/usr/share/pyshared/pychart/chart_data.py is in python-pychart 1.39-7.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | #
# Copyright (C) 2000-2005 by Yasushi Saito (yasushi.saito@gmail.com)
#
# Jockey is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the
# Free Software Foundation; either version 2, or (at your option) any
# later version.
#
# Jockey is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
# for more details.
#
import pychart_util
import copy
import math
def _convert_item(v, typ, line):
if typ == "a":
try:
i = float(v)
except ValueError: # non-number
i = v
return i
elif typ == "d":
try:
return int(v)
except ValueError:
raise ValueError, "Can't convert %s to int; line=%s" % (v, line)
elif typ == "f":
try:
return float(v)
except ValueError:
raise ValueError, "Can't convert %s to float; line=%s" % (v, line)
elif typ == "s":
return v
else:
raise ValueError, "Unknown conversion type, type=%s; line=%s" % (typ,line)
def parse_line(line, delim):
if delim.find("%") < 0:
return [ _convert_item(item, "a", None) for item in line.split(delim) ]
data = []
idx = 0 # indexes delim
ch = 'f'
sep = ','
while idx < len(delim):
if delim[idx] != '%':
raise ValueError, 'Bad delimitor: "%s"' % delim
ch = delim[idx+1]
idx += 2
sep = ""
while idx < len(delim) and delim[idx] != '%':
sep += delim[idx]
idx += 1
if sep != "":
xx = line.split(sep, 1)
else:
# reached the end of the delimiter string.
xx = (line, )
data.append(_convert_item(xx[0], ch, line))
if len(xx) >= 2:
line = xx[1]
else:
line = ""
break
if line != "":
for item in line.split(sep):
data.append(_convert_item(item, ch, line))
return data
def escape_string(str):
return str.replace("/", "//")
def extract_rows(data, *rows):
"""Extract rows specified in the argument list.
>>> chart_data.extract_rows([[10,20], [30,40], [50,60]], 1, 2)
[[30,40],[50,60]]
"""
try:
# for python 2.2
# return [data[r] for r in rows]
out = []
for r in rows:
out.append(data[r])
return out
except IndexError:
raise IndexError, "data=%s rows=%s" % (data, rows)
return out
def extract_columns(data, *cols):
"""Extract columns specified in the argument list.
>>> chart_data.extract_columns([[10,20], [30,40], [50,60]], 0)
[[10],[30],[50]]
"""
out = []
try:
# for python 2.2:
# return [ [r[c] for c in cols] for r in data]
for r in data:
col = []
for c in cols:
col.append(r[c])
out.append(col)
except IndexError:
raise IndexError, "data=%s col=%s" % (data, col)
return out
def moving_average(data, xcol, ycol, width):
"""Compute the moving average of YCOL'th column of each sample point
in DATA. In particular, for each element I in DATA,
this function extracts up to WIDTH*2+1 elements, consisting of
I itself, WIDTH elements before I, and WIDTH
elements after I. It then computes the mean of the YCOL'th
column of these elements, and it composes a two-element sample
consisting of XCOL'th element and the mean.
>>> data = [[10,20], [20,30], [30,50], [40,70], [50,5]]
... chart_data.moving_average(data, 0, 1, 1)
[(10, 25.0), (20, 33.333333333333336), (30, 50.0), (40, 41.666666666666664), (50, 37.5)]
The above value actually represents:
[(10, (20+30)/2), (20, (20+30+50)/3), (30, (30+50+70)/3),
(40, (50+70+5)/3), (50, (70+5)/2)]
"""
out = []
try:
for i in range(len(data)):
n = 0
total = 0
for j in range(i-width, i+width+1):
if j >= 0 and j < len(data):
total += data[j][ycol]
n += 1
out.append((data[i][xcol], float(total) / n))
except IndexError:
raise IndexError, "bad data: %s,xcol=%d,ycol=%d,width=%d" % (data,xcol,ycol,width)
return out
def filter(func, data):
"""Parameter <func> must be a single-argument
function that takes a sequence (i.e.,
a sample point) and returns a boolean. This procedure calls <func> on
each element in <data> and returns a list comprising elements for
which <func> returns True.
