bscampp 1.0.1a0__py3-none-any.whl → 1.0.1b0__py3-none-any.whl

bscampp/__init__.py

@@ -12,7 +12,7 @@ import logging, os
 # not really needed for BSCAMPP but safe to update here
 os.sys.setrecursionlimit(1000000)
 
-__version__ = "1.0.1a"
+__version__ = "1.0.1b"
 _INSTALL_PATH = __path__[0]
 
 # global variables to store all loggers

bscampp/functions.py

@@ -15,10 +15,13 @@ Function to read in the placement tree and alignment.
 If query alignment is provided, will use the provided query instead of
 the ones (potentially) included in the reference alignment
 '''
-def readData(workdir):
+def readData(workdir, dry_run=False):
     t0 = time.perf_counter()
     _LOG.info('Reading in input data...')
 
+    if dry_run:
+        return None, dict(), '', dict(), '', dict()
+
     # (1) load reference tree
     tree = treeswift.read_tree_newick(Configs.tree_path)
     tree.resolve_polytomies()
@@ -45,10 +48,10 @@ def readData(workdir):
         # after separating queries from the reference alignment, write
         # them to to TEMP/
         qaln_path = os.path.join(workdir, 'qaln.fa')
-        write_fasta(temp_qaln_path, q_dict)
+        write_fasta(qaln_path, q_dict)
         
         aln_path = os.path.join(workdir, 'aln.fa')
-        write_fasta(temp_aln_path, ref_dict)
+        write_fasta(aln_path, ref_dict)
 
     t1 = time.perf_counter()
     _LOG.info('Time to read in input data: {} seconds'.format(t1 - t0))
@@ -58,19 +61,22 @@ def readData(workdir):
 Function to get the closest leaf for each query sequence based on Hamming
 distance
 '''
-def getClosestLeaves(aln_path, qaln_path, aln, qaln, workdir):
+def getClosestLeaves(aln_path, qaln_path, aln, qaln, workdir, dry_run=False):
     t0 = time.perf_counter()
     _LOG.info('Computing closest leaves for query sequences...')
+
+    if dry_run:
+        return dict(), dict()
+
     query_votes_dict = dict()
     query_top_vote_dict = dict()
-    
     tmp_output = os.path.join(workdir, 'closest.txt') 
 
     cmd = []
     if Configs.similarityflag:
         cmd.append(os.path.join(Configs.hamming_distance_dir, 'homology'))
     else:
-        if fragment_flag == False:
+        if Configs.fragmentflag == False:
             cmd.append(os.path.join(Configs.hamming_distance_dir, 'hamming'))
         else: 
             cmd.append(os.path.join(
@@ -115,10 +121,13 @@ def getClosestLeaves(aln_path, qaln_path, aln, qaln, workdir):
 Function to assign queries to subtrees based on their votes
 '''
 def assignQueriesToSubtrees(query_votes_dict, query_top_vote_dict,
-        tree, leaf_dict):
+        tree, leaf_dict, dry_run=False):
     t0 = time.perf_counter()
     _LOG.info('Adding query votes to the placement tree...')
 
+    if dry_run:
+        return dict(), []
+
     # (1) go over the query votes and add them to corresponding leaves
     lf_votes = Counter()
     leaf_queries = dict()
@@ -229,10 +238,13 @@ def placeOneSubtree():
 Function to perform placement of queries for each subtree
 '''
 def placeQueriesToSubtrees(tree, leaf_dict, new_subtree_dict, placed_query_list,
-        aln, qaln, cmdline_args, workdir, pool, lock):
+        aln, qaln, cmdline_args, workdir, pool, lock, dry_run=False):
     t0 = time.perf_counter()
     _LOG.info('Performing placement on each subtree...')
 
+    if dry_run:
+        return dict()
+
     # prepare to write an aggregated results to local
     jplace = dict()
     utils.add_edge_nbrs(tree)
@@ -381,9 +393,12 @@ def placeQueriesToSubtrees(tree, leaf_dict, new_subtree_dict, placed_query_list,
 '''
 Function to write a given jplace object to local output
 '''
-def writeOutputJplace(output_jplace):
+def writeOutputJplace(output_jplace, dry_run=False):
     t0 = time.perf_counter()
     _LOG.info('Writing aggregated placements to local...')
+    
+    if dry_run:
+        return
 
     outpath = os.path.join(Configs.outdir, Configs.outname)
     outf = open(outpath, 'w')

bscampp/pipeline.py

@@ -22,8 +22,13 @@ def bscampp_pipeline(*args, **kwargs):
     t0 = time.perf_counter()
     m = Manager(); lock = m.Lock()
 
