Add --skip option to nilm-insert

If the max scale in the exemplar was a column we weren't using, it
would bail out when looking for that correlation later.  Change things
around so exemplars in RAM only keep around the columns we care about.

Makefile

@@ -8,19 +8,26 @@ else
 	@echo "Try 'make install'"
 endif
 
-test: test_trainola
+test: test_insert
+
+test_pipewatch:
+	nilmtools/pipewatch.py -t 3 "seq 10 20" "seq 20 30"
 
 test_trainola:
+	-nilmtool -u http://bucket/nilmdb remove -s min -e max \
+		/sharon/prep-a-matches
+	nilmtools/trainola.py "$$(cat extras/trainola-test-param-2.js)"
 	-nilmtool -u http://bucket/nilmdb remove -s min -e max \
 		/sharon/prep-a-matches
 	nilmtools/trainola.py "$$(cat extras/trainola-test-param.js)"
 
+
 test_cleanup:
 	nilmtools/cleanup.py -e extras/cleanup.cfg
 	nilmtools/cleanup.py extras/cleanup.cfg
 
 test_insert:
-	nilmtools/insert.py --file --dry-run  /test/foo </dev/null
+	nilmtools/insert.py --skip --file --dry-run /foo/bar ~/data/20130311T2100.prep1.gz ~/data/20130311T2100.prep1.gz ~/data/20130311T2200.prep1.gz
 
 test_copy:
 	nilmtools/copy_wildcard.py -U "http://nilmdb.com/bucket/" -D /lees*
@@ -39,7 +46,8 @@ test_prep: /tmp/raw.dat
 	nilmtool create /test/sinefit float32_3
 	nilmtool create /test/prep float32_8
 	nilmtool insert -s '@0' -t -r 8000 /test/raw /tmp/raw.dat
-	nilmtools/sinefit.py -a 0.5 -c 1 /test/raw /test/sinefit
+	nilmtools/sinefit.py -a 0.5 -c 1 -s '@0' -e '@5000000' /test/raw /test/sinefit
+	nilmtools/prep.py -c 2 /test/raw /test/sinefit /test/prep
 	nilmtools/prep.py -c 2 /test/raw /test/sinefit /test/prep
 	nilmtool extract -s min -e max /test/prep | head -20
 

README.txt

@@ -5,10 +5,10 @@ by Jim Paris <jim@jtan.com>
 Prerequisites:
 
   # Runtime and build environments
-  sudo apt-get install python2.7 python2.7-dev python-setuptools python-pip
+  sudo apt-get install python2.7 python2.7-dev python-setuptools
-  sudo apt-get install python-numpy python-scipy
+  sudo apt-get install python-numpy python-scipy python-daemon
 
-  nilmdb (1.8.1+)
+  nilmdb (1.8.5+)
 
 Install:
 

extras/sample-cron-scripts/capture.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# Start the ethstream capture using nilm-pipewatch
+
+# Bail out on errors
+set -e
+
+nilm-pipewatch --daemon --lock "/tmp/nilmdb-capture.lock" --timeout 30 \
+    "ethstream -a 192.168.1.209 -n 9 -r 8000 -N" \
+    "nilm-insert -m 10 -r 8000 --live /sharon/raw"

extras/sample-cron-scripts/cleanup.cfg

@@ -0,0 +1,8 @@
+[/sharon/prep-*]
+keep = 1y
+
+[/sharon/raw]
+keep = 2w
+
+[/sharon/sinefit]
+keep = 1y

extras/sample-cron-scripts/crontab

@@ -0,0 +1,9 @@
+# Install this by running "crontab crontab" (will replace existing crontab)
+
+# m h dom mon dow cmd
+
+# Run NilmDB processing every 5 minutes
+*/5 * * * * chronic /home/nilm/data/process.sh
+
+# Check the capture process every minute
+*/1 * * * * chronic /home/nilm/data/capture.sh

extras/sample-cron-scripts/process.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+# Run all necessary processing on NilmDB data.
+
+# Bail out on errors
+set -e
+
+# Ensure only one copy of this code runs at a time:
+LOCKFILE="/tmp/nilmdb-process.lock"
+exec 99>"$LOCKFILE"
+if ! flock -n -x 99 ; then
+    echo "NilmDB processing already running, giving up..."
+    exit 0
+fi
+trap 'rm -f "$LOCKFILE"' 0
+
+# sinefit on phase A voltage
+nilm-sinefit -c 5 /sharon/raw /sharon/sinefit
+
+# prep on A, B, C with appropriate rotations
+nilm-prep -c 1 -r 0 /sharon/raw /sharon/sinefit /sharon/prep-a
+nilm-prep -c 2 -r 120 /sharon/raw /sharon/sinefit /sharon/prep-b
+nilm-prep -c 3 -r 240 /sharon/raw /sharon/sinefit /sharon/prep-c
+
+# decimate raw and prep data
+nilm-decimate-auto /sharon/raw /sharon/prep*
+
+# run cleanup
+nilm-cleanup --yes /home/nilm/data/cleanup.cfg

