def generate(self, input=None): #, config, algorithms):
# Generate bin values for range start_scale to end_scale
# Calculate the number of bins at binsize across range
dso = DataSet(size=input.shape)
dso.import_data(input)
#ng.analysis.peakpick.pick(data, thres, msep=None, direction='both', algorithm='thres', est_params=True, lineshapes=None)
threshold = self.config.get('peak_threshold')
algorithm = self.algorithms[self.config.get('algorithm')]
msep = (self.config.get('peak_separation'), )
# Take input dataset and flatten in first dimension (average spectra)
data_avg = np.mean(input.data, axis=0)
# pick peaks and return locations;
#nmrglue.analysis.peakpick.pick(data, pthres, nthres=None, msep=None, algorithm='connected', est_params=True, lineshapes=None, edge=None, diag=False, c_struc=None, c_ndil=0, cluster=True, table=True, axis_names=['A', 'Z', 'Y', 'X'])[source]¶
locations, scales, amps = ng.analysis.peakpick.pick(
data_avg,
threshold,
msep=msep,
algorithm=algorithm,
est_params=True,
cluster=False,
table=False)
#n_cluster = max( cluster_ids )
n_locations = len(locations)
new_shape = list(input.shape)
new_shape[1] = n_locations # correct number; tho will be zero indexed
# Convert to numpy arrays so we can do clever things
scales = [dso.scales[1][l[0]] for l in locations]
# Adjust the scales (so aren't lost in crop)
dso.labels[1] = [str(l) for l in scales]
dso.scales[1] = scales
dso.crop(new_shape)
# Iterate over the clusters (1 to n)
for n, l in enumerate(locations):
#l = locations[ cluster_ids == n ]
#peak_data = np.amax( peak_data, axis=1 ) # max across cols
dso.data[:, n - 1] = input.data[:, l[0]]
# FIXME:
# Extract the location numbers (positions in original spectra)
# Get max value in each row for those regions
# Append that to n position in new dataset
# -- optionally use the line widths and take max within each of these for each spectra (peak shiftiness)
# Filter the original data with those locations and output\
return {'output': dso}
def normalise(self, dsi):
# Generate bin values for range start_scale to end_scale
# Calculate the number of bins at binsize across range
dso = DataSet(size=dsi.shape)
dso.import_data(dsi)
dso.data = self.algorithms[self.config.get('algorithm')](dso.data)
# -- optionally use the line widths and take max within each of these for each spectra (peak shiftiness)
# Filter the original data with those locations and output\
return dso
def normalise(self, dsi):
# Generate bin values for range start_scale to end_scale
# Calculate the number of bins at binsize across range
dso = DataSet(size=dsi.shape)
dso.import_data(dsi)
dso.data = self.algorithms[self.config.get('algorithm')](dso.data)
# -- optionally use the line widths and take max within each of these for each spectra (peak shiftiness)
# Filter the original data with those locations and output\
return dso
def generate(self, input=None): #, config, algorithms):
# Generate bin values for range start_scale to end_scale
# Calculate the number of bins at binsize across range
dso = DataSet( size=input.shape )
dso.import_data(input)
#ng.analysis.peakpick.pick(data, thres, msep=None, direction='both', algorithm='thres', est_params=True, lineshapes=None)
threshold = self.config.get('peak_threshold')
algorithm = self.algorithms[ self.config.get('algorithm')]
msep = ( self.config.get('peak_separation'),)
# Take input dataset and flatten in first dimension (average spectra)
data_avg = np.mean( input.data, axis=0)
# pick peaks and return locations;
#nmrglue.analysis.peakpick.pick(data, pthres, nthres=None, msep=None, algorithm='connected', est_params=True, lineshapes=None, edge=None, diag=False, c_struc=None, c_ndil=0, cluster=True, table=True, axis_names=['A', 'Z', 'Y', 'X'])[source]¶
locations, scales, amps = ng.analysis.peakpick.pick(data_avg, threshold, msep=msep, algorithm=algorithm, est_params = True, cluster=False, table=False)
#n_cluster = max( cluster_ids )
n_locations = len( locations )
new_shape = list( input.shape )
new_shape[1] = n_locations # correct number; tho will be zero indexed
# Convert to numpy arrays so we can do clever things
scales = [dso.scales[1][l[0]] for l in locations ]
# Adjust the scales (so aren't lost in crop)
dso.labels[1] = [ str(l) for l in scales]
dso.scales[1] = scales
dso.crop( new_shape )
# Iterate over the clusters (1 to n)
for n, l in enumerate(locations):
#l = locations[ cluster_ids == n ]
#peak_data = np.amax( peak_data, axis=1 ) # max across cols
dso.data[:,n-1] = input.data[:, l[0]]
# FIXME:
# Extract the location numbers (positions in original spectra)
# Get max value in each row for those regions
# Append that to n position in new dataset
# -- optionally use the line widths and take max within each of these for each spectra (peak shiftiness)
# Filter the original data with those locations and output\
return {'output':dso}
def generate(self, input=None):
dsi = input
###### BINNING USING CONFI
# Generate bin values for range start_scale to end_scale
# Calculate the number of bins at binsize across range
dso = DataSet()
dso.import_data(dsi)
r = dsi.scales_r[1]
self._bin_size, self._bin_offset = self.config.get('bin_size'), self.config.get('bin_offset')
bins = np.arange(r[0] + self._bin_offset, r[1] + self._bin_offset, self._bin_size)
number_of_bins = len(bins) - 1
# Can't increase the size of data, if bins > current size return the original
if number_of_bins >= len(dso.scales[1]):
return {'dso': dso}
# Resize (lossy) to the new shape
old_shape, new_shape = list(dsi.data.shape), list(dso.data.shape)
new_shape[1] = number_of_bins
dso.crop(new_shape) # Lossy crop, but we'll be within the boundary below
for n, d in enumerate(dsi.data):
binned_data = np.histogram(dsi.scales[1], bins=bins, weights=d)
binned_num = np.histogram(dsi.scales[1], bins=bins) # Number of data points that ended up contributing to each bin
dso.data[n, :] = binned_data[0] / binned_num[0] # Mean
dso.scales[1] = [float(x) for x in binned_data[1][:-1]]
#dso.labels[1] = [str(x) for x in binned_data[1][:-1]]
# Remove any NaNs that have crept in (due to the histogram)
dso.remove_invalid_data()
return {'output': dso, 'input': input} # Pass back input for difference plot