+    # set up a dry run if specified
+    dry_run = False
+    if 'dry_run' in kwargs and isinstance(kwargs['dry_run'], bool):
+        dry_run = kwargs['dry_run']
+
     # parse command line arguments and build configurations
-    parser, cmdline_args = parseArguments()
+    parser, cmdline_args = parseArguments(dry_run=dry_run)
 
     # initialize multiprocessing (if needed)
     _LOG.warning('Initializing ProcessPoolExecutor...')
@@ -31,33 +36,39 @@ def bscampp_pipeline(*args, **kwargs):
             initargs=(parser, cmdline_args,))
 
     # (0) temporary files wrote to here
-    workdir = os.path.join(Configs.outdir, f'tmp{Configs.tmpfilenbr}')
-    try:
-        if not os.path.isdir(workdir):
-            os.makedirs(workdir)
-    except OSError:
-        log_exception(_LOG)
+    if not dry_run:
+        workdir = os.path.join(Configs.outdir, f'tmp{Configs.tmpfilenbr}')
+        try:
+            if not os.path.isdir(workdir):
+                os.makedirs(workdir)
+        except OSError:
+            log_exception(_LOG)
+    else:
+        workdir = os.getcwd()
 
     # (1) read in tree, alignment, and separate reference sequences from
     # query sequences
-    tree, leaf_dict, aln_path, aln, qaln_path, qaln = readData(workdir)
+    tree, leaf_dict, aln_path, aln, qaln_path, qaln = readData(workdir,
+            dry_run=dry_run)
 
     # (2) compute closest leaves for all query sequences
     query_votes_dict, query_top_vote_dict = getClosestLeaves(
-            aln_path, qaln_path, aln, qaln, workdir)
+            aln_path, qaln_path, aln, qaln, workdir, dry_run=dry_run)
 
     # (3) first assign all queries to their closest-leaf subtrees,
     # then do reassignment to minimize distance between each's top vote
     # and the subtree's seed leaf
     new_subtree_dict, placed_query_list = assignQueriesToSubtrees(
-            query_votes_dict, query_top_vote_dict, tree, leaf_dict)
+            query_votes_dict, query_top_vote_dict, tree, leaf_dict,
+            dry_run=dry_run)
 
     # (4) perform placement for each subtree
     output_jplace = placeQueriesToSubtrees(tree, leaf_dict, new_subtree_dict,
-            placed_query_list, aln, qaln, cmdline_args, workdir, pool, lock)
+            placed_query_list, aln, qaln, cmdline_args, workdir, pool, lock,
+            dry_run=dry_run)
 
     # (5) write the output jplace to local
-    writeOutputJplace(output_jplace)
+    writeOutputJplace(output_jplace, dry_run=dry_run)
 
     # shutdown pool
     _LOG.warning('Shutting down ProcessPoolExecutor...')
@@ -73,6 +84,11 @@ def bscampp_pipeline(*args, **kwargs):
     send = time.perf_counter()
     _LOG.info('BSCAMPP completed in {} seconds...'.format(send - t0))
 
+    if dry_run:
+        return True
+    else:
+        return False
+
 def clean_temp_files():
     # all temporary files/directories to remove
     temp_items = [f'tmp{Configs.tmpfilenbr}']
@@ -86,10 +102,15 @@ def clean_temp_files():
             continue
         _LOG.info(f'- Removed {temp}')
 
-def parseArguments():
+def parseArguments(dry_run=False):
     global _root_dir, main_config_path
+
     parser = _init_parser()
     cmdline_args = sys.argv[1:]
+
+    if dry_run:
+        cmdline_args = ['-i', 'dummy.info', '-t', 'dummy.tre',
+                '-a', 'dummy.fa'] 
     
     # build config
     buildConfigs(parser, cmdline_args)

bscampp/utils.py

@@ -8,6 +8,7 @@ from os.path import expanduser,isfile
 import random
 import statistics
 import copy
+import gzip
 
 import argparse
 # reformat argparse help text formatting
@@ -813,25 +814,25 @@ def newick_edge_tokens_node(node):
             node_to_str[node] = ''.join(out)
     return node_to_str[node]
 
