added a last couple of notes for my future reference #2 #20 #19

dkoslicki · Mar 18, 2020 · f7bee92 · f7bee92
1 parent a49980f
commit f7bee92
Show file tree

Hide file tree

Showing 5 changed files with 4 additions and 4 deletions.
diff --git a/dataForShaopeng/test_issue/TrainingDatabase_k_61.h5 b/dataForShaopeng/test_issue/TrainingDatabase_k_61.h5
diff --git a/dataForShaopeng/test_issue/out_40_61_1.csv b/dataForShaopeng/test_issue/out_40_61_1.csv
@@ -1,3 +1,3 @@
 ,k=40,k=41,k=42,k=43,k=44,k=45,k=46,k=47,k=48,k=49,k=50,k=51,k=52,k=53,k=54,k=55,k=56,k=57,k=58,k=59,k=60,k=61
 taxid_1909294_104_genomic.fna.gz,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0
-taxid_1909294_109_genomic.fna.gz,0.677,0.585,0.576,0.576,0.566,0.56,0.556,0.555,0.551,0.552,0.543,0.537,0.533,0.528,0.523,0.519,0.518,0.515,0.504,0.501,0.497,0.493
+taxid_1909294_109_genomic.fna.gz,0.677,0.582,0.575,0.57,0.564,0.559,0.555,0.555,0.551,0.547,0.542,0.535,0.532,0.527,0.523,0.52,0.518,0.513,0.504,0.5,0.497,0.493
diff --git a/dataForShaopeng/test_issue/out_50_61_1.csv b/dataForShaopeng/test_issue/out_50_61_1.csv
@@ -1,3 +1,3 @@
 ,k=50,k=51,k=52,k=53,k=54,k=55,k=56,k=57,k=58,k=59,k=60,k=61
 taxid_1909294_104_genomic.fna.gz,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0
-taxid_1909294_109_genomic.fna.gz,0.589,0.536,0.532,0.527,0.525,0.522,0.518,0.515,0.504,0.501,0.497,0.493
+taxid_1909294_109_genomic.fna.gz,0.589,0.535,0.532,0.527,0.523,0.519,0.518,0.513,0.504,0.5,0.497,0.493
diff --git a/scripts/MakeStreamingDNADatabase.py b/scripts/MakeStreamingDNADatabase.py
@@ -88,7 +88,7 @@ def main():
 		print("Creating ternary search tree")
 	to_insert = set()
 	for i in range(len(genome_sketches)):
-		for kmer_index in range(len(genome_sketches[i]._kmers)):
+		for kmer_index in range(len(genome_sketches[i]._kmers)):  # FIXME: think about which suffix/prefixes to add here
 			kmer = genome_sketches[i]._kmers[kmer_index]
 			to_insert.add(kmer + 'x' + str(i) + 'x' + str(kmer_index))  # format here is kmer+x+hash_index+kmer_index
 			kmer = khmer.reverse_complement(genome_sketches[i]._kmers[kmer_index])

diff --git a/scripts/StreamingQueryDNADatabase.py b/scripts/StreamingQueryDNADatabase.py
@@ -163,7 +163,7 @@ def keyfunction(item):
 		try:
 			all_kmers_bf = WritingBloomFilter(len(sketches)*len(k_range)*num_hashes*10, 0.01)
 			for sketch in sketches:
-				for kmer in sketch._kmers:
+				for kmer in sketch._kmers:  # FIXME: think about what all actually needs to be added
 					for ksize in k_range:
 						all_kmers_bf.add(kmer[0:ksize])  # put all the k-mers and the appropriate suffixes in
 						all_kmers_bf.add(kmer[0:ksize][::-1])