Commit 729ebbcc3da2a194fee324b5b0108a27a2a8c091
1 parent
130f3114
initial version
Showing
1 changed file
with
155 additions
and
0 deletions
examples/show_ts_distribution.py
0 → 100755
| 1 | +#! /usr/bin/env python | ||
| 2 | +# ========================================================================== | ||
| 3 | +# This script displays pull histograms that have been generated using the | ||
| 4 | +# cspull script. The pull is defined by | ||
| 5 | +# | ||
| 6 | +# (fitted value - simulated value) / estimated error | ||
| 7 | +# | ||
| 8 | +# and the pull histogram allows to assess possible biases in the fit | ||
| 9 | +# parameters and errors. | ||
| 10 | +# | ||
| 11 | +# Required 3rd party modules: | ||
| 12 | +# - matplotlib | ||
| 13 | +# - numpy | ||
| 14 | +# | ||
| 15 | +# Copyright (C) 2011 Jurgen Knodlseder | ||
| 16 | +# | ||
| 17 | +# This program is free software: you can redistribute it and/or modify | ||
| 18 | +# it under the terms of the GNU General Public License as published by | ||
| 19 | +# the Free Software Foundation, either version 3 of the License, or | ||
| 20 | +# (at your option) any later version. | ||
| 21 | +# | ||
| 22 | +# This program is distributed in the hope that it will be useful, | ||
| 23 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| 24 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| 25 | +# GNU General Public License for more details. | ||
| 26 | +# | ||
| 27 | +# You should have received a copy of the GNU General Public License | ||
| 28 | +# along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
| 29 | +# | ||
| 30 | +# ========================================================================== | ||
| 31 | +import matplotlib.mlab as mlab | ||
| 32 | +import matplotlib.pyplot as plt | ||
| 33 | +import numpy as np | ||
| 34 | +import sys | ||
| 35 | +import csv | ||
| 36 | +import math | ||
| 37 | + | ||
| 38 | + | ||
| 39 | +# ==================== # | ||
| 40 | +# Read TS distribution # | ||
| 41 | +# ==================== # | ||
| 42 | +def read_ts(filename): | ||
| 43 | + """ | ||
| 44 | + Read TS distribution. | ||
| 45 | + """ | ||
| 46 | + # Initialise list | ||
| 47 | + values = [] | ||
| 48 | + | ||
| 49 | + # Open reader | ||
| 50 | + reader = csv.reader(open(filename, 'r'), delimiter=',') | ||
| 51 | + | ||
| 52 | + # Read rows | ||
| 53 | + first = True | ||
| 54 | + index = -1 | ||
| 55 | + for row in reader: | ||
| 56 | + | ||
| 57 | + # Get column index if first row | ||
| 58 | + if first: | ||
| 59 | + try: | ||
| 60 | + index = row.index("TS") | ||
| 61 | + except: | ||
| 62 | + print 'ERROR: Column "TS" not found in file' | ||
| 63 | + raise NameError("TS") | ||
| 64 | + #print index | ||
| 65 | + | ||
| 66 | + # Handle data rows | ||
| 67 | + else: | ||
| 68 | + values.append(float(row[index])) | ||
| 69 | + | ||
| 70 | + # Flag that first row has been passed | ||
| 71 | + first = False | ||
| 72 | + | ||
| 73 | + # Create numpy array | ||
| 74 | + a = np.array(values) | ||
| 75 | + #print a | ||
| 76 | + | ||
| 77 | + # Return array | ||
| 78 | + return a | ||
| 79 | + | ||
| 80 | + | ||
| 81 | +# ======================== # | ||
| 82 | +# Main routine entry point # | ||
| 83 | +# ======================== # | ||
| 84 | +if __name__ == '__main__': | ||
| 85 | + """ | ||
| 86 | + Display pull histogram generated by cspull using matplotlib. | ||
| 87 | + """ | ||
| 88 | + # Print usage information | ||
| 89 | + usage = "Usage: show_ts_distribution filename [bins]" | ||
| 90 | + if len(sys.argv) < 2: | ||
| 91 | + print usage | ||
| 92 | + sys.exit() | ||
| 93 | + | ||
| 94 | + # Extract parameters | ||
| 95 | + filename = sys.argv[1] | ||
| 96 | + if len(sys.argv) == 3: | ||
| 97 | + nbins = int(sys.argv[2]) | ||
| 98 | + else: | ||
| 99 | + nbins = 30 | ||
| 100 | + | ||
| 101 | + # Set lin/log | ||
| 102 | + log = False | ||
| 103 | + | ||
| 104 | + # Read values from CSV file | ||
| 105 | + values = read_ts(filename) | ||
| 106 | + print len(values), "values read." | ||
| 107 | + | ||
| 108 | + # Set range and adapt number of bins. We make sure that we have a | ||
| 109 | + # histogram bin centred on 0 that will capture the TS=0 part. | ||
| 110 | + max_value = max(values) | ||
| 111 | + binsize = max_value/nbins | ||
| 112 | + min_value = 0.5*binsize | ||
| 113 | + while min_value > min(values): | ||
| 114 | + min_value -= binsize | ||
| 115 | + nbins += 1 | ||
| 116 | + | ||
| 117 | + # Create histogram | ||
| 118 | + n, bins, patches = plt.hist(values, nbins, range=[min_value, max_value], \ | ||
| 119 | + align='mid', normed=True, facecolor='green', \ | ||
| 120 | + log=log) | ||
| 121 | + | ||
| 122 | + # Create expected distribution (onyl for positive TS). We compute the | ||
| 123 | + # full and half of the distribution, as for positively constrained | ||
| 124 | + # quantities half of the values have TS=0 | ||
| 125 | + x = [] | ||
| 126 | + y_full = [] | ||
| 127 | + y_half = [] | ||
| 128 | + norm = 1.0/(math.sqrt(2.0)*math.sqrt(math.pi)) | ||
| 129 | + width = bins[1]-bins[0] | ||
| 130 | + x.append(0.0) | ||
| 131 | + y_full.append(1.0/width) | ||
| 132 | + y_half.append(0.5/width) | ||
| 133 | + for bin in bins: | ||
| 134 | + ts = bin + 0.5*width | ||
| 135 | + if ts > 0: | ||
| 136 | + y = norm*math.pow(ts,-0.5)*math.exp(-0.5*ts) | ||
| 137 | + x.append(ts) | ||
| 138 | + y_full.append(y) | ||
| 139 | + y_half.append(0.5*y) | ||
| 140 | + | ||
| 141 | + # Show expected distribution (half) | ||
| 142 | + if log: | ||
| 143 | + l = plt.semilogy(x, y_half, 'ro', linewidth=2) | ||
| 144 | + else: | ||
| 145 | + l = plt.plot(x, y_half, 'r-', linewidth=2) | ||
| 146 | + | ||
| 147 | + # Set plot | ||
| 148 | + plt.xlabel('TS') | ||
| 149 | + plt.ylabel('Arbitrary units') | ||
| 150 | + plt.title('TS distribution') | ||
| 151 | + plt.grid(True) | ||
| 152 | + | ||
| 153 | + # Show histogram | ||
| 154 | + plt.show() | ||
| 155 | + | ||
| 0 | \ No newline at end of file | 156 | \ No newline at end of file |