Bio.Graphics.GenomeDiagram.

37 """ GraphData 38 39 Provides: 40 41 Methods: 42 43 o __init__(self, id=None, data=None, name=None, style='bar', 44 color=colors.lightgreen, altcolor=colors.darkseagreen) 45 Called on instantiation 46 47 o set_data(self, data) Load the object with data to be plotted 48 49 o get_data(self) Returns the data to be plotted as a list of 50 (position, value) tuples 51 52 o add_point(self, point) Add a single point to the data set 53 54 o quartiles(self) Returns a tuple of the data quartiles 55 56 o range(self) Returns a tuple of the base range covered by the graph 57 data 58 59 o mean(self) Returns a float of the mean data point value 60 61 o stdev(self) Returns the sample standard deviation of the data values 62 63 o __len__(self) Returns the length of sequence covered by the data 64 65 o __getitem__(self, index) Returns the value at the base specified, 66 or graph data in the base range 67 68 o __str__(self) Returns a formatted string describing the graph data 69 70 Attributes: 71 72 o id Unique identifier for the data 73 74 o data Dictionary of describing the data, keyed by position 75 76 o name String describing the data 77 78 o style String ('bar', 'heat', 'line') describing how to draw the data 79 80 o poscolor colors.Color for drawing high (some styles) or all 81 values 82 83 o negcolor colors.Color for drawing low values (some styles) 84 85 o linewidth Int, thickness to draw the line in 'line' styles 86 """

87 - def __init__(self, id=None, data=None, name=None, style='bar', 88 color=colors.lightgreen, altcolor=colors.darkseagreen, 89 center=None, colour=None, altcolour=None, centre=None):

90 """__init__(self, id=None, data=None, name=None, style='bar', 91 color=colors.lightgreen, altcolor=colors.darkseagreen) 92 93 o id Unique ID for the graph 94 95 o data List of (position, value) tuples 96 97 o name String describing the graph 98 99 o style String describing the presentation style ('bar', 'line', 100 'heat') 101 102 o color colors.Color describing the color to draw all or the 103 'high' (some styles) values (overridden by backwards 104 compatible argument with UK spelling, colour). 105 106 o altcolor colors.Color describing the color to draw the 'low' 107 values (some styles only) (overridden by backwards 108 compatible argument with UK spelling, colour). 109 110 o center Value at which x-axis crosses y-axis (overridden by 111 backwards comparible argument with UK spelling, centre). 112 113 """ 114 115 #Let the UK spelling (colour) override the USA spelling (color) 116 if colour is not None: 117 color = colour 118 if altcolour is not None: 119 altcolor = altcolour 120 if centre is not None: 121 center = centre 122 123 self.id = id # Unique identifier for the graph 124 self.data = {} # holds values, keyed by sequence position 125 if data is not None: 126 self.set_data(data) 127 self.name = name # Descriptive string 128 129 # Attributes describing how the graph will be drawn 130 self.style = style # One of 'bar', 'heat' or 'line' 131 self.poscolor = color # Color to draw all, or 'high' values 132 self.negcolor = altcolor # Color to draw 'low' values 133 self.linewidth = 2 # linewidth to use in line graphs 134 self.center = center # value at which x-axis crosses y-axis

135 136 @property

137 - def centre(self):

138 """Backwards compatible alias for center (DEPRECATED).""" 139 warnings.warn("The .centre attribute is deprecated, use .center instead", 140 Bio.BiopythonDeprecationWarning) 141 return self.center

142

143 - def set_data(self, data):

144 """ set_data(self, data) 145 146 o data List of (position, value) tuples 147 148 Add data with a list of (position, value) tuples 149 """ 150 for (pos, val) in data: # Fill data dictionary 151 self.data[pos] = val

152

153 - def get_data(self):

154 """ get_data(self) -> [(int, float), (int, float), ...] 155 156 Return data as a list of sorted (position, value) tuples 157 """ 158 data = [] 159 for xval in self.data.keys(): 160 yval = self.data[xval] 161 data.append((xval, yval)) 162 data.sort() 163 return data

164

165 - def add_point(self, point):

166 """ add_point(self, point) 167 168 o point (position, value) tuple 169 170 Add a single point to the set of data 171 """ 172 pos, val = point 173 self.data[pos] = val

174

175 - def quartiles(self):

176 """ quartiles(self) -> (float, float, float, float, float) 177 178 Returns the (minimum, lowerQ, medianQ, upperQ, maximum) values as 179 a tuple 180 """ 181 data = self.data.values() 182 data.sort() 183 datalen = len(data) 184 return(data[0], data[datalen//4], data[datalen//2], 185 data[3*datalen//4], data[-1])

186

187 - def range(self):

188 """ range(self) -> (int, int) 189 190 Returns the range of the data, i.e. its start and end points on 191 the genome as a (start, end) tuple 192 """ 193 positions = self.data.keys() 194 positions.sort() 195 # Return first and last positions in graph 196 #print len(self.data) 197 return (positions[0], positions[-1])

198

199 - def mean(self):

200 """ mean(self) -> Float 201 202 Returns the mean value for the data points 203 """ 204 data = self.data.values() 205 sum = 0. 206 for item in data: 207 sum += float(item) 208 return sum/len(data)

209

210 - def stdev(self):

211 """ stdev(self) -> Float 212 213 Returns the sample standard deviation for the data 214 """ 215 data = self.data.values() 216 m = self.mean() 217 runtotal = 0. 218 for entry in data: 219 runtotal += float((entry - m)**2) 220 # This is sample standard deviation; population stdev would involve 221 # division by len(data), rather than len(data)-1 222 return sqrt(runtotal/(len(data)-1))

223

224 - def __len__(self):

225 """ __len__(self) -> Int 226 227 Returns the number of points in the data set 228 """ 229 return len(self.data)

230

231 - def __getitem__(self, index):

232 """ __getitem__(self, index) -> Float or list of tuples 233 234 Given an integer representing position on the sequence 235 returns a float - the data value at the passed position. 236 237 If a slice, returns graph data from the region as a list or 238 (position, value) tuples. Slices with step are not supported. 239 240 Returns the data value at the passed position 241 """ 242 if isinstance(index, int): 243 return self.data[index] 244 elif isinstance(index, slice): 245 #TODO - Why does it treat the end points both as inclusive? 246 #This doesn't match Python norms does it? 247 low = index.start 248 high = index.stop 249 if index.step is not None and index.step != 1: 250 raise ValueError 251 positions = self.data.keys() 252 positions.sort() 253 outlist = [] 254 for pos in positions: 255 if pos >= low and pos <=high: 256 outlist.append((pos, self.data[pos])) 257 return outlist 258 else: 259 raise TypeError("Need an integer or a slice")

260

261 - def __str__(self):

262 """ __str__(self) -> "" 263 264 Returns a string describing the graph data 265 """ 266 outstr = ["\nGraphData: %s, ID: %s" % (self.name, self.id)] 267 outstr.append("Number of points: %d" % len(self.data)) 268 outstr.append("Mean data value: %s" % self.mean()) 269 outstr.append("Sample SD: %.3f" % self.stdev()) 270 outstr.append("Minimum: %s\n1Q: %s\n2Q: %s\n3Q: %s\nMaximum: %s" % self.quartiles()) 271 outstr.append("Sequence Range: %s..%s" % self.range()) 272 return "\n".join(outstr)

Source Code for Module Bio.Graphics.GenomeDiagram._Graph