extras/trainola-test-param-2.js

@@ -0,0 +1,29 @@
+{ "columns" : [ { "index" : 0, "name" : "P1" },
+                { "index" : 1, "name" : "Q1" },
+                { "index" : 2, "name" : "P3" } ],
+  "stream" : "/sharon/prep-a",
+  "url" : "http://bucket.mit.edu/nilmdb",
+  "dest_stream" : "/sharon/prep-a-matches",
+  "start" : 1365153062643133.5,
+  "end"   : 1365168814443575.5,
+  "exemplars" : [ { "columns" : [ { "index" : 0,
+                                    "name" : "P1"
+                                  } ],
+                    "dest_column" : 0,
+                    "end" : 1365073657682000,
+                    "name" : "Turn ON",
+                    "start" : 1365073654321000,
+                    "stream" : "/sharon/prep-a",
+                    "url" : "http://bucket.mit.edu/nilmdb"
+                  },
+                  { "columns" : [ { "index" : 2, "name" : "P3" },
+                                  { "index" : 0, "name" : "P1" } ],
+                    "dest_column" : 1,
+                    "end" : 1365176528818000,
+                    "name" : "Type 2 turn ON",
+                    "start" : 1365176520030000,
+                    "stream" : "/sharon/prep-a",
+                    "url" : "http://bucket.mit.edu/nilmdb"
+                  }
+                ]
+}

nilmtools/filter.py

@@ -316,7 +316,8 @@ class Filter(object):
         self._client_dest.stream_update_metadata(self.dest.path, data)
 
     # The main filter processing method.
-    def process_numpy(self, function, args = None, rows = 100000):
+    def process_numpy(self, function, args = None, rows = 100000,
+                      intervals = None):
         """Calls process_numpy_interval for each interval that currently
         exists in self.src, but doesn't exist in self.dest.  It will
         process the data in chunks as follows:
@@ -325,6 +326,9 @@ class Filter(object):
         corresponding to the data.  The data is converted to a Numpy
         array in chunks of 'rows' rows at a time.
 
+        If 'intervals' is not None, process those intervals instead of
+        the default list.
+
         'function' should be defined as:
         # def function(data, interval, args, insert_func, final)
 
@@ -358,7 +362,7 @@ class Filter(object):
                                            maxrows = rows)
         inserter_func = functools.partial(inserter, self.dest.path)
 
-        for interval in self.intervals():
+        for interval in (intervals or self.intervals()):
             print "Processing", interval.human_string()
             process_numpy_interval(interval, extractor_func, inserter_func,
                                    rows * 3, function, args)

nilmtools/insert.py

@@ -53,7 +53,8 @@ def parse_args(argv = None):
       is stepped forward to match 'clock'.
 
     - If 'data' is running ahead, there is overlap in the data, and an
-      error is raised.
+      error is raised.  If '--ignore' is specified, the current file
+      is skipped instead of raising an error.
     """))
     parser.add_argument("-u", "--url", action="store",
                         default="http://localhost/nilmdb/",
@@ -61,6 +62,8 @@ def parse_args(argv = None):
     group = parser.add_argument_group("Misc options")
     group.add_argument("-D", "--dry-run", action="store_true",
                        help="Parse files, but don't insert any data")
+    group.add_argument("-s", "--skip", action="store_true",
+                       help="Skip files if the data would overlap")
     group.add_argument("-m", "--max-gap", action="store", default=10.0,
                        metavar="SEC", type=float,
                        help="Max discrepency between clock and data "
@@ -235,6 +238,10 @@ def main(argv = None):
                                       "is %s but clock time is only %s",
                                       timestamp_to_human(data_ts),
                                       timestamp_to_human(clock_ts))
+                        if args.skip:
+                            printf("%s\n", err)
+                            printf("Skipping the remainder of this file\n")
+                            break
                         raise ParseError(filename, err)
 
                     if (data_ts + max_gap) < clock_ts:

