diff options
| -rw-r--r-- | bibliography.bib | 134 | ||||
| -rw-r--r-- | software/chapter.tex | 49 |
2 files changed, 147 insertions, 36 deletions
diff --git a/bibliography.bib b/bibliography.bib index 9039484..9e5921c 100644 --- a/bibliography.bib +++ b/bibliography.bib @@ -107,6 +107,19 @@ month = {feb},
}
+@article{BarnesNick2010a,
+ author = {Nick Barnes},
+ title = {Publish your computer code: it is good enough},
+ journal = {Nature},
+ volume = 467,
+ number = 7317,
+ pages = {753--753},
+ year = 2010,
+ doi = {10.1038/467753a},
+ month = {oct},
+ publisher = {Springer Nature},
+}
+
@article{BesemannDanielM2004a,
author = {Besemann, Daniel M. and Meyer, Kent A. and Wright, John C.},
title = {{Spectroscopic Characteristics of Triply Vibrationally Enhanced Four-Wave Mixing
@@ -223,6 +236,12 @@ pmid = 15332970,
}
+@misc{CRAN,
+ note = {Accessed: 2018-04-04},
+ title = {The Comprehensive R Archive Network},
+ url = {https://cran.r-project.org/},
+}
+
@article{CardDavidN1986a,
author = {David N. Card and Victor E. Church and William W. Agresti},
title = {An empirical study of software design practices},
@@ -292,6 +311,14 @@ month = {jul},
}
+@phdthesis{CarlsonRogerJohn1988a,
+ author = {Roger John Carlson},
+ school = {University of Wisconsin-Madison},
+ title = {Quantitative Aspects of High Resolution, Fully Resonant, Four-Wave Mixing
+ Spectroscopy For the Analysis of Vibronic Mode Coupling in Molecules},
+ year = 1988,
+}
+
@inproceedings{CarverJeffreyC2007a,
author = {Jeffrey C. Carver and Richard P. Kendall and Susan E. Squires and Douglass E.
Post},
@@ -475,14 +502,6 @@ year = {1998} publisher = {American Chemical Society ({ACS})},
}
-@phdthesis{CarlsonRogerJohn1988a,
- author = {Roger John Carlson},
- school = {University of Wisconsin-Madison},
- title = {Quantitative Aspects of High Resolution, Fully Resonant, Four-Wave Mixing
- Spectroscopy For the Analysis of Vibronic Mode Coupling in Molecules},
- year = 1988,
-}
-
@phdthesis{DonaldsonPaulMurray2007a,
author = {Donaldson, Paul Murray},
school = {Imperial College London},
@@ -579,6 +598,12 @@ year = {1998} month = {may},
}
+@misc{FITS,
+ note = {Accessed: 2018-03-27},
+ title = {FITS: Flexable image transport},
+ url = {https://fits.gsfc.nasa.gov/},
+}
+
@article{FangHui2014a,
author = {H. Fang and C. Battaglia and C. Carraro and S. Nemsak and B.
Ozdol and J. S. Kang and H. A. Bechtel and S. B. Desai and F.
@@ -596,6 +621,12 @@ year = {1998} month = {apr},
}
+@misc{FileExchange,
+ note = {Accessed: 2018-04-04},
+ title = {File Exchange - MATLAB Central},
+ url = {https://www.mathworks.com/matlabcentral/fileexchange},
+}
+
@article{FlemingGrahmR1998a,
author = {Fleming, G. R. and Passino, S A and Nagasawa, Y.},
title = {{The interaction of solutes with their environments}},
@@ -612,6 +643,17 @@ year = {1998} month = {feb},
}
+@inproceedings{FolkMike2011a,
+ author = {Mike Folk and Gerd Heber and Quincey Koziol and Elena Pourmal and Dana Robinson},
+ title = {An overview of the {HDF}5 technology suite and its applications},
+ booktitle = {Proceedings of the {EDBT}/{ICDT} 2011 Workshop on Array Databases - {AD}
+ {\textquotesingle}11},
+ year = 2011,
+ doi = {10.1145/1966895.1966900},
+ publisher = {{ACM} Press},
+}
+
+
@article{FourkasJohnT1992a,
author = {Fourkas, John T. and Trebino, Rick and Fayer, M. D.},
title = {{The grating decomposition method: A new approach for understanding
@@ -659,7 +701,6 @@ year = {1998} pmid = 18832166,
}
-
@article{FurutaKoichi2012a,
author = {Furuta, Koichi and Fuyuki, Masanori and Wada, Akihide},
title = {Cross-Term Selective, Two-Pulse Correlation Measurements by Phase-Shifted
@@ -733,6 +774,12 @@ year = {1998} pmid = 19449854,
}
+@misc{GitHub,
+ note = {Accessed: 2018-04-04},
+ title = {The world's leading software development platform ยท GitHub},
+ url = {https://github.com/},
+}
+
@article{GriffinGrahamB2013a,
author = {Graham B. Griffin and Sandrine Ithurria and Dmitriy S. Dolzhnikov and Alexander