-def write_tree_newick_edge_tokens(tree, filename, hide_rooted_prefix=False):
-    '''
-    Modified from treeswift tree.write_tree_newick()
-    Write this ``Tree`` to a Newick file
-       Args:
-        ``filename`` (``str``): Path to desired output file (plain-text or gzipped)
-    '''
-    if not isinstance(filename, str):
-        raise TypeError("filename must be a str")
-    treestr = newick_edge_nbr_string(tree)
-    if hide_rooted_prefix:
-        if treestr.startswith('[&R]'):
-            treestr = treestr[4:].strip()
-    else:
-        warn("Specified hide_rooted_prefix, but tree was not rooted")
-    if filename.lower().endswith('.gz'): # gzipped file
-        f = gopen(expanduser(filename),'wb',9); f.write(treestr.encode()); f.close()
-    else: # plain-text file
-        f = open(expanduser(filename),'w'); f.write(treestr); f.close()
+#def write_tree_newick_edge_tokens(tree, filename, hide_rooted_prefix=False):
+#    '''
+#    Modified from treeswift tree.write_tree_newick()
+#    Write this ``Tree`` to a Newick file
+#       Args:
+#        ``filename`` (``str``): Path to desired output file (plain-text or gzipped)
+#    '''
+#    if not isinstance(filename, str):
+#        raise TypeError("filename must be a str")
+#    treestr = newick_edge_nbr_string(tree)
+#    if hide_rooted_prefix:
+#        if treestr.startswith('[&R]'):
+#            treestr = treestr[4:].strip()
+#    else:
+#        warn("Specified hide_rooted_prefix, but tree was not rooted")
+#    if filename.lower().endswith('.gz'): # gzipped file
+#        f = gopen(expanduser(filename),'wb',9); f.write(treestr.encode()); f.close()
+#    else: # plain-text file
+#        f = open(expanduser(filename),'w'); f.write(treestr); f.close()
 
 def read_tree_newick_edge_tokens(newick):
     '''
@@ -850,7 +851,7 @@ def read_tree_newick_edge_tokens(newick):
         except:
             raise TypeError("newick must be a str")
     if newick.lower().endswith('.gz'): # gzipped file
-        f = gopen(expanduser(newick)); ts = f.read().decode().strip(); f.close()
+        f = gzip.open(expanduser(newick)); ts = f.read().decode().strip(); f.close()
     elif isfile(expanduser(newick)): # plain-text file
         f = open(expanduser(newick)); ts = f.read().strip(); f.close()
     else:
@@ -867,7 +868,7 @@ def read_tree_newick_edge_tokens(newick):
             # end of Newick string
             if ts[i] == ';':
                 if i != len(ts)-1 or n != t.root:
-                    raise RuntimeError(INVALID_NEWICK)
+                    raise RuntimeError("INVALID NEWICK")
 
             # go to new child
             elif ts[i] == '(':

{bscampp-1.0.1a0.dist-info → bscampp-1.0.1b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: bscampp
-Version: 1.0.1a0
+Version: 1.0.1b0
 Summary: BSCAMPP - A Scalable Phylogenetic Placement Tool
 Author-email: Eleanor Wedell <ewedell2@illinois.edu>, Chengze Shen <chengze5@illinois.edu>
 License: MIT License
@@ -51,6 +51,11 @@ Requires-Dist: treeswift>=1.1.45
 Requires-Dist: taxtastic>=0.9.3
 
 # BSCAMPP - A Scalable Phylogenetic Placement Method and Framework
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/bscampp)](https://pypi.org/project/bscampp/)
+[![PyPI - Version](https://img.shields.io/pypi/v/bscampp?color=blue)](https://pypi.org/project/bscampp/#history)
+[![Build Status](https://img.shields.io/github/actions/workflow/status/ewedell/BSCAMPP/python-package.yml?branch=main&label=build)](https://github.com/ewedell/BSCAMPP/)
+[![PyPI - License](https://img.shields.io/pypi/l/bscampp?color=blue)](https://github.com/ewedell/BSCAMPP/blob/main/LICENSE)
+[![Changelog](https://img.shields.io/badge/CHANGELOG-grey)](https://github.com/ewedell/BSCAMPP/blob/main/CHANGELOG.md)
 
