columns with many unique values such as Income, Sales, etc.
34. Otherwise, you don’t see any patterns if each value has its own bar…
35. But the categorization doesn’t always work especially when the columns have only a few number of unique values.
36. Now, if the number of unique values is less than 10 it won’t automatically categorize.
37. • Snowflake • ODBC Data Source
38. Snowflake Database Support
39. Improvements for ODBC Data Source
40. • Improved Performance (in General) • Better Encoding Handling - Multi-byte characters • Easier Setup
41. Improvements for ODBC Data Source
42. Improvements for ODBC Data Source
43. Dashboard Now, you can adjust Height and Width! 🎉
44. Adjust the heights by dragging.
45. Adjust the width by dragging.
46. Dashboard And, you can add or delete Row easily! 🔥
48. One More Thing…
49. Stats Page Exploratory Server
50. With Exploratory Server, you can Share, Schedule, and Interact with all your insights - Data, Chart, Analytics, Dashboard, Notes, and Slides. Exploratory Server
51. 1. You can publish Data, Chart, Dashboard, Note, & Slides.
52. 2. You can Open them in browser and Share!
53. 3. You can find all your insights under My Insights page.
54. 3. You can find all your insights under My Insights page.
55. 4. You can schedule them to update the data automatically.
56. 5. You or others you’ve shared with can interact with Parameters.
57. 6. You can monitor them to see the number of views.
58. 6. You can monitor them to see the number of views.
59. • Instead of monitoring them one by one, can I see them all together? • How much of the allocated quota I have used so far this month? Problems
60. Stats Page - Monitor All Your Insights’ Performance
61. You can quickly access your Stats page.
62. Check how many views each of your insights is getting.
63. Check how many rows have been processed this month.
64. Q & A
65. Information Email kan@exploratory.io Website https://exploratory.io Twitter @ExploratoryData Seminar https://exploratory.io/online-seminar
66. EXPLORATORY 66