def computeBaseLine(self, baselineType=0):
iterWeek, endWeek = datetime(2013, 3, 23), datetime(2013, 4, 20)
db = DBController()
fg = FeatureGenerator()
baselineScore = 0
while iterWeek <= endWeek:
lastWeek = iterWeek - timedelta(weeks=1)
featureList = db.getFeatureListByWeek(iterWeek)
y_pred, y_test = [], []
for featureVector in featureList:
songId = featureVector["id"]
lastWeekRank = db.getTop50Rank(lastWeek, songId)
if lastWeekRank is None:
lastWeekScore = 0
else:
lastWeekScore = fg.rankToPopScore(lastWeekRank)
currentWeekRank = featureVector["rank"]
currentWeekScore = fg.rankToPopScore(currentWeekRank) if currentWeekRank is not None else lastWeekScore
y_pred.append(lastWeekScore)
y_test.append(currentWeekScore)
y_pred, y_test = self.getRankArray(numpy.asarray(y_pred)), self.getRankArray(numpy.asarray(y_test))
if baselineType == 0:
baselineScore += self.getRankEvalationScore(y_pred, y_test)
elif baselineType == 1:
baselineScore += metrics.r2_score(y_pred, y_test)
else:
baselineScore += metrics.mean_squared_error(y_pred, y_test)
iterWeek += timedelta(weeks=1)
baselineScore = baselineScore / 5
print baselineScore
def getFeatureMatrix(self, beginWeek, endWeek=datetime.today(), mode=0, withSongId=False):
if beginWeek < datetime(2007, 1, 1) or endWeek > datetime.today():
raise Exception('Invalid input date!')
beginWeek, endWeek = dateToSaturday(beginWeek), dateToSaturday(endWeek)
endWeek = endWeek - timedelta(days=7) if endWeek > datetime.today() else endWeek
iterWeek = beginWeek
db = DBController()
matrix = []
while iterWeek <= endWeek:
featureList = db.getFeatureListByWeek(iterWeek)
for featureDict in featureList:
featureVector = self.featureDictToList(featureDict, mode, withSongId)
if featureVector is None:
continue
else:
matrix.append(featureVector)
iterWeek += timedelta(weeks=1)
matrix = numpy.matrix(matrix)
return matrix
