Merge pull request #201 from wltrimbl/master

Maintenance

Author: wgerlach

examples/python/list_all_mg.py

@@ -1,24 +1,29 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python
 '''This script retrieves a list of metagenomes from the MG-RAST API.'''
 from __future__ import print_function
-import urllib
+from __future__ import unicode_literals
 import sys
 
-from mglib import get_auth_token, obj_from_url, API_URL
+from mglib import get_auth_token, obj_from_url, API_URL, urlencode
 
 def printlist(js):
     '''prints essential fields from metagenome list'''
     for item in js["data"]:
         if "public" in item.keys():
-            public = repr(item["public"])
+            public = item["public"]
         else:
-            public = "False"
-        sys.stdout.write( ("\t".join([item["metagenome_id"],
-#                         str(len(item.keys())),
-                          public, item["created_on"],
-                          item["name"]]) + "\n").encode("utf-8"))
+            public = False
+        try:
+            mg_name= item["name"]
+            project_id = item["project_id"]
+            project_name = item["project_name"]
+        except KeyError:
+            sys.stderr.write(repr(item))
+        sys.stdout.write(("\t".join([item["metagenome_id"],
+#                        str(len(item.keys())),
+                         repr(public), item["created_on"],
+                         mg_name, project_id, project_name]) + "\n"))
 
-CALL = "/metagenome"
 CALL = "/search"
 
 key = get_auth_token()
@@ -28,19 +33,21 @@ def printlist(js):
 
 # construct API call
 
-parameters = {"limit": limit, "auth": key, "order":"created_on", "direction": "asc"}
-base_url = API_URL + CALL + "?" + urllib.urlencode(parameters)
+parameters = {"limit": limit, "order":"created_on", "direction": "asc", "public": "1"}
+API_URL= "https://api.mg-rast.org/"
+
+base_url = API_URL + CALL + "?" + urlencode(parameters)
 
 # convert the data from a JSON structure to a python data type, a dict of dicts.
-jsonstructure = obj_from_url(base_url)
+jsonstructure = obj_from_url(base_url, auth=key)
 
 # unpack and display the data table
 total_count = int(jsonstructure["total_count"])
 sys.stderr.write("Total number of records: {:d}\n".format(total_count))
 
-for i in range(0, total_count / limit +1):
+for i in range(0, int(total_count / limit) +1):
     sys.stderr.write("Page {:d}\t".format(i))
-    jsonstructure = obj_from_url(base_url)
+    jsonstructure = obj_from_url(base_url, auth=key)
     printlist(jsonstructure)
     try:
         next_url = jsonstructure["next"]

scripts/mg-abundant-functions.py

@@ -48,7 +48,7 @@ def main(args):
     parser.add_argument("--filter_level", dest="filter_level", default=None, help="function level to filter by")
     parser.add_argument("--top", dest="top", type=int, default=10, help="display only the top N taxa, default is 10")
     parser.add_argument("--evalue", dest="evalue", type=int, default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", type=int, default=15, help="value for minimum alignment length cutoff, default is 15")
     parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
 

scripts/mg-abundant-taxa.py

@@ -48,7 +48,7 @@ def main(args):
     parser.add_argument("--filter_level", dest="filter_level", default=None, help="taxon level to filter by")
     parser.add_argument("--top", dest="top", type=int, default=10, help="display only the top N taxa, default is 10")
     parser.add_argument("--evalue", dest="evalue", type=int, default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", type=int, default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", type=int, default=15, help="value for minimum alignment length cutoff, default is 15")
     parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
 

scripts/mg-compare-functions.py

@@ -55,7 +55,7 @@ def main(args):
     parser.add_argument("--output", dest="output", default='-', help="output: filename or stdout (-), default is stdout")
     parser.add_argument("--format", dest="format", default='biom', help="output format: 'text' for tabbed table, 'biom' for BIOM format, default is biom")
     parser.add_argument("--evalue", type=int, dest="evalue", default=15, help="negative exponent value for maximum e-value cutoff, default is 15")
-    parser.add_argument("--identity", type=int, dest="identity", default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", type=int, dest="identity", default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", type=int, dest="length", default=15, help="value for minimum alignment length cutoff, default is 15")
     parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
     parser.add_argument("--temp", dest="temp", default=None, help="filename to temporarly save biom output at each iteration")

