yup yup, remove the BF, and while the performance is terrible wrt tim…

…e, the results are accurate. #2 and #20

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,0.581,0.578,0.181,0.177,0.174,0.172,0.17,0.169,0.168,0.167,0.166,0.165,0.164,0.162,0.161,0.159,0.159,0.159,0.154,0.152,0.151,0.15
+taxid_1909294_109_genomic.fna.gz,0.581,0.578,0.576,0.57,0.565,0.561,0.555,0.55,0.545,0.541,0.535,0.532,0.529,0.525,0.522,0.517,0.514,0.512,0.502,0.5,0.496,0.493

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,0.535,0.532,0.166,0.162,0.161,0.159,0.159,0.159,0.154,0.152,0.151,0.15
+taxid_1909294_109_genomic.fna.gz,0.535,0.532,0.529,0.525,0.522,0.517,0.514,0.512,0.502,0.5,0.496,0.493

scripts/StreamingQueryDNADatabase.py

@@ -239,7 +239,8 @@ def process_seq(self, seq):
 				if possible_match:
 					for other_k_size in [x for x in k_range[1:] if i+x <= len(seq)]:
 						kmer = seq[i:i + other_k_size]
-						if kmer in all_kmers_bf:
+						#if kmer in all_kmers_bf:
+						if True:
 							k_size_loc = k_range.index(other_k_size)
 							match_list, saw_match = self.return_matches(kmer, k_size_loc)
 							if saw_match: