def run()

in senteval/tools/validation.py [0:0]
40 lines of code
12 McCabe index (conditional complexity)

    def run(self):
        logging.info('Training {0} with standard validation..'
                     .format(self.modelname))
        regs = [10**t for t in range(-5, -1)] if self.usepytorch else \
               [2**t for t in range(-2, 4, 1)]
        if self.noreg:
            regs = [1e-9 if self.usepytorch else 1e9]
        scores = []
        for reg in regs:
            if self.usepytorch:
                clf = MLP(self.classifier_config, inputdim=self.featdim,
                          nclasses=self.nclasses, l2reg=reg,
                          seed=self.seed, cudaEfficient=self.cudaEfficient)

                # TODO: Find a hack for reducing nb epoches in SNLI
                clf.fit(self.X['train'], self.y['train'],
                        validation_data=(self.X['valid'], self.y['valid']))
            else:
                clf = LogisticRegression(C=reg, random_state=self.seed)
                clf.fit(self.X['train'], self.y['train'])
            scores.append(round(100*clf.score(self.X['valid'],
                                self.y['valid']), 2))
        logging.info([('reg:'+str(regs[idx]), scores[idx])
                      for idx in range(len(scores))])
        optreg = regs[np.argmax(scores)]
        devaccuracy = np.max(scores)
        logging.info('Validation : best param found is reg = {0} with score \
            {1}'.format(optreg, devaccuracy))
        clf = LogisticRegression(C=optreg, random_state=self.seed)
        logging.info('Evaluating...')
        if self.usepytorch:
            clf = MLP(self.classifier_config, inputdim=self.featdim,
                      nclasses=self.nclasses, l2reg=optreg,
                      seed=self.seed, cudaEfficient=self.cudaEfficient)

            # TODO: Find a hack for reducing nb epoches in SNLI
            clf.fit(self.X['train'], self.y['train'],
                    validation_data=(self.X['valid'], self.y['valid']))
        else:
            clf = LogisticRegression(C=optreg, random_state=self.seed)
            clf.fit(self.X['train'], self.y['train'])

        testaccuracy = clf.score(self.X['test'], self.y['test'])
        testaccuracy = round(100*testaccuracy, 2)
        return devaccuracy, testaccuracy