22 files changed, 181 insertions, 71 deletions

diff --git a/analysis/year.R b/analysis/year.R
index b7da3c8..6d68925 100644
--- a/analysis/year.R
+++ b/analysis/year.R
@@ -5,21 +5,23 @@ require(hdf5);
 hdf5load("/home/don/exp007/src/influenza.h5", tidy = TRUE);
 
 A <- influenza.aa.dat;
-
 B <- influenza.faa;
 
+# Join the two tables by GB value.
+C <- merge (A, B, by.x = "GenBank accession number", by.y = "GB");
+
 # All records for 1918.  Based on code from
 # http://wiki.r-project.org/rwiki/doku.php?id=tips:data-frames:select_observations
-C <- A[A$Year == 1918, ]
+D <- C[C$Year == 1918, ]
 
-# Countries represented in the 1918 dataset.
-C$Country;
+summary (D);
 
-# All record with a year value.
-D <- A[A$Year != 0, ];
+# Countries represented in the 1918 dataset.
+D$Country;
 
-hist(D$Year);
+D[D$"Protein Type" == "HA", ]
 
-B[B$GI == 305182, ]
+# All record with a year value.
+E <- A[A$Year != 0, ];
 
-B[B$"Protein Type" == "HA", ]
+hist(E$Year);