nilmtools/pipewatch.py

@@ -0,0 +1,168 @@
+#!/usr/bin/python
+
+import nilmdb.client
+from nilmdb.utils.printf import *
+import nilmdb.utils.lock
+import nilmtools
+
+import time
+import sys
+import os
+import argparse
+import subprocess
+import tempfile
+import threading
+import select
+import signal
+import Queue
+import daemon
+
+def parse_args(argv = None):
+    parser = argparse.ArgumentParser(
+        formatter_class = argparse.ArgumentDefaultsHelpFormatter,
+        version = nilmtools.__version__,
+        description = """\
+    Pipe data from 'generator' to 'consumer'.  This is intended to be
+    executed frequently from cron, and will exit if another copy is
+    already running.  If 'generator' or 'consumer' returns an error,
+    or if 'generator' stops sending data for a while, it will exit.
+
+    Intended for use with ethstream (generator) and nilm-insert
+    (consumer).  Commands are executed through the shell.
+    """)
+    parser.add_argument("-d", "--daemon", action="store_true",
+                        help="Run in background")
+    parser.add_argument("-l", "--lock", metavar="FILENAME", action="store",
+                        default=tempfile.gettempdir() +
+                        "/nilm-pipewatch.lock",
+                        help="Lock file for detecting running instance")
+    parser.add_argument("-t", "--timeout", metavar="SECONDS", action="store",
+                        type=float, default=30,
+                        help="Restart if no output from " +
+                        "generator for this long")
+    group = parser.add_argument_group("commands to execute")
+    group.add_argument("generator", action="store",
+                       help="Data generator (e.g. \"ethstream -r 8000\")")
+    group.add_argument("consumer", action="store",
+                       help="Data consumer (e.g. \"nilm-insert /foo/bar\")")
+    args = parser.parse_args(argv)
+
+    return args
+
+def reader_thread(queue, fd):
+    # Read from a file descriptor, write to queue.
+    try:
+        while True:
+            (r, w, x) = select.select([fd], [], [fd], 0.25)
+            if x:
+                raise Exception # generator died?
+            if not r:
+                # short timeout -- just try again.  This is to catch the
+                # fd being closed elsewhere, which is only detected
+                # when select restarts.
+                continue
+            data = os.read(fd, 65536)
+            if data == "": # generator EOF
+                raise Exception
+            queue.put(data)
+    except Exception:
+        queue.put(None)
+
+def watcher_thread(queue, procs):
+    # Put None in the queue if either process dies
+    while True:
+        for p in procs:
+            if p.poll() is not None:
+                queue.put(None)
+                return
+        time.sleep(0.25)
+
+def pipewatch(args):
+    # Run the processes, etc
+    with open(os.devnull, "r") as devnull:
+        generator = subprocess.Popen(args.generator, shell = True,
+                                     bufsize = -1, close_fds = True,
+                                     stdin = devnull,
+                                     stdout = subprocess.PIPE,
+                                     stderr = None)
+        consumer = subprocess.Popen(args.consumer, shell = True,
+                                    bufsize = -11, close_fds = True,
+                                    stdin = subprocess.PIPE,
+                                    stdout = None, stderr = None)
+
+        queue = Queue.Queue(maxsize = 32)
+        reader = threading.Thread(target = reader_thread,
+                                  args = (queue, generator.stdout.fileno()))
+        reader.start()
+        watcher = threading.Thread(target = watcher_thread,
+                                   args = (queue, [generator, consumer]))
+        watcher.start()
+        try:
+            while True:
+                try:
+                    data = queue.get(True, args.timeout)
+                    if data is None:
+                        break
+                    consumer.stdin.write(data)
+                except Queue.Empty:
+                    # Timeout: kill the generator
+                    fprintf(sys.stderr, "pipewatch: timeout\n")
+                    generator.terminate()
+                    break
+
+            generator.stdout.close()
+            consumer.stdin.close()
+        except IOError:
+            fprintf(sys.stderr, "pipewatch: I/O error\n")
+
+        def kill(proc):
+            # Wait for a process to end, or kill it
+            def poll_timeout(proc, timeout):
+                for x in range(1+int(timeout / 0.1)):
+                    if proc.poll() is not None:
+                        break
+                    time.sleep(0.1)
+                return proc.poll()
+            try:
+                if poll_timeout(proc, 0.5) is None:
+                    proc.terminate()
+                    if poll_timeout(proc, 0.5) is None:
+                        proc.kill()
+            except OSError:
+                pass
+            return poll_timeout(proc, 0.5)
+
+        # Wait for them to die, or kill them
+        gret = kill(generator)
+        cret = kill(consumer)
+
+        fprintf(sys.stderr, "pipewatch: generator returned %d, " +
+                "consumer returned %d\n", gret, cret)
+        if gret == 0 and cret == 0:
+            sys.exit(0)
+        sys.exit(1)
+
+def main(argv = None):
+    args = parse_args(argv)
+
+    lockfile = open(args.lock, "w")
+    if not nilmdb.utils.lock.exclusive_lock(lockfile):
+        printf("pipewatch process already running (according to %s)\n",
+               args.lock)
+        sys.exit(0)
+    try:
+        # Run as a daemon if requested, otherwise run directly.
+        if args.daemon:
+            with daemon.DaemonContext(files_preserve = [ lockfile ]):
+                pipewatch(args)
+        else:
+            pipewatch(args)
+    finally:
+        # Clean up lockfile
+        try:
+            os.unlink(args.lock)
+        except OSError:
+            pass
+
+if __name__ == "__main__":
+    main()

nilmtools/prep.py

@@ -12,6 +12,7 @@ import scipy.fftpack
 import scipy.signal
 #from matplotlib import pyplot as p
 import bisect
+from nilmdb.utils.interval import Interval
 
 def main(argv = None):
     # Set up argument parser
@@ -82,9 +83,20 @@ def main(argv = None):
                             "prep_column": args.column,
                             "prep_rotation": repr(rotation) })
 
