Fix non-string arguments to metadata_check

And adjust the period locator accordingly.
Fitting \sin is the same mathematically, it's just conceptually more
straightforward since we're locating zero crossings anyway.

setup.py

@@ -61,7 +61,7 @@ setup(name='nilmtools',
       long_description = "NILM Database Tools",
       license = "Proprietary",
       author_email = 'jim@jtan.com',
-      install_requires = [ 'nilmdb >= 1.5.0',
+      install_requires = [ 'nilmdb >= 1.6.0',
                            'numpy',
                            'scipy',
                            'matplotlib',

src/cleanup.py

@@ -238,12 +238,15 @@ def main(argv = None):
                        timestamp_to_seconds(total)))
             continue
         printf("  removing data before %s\n", timestamp_to_human(remove_before))
-        if args.yes:
-            client.stream_remove(path, None, remove_before)
-        for ap in streams[path].also_clean_paths:
-            printf("  also removing from %s\n", ap)
+        # Clean in reverse order.  Since we only use the primary stream and not
+        # the decimated streams to figure out which data to remove, removing
+        # the primary stream last means that we might recover more nicely if
+        # we are interrupted and restarted.
+        clean_paths = list(reversed(streams[path].also_clean_paths)) + [ path ]
+        for p in clean_paths:
+            printf("  removing from %s\n", p)
             if args.yes:
-                client.stream_remove(ap, None, remove_before)
+                client.stream_remove(p, None, remove_before)
 
     # All done
     if not args.yes:

src/filter.py

@@ -67,7 +67,7 @@ def get_stream_info(client, path):
 
 class Filter(object):
 
-    def __init__(self):
+    def __init__(self, parser_description = None):
         self._parser = None
         self._client_src = None
         self._client_dest = None
@@ -78,6 +78,9 @@ class Filter(object):
         self.end = None
         self.interhost = False
         self.force_metadata = False
+        if parser_description is not None:
+            self.setup_parser(parser_description)
+            self.parse_args()
 
     @property
     def client_src(self):
@@ -233,8 +236,14 @@ class Filter(object):
         metadata = self._client_dest.stream_get_metadata(self.dest.path)
         if not self.force_metadata:
             for key in data:
-                wanted = str(data[key])
+                wanted = data[key]
+                if not isinstance(wanted, basestring):
+                    wanted = str(wanted)
                 val = metadata.get(key, wanted)
+                # Force UTF-8 encoding for comparison and display
+                wanted = wanted.encode('utf-8')
+                val = val.encode('utf-8')
+                key = key.encode('utf-8')
                 if val != wanted and self.dest.rows > 0:
                     m =  "Metadata in destination stream:\n"
                     m += "  %s = %s\n" % (key, val)
@@ -275,6 +284,10 @@ class Filter(object):
         Return value of 'function' is the number of data rows processed.
         Unprocessed data will be provided again in a subsequent call
         (unless 'final' is True).
+
+        If unprocessed data remains after 'final' is True, the interval
+        being inserted will be ended at the timestamp of the first
+        unprocessed data point.
         """
         if args is None:
             args = []
@@ -319,7 +332,13 @@ class Filter(object):
 
                 # Last call for this contiguous interval
                 if old_array.shape[0] != 0:
-                    function(old_array, interval, args, insert_function, True)
+                    processed = function(old_array, interval, args,
+                                         insert_function, True)
+                    if processed != old_array.shape[0]:
+                        # Truncate the interval we're inserting at the first
+                        # unprocessed data point.  This ensures that
+                        # we'll not miss any data when we run again later.
+                        insert_ctx.update_end(old_array[processed][0])
 
 def main(argv = None):
     # This is just a dummy function; actual filters can use the other

src/prep.py

@@ -3,6 +3,8 @@
 # Spectral envelope preprocessor.
 # Requires two streams as input: the original raw data, and sinefit data.
 
+from nilmdb.utils.printf import *
+from nilmdb.utils.time import timestamp_to_human
 import nilmtools.filter
 import nilmdb.client
 from numpy import *
@@ -78,7 +80,7 @@ def main(argv = None):
     f.check_dest_metadata({ "prep_raw_source": f.src.path,
                             "prep_sinefit_source": sinefit.path,
                             "prep_column": args.column,
-                            "prep_rotation": rotation })
+                            "prep_rotation": repr(rotation) })
 