>>> data = [[1,5], [2,10], [3,13], [4,16]]
... chart_data.filter(lambda x: x[1] % 2 == 0, data)
[[2,10], [4,16]].
"""
out = []
for r in data:
if func(r):
out.append(r)
return out
def transform(func, data):
"""Apply <func> on each element in <data> and return the list
consisting of the return values from <func>.
>>> data = [[10,20], [30,40], [50,60]]
... chart_data.transform(lambda x: [x[0], x[1]+1], data)
[[10, 21], [30, 41], [50, 61]]
"""
out = []
for r in data:
out.append(func(r))
return out
def aggregate_rows(data, col):
out = copy.deepcopy(data)
total = 0
for r in out:
total += r[col]
r[col] = total
return out
def empty_line_p(s):
return s.strip() == ""
def _try_open_file(path, mode, error_message):
try:
fd = open(path, mode)
except TypeError:
fd = path
if not getattr(fd, "readline", None):
raise TypeError, error_message + "(got %s)" % str(fd)
return fd
def _try_close_file(fd, path):
if fd != path:
fd.close()
def read_csv(path, delim = ','):
"""This function reads comma-separated values from a
file. Parameter <path> is either a pathname or a file-like object
that supports the |readline()| method.
Empty lines and lines
beginning with "#" are ignored. Parameter <delim> specifies how
a line is separated into values. If it does not contain the
letter "%", then <delim> marks the end of a value.
Otherwise, this function acts like scanf in C:
chart_data.read_csv('file', '%d,%s:%d')
Paramter <delim> currently supports
only three conversion format specifiers:
"d"(int), "f"(double), and "s"(string)."""
fd = _try_open_file(path, 'r',
'The first argument must be a pathname or an object that supports readline() method')
data = []
line = fd.readline()
while line != "":
if line[0] != '#' and not empty_line_p(line):
data.append(parse_line(line, delim))
line = fd.readline()
_try_close_file(fd, path)
return data
def fread_csv(fd, delim = ','):
"""This function is deprecated. Use read_csv instead."""
pychart_util.warn("chart_data.fread_csv is deprecated. Use read_csv instead.")
return read_csv(fd, delim)
def write_csv(path, data):
"""This function writes comma-separated <data> to
<path>. Parameter <path> is either a pathname or a file-like
object that supports the |write()| method."""
fd = _try_open_file(path, 'w',
'The first argument must be a pathname or an object that supports write() method')
for v in data:
fd.write(",".join([str(x) for x in v]))
fd.write("\n")
_try_close_file(fd, path)
def fwrite_csv(fd, delim = ','):
"""This function is deprecated. Use write_csv instead."""
pychart_util.warn("chart_data.fwrite_csv is deprecated. Use write_csv instead.")
return write_csv(fd, delim)
def read_str(delim = ',', *lines):
"""This function is similar to read_csv, but it reads data from the
list of <lines>.
fd = open("foo", "r")
data = chart_data.read_str(",", fd.readlines())"""
data = []
for line in lines:
com = parse_line(line, delim)
data.append(com)
return data
def func(f, xmin, xmax, step = None):
"""Create sample points from function <f>, which must be a
single-parameter function that returns a number (e.g., math.sin).
Parameters <xmin> and <xmax> specify the first and last X values, and
<step> specifies the sampling interval.
>>> chart_data.func(math.sin, 0, math.pi * 4, math.pi / 2)
[(0, 0.0), (1.5707963267948966, 1.0), (3.1415926535897931, 1.2246063538223773e-16), (4.7123889803846897, -1.0), (6.2831853071795862, -2.4492127076447545e-16), (7.8539816339744828, 1.0), (9.4247779607693793, 3.6738190614671318e-16), (10.995574287564276, -1.0)]
"""
data = []
x = xmin
if not step:
step = (xmax - xmin) / 100.0
while x < xmax:
data.append((x, f(x)))
x += step
return data
def _nr_data(data, col):
nr_data = 0
for d in data:
nr_data += d[col]
return nr_data
def median(data, freq_col=1):
"""Compute the median of the <freq_col>'th column of the values is <data>.