Linkin and Dmitri V. Talapin and Gregory S. Engel},
@@ -839,7 +886,6 @@ year = {1998} journal = {Science},
doi = {10.1126/science.37.955.610},
}
-
@article{HyblJohnD2001a,
author = {Hybl, John D. and {Albrecht Ferro}, Allison and Jonas, David M.},
title = {{Two-dimensional Fourier transform electronic spectroscopy}},
@@ -891,6 +937,7 @@ year = {1998} month = {apr},
pmid = 19745871,
}
+
@book{KahnemanDaniel2013a,
author = {Kahneman, Daniel},
title = {Thinking, Fast and Slow},
@@ -1301,6 +1348,13 @@ year = {1998} month = {dec},
}
+@book{OliphantTravisE2006a,
+ author = {Travis E Oliphant},
+ title = {A guide to NumPy},
+ year = 2006,
+ publisher = {Trelgol Publishing},
+}
+
@article{OliphantTravisE2007a,
author = {Oliphant, Travis E.},
title = {{Python for Scientific Computing}},
@@ -1517,6 +1571,18 @@ year = {1998} publisher = {{ACM} Press},
}
+@misc{PyPI,
+ note = {Accessed: 2018-04-04},
+ title = {PyPI - the Python Package Index},
+ url = {https://pypi.org/},
+}
+
+@misc{PythonProfilers,
+ note = {Accessed: 2018-04-04},
+ title = {The Python Profilers (Python 3.5)},
+ url = {https://docs.python.org/3.5/library/profile.html},
+}
+
@misc{QMutex,
note = {Accessed: 2018-03-27},
title = {QMutex Class.},
@@ -1620,6 +1686,13 @@ year = {1998} month = {mar},
}
+@Misc{SciPy,
+ author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
+ note = {Accessed: 2018-04-04},
+ title = {{SciPy}: Open source scientific tools for {Python}},
+ url = {http://www.scipy.org/},
+}
+
@inproceedings{SeamanCarolynB1997a,
author = {Carolyn B. Seaman and Victor R. Basili},
title = {An empirical study of communication in code inspections},
@@ -1650,6 +1723,12 @@ year = {1998} doi = {10.1007/s10664-005-3865-y},
}
+@misc{SemanticVersioning,
+ note = {Accessed: 2018-04-04},
+ title = {Semantic Versioning},
+ url = {https://semver.org/},
+}
+
@article{ShanmugamMariyappan2012a,
author = {Mariyappan Shanmugam and Chris A. Durcan and Bin Yu},
title = {Layered semiconductor molybdenum disulfide nanomembrane based Schottky-barrier
@@ -1690,6 +1769,12 @@ year = {1998} month = {feb},
}
+@misc{SnakeViz,
+ note = {Accessed: 2018-04-04},
+ title = {SnakeViz},
+ url = {https://jiffyclub.github.io/snakeviz/},
+}
+
@article{SpectorIvanC2015a,
author = {Spector, Ivan C. and Olson, Courtney M. and Huber, Christopher J. and Massari, Aaron M.},
title = {Simple fully reflective method of scatter reduction in 2D-IR spectroscopy},
@@ -1904,6 +1989,17 @@ year = {1998} month = jun,
}
+@article{WickhamHadley2014a,
+ author = {Hadley Wickham},
+ title = {Tidy data},
+ journal = {Journal of Statistical Software},
+ volume = 59,
+ number = 10,
+ pages = {1--23},
+ year = 2014,
+ publisher = {Foundation for Open Access Statistics},
+}
+
@article{WilsonGreg2017a,
author = {Greg Wilson and Jennifer Bryan and Karen Cranston and Justin Kitzes and Lex
Nederbragt and Tracy K. Teal},
@@ -1948,6 +2044,7 @@ year = {1998} month = {oct},
}
+
@article{WrightJohnCurtis1997a,
author = {Wright, John C.},
title = {{New selective nonlinear vibrational spectroscopies}},
@@ -2072,7 +2169,6 @@ year = {1998} month = {nov},
}
-
@article{ZanniMartinT2001a,
author = {Zanni, Martin T and Asplund, Matthew C and Hochstrasser, Robin M},
title = {{Two-dimensional heterodyned and stimulated infrared photon echoes of
@@ -2137,6 +2233,19 @@ year = {1998} publisher = {Wiley-Blackwell},
}
+@misc{git.chem.wisc.edu,
+ note = {Accessed: 2018-04-04},
+ title = {GitLab (University of Wisconsin-Madison Chemistry},
+ url = {https://git.chem.wisc.edu/},
+}
+
+@misc{h5py,
+ note = {Accessed: 2018-04-04},
+ title = {h5py: HDF5 for Python},
+ url = {https://www.h5py.org/},
+}
+
+
@misc{h5py.Group,
note = {Accessed: 2018-03-25},
title = {h5py Groups documentation.},
@@ -2147,4 +2256,5 @@ year = {1998} note = {Accessed: 2018-03-27},
title = {PyQtGraph: Scientific Graphics and GUI Library for Python},
url = {http://pyqtgraph.org/},
-}
\ No newline at end of file +}
+
