prep: only process intervals present in both raw & sinefit

Makefile

@@ -46,7 +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

@@ -8,7 +8,7 @@ Prerequisites:
   sudo apt-get install python2.7 python2.7-dev python-setuptools
   sudo apt-get install python-numpy python-scipy python-daemon
 
-  nilmdb (1.8.1+)
+  nilmdb (1.8.5+)
 
 Install:
 

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/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

setup.py

@@ -61,7 +61,7 @@ setup(name='nilmtools',
       long_description = "NILM Database Tools",
       license = "Proprietary",
       author_email = 'jim@jtan.com',
-      install_requires = [ 'nilmdb >= 1.8.1',
+      install_requires = [ 'nilmdb >= 1.8.5',
                            'numpy',
                            'scipy',
                            'python-daemon >= 1.5',