Systems and methods for summarizing and steering multi-user collaborative data analyses
Example implementations described herein are directed to a graphical user interface (GUI) tool that provides representations of generated charts on a map, wherein distances between representations are provided based on similarity between charts. Similarity is determined through machine learning techniques that are applied on a vectorized form of charts. Example implementations described herein encode charts into vectors using deep learning techniques, which facilitates machine learning techniques such as nearest neighbor to be utilized to determine similarity between charts based on their corresponding vectors.
1. A method for providing a graphical user interface (GUI) to generate recommended charts, the method comprising:
providing a first visualization of the GUI, the first visualization configured to provide representations of a plurality of data charts on a map, the representations of the plurality of data charts distributed within the map of the first visualization based on similarities derived from a encoded vectorization of the plurality of charts into a plurality of vectors;
upon selection of an area within the map on the first visualization, generating a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area;
displaying the generated data chart recommendation on a second visualization of the GUI; and
providing another representation of the generated data chart recommendation on the first visualization and within the selected area on the map based on similarity between the generated data chart recommendation and the plurality of data charts.
2. The method of claim 1 , wherein the encoded vectorization of the plurality of data charts into the plurality of vectors is conducted by a vectorization process trained by Grammar Variational Autoencoder (GVAE).
3. The method of claim 1 , wherein the representations of the plurality of data charts are distributed within the map on the first visualization as determined from a dimensionality reduction process configured to determine a distance between each of the representations of the plurality of data charts based on the similarity between the plurality of vectors.
4. The method of claim 1 , wherein the generating a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area comprises:
sampling a point within the selected area;
determining a vector corresponding to the point within the selected area;
conducting a vector decoding process configured to convert the vector into a decoded data chart; and
providing the decoded chart as the recommended data chart.
5. The method of claim 1 , further comprising:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, generating a third visualization comprising a text editor to edit source code that generates the data chart, and dropdown controls to modify the data chart.
6. The method of claim 1 , further comprising:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, conducting a vector decoding process configured to convert a vector from the plurality of vectors corresponding to the representation from the representations of the plurality of data charts into a chart and;
generating the data chart for display.
7. The method of claim 1 , wherein each data chart of the plurality of data charts comprising a graphical representation of data.
8. The method of claim 1 , wherein each of the representations is a circle glyph, wherein an inner circle color indicates an identity of a user who created the data chart and an outer part is indicative of data attributes used in the respective data chart.
9. A non-transitory computer readable medium storing instructions for providing a graphical user interface (GUI) to generate recommended charts, the instructions comprising:
providing a first visualization of the GUI, the first visualization configured to provide representations of a plurality of data charts on a map, the representations of the plurality of data charts distributed within the map of the first visualization based on similarities derived from a encoded vectorization of the plurality of charts into a plurality of vectors;
upon selection of an area within the map on the first visualization, generating a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area;
displaying the generated data chart recommendation on a second visualization of the GUI; and
providing another representation of the generated data chart recommendation on the first visualization and within the selected area on the map based on similarity between the generated data chart recommendation and the plurality of data charts.
10. The non-transitory computer readable medium of claim 9 , wherein the encoded vectorization of the plurality of data charts into the plurality of vectors is conducted by a vectorization process trained by Grammar Variational Autoencoder (GVAE).
11. The non-transitory computer readable medium of claim 9 , wherein the representations of the plurality of data charts are distributed within the map on the first visualization as determined from a dimensionality reduction process configured to determine a distance between each of the representations of the plurality of data charts based on the similarity between the plurality of vectors.
12. The non-transitory computer readable medium of claim 9 , wherein the generating a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area comprises:
sampling a point within the selected area;
determining a vector corresponding to the point within the selected area;
conducting a vector decoding process configured to convert the vector into a decoded data chart; and
providing the decoded chart as the recommended data chart.
13. The non-transitory computer readable medium of claim 9 , the instructions further comprising:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, generating a third visualization comprising a text editor to edit source code that generates the data chart, and dropdown controls to modify the data chart.
14. The non-transitory computer readable medium of claim 9 , the instructions further comprising:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, conducting a vector decoding process configured to convert a vector from the plurality of vectors corresponding to the representation from the representations of the plurality of data charts into a chart and;
generating the data chart for display.
15. An apparatus configured to provide a graphical user interface (GUI) to generate recommended charts, the apparatus comprising:
a processor, configured to:
provide a first visualization of the GUI, the first visualization configured to provide representations of a plurality of data charts on a map, the representations of the plurality of data charts distributed within the map of the first visualization based on similarities derived from a encoded vectorization of the plurality of charts into a plurality of vectors;
upon selection of an area within the map on the first visualization, generate a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area;
display the generated data chart recommendation on a second visualization of the GUI; and
provide another representation of the generated data chart recommendation on the first visualization and within the selected area on the map based on similarity between the generated data chart recommendation and the plurality of data charts.
16. The apparatus of claim 15 , wherein the encoded vectorization of the plurality of data charts into the plurality of vectors is conducted by a vectorization process trained by Grammar Variational Autoencoder (GVAE).
17. The apparatus of claim 15 , wherein the representations of the plurality of data charts are distributed within the map on the first visualization as determined from a dimensionality reduction process configured to determine a distance between each of the representations of the plurality of data charts based on the similarity between the plurality of vectors.
18. The apparatus of claim 15 , wherein the processor is configured to generate a recommended data chart derived from similarity between the selected area and one or more of the plurality of data charts within or in proximity to the selected area by:
sampling a point within the selected area;
determining a vector corresponding to the point within the selected area;
conducting a vector decoding process configured to convert the vector into a decoded data chart; and
providing the decoded chart as the recommended data chart.
19. The apparatus of claim 15 , the processor further configured to:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, generate a third visualization comprising a text editor to edit source code that generates the data chart, and dropdown controls to modify the data chart.
20. The apparatus of claim 15 , the processor further configured to:
for receiving a selection of a representation from the representations of the plurality of data charts distributed within the map on the first visualization, conduct a vector decoding process configured to convert a vector from the plurality of vectors corresponding to the representation from the representations of the plurality of data charts into a chart and;
generate the data chart for display.