Fix up sandbox scripts

sandbox/correct-reads.py

@@ -54,6 +54,7 @@
 import screed
 import khmer
 
+from khmer import Countgraph
 from khmer.khmer_args import (build_counting_args, info, add_loadgraph_args,
                               report_on_config, sanitize_help,
                               calculate_graphsize, create_countgraph)
@@ -171,7 +172,7 @@ def main():
 
     if args.loadgraph:
         print('loading k-mer countgraph from', args.loadgraph, file=sys.stderr)
-        ct = khmer.load_countgraph(args.loadgraph)
+        ct = Countgraph.load(args.loadgraph)
     else:
         print('making k-mer countgraph', file=sys.stderr)
         ct = create_countgraph(args, multiplier=8 / (9. + 0.3))

sandbox/count-kmers-single.py

@@ -84,8 +84,8 @@ def main():
 
     kmer_size = countgraph.ksize()
     hashsizes = countgraph.hashsizes()
-    tracking = khmer._Nodegraph(  # pylint: disable=protected-access
-        kmer_size, hashsizes)
+    tracking = khmer.Nodegraph(  # pylint: disable=protected-access
+        kmer_size, 1, 1, primes=hashsizes)
 
     print ('kmer_size: %s' % countgraph.ksize(), file=sys.stderr)
     print ('k-mer countgraph sizes: %s' % (countgraph.hashsizes(),),

sandbox/count-kmers.py

@@ -48,6 +48,7 @@
 import argparse
 import screed
 import csv
+from khmer import Countgraph
 from khmer.khmer_args import info
 
 
@@ -76,13 +77,13 @@ def main():
 
     print ('hashtable from', args.input_count_graph_filename,
            file=sys.stderr)
-    countgraph = khmer.load_countgraph(
+    countgraph = Countgraph.load(
         args.input_count_graph_filename)
 
     kmer_size = countgraph.ksize()
     hashsizes = countgraph.hashsizes()
-    tracking = khmer._Nodegraph(  # pylint: disable=protected-access
-        kmer_size, hashsizes)
+    tracking = khmer.Nodegraph(  # pylint: disable=protected-access
+        kmer_size, 1, 1, primes=hashsizes)
 
     if args.output_file is None:
         args.output_file = sys.stdout

sandbox/error-correct-pass2.py

@@ -46,6 +46,7 @@
 import os
 import screed
 import khmer
+from khmer import Countgraph
 from khmer import khmer_args
 from khmer.khmer_args import FileType as khFileType
 
@@ -87,7 +88,7 @@ def main():
     args = parser.parse_args()
 
     print('loading counts')
-    ht = khmer.load_countgraph(args.counts_table)
+    ht = Countgraph.load(args.counts_table)
 
     aligner = khmer.ReadAligner(ht,
                                 args.trusted_cov,

sandbox/extract-compact-dbg.py

@@ -53,7 +53,7 @@ def add_adjacency(self, node_id, adj):
 
 def traverse_and_mark_linear_paths(graph, nk, stop_bf, pathy, degree_nodes):
     size, conns, visited = graph.traverse_linear_path(nk, degree_nodes,
-                                                      stop_bf)
+                                                      stop_filter=stop_bf)
     if not size:
         return
 
@@ -86,6 +86,7 @@ def main():
     # if memory is a problem.
 
     graph = khmer.Nodegraph(args.ksize, args.tablesize, 2)
+    print(graph.ksize(), graph.hashsizes())
     stop_bf = khmer.Nodegraph(args.ksize, args.tablesize, 2)
     stop_bf2 = khmer.Nodegraph(args.ksize, args.tablesize, 2)
     n = 0

sandbox/sweep-reads.py

@@ -67,6 +67,7 @@
 import os
 import time
 import khmer
+from khmer import GraphLabels
 from khmer.khmer_args import (build_nodegraph_args, report_on_config, info,
                               sanitize_help)
 from khmer.kfile import (check_input_files, check_valid_file_exists,
@@ -78,7 +79,7 @@
 DEFAULT_MAX_READS = 1000000
 DEFAULT_BUFFER_SIZE = 10
 DEFAULT_OUT_PREF = 'reads'
-DEFAULT_RANGE = -1
+DEFAULT_RANGE = None
 
 MAX_HSIZE = 4e7
 MIN_KSIZE = 21
@@ -283,7 +284,7 @@ def main():
         max_buffers, max_reads, buf_size, output_pref, outdir, extension)
 
     # consume the partitioned fasta with which to label the graph
-    ht = khmer.GraphLabels(K, HT_SIZE, N_HT)
+    ht = GraphLabels.NodeGraphLabels(K, HT_SIZE, N_HT)
     try:
         print('consuming input sequences...', file=sys.stderr)
         if args.label_by_pid:
@@ -331,8 +332,8 @@ def main():
 
     print('done consuming input sequence. \
                         added {t} tags and {l} \
-                        labels...'.format(t=ht.graph.n_tags(),
-                                          l=ht.n_labels()))
+                        labels...'.format(t=ht.graph.n_tags,
+                                          l=ht.n_labels))
 
     label_dict = defaultdict(int)
     label_number_dist = []
@@ -369,7 +370,8 @@ def main():
                 seq = record.sequence
                 name = record.name
                 try:
-                    labels = ht.sweep_label_neighborhood(seq, traversal_range)
+                    labels = list(ht.sweep_label_neighborhood(seq,
+                                                              traversal_range))
                 except ValueError as e:
                     pass
                 else:

tests/test_sandbox_scripts.py

@@ -333,7 +333,7 @@ def test_multirename_fasta():
 def test_extract_compact_dbg_1():
     infile = utils.get_test_data('simple-genome.fa')
     outfile = utils.get_temp_filename('out.gml')
-    args = ['-x', '1e4', '-o', outfile, infile]
+    args = ['-x', '1e5', '-o', outfile, infile]
     _, out, err = utils.runscript('extract-compact-dbg.py', args, sandbox=True)
 
     print(out)