def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
trainData = buildTrainingSets(DIR + team + '-train.csv.knn')
trainLabels = buildTrainingLabels(DIR + team + '-train.csv.knn')
testData = buildTestingSets(DIR + team + '-test.csv.knn')
testLabels = buildTestingLabels(DIR + team + '-test.csv.knn')
total = total + len(testLabels)
svm = cv2.SVM()
svm.train(trainData, trainLabels, params=svm_params)
svm.save('svm_data.dat')
# Accuracy
count = 0
for i in range(len(testLabels)):
ret = svm.predict(np.array([testData[i]]))
if ret == testLabels[i][0]:
count = count + 1
countTotal = countTotal + count
print 'INFO: Accuracy(', team, ')', count / float(len(testLabels))
print 'INFO: Total Accuracy: ', countTotal / float(total)
def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
trainData = buildTrainingSets(DIR + team + '-train.csv')
trainLabels = buildTrainingLabels(DIR + team + '-train.csv')
testData = buildTestingSets(DIR + team + '-test.csv')
testLabels = buildTestingLabels(DIR + team + '-test.csv')
total = total + len(testLabels)
knn = cv2.KNearest()
knn.train(trainData, trainLabels)
# Accuracy
count = 0
for i in range(len(testLabels)):
ret, results, neighbours, dist = knn.find_nearest(
np.array([testData[i]]), 11)
if results[0][0] == testLabels[i][0]:
count = count + 1
countTotal = countTotal + count
print 'INFO: Accuracy(', teamNames[teamIds.index(
team)], ')', count / float(len(testLabels))
print 'INFO: Total Accuracy: ', countTotal / float(total)
def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
trainData = buildTrainingSets(DIR + team + '-train.csv.knn')
trainLabels = buildTrainingLabels(DIR + team + '-train.csv.knn')
testData = buildTestingSets(DIR + team + '-test.csv.knn')
testLabels = buildTestingLabels(DIR + team + '-test.csv.knn')
total = total + len(testLabels)
svm = cv2.SVM()
svm.train(trainData, trainLabels, params=svm_params)
svm.save('svm_data.dat')
# Accuracy
count = 0
for i in range(len(testLabels)):
ret = svm.predict(np.array([testData[i]]))
if ret == testLabels[i][0]:
count = count + 1
countTotal = countTotal + count
print 'INFO: Accuracy(', team, ')', count/float(len(testLabels))
print 'INFO: Total Accuracy: ', countTotal/float(total)
def teamMain():
DIR = '/home/archer/Documents/Python/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
train = buildTrainingSets(DIR + team + '-train.csv')
test = buildTestingSets(DIR + team + '-test.csv')
labels = buildTestingLabels(DIR + team + '-test.csv')
total = total + len(labels)
classifier = NaiveBayesClassifier.train(train)
res = classifier.batch_classify(test)
# accuracy
count = 0
for i in range(len(res)):
if labels[i] == res[i]:
count = count + 1
countTotal = countTotal + count
print 'INFO: Accuracy(', teamNames[teamIds.index(
team)], ')', count / float(len(res))
print 'INFO: Total Accuracy: ', countTotal / float(total)
def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
train = buildTrainingSets(DIR + team + '-train.csv')
test = buildTestingSets(DIR + team + '-test.csv')
labels = buildTestingLabels(DIR + team + '-test.csv')
total = total + len(labels)
# train
classifier = nltk.MaxentClassifier.train(train, 'IIS', trace=0, max_iter=1000)
# test
count = 0
for i in range(len(labels)):
pdist = classifier.prob_classify(test[i])
if pdist.prob('L') >= pdist.prob('W'):
flag = 'L'
else:
flag = 'W'
#print 'DEBUG: ', flag, labels[i]
if flag == labels[i]:
count = count + 1
print 'INFO: accuracy ', team, " ", float(count)/len(labels)
def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
train = buildTrainingSets(DIR + team + '-train.csv')
test = buildTestingSets(DIR + team + '-test.csv')
labels = buildTestingLabels(DIR + team + '-test.csv')
total = total + len(labels)
# train
classifier = nltk.MaxentClassifier.train(train,
'IIS',
trace=0,
max_iter=1000)
# test
count = 0
for i in range(len(labels)):
pdist = classifier.prob_classify(test[i])
if pdist.prob('L') >= pdist.prob('W'):
flag = 'L'
else:
flag = 'W'
#print 'DEBUG: ', flag, labels[i]
if flag == labels[i]:
count = count + 1
