Data analysis is a complex process with frequent shifts among data formats and models, and among textual and graphical media. We are investigating how to better support the lifecycle of analysis by identifying critical bottlenecks and developing new methods at the intersection of data visualization, machine learning, and computer systems. Can we empower users to transform and clean data without programming? How can we support more expressive and effective visualization tools? How might we enable domain experts to guide machine learning methods to produce effective models? This talk will present selected projects that attempt to address these challenges and introduce new tools for interactive visual analysis.