     # Run the processing function on all data
     f.process_numpy(process, args = (client_sinefit, sinefit.path, args.column,
@@ -106,7 +108,6 @@ def process(data, interval, args, insert_function, final):
     # Pull out sinefit data for the entire time range of this block
     for sinefit_line in client.stream_extract(sinefit_path,
                                               data[0, 0], data[rows-1, 0]):
-
         def prep_period(t_min, t_max, rot):
             """
             Compute prep coefficients from time t_min to t_max, which
@@ -163,7 +164,15 @@ def process(data, interval, args, insert_function, final):
                 break
             processed = idx_max
 
-    print "Processed", processed, "of", rows, "rows"
+    # If we processed no data but there's lots in here, pretend we
+    # processed half of it.
+    if processed == 0 and rows > 10000:
+        processed = rows / 2
+        printf("%s: warning: no periods found; skipping %d rows\n",
+               timestamp_to_human(data[0][0]), processed)
+    else:
+        printf("%s: processed %d of %d rows\n",
+               timestamp_to_human(data[0][0]), processed, rows)
     return processed
 
 if __name__ == "__main__":

src/sinefit.py

@@ -25,7 +25,7 @@ def main(argv = None):
                        help='Maximum valid frequency '
                        '(default: approximate frequency * 2))')
     group.add_argument('-a', '--min-amp', action='store', type=float,
-                       default=10.0,
+                       default=20.0,
                        help='Minimum signal amplitude (default: %(default)s)')
 
     # Parse arguments
@@ -98,12 +98,12 @@ def process(data, interval, args, insert_function, final):
             continue
 
         #p.plot(arange(N), this)
-        #p.plot(arange(N), A * cos(f0/fs * 2 * pi * arange(N) + phi) + C, 'g')
+        #p.plot(arange(N), A * sin(f0/fs * 2 * pi * arange(N) + phi) + C, 'g')
 
-        # Period starts when the argument of cosine is 3*pi/2 degrees,
+        # Period starts when the argument of sine is 0 degrees,
         # so we're looking for sample number:
-        #     n = (3 * pi / 2 - phi) / (f0/fs * 2 * pi)
-        zc_n = (3 * pi / 2 - phi) / (f0 / fs * 2 * pi)
+        #     n = (0 - phi) / (f0/fs * 2 * pi)
+        zc_n = (0 - phi) / (f0 / fs * 2 * pi)
         period_n = fs/f0
 
         # Add periods to make N positive
@@ -149,15 +149,15 @@ def sfit4(data, fs):
 
     Output:
       Parameters [A, f0,  phi, C] to fit the equation
-        x[n] = A * cos(f0/fs * 2 * pi * n + phi) + C
+        x[n] = A * sin(f0/fs * 2 * pi * n + phi) + C
       where n is sample number.  Or, as a function of time:
-        x(t) = A * cos(f0 * 2 * pi * t + phi) + C
+        x(t) = A * sin(f0 * 2 * pi * t + phi) + C
 
     by Jim Paris
     (Verified to match sfit4.m)
     """
     N = len(data)
-    t = linspace(0, (N-1) / fs, N)
+    t = linspace(0, (N-1) / float(fs), N)
 
     ## Estimate frequency using FFT (step b)
     Fc = fft(data)
@@ -182,18 +182,17 @@ def sfit4(data, fs):
     i = arccos((Z2*cos(ni2) - Z1*cos(ni1)) / (Z2-Z1)) / n
 
     # Convert to Hz
-    f0 = i * fs / N
+    f0 = i * float(fs) / N
 
     # Fit it.  We'll catch exceptions here and just returns zeros
     # if something fails with the least squares fit, etc.
     try:
         # first guess for A0, B0 using 3-parameter fit (step c)
+        s = zeros(3)
         w = 2*pi*f0
-        D = c_[cos(w*t), sin(w*t), ones(N)]
-        s = linalg.lstsq(D, data)[0]
 
-        # Now iterate 6 times (step i)
-        for idx in range(6):
+        # Now iterate 7 times (step b, plus 6 iterations of step i)
+        for idx in range(7):
             D = c_[cos(w*t), sin(w*t), ones(N),
                   -s[0] * t * sin(w*t) + s[1] * t * cos(w*t) ] # eqn B.16
             s = linalg.lstsq(D, data)[0] # eqn B.18
@@ -202,7 +201,7 @@ def sfit4(data, fs):
         ## Extract results
         A = sqrt(s[0]*s[0] + s[1]*s[1]) # eqn B.21
         f0 = w / (2*pi)
-        phi = -arctan2(s[1], s[0]) # eqn B.22
+        phi = arctan2(s[0], s[1]) # eqn B.22 (flipped for sin instead of cos)
         C = s[2]
         return (A, f0, phi, C)
     except Exception as e: