Friis/TancNote/build_nn_observables.py

#!/usr/bin/env python
import os
import glob
import re
from string import Template

LATEX_NAME_MAPPING = {
    'OneProngNoPiZero':
    r'$\tau^{-} \rightarrow \pi^{-}$',
    'OneProngOnePiZero':
    r'$\tau^{-} \rightarrow \pi^{-}\pi^0$',
    'OneProngTwoPiZero':
    r'$\tau^{-} \rightarrow \pi^{-}\pi^0\pi^0$',
    'ThreeProngNoPiZero':
    r'$\tau^{-} \rightarrow \pi^{-}\pi^{+}\pi^{-}$',
    'ThreeProngOnePiZero':
    r'$\tau^{-} \rightarrow \pi^{-}\pi^{+}\pi^{-}\pi^0$',
}

PLOT_TEMPLATE = Template(
r'''\put($x, $y) {\mbox{\includegraphics*[height=60mm]{${file_location}}}}
    \put(${letterx}, ${lettery}){\small ($letter)}
''')


FIGURE_TEMPLATE = Template(
r'''
\begin{figure}[b]
\setlength{\unitlength}{1mm}
\begin{center}

\begin{picture}($width, $height)(0,0)
${figures}
\end{picture}

\caption{ 
    Training sample distributions of signal (red) and background (blue) for different observables used
    (see section~\ref{sec:$decayModeSection}) in the neural network corresponding to the $decaymode decay mode.
}

\label{fig:${label}}
\end{center}
\end{figure}
''')

VARIABLE_TEMPLATE = Template(
r'''
\begin{itemize}
    $items
\end{itemize}
''')

VARIABLE_ITEM_TEMPLATE = Template(
r'''
    \item $item (Figure~$description)
''')

#VARIABLE_TEMPLATE = Template(
#r'''
#\begin{table}[h]
#   \centering
#   \begin{tabular}{l|r}
#   Input observable & Figure index \\
#   \hline
#    $items
#   \end{tabular}
#\end{table}
#''')
#
#VARIABLE_ITEM_TEMPLATE = Template(
#r'''
#$item & $description \\
#''')

DESCRIPTION_TEMPLATE = Template(
r'''
\begin{description}
    $items
\end{description}
    
''')

DESCRIPTION_ITEM_TEMPLATE = Template(
r'''
  \item[$item] \hfill \\
  $description
''')

VAR_DESCRIPTIONS = {
    'ChargedOutlierAngleN': 
    r'''$\Delta R$ between the Nth charged object (ordered by $P_T$) in the isolation region
    and the tau--candidate momentum axis. If the number of
    isolation region objects is less than N, the input is set at one.''',

    'ChargedOutlierPtN': r'''Transverse momentum of the Nth charged object in the isolation region.  If the number of
    isolation region objects is less than N, the input is set at zero.''',

    'DalitzN': r''' Invariant mass of four vector sum of the ``main track'' and the Nth signal
    region object ''',

    'Eta': r'''Pseudo-rapidity of the signal region objects ''',

    'InvariantMassOfSignal': r'''Invariant mass of the composite object formed by the signal region constituents''',
    
    'MainTrackAngle': r'''$\Delta R$ between the ``main track'' and the composite four--vector formed by the 
    signal region constituents''',
    
    'MainTrackPt': r'''Transverse momentum of the ``main track'' ''',

    'OutlierNCharged': r'''Number of charged objects in the isolation region''',

    'OutlierSumPt': r'''Sum of the transverse momentum of objects in the isolation region''',

    'PiZeroAngleN': r'''$\Delta R$ between the Nth $\pi^0$ object in the signal region (ordered by $P_T$) and
    the tau--candidate momentum axis''',

    'PiZeroPtN': r'''Transverse momentum of the Nth $\pi^0$ object in the signal region.''',

    'TrackAngleN': r'''$\Delta R$ between the Nth charged object in the signal region (ordered by $P_T$) and
    the tau--candidate momentum axis, exclusive of the main track.''',

    'TrackPtN': r'''Transverse momentum of the Nth charged object in the signal region, exclusive of the 
    main track''',
}

def groups_of(group_size, iterable):
    count = 0
    output = []
    for item in iterable:
        output.append(item)
        count += 1
        if count == group_size:
            count = 0
            yield output
            output = []
    # Yield partial at end
    if output:
        yield output

def put_eta_first(x, y):
    if x == 'Eta':
        return 1
    if y == 'Eta':
        return -1
    return cmp(x,y)

if __name__=="__main__":
    # parse file names
    file_name_matcher = re.compile(r'(?P<network>[^_]*)_(?P<variable>\w*).pdf')

    figures_list = glob.glob('figures/NeuralNetObservables/*.pdf')

    # Keep track of all our plots
    info_dict = {}

    variable_list = []

    for figure_file in figures_list:
        figure_file_name = os.path.basename(figure_file)
        parse = file_name_matcher.match(figure_file_name)
        network = parse.group('network')
        variable = parse.group('variable')

        # skip correlation variable
        if variable == 'correlation':
            continue

        # Get the dict for this network, otherwise create a new one
        network_dict = info_dict.setdefault(network, {})
        network_dict[variable] = figure_file

        # Remove trailing indices from variables

        variable_list.append(re.sub("[0-9]+$", "N", variable))

    # Build description of variables
    variable_set = list(set(variable_list))
    variable_set.sort()
    print variable_set

    description_output_file = open(os.path.join(
            'note/observable_distributions/','var_descriptions.tex'), 'w')
    description_items = ""
    for variable in variable_set:
        description_items += DESCRIPTION_ITEM_TEMPLATE.substitute(
            item = variable, description=VAR_DESCRIPTIONS[variable]
        )

    description_output_file.write(DESCRIPTION_TEMPLATE.substitute(
        items = description_items))

    # Loop over neural nets and build each section
    for network, network_info in info_dict.iteritems():
        print ""
        print "Building %s" % network
        output_file = open(os.path.join(
            'note/observable_distributions/', network+'.tex'), 'w')

        section_label = '%s_input_descriptions' % network
        output = "\label{sec:%s}\n" % section_label

        # Count variables
        variables = network_info.keys()
        # Sort nicely
        variables.sort(put_eta_first)
        n_vars = len(variables)


        variable_table_entries=""

        # max group size of 5
        for figure_index, plot_group in enumerate(groups_of(6, variables)):
            letter_values = list("abcdefghijklmnopqrstuv")
            current_height = 0
            figures_list = ""
            figure_label = "%s_%i" % (network, figure_index)
            for plot_row in groups_of(2, plot_group):

                letter = letter_values.pop(0)
                figures_list += PLOT_TEMPLATE.substitute(
                    x = 0.5, y = current_height, 
                    letterx=0.5+10, lettery=current_height+60, letter=letter,
                    file_location = network_info[plot_row[0]])

                # Update variable table
                variable_table_entries += VARIABLE_ITEM_TEMPLATE.substitute(
                    item=plot_row[0], 
                    description=r"\ref{fig:%s}%s"% (figure_label, letter))

                letter = letter_values.pop(0)
                figures_list += PLOT_TEMPLATE.substitute(
                    x = 65, y = current_height, 
                    letterx=65+10, lettery=current_height+60, letter=letter,
                    file_location = network_info[plot_row[1]])

                # Update variable table
                variable_table_entries += VARIABLE_ITEM_TEMPLATE.substitute(
                    item=plot_row[1], 
                    description=r"\ref{fig:%s}%s"% (figure_label, letter))

                # go to next row
                current_height += 65

            output += FIGURE_TEMPLATE.substitute(
                width=130, height=current_height,
                figures = figures_list,
                decaymode = LATEX_NAME_MAPPING[network],
                decayModeSection=section_label, label = figure_label)

        variable_index = VARIABLE_TEMPLATE.substitute(
            items = variable_table_entries)

        output_file.write(variable_index)

        output_file.write(output)


Revision:	1.1
Committed:	Thu Apr 22 16:28:45 2010 UTC (15 years ago) by friis
Content type:	text/x-python
Branch:	MAIN
Log Message:	Cleanup some, (not all) of references/citations
#	User	Rev	Content
1	friis	1.1	#!/usr/bin/env python
2			import os
3			import glob
4			import re
5			from string import Template
6
7			LATEX_NAME_MAPPING = {
8			'OneProngNoPiZero':
9			r'$\tau^{-} \rightarrow \pi^{-}$',
10			'OneProngOnePiZero':
11			r'$\tau^{-} \rightarrow \pi^{-}\pi^0$',
12			'OneProngTwoPiZero':
13			r'$\tau^{-} \rightarrow \pi^{-}\pi^0\pi^0$',
14			'ThreeProngNoPiZero':
15			r'$\tau^{-} \rightarrow \pi^{-}\pi^{+}\pi^{-}$',
16			'ThreeProngOnePiZero':
17			r'$\tau^{-} \rightarrow \pi^{-}\pi^{+}\pi^{-}\pi^0$',
18			}
19
20			PLOT_TEMPLATE = Template(
21			r'''\put($x, $y) {\mbox{\includegraphics*[height=60mm]{${file_location}}}}
22			\put(${letterx}, ${lettery}){\small ($letter)}
23			''')
24
25
26			FIGURE_TEMPLATE = Template(
27			r'''
28			\begin{figure}[b]
29			\setlength{\unitlength}{1mm}
30			\begin{center}
31
32			\begin{picture}($width, $height)(0,0)
33			${figures}
34			\end{picture}
35
36			\caption{
37			Training sample distributions of signal (red) and background (blue) for different observables used
38			(see section~\ref{sec:$decayModeSection}) in the neural network corresponding to the $decaymode decay mode.
39			}
40
41			\label{fig:${label}}
42			\end{center}
43			\end{figure}
44			''')
45
46			VARIABLE_TEMPLATE = Template(
47			r'''
48			\begin{itemize}
49			$items
50			\end{itemize}
51			''')
52
53			VARIABLE_ITEM_TEMPLATE = Template(
54			r'''
55			\item $item (Figure~$description)
56			''')
57
58			#VARIABLE_TEMPLATE = Template(
59			#r'''
60			#\begin{table}[h]
61			# \centering
62			# \begin{tabular}{l\|r}
63			# Input observable & Figure index \\
64			# \hline
65			# $items
66			# \end{tabular}
67			#\end{table}
68			#''')
69			#
70			#VARIABLE_ITEM_TEMPLATE = Template(
71			#r'''
72			#$item & $description \\
73			#''')
74
75			DESCRIPTION_TEMPLATE = Template(
76			r'''
77			\begin{description}
78			$items
79			\end{description}
80
81			''')
82
83			DESCRIPTION_ITEM_TEMPLATE = Template(
84			r'''
85			\item[$item] \hfill \\
86			$description
87			''')
88
89			VAR_DESCRIPTIONS = {
90			'ChargedOutlierAngleN':
91			r'''$\Delta R$ between the Nth charged object (ordered by $P_T$) in the isolation region
92			and the tau--candidate momentum axis. If the number of
93			isolation region objects is less than N, the input is set at one.''',
94
95			'ChargedOutlierPtN': r'''Transverse momentum of the Nth charged object in the isolation region. If the number of
96			isolation region objects is less than N, the input is set at zero.''',
97
98			'DalitzN': r''' Invariant mass of four vector sum of the ``main track'' and the Nth signal
99			region object ''',
100
101			'Eta': r'''Pseudo-rapidity of the signal region objects ''',
102
103			'InvariantMassOfSignal': r'''Invariant mass of the composite object formed by the signal region constituents''',
104
105			'MainTrackAngle': r'''$\Delta R$ between the ``main track'' and the composite four--vector formed by the
106			signal region constituents''',
107
108			'MainTrackPt': r'''Transverse momentum of the ``main track'' ''',
109
110			'OutlierNCharged': r'''Number of charged objects in the isolation region''',
111
112			'OutlierSumPt': r'''Sum of the transverse momentum of objects in the isolation region''',
113
114			'PiZeroAngleN': r'''$\Delta R$ between the Nth $\pi^0$ object in the signal region (ordered by $P_T$) and
115			the tau--candidate momentum axis''',
116
117			'PiZeroPtN': r'''Transverse momentum of the Nth $\pi^0$ object in the signal region.''',
118
119			'TrackAngleN': r'''$\Delta R$ between the Nth charged object in the signal region (ordered by $P_T$) and
120			the tau--candidate momentum axis, exclusive of the main track.''',
121
122			'TrackPtN': r'''Transverse momentum of the Nth charged object in the signal region, exclusive of the
123			main track''',
124			}
125
126			def groups_of(group_size, iterable):
