🔭👽📡 Volker

Work

  • 2017 ~ Research Scientist (AI/ML/DS) at SINTEF
  • 2016 ~ (Scientific) Software Engineer at S[&]T
  • 2011 ~ PhD/PostDoc (Astrophysics) at CTAC

Papers

Posters

Talks

  • Apr 2019 ~ The Electric Weather Forecast [N/A]
  • Apr 2019 ~ Explainable AI [PDF]
  • Feb 2019 ~ Shapley Additive Explanations [PDF]
  • Feb 2019 ~ Weather Related Power Outages [PDF] [Video]

Notebooks

Hyperlinks & Contact

Not Tweets

[feed]
  • #

    Quick benchmark on how to read/write/store your Pandas dataframe if you don’t want to read from CSV all the time. Conclusion:

    1. Parquet gives smallest files
    2. Feather has fastest read
    3. HDF5 (no PyTables) has fastest write
    4. Benchmark suspect. Feather throughput exceeds RAID bandwidth.

    Figures:

  • #

    hello, world!