def score(self):
self.logger.info('Scoring...')
npXTest = np.array(self.X_test).astype(np.float32)
y_pred = self.classifier.predict(npXTest)
yy_pred = self.classifier.predict_proba(npXTest)[:,1]
print('\n***')
print(self.features.shape)
print(self.test.shape)
print('***\n')
reportName = 'Cross Verification Data Report \t\t' + str(dt.datetime.now())
scorer = Scorer()
y_test = self.y_test
rpt = scorer.score(
y_test,
y_pred,
yy_pred,
classifier=self.classifier,
title=reportName,
configuration=self.configuration )
self.y_pred = y_pred
self.yy_pred = yy_pred
self.scoringrpt = rpt
return(rpt)
def predict(self):
self.logger.info('Predicting...')
submissionSample = self.configuration['submissionSample']
submissionDir = self.configuration['submissionDir']
timestamp = dt.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
submissionVFile = submissionDir + '/' + 'submission-values-' + timestamp + '.csv'
submissionPFile = submissionDir + '/' + 'submission-probabilities-' + timestamp + '.csv'
submissionLog = submissionDir + '/' + 'submission-' + timestamp + '.txt'
npTest = np.array(self.test).astype(np.float32)
y_pred = self.classifier.predict(npTest)
yy_pred = self.classifier.predict_proba(npTest)[:,1]
predictionrpt = None
if self.hasExpected:
self.logger.debug('Target is available... Scoring target')
# The second column contains the actual values
y_test = self.expected.iloc[:,1]
scorer = Scorer()
reportName = '\nTarget Data Prediction Report \t\t' + timestamp
predictionrpt = scorer.score(
y_test,
y_pred,
yy_pred,
classifier=self.classifier,
title=reportName,
configuration=self.configuration )
print(predictionrpt)
sample = pd.read_csv(submissionSample)
sample.QuoteConversion_Flag = y_pred
sample.to_csv(submissionVFile, index=False)
probabilities = pd.read_csv(submissionSample)
probabilities.QuoteConversion_Flag = yy_pred
probabilities.to_csv(submissionPFile, index=False)
mfeatures, nfeatures= self.features.shape
mtest, ntest = self.test.shape
mxtrain, nxtrain= self.X_train.shape
mxtest, nxtest = self.X_test.shape
self.logger.debug('Saving submission information')
with open(submissionLog, 'a') as f:
f.write('Submission Report \t\t\t Generated at: {0}'.format(timestamp))
f.write('\n\nData Statistics:')
f.write('\n\Feature data: \trows: {0}, columns: {1}'.format(mfeatures, nfeatures))
f.write('\n\tTest data: \t\trows: {0}, columns: {1}'.format(mtest, ntest))
f.write('\n\nCross Validation Statistics:')
f.write('\n\tTraining data: \trows: {0}, columns: {1}'.format(mxtrain, nxtrain))
f.write('\n\tTest data: \t\trows: {0}, columns: {1}'.format(mxtest, nxtest))
f.write('\n\nValues file:\t\t{0}'.format(submissionVFile))
f.write('\nProbabilities file:\t{0}'.format(submissionPFile))
f.write('\nProbabilities file:\t{0}'.format(submissionPFile))
f.write('\n')
f.write('{0}'.format(self.report()))
if predictionrpt:
f.write('\n\n{0}'.format(predictionrpt))
return(submissionLog, submissionVFile, submissionPFile, self.classifier)
