Browse Source

Fix issue with column ordering in the exemplars

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.
tags/nilmtools-1.3.4
Jim Paris 8 years ago
parent
commit
62e11a11c0
3 changed files with 47 additions and 7 deletions
  1. +4
    -0
      Makefile
  2. +29
    -0
      extras/trainola-test-param-2.js
  3. +14
    -7
      nilmtools/trainola.py

+ 4
- 0
Makefile View File

@@ -11,10 +11,14 @@ endif
test: test_trainola

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


+ 29
- 0
extras/trainola-test-param-2.js View File

@@ -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"
}
]
}

+ 14
- 7
nilmtools/trainola.py View File

@@ -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
c['index'] in columns.values()):
col_num = c['index'] + 1 # skip timestamp
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
@@ -79,10 +79,17 @@ class Exemplar(object):
maxrows = self.count)
self.data = list(datagen)[0]

# Discard timestamp
self.data = self.data[:,1:]
# Extract just the columns that were specified in self.columns,
# 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
@@ -147,7 +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]



Loading…
Cancel
Save