R worksheet to explore the data from the HDF5 file.

1 files changed, 19 insertions, 0 deletions

diff --git a/analysis/year.R b/analysis/year.R
new file mode 100644
index 0000000..85d3da1
--- a/dev/null
+++ b/analysis/year.R
@@ -0,0 +1,19 @@
+# Explore the qualities of the year feature.
+
+require(hdf5);
+
+hdf5load("/home/don/exp007/src/influenza.h5", tidy = TRUE);
+
+d <- influenza.aa.dat;
+
+# All records for 1918.  Based on code from
+# http://wiki.r-project.org/rwiki/doku.php?id=tips:data-frames:select_observations
+p1918 <- d[d$Year == 1918, ]
+
+# Countries represented in the 1918 dataset.
+p1918$Country;
+
+# All record with a year value.
+years <- d[d$Year != 0, ];
+
+hist(years$Year);