scripts/mg-compare-taxa.py

@@ -56,7 +56,7 @@ def main(args):
     parser.add_argument("--output", dest="output", default='-', help="output: filename or stdout (-), default is stdout")
     parser.add_argument("--format", dest="format", default='biom', help="output format: 'text' for tabbed table, 'biom' for BIOM format, default is biom")
     parser.add_argument("--evalue", type=int, dest="evalue", default=15, help="negative exponent value for maximum e-value cutoff, default is 15")
-    parser.add_argument("--identity", type=int, dest="identity", default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", type=int, dest="identity", default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", type=int, dest="length", default=15, help="value for minimum alignment length cutoff, default is 15")
     parser.add_argument("--version", type=int, dest="version", default=1, help="M5NR annotation version to use, default is 1")
     parser.add_argument("--temp", dest="temp", default=None, help="filename to temporarly save biom output at each iteration")

scripts/mg-export-metadata.py

@@ -83,7 +83,11 @@ def write_worksheet_value(worksheet, r, c, v, f):
     if f == "text" or f == "ontology" or f == "select" or f == "timezone" or v == "":
         worksheet.write_string(r, c, v)
     elif f == "float" or f == "coordinate" or f == "int":
-        worksheet.write_number(r, c, float(v))
+        try:
+            worksheet.write_number(r, c, float(v))
+        except ValueError:
+            worksheet.write_number(r, c, float(v.split(";")[0]))
+
     elif f == "date":
         worksheet.write_string(r, c, v)
     elif f == "time":

scripts/mg-extract-sequences.py

@@ -45,7 +45,7 @@ def main(args):
     parser.add_argument("--level", dest="level", default='function', help="function level to filter by")
     parser.add_argument("--source", dest="source", default='Subsystems', help="datasource to filter results by, default is Subsystems")
     parser.add_argument("--evalue", dest="evalue", default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", default=15, help="value for minimum alignment length cutoff, default is 15")
     parser.add_argument("--status", dest="status", default="public", help="types of metagenomes to return. 'both' for all data (public and private), 'public' for public data, 'private' for users private data, default is public")
     for sfield in SEARCH_FIELDS:

scripts/mg-get-sequences-for-taxon.py

@@ -45,7 +45,7 @@ def main(args):
     parser.add_argument("--level", dest="level", default=None, type=str, help="taxon level to filter by")
     parser.add_argument("--source", dest="source", default='SEED', type=str,  help="datasource to filter results by, default is SEED")
     parser.add_argument("--evalue", dest="evalue", default=5, type=float, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", default=60, type=float, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", default=60, type=float, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", default=15, type=float, help="value for minimum alignment length cutoff, default is 15")
 
     # get inputs

scripts/mg-get-similarity-for-function.py

@@ -45,7 +45,7 @@ def main(args):
     parser.add_argument("--level", dest="level", default=None, help="function level to filter by")
     parser.add_argument("--source", dest="source", default='Subsystems', help="datasource to filter results by, default is Subsystems")
     parser.add_argument("--evalue", dest="evalue", default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", default=15, help="value for minimum alignment length cutoff, default is 15")
 
     # get inputs

scripts/mg-get-similarity-for-taxon.py

@@ -45,7 +45,7 @@ def main(args):
     parser.add_argument("--level", dest="level", default=None, help="taxon level to filter by")
     parser.add_argument("--source", dest="source", default='SEED', help="datasource to filter results by, default is SEED")
     parser.add_argument("--evalue", dest="evalue", default=5, help="negative exponent value for maximum e-value cutoff, default is 5")
-    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum % identity cutoff, default is 60")
+    parser.add_argument("--identity", dest="identity", default=60, help="percent value for minimum %% identity cutoff, default is 60")
     parser.add_argument("--length", dest="length", default=15, help="value for minimum alignment length cutoff, default is 15")
 
     # get inputs