Package rdkit :: Package ML :: Package MLUtils :: Module VoteImg
[hide private]
[frames] | no frames]

Source Code for Module rdkit.ML.MLUtils.VoteImg

  1  # 
  2  #  Copyright (C) 2000  greg Landrum 
  3  # 
  4  """ functionality for generating an image showing the results of a composite model 
  5  voting on a data set 
  6   
  7    Uses *Numeric* and *PIL* 
  8   
  9  """ 
 10  from __future__ import print_function 
 11   
 12  from PIL import Image, ImageDraw 
 13  import numpy 
 14   
 15   
16 -def CollectVotes(composite, data, badOnly):
17 """ collects the votes from _composite_ for the examples in _data_ 18 19 **Arguments** 20 21 - composite: a composite model 22 23 - data: a list of examples to run through _composite_ 24 25 - badOnly: if set only bad (misclassified) examples will be kept 26 27 **Returns** 28 29 a 4-tuple containing: 30 31 1) the expanded list of vote details (see below) 32 33 2) the list of predicted results 34 35 3) the list of true results 36 37 4) the number of miscounted examples 38 39 40 **Notes** 41 42 pp - the expanded list of vote details consists of: 43 44 '[ vote1, vote2, ... voteN, 0, res, trueRes]' 45 46 where _res_ is the predicted results and _trueRes_ is the actual result. 47 The extra zero is included to allow a line to be drawn between the votes 48 and the results. 49 50 """ 51 res = [] 52 values = [] 53 trueValues = [] 54 misCount = 0 55 for pt in data: 56 val, _ = composite.ClassifyExample(pt) 57 predict = pt[-1] 58 if not badOnly or val != predict: 59 values.append(val) 60 trueValues.append(predict) 61 if val != predict: 62 misCount = misCount + 1 63 res.append(composite.GetVoteDetails() + [0, val, pt[-1]]) 64 return res, values, trueValues, misCount
65 66
67 -def BuildVoteImage(nModels, data, values, trueValues=[], sortTrueVals=0, xScale=10, yScale=2, 68 addLine=1):
69 """ constructs the actual image 70 71 **Arguments** 72 73 - nModels: the number of models in the composite 74 75 - data: the results of voting 76 77 - values: predicted values for each example 78 79 - trueValues: true values for each example 80 81 - sortTrueVals: if nonzero the votes will be sorted so 82 that the _trueValues_ are in order, otherwise the sort 83 is by _values_ 84 85 - xScale: number of pixels per vote in the x direction 86 87 - yScale: number of pixels per example in the y direction 88 89 - addLine: if nonzero, a purple line is drawn separating 90 the votes from the examples 91 92 **Returns** 93 94 a PIL image 95 96 """ 97 nData = len(data) 98 data = numpy.array(data, numpy.integer) 99 if sortTrueVals and trueValues != []: 100 order = numpy.argsort(trueValues) 101 else: 102 order = numpy.argsort(values) 103 data = [data[x] for x in order] 104 maxVal = max(numpy.ravel(data)) 105 data = data * 255 / maxVal 106 datab = data.astype('B') 107 img = getattr(Image, 'frombytes', Image.fromstring)('L', (nModels, nData), 108 getattr(datab, 'tobytes', datab.tostring)()) 109 110 if addLine: 111 img = img.convert('RGB') 112 canvas = ImageDraw.Draw(img) 113 if trueValues != []: 114 canvas.line([(nModels - 3, 0), (nModels - 3, nData)], fill=(128, 0, 128)) 115 else: 116 canvas.line([(nModels - 2, 0), (nModels - 2, nData)], fill=(128, 0, 128)) 117 img = img.resize((nModels * xScale, nData * yScale)) 118 return img
119 120
121 -def VoteAndBuildImage(composite, data, badOnly=0, sortTrueVals=0, xScale=10, yScale=2, addLine=1):
122 """ collects votes on the examples and constructs an image 123 124 **Arguments** 125 126 - composte: a composite model 127 128 - data: the examples to be voted upon 129 130 - badOnly: if nonzero only the incorrect votes will be shown 131 132 - sortTrueVals: if nonzero the votes will be sorted so 133 that the _trueValues_ are in order, otherwise the sort 134 is by _values_ 135 136 - xScale: number of pixels per vote in the x direction 137 138 - yScale: number of pixels per example in the y direction 139 140 - addLine: if nonzero, a purple line is drawn separating 141 the votes from the examples 142 143 **Returns** 144 145 a PIL image 146 147 """ 148 nModels = len(composite) + 3 149 print('nModels:', nModels - 3) 150 151 res, values, trueValues, misCount = CollectVotes(composite, data, badOnly) 152 print('%d examples were misclassified' % misCount) 153 img = BuildVoteImage(nModels, res, values, trueValues, sortTrueVals, xScale, yScale, addLine) 154 return img
155 156
157 -def Usage():
158 """ provides a list of arguments for when this is used from the command line 159 160 """ 161 import sys 162 163 print('Usage: VoteImg.py [optional arguments] <modelfile.pkl> <datafile.qdat>') 164 print('Optional Arguments:') 165 print('\t-o outfilename: the name of the output image file.') 166 print('\t The extension determines the type of image saved.') 167 print('\t-b: only include bad (misclassified) examples') 168 print('\t-t: sort the results by the true (input) classification') 169 print('\t-x scale: scale the image along the x axis (default: 10)') 170 print('\t-y scale: scale the image along the y axis (default: 2)') 171 print('\t-d databasename: instead of using a qdat file, pull the data from') 172 print('\t a database. In this case the filename argument') 173 print('\t is used to indicate the name of the table in the database.') 174 175 sys.exit(-1)
176 177 178 if __name__ == '__main__': 179 import sys 180 import getopt 181 from rdkit.six.moves import cPickle 182 from rdkit.ML.Data import DataUtils 183 184 args, extra = getopt.getopt(sys.argv[1:], 'o:bthx:y:d:') 185 if len(extra) < 2: 186 Usage() 187 badOnly = 0 188 sortTrueVals = 0 189 xScale = 10 190 yScale = 2 191 dbName = '' 192 outFileName = 'foo.png' 193 for arg, val in args: 194 if arg == '-b': 195 badOnly = 1 196 elif arg == '-t': 197 sortTrueVals = 1 198 elif arg == '-o': 199 outFileName = val 200 elif arg == '-x': 201 xScale = int(val) 202 elif arg == '-y': 203 yScale = int(val) 204 elif arg == '-d': 205 dbName = val 206 elif arg == '-h': 207 Usage() 208 else: 209 Usage() 210 modelFile = open(extra[0], 'rb') 211 model = cPickle.load(modelFile) 212 213 fName = extra[1] 214 if dbName == '': 215 data = DataUtils.BuildQuantDataSet(fName) 216 else: 217 data = DataUtils.DBToQuantData(dbName, fName) # Function no longer defined 218 219 dataSet = data.GetNamedData() 220 221 img = VoteAndBuildImage(model, dataSet, badOnly=badOnly, sortTrueVals=sortTrueVals, xScale=xScale, 222 yScale=yScale) 223 img.save(outFileName) 224