127			count = 0
128			output = []
129			for item in iterable:
130			output.append(item)
131			count += 1
132			if count == group_size:
133			count = 0
134			yield output
135			output = []
136			# Yield partial at end
137			if output:
138			yield output
139
140			def put_eta_first(x, y):
141			if x == 'Eta':
142			return 1
143			if y == 'Eta':
144			return -1
145			return cmp(x,y)
146
147			if __name__=="__main__":
148			# parse file names
149			file_name_matcher = re.compile(r'(?P<network>[^_])_(?P<variable>\w).pdf')
150
151			figures_list = glob.glob('figures/NeuralNetObservables/*.pdf')
152
153			# Keep track of all our plots
154			info_dict = {}
155
156			variable_list = []
157
158			for figure_file in figures_list:
159			figure_file_name = os.path.basename(figure_file)
160			parse = file_name_matcher.match(figure_file_name)
161			network = parse.group('network')
162			variable = parse.group('variable')
163
164			# skip correlation variable
165			if variable == 'correlation':
166			continue
167
168			# Get the dict for this network, otherwise create a new one
169			network_dict = info_dict.setdefault(network, {})
170			network_dict[variable] = figure_file
171
172			# Remove trailing indices from variables
173
174			variable_list.append(re.sub("[0-9]+$", "N", variable))
175
176			# Build description of variables
177			variable_set = list(set(variable_list))
178			variable_set.sort()
179			print variable_set
180
181			description_output_file = open(os.path.join(
182			'note/observable_distributions/','var_descriptions.tex'), 'w')
183			description_items = ""
184			for variable in variable_set:
185			description_items += DESCRIPTION_ITEM_TEMPLATE.substitute(
186			item = variable, description=VAR_DESCRIPTIONS[variable]
187			)
188
189			description_output_file.write(DESCRIPTION_TEMPLATE.substitute(
190			items = description_items))
191
192			# Loop over neural nets and build each section
193			for network, network_info in info_dict.iteritems():
194			print ""
195			print "Building %s" % network
196			output_file = open(os.path.join(
197			'note/observable_distributions/', network+'.tex'), 'w')
198
199			section_label = '%s_input_descriptions' % network
200			output = "\label{sec:%s}\n" % section_label
201
202			# Count variables
203			variables = network_info.keys()
204			# Sort nicely
205			variables.sort(put_eta_first)
206			n_vars = len(variables)
207
208
209			variable_table_entries=""
210
211			# max group size of 5
212			for figure_index, plot_group in enumerate(groups_of(6, variables)):
213			letter_values = list("abcdefghijklmnopqrstuv")
214			current_height = 0
215			figures_list = ""
216			figure_label = "%s_%i" % (network, figure_index)
217			for plot_row in groups_of(2, plot_group):
218
219			letter = letter_values.pop(0)
220			figures_list += PLOT_TEMPLATE.substitute(
221			x = 0.5, y = current_height,
222			letterx=0.5+10, lettery=current_height+60, letter=letter,
223			file_location = network_info[plot_row[0]])
224
225			# Update variable table
226			variable_table_entries += VARIABLE_ITEM_TEMPLATE.substitute(
227			item=plot_row[0],
228			description=r"\ref{fig:%s}%s"% (figure_label, letter))
229
230			letter = letter_values.pop(0)
231			figures_list += PLOT_TEMPLATE.substitute(
232			x = 65, y = current_height,
233			letterx=65+10, lettery=current_height+60, letter=letter,
234			file_location = network_info[plot_row[1]])
235
236			# Update variable table
237			variable_table_entries += VARIABLE_ITEM_TEMPLATE.substitute(
238			item=plot_row[1],
239			description=r"\ref{fig:%s}%s"% (figure_label, letter))
240
241			# go to next row
242			current_height += 65
243
244			output += FIGURE_TEMPLATE.substitute(
245			width=130, height=current_height,
246			figures = figures_list,
247			decaymode = LATEX_NAME_MAPPING[network],
248			decayModeSection=section_label, label = figure_label)
249
250			variable_index = VARIABLE_TEMPLATE.substitute(
251			items = variable_table_entries)
252
253			output_file.write(variable_index)
254
255			output_file.write(output)
256
257
258
259