Prepare STREAMLINE v1.0.1 bug-fix and documentation release

[raptor419]

Summary

This PR prepares STREAMLINE v1.0.1 as a focused bug-fix and documentation update.

Fixes

• Fixed Phase 1 regression EDA so skewness and kurtosis calculations no longer crash on mixed-type, missing, infinite, or nonnumeric continuous outcome values.
• Fixed Phase 11 report task-type detection so explicit saved or CLI outcome_type values are respected before falling back to dataset inference.
• Fixed regression reports where low-cardinality continuous outcomes could be misidentified as multiclass based on ClassCounts.csv.
• Fixed regression report performance tables so both display-style metric names and snake_case metric keys are recognized.
• Fixed multiclass weighted composite feature-importance plots so the balanced-accuracy no-skill baseline uses 1 / number_of_classes instead of always 0.5.

Documentation

• Added a dedicated HPC and cluster-running documentation page covering:
  • Conda setup on clusters
  • tmux basics for long runs
  • SLURM and LSF monitoring commands
  • scheduler config fields
  • recovery/rerun guidance
• Added a UPenn/LSF HCC demo config template alongside the existing Cedars/SLURM template.
• Updated README, installation, running, parameter, and changelog docs to point to both HPC examples.

[raptor419]

Fixed Issues #9 and #10