This is an automated email from the ASF dual-hosted git repository.
fgreg pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-sdap-nexus.git
The following commit(s) were added to refs/heads/master by this push:
new 584b2f5 SDAP-192 Created DOMS netCDF reader tool. (#68)
584b2f5 is described below
commit 584b2f5b91300fd0952cb4de32068a008c551936
Author: Jocelyn Elya <[email protected]>
AuthorDate: Wed Apr 3 13:55:08 2019 -0400
SDAP-192 Created DOMS netCDF reader tool. (#68)
* SDAP-192 Created DOMS netCDF reader tool.
* SDAP-192 DOMS netCDF reader updated to use num2date function to get
datetime object from timestamp.
* SDAP-192 Added logging to DOMS netCDF reader tool.
* SDAP-192 Miscellaneous variable updates with DOMS netCDF reader.
* SDAP-192 'try/except' blocks around 'with' statements for netCDF and CSV
file handling. Changed name of CSV file output from main. Moved print statement.
* SDAP-192 Changed print to LOGGER.info in DOMS netCDF reader.
---
tools/doms/doms_reader.py | 138 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 138 insertions(+)
diff --git a/tools/doms/doms_reader.py b/tools/doms/doms_reader.py
new file mode 100644
index 0000000..ffd24b6
--- /dev/null
+++ b/tools/doms/doms_reader.py
@@ -0,0 +1,138 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import argparse
+from netCDF4 import Dataset, num2date
+import sys
+import datetime
+import csv
+from collections import OrderedDict
+import logging
+
+LOGGER = logging.getLogger("doms_reader")
+
+def assemble_matches(filename):
+ """
+ Read a DOMS netCDF file and return a list of matches.
+
+ Arguments:
+ filename (string): the DOMS netCDF file name.
+
+ Returns:
+ matches (list): List of matches. Each list element is a dictionary:
+ For netCDF group GROUP (SatelliteData or InsituData) and group
+ variable VARIABLE:
+ matches[GROUP]['matchID']: MatchedRecords dimension ID for the
match
+ matches[GROUP]['GROUPID']: GROUP dim dimension ID for the record
+ matches[GROUP][VARIABLE]: variable value
+ """
+
+ try:
+ # Open the netCDF file
+ with Dataset(filename, 'r') as doms_nc:
+ # Check that the number of groups is consistent w/ the
MatchedGroups
+ # dimension
+ assert len(doms_nc.groups) ==
doms_nc.dimensions['MatchedGroups'].size,\
+ ("Number of groups isn't the same as MatchedGroups dimension.")
+
+ matches = []
+ matched_records = doms_nc.dimensions['MatchedRecords'].size
+
+ # Loop through the match IDs to assemble matches
+ for match in range(0, matched_records):
+ match_dict = OrderedDict()
+ # Grab the data from each platform (group) in the match
+ for group_num, group in enumerate(doms_nc.groups):
+ match_dict[group] = OrderedDict()
+ match_dict[group]['matchID'] = match
+ ID = doms_nc.variables['matchIDs'][match][group_num]
+ match_dict[group][group + 'ID'] = ID
+ for var in doms_nc.groups[group].variables.keys():
+ match_dict[group][var] = doms_nc.groups[group][var][ID]
+
+ # Create a UTC datetime field from timestamp
+ dt = num2date(match_dict[group]['time'],
+ doms_nc.groups[group]['time'].units)
+ match_dict[group]['datetime'] = dt
+ LOGGER.info(match_dict)
+ matches.append(match_dict)
+
+ return matches
+ except (OSError, IOError) as err:
+ LOGGER.exception("Error reading netCDF file " + filename)
+ raise err
+
+def matches_to_csv(matches, filename):
+ """
+ Write the DOMS matches to a CSV file. Include a header of column names
+ which are based on the group and variable names from the netCDF file.
+
+ Arguments:
+ matches (list): the list of dictionaries containing the DOMS matches as
+ returned from assemble_matches.
+
+ filename (string): the name of the CSV output file.
+ """
+ # Create a header for the CSV. Column names are GROUP_VARIABLE or
+ # GROUP_GROUPID.
+ header = []
+ for key, value in matches[0].items():
+ for otherkey in value.keys():
+ header.append(key + "_" + otherkey)
+
+ try:
+ # Write the CSV file
+ with open(filename, 'w') as output_file:
+ csv_writer = csv.writer(output_file)
+ csv_writer.writerow(header)
+ for match in matches:
+ row = []
+ for group, data in match.items():
+ for value in data.values():
+ row.append(value)
+ csv_writer.writerow(row)
+ except (OSError, IOError) as err:
+ LOGGER.exception("Error writing CSV file " + filename)
+ raise err
+
+if __name__ == '__main__':
+ """
+ Execution:
+ python doms_reader.py filename
+ OR
+ python3 doms_reader.py filename
+ """
+ logging.basicConfig(format='%(asctime)s %(levelname)-8s %(message)s',
+ level=logging.INFO,
+ datefmt='%Y-%m-%d %H:%M:%S')
+
+ p = argparse.ArgumentParser()
+ p.add_argument('filename', help='DOMS netCDF file to read')
+ args = p.parse_args()
+
+ doms_matches = assemble_matches(args.filename)
+
+ matches_to_csv(doms_matches, 'doms_matches.csv')
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