 **Table of Contents**
 1. [Overview](#overview)

{bscampp-1.0.1a0.dist-info → bscampp-1.0.1b0.dist-info}/RECORD

@@ -1,11 +1,11 @@
-bscampp/__init__.py,sha256=WQ01lWQA9s702tTmbq99PAg_HE_-yyidAQTESo0ny-Y,2290
+bscampp/__init__.py,sha256=Wnn_Bm543hAgQCd9PmwdT_kFBZzGLDW4dcSeP0iLVTk,2290
 bscampp/configs.py,sha256=XuzRbtcUE5bExe-vEZGZ1CeXBmp4oP7LWFveQySx2xs,5745
 bscampp/default.config,sha256=CEfsUHBy--vwJhEcUuJ0btfuGQWb_lKMVWUIP9f5YGw,112
-bscampp/functions.py,sha256=xcx1phGZF1yCMKk41nP2_V-4F1FziwzX1pZEgmmMaCY,15338
+bscampp/functions.py,sha256=cPT5eSy_8CSNzDx-5ma43Hp9_AMmaWSTXM89bjdrkRs,15640
 bscampp/init_configs.py,sha256=EA9sMN5jWj6zj2b-7tN19LhX2Ef61ByQLxQRLHAqLDM,3600
 bscampp/jobs.py,sha256=de0Dr3ynORwACJqVbeWDfqTwJhWvMYG-7yfRYirGx8M,6703
-bscampp/pipeline.py,sha256=5B8cZ3iPYUnzQMYRxAPvFdkIKDk136o5iPDtvPGPPQw,8972
-bscampp/utils.py,sha256=va8S6tHPezMaKcONRbcb8WlRdhNrUkV_5DTx57HoUSM,28968
+bscampp/pipeline.py,sha256=UT8y6ObFZ12q5Vw3731r50k8pLMioFNV4qCy0tz_wuk,9550
+bscampp/utils.py,sha256=ragaI14Lqb2fVp_uYDkFQnV7a50G9-sUOWdVM-sNhUE,29005
 bscampp/tools/epa-ng,sha256=f3EVoZAAOXLN6l521qp-TrWDl5J2nqL3tGgjPaQE9WQ,3772096
 bscampp/tools/pplacer,sha256=p0H4eo9uuiYoWS_kJbPfauOV99i7BXJdZSiwXIuLxTw,7834576
 bscampp/tools/hamming_distance/CMakeLists.txt,sha256=yf9iq7Y61t3WObJHoR4RoGDEvUw_Q8JW3UnI4uh0cfU,389
@@ -17,9 +17,9 @@ bscampp/tools/hamming_distance/src/fragment_tree_hamming.cpp,sha256=xCmyAT-OZJOD
 bscampp/tools/hamming_distance/src/fragment_tree_hamming_new.cpp,sha256=eKxgODRlpf0hU84QjNhigvRhWCT9tiJZjA5oQFQ1bUk,7404
 bscampp/tools/hamming_distance/src/homology.cpp,sha256=ZE0uXZWQ-cN4U1Wk5kUr_KKHgzsgA6Sno-IViRa4tmI,6053
 bscampp/tools/hamming_distance/src/new_hamming.cpp,sha256=fBRm99RquBZgZjaLOn9xDI3cH9NchhrxKbL-11j8fmk,5342
-bscampp-1.0.1a0.dist-info/LICENSE,sha256=HEa4YQdOR0e2Gz-NiOwr9X6aJcZtY0AGmlJQDmfN0Iw,1064
-bscampp-1.0.1a0.dist-info/METADATA,sha256=spokmK4AGqKPzgZ9SdCQXxjMP3-UMQpJQNc8pG0wyFw,10509
-bscampp-1.0.1a0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-bscampp-1.0.1a0.dist-info/entry_points.txt,sha256=dZygBmg2OncVyeLeIjh_9e-GBIOesFvMemyW9BRRcXY,113
-bscampp-1.0.1a0.dist-info/top_level.txt,sha256=1loGRUAft6Tcdq0f3lHbVwWN7W_SW1srfhAVSpg9DWE,8
-bscampp-1.0.1a0.dist-info/RECORD,,
+bscampp-1.0.1b0.dist-info/LICENSE,sha256=HEa4YQdOR0e2Gz-NiOwr9X6aJcZtY0AGmlJQDmfN0Iw,1064
+bscampp-1.0.1b0.dist-info/METADATA,sha256=hCpwS1vbd07cuwW7D5AkiO_I_GP-kqk21IH2yxiPUwM,11144
+bscampp-1.0.1b0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+bscampp-1.0.1b0.dist-info/entry_points.txt,sha256=dZygBmg2OncVyeLeIjh_9e-GBIOesFvMemyW9BRRcXY,113
+bscampp-1.0.1b0.dist-info/top_level.txt,sha256=1loGRUAft6Tcdq0f3lHbVwWN7W_SW1srfhAVSpg9DWE,8
+bscampp-1.0.1b0.dist-info/RECORD,,