InfoGuides: ProQuest TDM Studio: Part 2: Analyze Your Dataset

Part 2: Analyze Your Dataset

Change the toggle button to on to restart your environment when you are ready to begin analyzing your dataset in Jupyter Notebook. It may take up to ten minutes for your environment to be ready.
Click open Jupyter Notebook in the upper right hand corner of the workbench. A separate browser tab or window will open to your Jupyter Notebook.
Within the Jupyter Notebook you will have access to a few files and directories. Click the directory titled Getting Started. From here you can access the following:
1. ProQuest TDM Studio manuals
  1. This contains scripts on common XML tags, a content selection guide, export instructions, a TDM Studio manual, and upload instructions.
2. ProQuest TDM Studio samples
  1. Convert to dataframe
  2. Convert to dataframe multiprocessing
  3. Convert to dataframe PQDT
  4. Display document counts
  5. Document term matrix
  6. Keyword in context
  7. KWIC over time
  8. Top 10 entity recognition
3. ProQuest TDM Studio visualization samples
  1. Geographic analysis
  2. Sentiment analysis
  3. Topic modeling
4. Resources
5. README
You can use the ProQuest Studio samples or you can create and upload your own scripts. If you use the ProQuest Studio samples, make a copy of the sample file and then rename it with the name of your dataset at the end.