print 'INFO: accuracy ', team, " ", float(count) / len(labels)
def teamMain():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [x[1] for x in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
countTotal = 0
total = 0
for team in teamIds:
trainData = buildTrainingSets(DIR + team + '-train.csv')
trainLabels = buildTrainingLabels(DIR + team + '-train.csv')
testData = buildTestingSets(DIR + team + '-test.csv')
testLabels = buildTestingLabels(DIR + team + '-test.csv')
total = total + len(testLabels)
knn = cv2.KNearest()
knn.train(trainData, trainLabels)
# Accuracy
count = 0
for i in range(len(testLabels)):
ret, results, neighbours, dist = knn.find_nearest(np.array([testData[i]]), 31)
if results[0][0] == testLabels[i][0]:
count = count + 1
countTotal = countTotal + count
print 'INFO: Accuracy(', teamNames[teamIds.index(team)], ')', count/float(len(testLabels))
print 'INFO: Total Accuracy: ', countTotal/float(total)
def generateTestDataByTeams():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [row[1] for row in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
for teamId in teamIds:
res = generateTestDataByTeam(teamId)
outputFile = DIR + teamId + '-test.csv.knn'
print 'INFO: ', outputFile
saveMatrixToFile(outputFile, res)
def generateTestDataByTeam(teamId):
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [row[1] for row in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
seasons = loadSeasons(DIR + 'seasons-18-Nov-2014.txt')
res = []
for season in seasons:
mat = loadMatrixFromFile(DIR + season + '.playoff.csv')
for row in mat:
if teamNames[teamIds.index(teamId)] not in row[6]:
continue
if row[0] == 'W':
WIN = 1
else:
WIN = 0
if 'vs.' in row[6]:
HOME = 1
else:
HOME = 0
season = row[3]
#heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + teamId + '.' + season + '.player.csv.processed.total')[0]
#heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + teamId + '.' + season + '.player.csv.processed.avg')[0]
heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + teamId + '.' + season + '.player.csv.processed.norm')[0]
leagueranks = loadMatrixFromFile(DIR + season + '.l')[0]
leaguerank = leagueranks[teamNames.index(row[6][0:3])]
vsTeamId = teamIds[teamNames.index(row[6][-3:])]
#vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.total')[0]
#vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.avg')[0]
vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.norm')[0]
vsLeaguerank = leagueranks[teamIds.index(vsTeamId)]
tmp = []
tmp.append(HOME)
tmp.append(heightTotal)
tmp.append(weightTotal)
tmp.append(ageTotal)
tmp.append(expTotal)
tmp.append(leaguerank)
tmp.append(vsHeightTotal)
tmp.append(vsWeightTotal)
tmp.append(vsAgeTotal)
tmp.append(vsExpTotal)
tmp.append(vsLeaguerank)
tmp.append(WIN)
res.append(tmp)
return res
def generateTrainDataBySeason(season):
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
teamNames = [row[1] for row in loadMatrixFromFile(DIR + 'teamidshortname.csv')]
leagueranks = loadMatrixFromFile(DIR + season + '.l')[0]
res = []
for team in teamIds:
mat = loadMatrixFromFile(DIR + team + '.csv.sorted')
for row in mat:
if row[2] != season:
continue
if row[0] == 'W':
WIN = 1
else:
WIN = 0
if 'vs.' in row[5]:
HOME = 1
else:
HOME = 0
#heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + team + '.' + season + '.player.csv.processed.total')[0]
#heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + team + '.' + season + '.player.csv.processed.avg')[0]
heightTotal, weightTotal, ageTotal, expTotal = loadMatrixFromFile(DIR + team + '.' + season + '.player.csv.processed.norm')[0]
leaguerank = leagueranks[teamNames.index(row[5][0:3])]
vsTeamId = teamIds[teamNames.index(row[5][-3:])]
#vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.total')[0]
#vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.avg')[0]
vsHeightTotal, vsWeightTotal, vsAgeTotal, vsExpTotal = loadMatrixFromFile(DIR + vsTeamId + '.' + season + '.player.csv.processed.norm')[0]
vsLeaguerank = leagueranks[teamIds.index(vsTeamId)]