diff --git a/software/chapter.tex b/software/chapter.tex index 0027c5f..b52764b 100644 --- a/software/chapter.tex +++ b/software/chapter.tex @@ -1,5 +1,4 @@ % TODO: add StoddenVictoria2016a (Enhancing reproducibility for computational methods)
-% TODO: http://pubs.acs.org/doi/10.1021/cen-09535-scitech2
\chapter{Software}
@@ -146,11 +145,11 @@ parallelization paradigms'' \section{Good-enough practices} % ================================================================
In their [...] perspective, ``Good enough practices in scientific computing'', (from which this
-section gets its name) [WILSON ET AL] describe a set of techniques that, in their words, ``every
-researcher can and should consider adopting''. %
+section gets its name) \textcite{WilsonGreg2017a} describe a set of techniques that, in their
+words, ``every researcher can and should consider adopting''. %
In this section, I attempt to very quickly summarize my personal perspective on what makes good
software development good---with citations to literature that supports each idea. %
-These practices are not, generally, ``extra work''. %
+These practices are not, generally, \emph{extra work}. %
In fact, many of them save massive amounts of time and effort in the long \emph{and} short run,
when properly applied. %
@@ -158,8 +157,8 @@ when properly applied. % Before you sit down and implement a piece of software, stop! %
First you should try hard to find a library that already has what you need. %
You'll often surprise yourself with what you can find. %
-Search the package repository for your language, such as PyPI [CITE], MATLAB File Exchange [CITE]
-or CRAN [CITE]. %
+Search the package repository for your language, such as PyPI \cite{PyPI}, MATLAB File Exchange
+\cite{FileExchange} or CRAN \cite{CRAN}. %
Even if there is not a full solution to your problem out there, there is almost certainly a
solution to some part of it. %
Much better to have a dependency than a custom implementation. %
@@ -177,8 +176,8 @@ As a general rule, once you have two classes you need multiple files. % Choose a non-proprietary format if at all possible---remember: you yourself might not have access
to the proprietary software in 10 years. %
Choose plain text if you can. %
-Consider conforming to specifications, such as Tidy Data. [CITE] %
-If you must, use open binary formats such as HDF5. %
+Consider conforming to specifications, such as Tidy Data \cite{WickhamHadley2014a}. %
+If you must, use open binary formats such as HDF5 \cite{FolkMike2011a}. %
Put as much metadata as you can into the file. %
Any piece of metadata that can automatically be added by the computer is essentially free---you
might as well do it. %
@@ -196,12 +195,13 @@ This is indispensable when trying to diagnose software problems. % In order to use version control as effectively as possible, try to save the package after every
change (feature addition, bugfix, etc). %
Typically version control is coupled with uploading to a remote server, for example using git with
-GitHub [CITE] or git.chem.wisc.edu [CITE], but version control need not be synonymous with
-uploading and distribution. %
+GitHub \cite{GitHub} or git.chem.wisc.edu \cite{git.chem.wisc.edu}, but version control need not be
+synonymous with uploading and distribution. %
Tools like git have a lot of fantastic features beyond simply saving [CITE], but those are beyond the
scope of these ``good enough'' recommendations. %
Also consider defining a version for the software package as a whole. %
-Use semantic versioning [CITE], unless there is a strong reason not to. %
+Use semantic versioning (MAJOR.MINOR.PATCH) \cite{SemanticVersioning}, unless there is a strong
+reason not to. %
If the language you are using has a convention for representing the version programmatically, such
as a \python{__version__} attribute in Python, comply with that convention. %
@@ -220,7 +220,7 @@ unless your project becomes very important. % Distribute test datasets, when appropriate. %
