def extractFeatureToDB(self, beginWeek, endWeek=datetime.today(), isReload=False, useAlchemyAPI=False):
if beginWeek < datetime(2007, 1, 7) 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()
while iterWeek <= endWeek:
lastWeek = iterWeek - timedelta(days=7)
songRankList = db.getSongIdListByWeek(lastWeek)
for songId in songRankList:
if isReload == False and db.isFeatureInDB(iterWeek, songId):
continue
featureDict = {}
featureDict['id'] = songId
featureDict['week'] = iterWeek
featureDict['sales'] = db.getSalesRank(lastWeek, songId)
featureDict['radio'] = db.getRadioRank(lastWeek, songId)
featureDict['streaming'] = db.getStreamingRank(lastWeek, songId)
featureDict['MVView'], featureDict['MVSocialInteraction'] = db.getIMVDBData(iterWeek, songId)
featureDict['MTVReviewCount'], featureDict['MTVReviewScore'] = db.getMTVReviewData(iterWeek, songId, useAlchemyAPI)
featureDict['youtubeCommentCount'], featureDict['youtubeCommentScore'] = db.getYoutubeData(iterWeek, songId, useAlchemyAPI)
featureDict['twitterCount'], featureDict['twitterScore'] = db.getTwitterData(iterWeek, songId, useAlchemyAPI)
featureDict['rank'] = db.getTop50Rank(iterWeek, songId)
db.insertFeatureToDB(featureDict)
iterWeek += timedelta(days=7)
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