-    # Run the processing function on all data
+    # Find the intersection of the usual set of intervals we'd filter,
+    # and the intervals actually present in sinefit data.  This is
+    # what we will process.
+    filter_int = f.intervals()
+    sinefit_int = ( Interval(start, end) for (start, end) in
+                    client_sinefit.stream_intervals(
+                        args.sinepath, start = f.start, end = f.end) )
+    intervals = nilmdb.utils.interval.intersection(filter_int, sinefit_int)
+
+    # Run the process (using the helper in the filter module)
     f.process_numpy(process, args = (client_sinefit, sinefit.path, args.column,
-                                     args.nharm, rotation, args.nshift))
+                                     args.nharm, rotation, args.nshift),
+                    intervals = intervals)
+
 
 def process(data, interval, args, insert_function, final):
     (client, sinefit_path, column, nharm, rotation, nshift) = args

nilmtools/trainola.py

@@ -28,12 +28,12 @@ def build_column_mapping(colinfo, streaminfo):
     pull out a dictionary mapping for the column names/numbers."""
     columns = OrderedDict()
     for c in colinfo:
-        if (c['name'] in columns.keys() or
+        col_num = c['index'] + 1  # skip timestamp
-            c['index'] in columns.values()):
+        if (c['name'] in columns.keys() or col_num in columns.values()):
             raise DataError("duplicated columns")
         if (c['index'] < 0 or c['index'] >= streaminfo.layout_count):
             raise DataError("bad column number")
-        columns[c['name']] = c['index']
+        columns[c['name']] = col_num
     if not len(columns):
         raise DataError("no columns")
     return columns
@@ -54,6 +54,9 @@ class Exemplar(object):
         # Get stream info
         self.client = nilmdb.client.numpyclient.NumpyClient(self.url)
         self.info = nilmtools.filter.get_stream_info(self.client, self.stream)
+        if not self.info:
+            raise DataError(sprintf("exemplar stream '%s' does not exist " +
+                                    "on server '%s'", self.stream, self.url))
 
         # Build up name => index mapping for the columns
         self.columns = build_column_mapping(exinfo['columns'], self.info)
@@ -76,10 +79,17 @@ class Exemplar(object):
                                                    maxrows = self.count)
         self.data = list(datagen)[0]
 
-        # Discard timestamp
+        # Extract just the columns that were specified in self.columns,
-        self.data = self.data[:,1:]
+        # skipping the timestamp.
+        extract_columns = [ value for (key, value) in self.columns.items() ]
+        self.data = self.data[:,extract_columns]
 
-        # Subtract the mean from each column
+        # Fix the column indices in e.columns, since we removed/reordered
+        # columns in self.data
+        for n, k in enumerate(self.columns):
+            self.columns[k] = n
+
+        # Subtract the means from each column
         self.data = self.data - self.data.mean(axis=0)
 
         # Get scale factors for each column by computing dot product
@@ -144,7 +154,7 @@ def trainola_matcher(data, interval, args, insert_func, final_chunk):
 
         # Compute cross-correlation for each column
         for col_name in e.columns:
-            a = data[:, src_columns[col_name] + 1]
+            a = data[:, src_columns[col_name]]
             b = e.data[:, e.columns[col_name]]
             corr = scipy.signal.fftconvolve(a, np.flipud(b), 'valid')[0:valid]
 

setup.py

@@ -61,9 +61,10 @@ setup(name='nilmtools',
       long_description = "NILM Database Tools",
       license = "Proprietary",
       author_email = 'jim@jtan.com',
-      install_requires = [ 'nilmdb >= 1.8.1',
+      install_requires = [ 'nilmdb >= 1.8.5',
                            'numpy',
                            'scipy',
+                           'python-daemon >= 1.5',
                            #'matplotlib',
                            ],
       packages = [ 'nilmtools',
@@ -80,6 +81,7 @@ setup(name='nilmtools',
               'nilm-cleanup = nilmtools.cleanup:main',
               'nilm-median = nilmtools.median:main',
               'nilm-trainola = nilmtools.trainola:main',
+              'nilm-pipewatch = nilmtools.pipewatch:main',
               ],
           },
       zip_safe = False,