>>> chart_data.median([(10,20), (20,4), (30,5)], 0)
20
>>> chart_data.median([(10,20), (20,4), (30,5)], 1)
5.
"""
nr_data = _nr_data(data, freq_col)
median_idx = nr_data / 2
i = 0
for d in data:
i += d[freq_col]
if i >= median_idx:
return d
raise Exception, "??? median ???"
def cut_extremes(data, cutoff_percentage, freq_col=1):
nr_data = _nr_data(data, freq_col)
min_idx = nr_data * cutoff_percentage / 100.0
max_idx = nr_data * (100 - cutoff_percentage) / 100.0
r = []
i = 0
for d in data:
if i < min_idx:
if i + d[freq_col] >= min_idx:
x = copy.deepcopy(d)
x[freq_col] = x[freq_col] - (min_idx - i)
r.append(x)
i += d[freq_col]
continue
elif i + d[freq_col] >= max_idx:
if i < max_idx and i + d[freq_col] >= max_idx:
x = copy.deepcopy(d)
x[freq_col] = x[freq_col] - (max_idx - i)
r.append(x)
break
i += d[freq_col]
r.append(d)
return r
def mean(data, val_col, freq_col):
nr_data = 0
sum = 0
for d in data:
sum += d[val_col] * d[freq_col]
nr_data += d[freq_col]
if nr_data == 0:
raise IndexError, "data is empty"
return sum / float(nr_data)
def mean_samples(data, xcol, ycollist):
"""Create a sample list that contains
the mean of the original list.
>>> chart_data.mean_samples([ [1, 10, 15], [2, 5, 10], [3, 8, 33] ], 0, (1, 2))
[(1, 12.5), (2, 7.5), (3, 20.5)]
"""
out = []
numcol = len(ycollist)
try:
for elem in data:
v = 0
for col in ycollist:
v += elem[col]
out.append( (elem[xcol], float(v) / numcol) )
except IndexError:
raise IndexError, "bad data: %s,xcol=%d,ycollist=%s" % (data,xcol,ycollist)
return out
def stddev_samples(data, xcol, ycollist, delta = 1.0):
"""Create a sample list that contains the mean and standard deviation of the original list. Each element in the returned list contains following values: [MEAN, STDDEV, MEAN - STDDEV*delta, MEAN + STDDEV*delta].
>>> chart_data.stddev_samples([ [1, 10, 15, 12, 15], [2, 5, 10, 5, 10], [3, 32, 33, 35, 36], [4,16,66, 67, 68] ], 0, range(1,5))
[(1, 13.0, 2.1213203435596424, 10.878679656440358, 15.121320343559642), (2, 7.5, 2.5, 5.0, 10.0), (3, 34.0, 1.5811388300841898, 32.418861169915807, 35.581138830084193), (4, 54.25, 22.094965489902897, 32.155034510097103, 76.344965489902904)]
"""
out = []
numcol = len(ycollist)
try:
for elem in data:
total = 0
for col in ycollist:
total += elem[col]
mean = float(total) / numcol
variance = 0
for col in ycollist:
variance += (mean - elem[col]) ** 2
stddev = math.sqrt(variance / numcol) * delta
out.append( (elem[xcol], mean, stddev, mean-stddev, mean+stddev) )
except IndexError:
raise IndexError, "bad data: %s,xcol=%d,ycollist=%s" % (data,xcol,ycollist)
return out
def nearest_match(data, col, val):
min_delta = None
match = None
for d in data:
if min_delta == None or abs(d[col] - val) < min_delta:
min_delta = abs(d[col] - val)
match = d
pychart_util.warn("XXX ", match)
return match
|