Remember, your tests can serve double duty as simple minimal examples. %
-\textbf{Collaborate and share.} \cite{WilsonGreg2017a} %
+\textbf{Collaborate and share.} \cite{WilsonGreg2017a, BarnesNick2010a} %
If you are part of a team, consider sharing software and collaborating to create it. %
Try using practices like code review and issue tracking, but don't feel obligated to use them if it
doesn't make sense for your project. %
@@ -228,7 +228,7 @@ When working as part of a team, making incremental changes and using version con more important. %
Earlier we mentioned ``do not reinvent''. %
The other side of that coin is ``if you make something, consider sharing it''. %
-Put your software on an open platform, like GitHub, and mint a DOI. %
+Put your software on an open platform, like GitHub \cite{GitHub}, and mint a DOI. %
Cite your software, and ask other people who are using your software to do the same. %
Choose a license early, and choose permissive and commercially compatible unless you 1. know what
you are doing and 2. plan to enforce. %
@@ -245,9 +245,11 @@ Try to follow the recommended style for your language, but don't obsess about it Don't get pulled into the trap of trying to make things perfect the first time. %
Software design is typically a very iterative process, and for good reason. %
Write first, and if it works, consider optimization. %
-If you do need to make your software faster, use profiling tools like cProfile [CITE] and SnakeVis
-[CITE] to empirically determine what operations are taking the longest, rather than trying to guess
-or use intuition. %
+If you do need to make your software faster, use profiling tools like cProfile
+\cite{PythonProfilers} and SnakeViz \cite{SnakeViz} to empirically determine what operations are
+taking the longest, rather than trying to guess or use intuition. %
+Only optimize speed-limiting operations, and stop optimizing once the code runs as quickly as
+needed. %
\section{Object oriented programming} % ----------------------------------------------------------
@@ -364,17 +366,15 @@ Certain metadata conventions were also introduced, including named dimensions. NetCDF remains popular in the aerospace and
The Flexable Image Transform System (FITS) is a similar format with a focus on visualization and
-backwards compatibility. \cite{WellsDC1981a} %
-% CITE https://fits.gsfc.nasa.gov/
-% CONSIDER CITING https://fits.gsfc.nasa.gov/rfc4047.txt
+backwards compatibility. \cite{FITS, WellsDC1981a} %
Fits is still popular in the astronomy community. %
Today, these hierarchical data formats have gathered under the umbrella of the HDF5 format, built
-and maintained by the HDF Group. [CITE] %
+and maintained by the HDF Group. \cite{FolkMike2011a} %
This format has all of the advantages of FITS, CDF, and NetCDF. %
It can support arbitrary datatypes and is optimized to quickly process large and complex
datasets. %
-In Python, HDF5 is supported primarily through the h5py package. [CITE] %
+In Python, HDF5 is supported primarily through the h5py package. \cite{h5py} %
\section{Scientific Python} % --------------------------------------------------------------------
@@ -383,7 +383,8 @@ SciPy is a collection of ``open-source software for mathematics, science, and eg SciPy was an absolute essential component of this dissertation and the work it describes. %
There are packages under the SciPy umbrella. %
NumPy is a very powerful and fast package for working with multidimensional arrays.
-\cite{vanderWaltStefan2011a} %
+\cite{OliphantTravisE2006a} %
The SciPy library contains a vast number of scientific computing tools, including many mathematical
-operations that this work depends on. [CITE] %
-Matplotlib is a beautiful visualization package for 1, 2, and 3D plotting. [CITE] %
+operations that this work depends on. \cite{SciPy} %
+Matplotlib is a beautiful visualization package for 1, 2, and 3D plotting.
+\cite{HunterJohnD2007a} %
|