tmp = []
tmp.append(HOME)
tmp.append(heightTotal)
tmp.append(weightTotal)
tmp.append(ageTotal)
tmp.append(expTotal)
tmp.append(leaguerank)
tmp.append(vsHeightTotal)
tmp.append(vsWeightTotal)
tmp.append(vsAgeTotal)
tmp.append(vsExpTotal)
tmp.append(vsLeaguerank)
tmp.append(WIN)
res.append(tmp)
return res
def main():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
seasons = loadSeasons(DIR + 'seasons-18-Nov-2014.txt')
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
seasonTypes = ['Regular Season', 'Playoffs']
# print seasons
# return
for team in teamIds:
for season in seasons:
#for seasonType in seasonTypes:
seasonType = 'Regular Season'
n = NBAStatsTeamPlayerExtractor(team, season, seasonType)
outputFile = DIR + team + '.' + season + '.player.csv'
print 'INFO: Processing ', outputFile
mat = n.getStats()
if mat == False:
saveMatrixToFile(outputFile, [])
else:
saveMatrixToFile(outputFile, mat)
def main():
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
seasons = loadSeasons(DIR + 'seasons-18-Nov-2014.txt')
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
seasonTypes = ['Regular Season', 'Playoffs']
# print seasons
# return
for team in teamIds:
for season in seasons:
#for seasonType in seasonTypes:
seasonType = 'Regular Season'
n = NBAStatsTeamPlayerExtractor(team, season, seasonType)
outputFile = DIR + team + '.' + season + '.player.csv'
print 'INFO: Processing ', outputFile
mat = n.getStats()
if mat == False:
saveMatrixToFile(outputFile, [])
else:
saveMatrixToFile(outputFile, mat)
# -*- coding: utf-8 -*-
#
# Author: Archer
# Date: 05/Jun/2015
# File: InsertPlayer.py
# Desc: insert into NBA.Player table
#
# Produced By CSRGXTU
import MySQLdb as mdb
import sys
from Utility import loadSeasons, loadTeamIds, loadMatrixFromFile
basePath = '/home/archer/Documents/Python/maxent/data/basketball/leaguerank/'
seasons = loadSeasons(basePath + 'seasons-18-Nov-2014.txt')
teamIds = loadTeamIds(basePath + 'teamidname-18-Nov-2014.csv')
def insertPlayer(cur):
for team in teamIds:
sql = "select TeamID from Team where StatsID = '%s'" % team
cur.execute(sql)
TeamID = cur.fetchone()[0]
for season in seasons:
sql = "select SeasonID from Season where Season = '%s' and Season_SeasonTypeID = 2" % season
cur.execute(sql)
SeasonID = cur.fetchone()[0]
matrix = loadMatrixFromFile(basePath + team + '.' + season +
'.player.csv')
#!/usr/bin/env python
# coding = utf-8
# Author: Archer Reilly
# Date: 24/DEC/2014
# File: NBAStatsTeamPlayerDataProcessor.py
# Desc: the data downloaded from net isnt good, so need this
# file process it before used in models
#
# Produced By CSRGXTU
from Utility import loadMatrixFromFile, saveMatrixToFile, readmatricefromfile, loadSeasons, loadTeamIds, saveLstToFile
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
seasons = loadSeasons(DIR + 'seasons-18-Nov-2014.txt')
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
# noneWithAVG
# replace None with average value
#
# @param teamId
# @param season
# @return res list(list)
def noneWithAVG(teamId, season):
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
mat = loadMatrixFromFile(DIR + teamId + "." + season + ".player.csv")
if len(mat) == 0:
return [[]]
heights = []
weights = []
ages = []
tmpLst.append(item['PTS'])
tmpLst.append(ranking['PPG'])
tmpLst.append(ranking['RPG'])
tmpLst.append(ranking['APG'])
tmpLst.append(ranking['OPPG'])
tmpLst.append(profile['Height'])
tmpLst.append(profile['Weight'])
tmpLst.append(profile['Age'])
appendlst2file(tmpLst, dataFile)
if __name__ == '__main__':
# first, load team id
teamIds = loadTeamIds('../../data/basketball/teamidname-18-Nov-2014.csv')
# second, load seasons
seasons = loadSeasons('../../data/basketball/seasons.txt')
# seasonTypes
seasonTypes = ['Regular Season']
# leagueId
leagueId = "00"
# for teamId in teamIds:
# dataFile = '../../data/basketball/' + teamId + '.csv'
# for t in seasonTypes:
# for s in seasons:
# print "Processing " + teamId + " " + s + " " + t,
#!/usr/bin/env python
# coding = utf-8
# Author: Archer Reilly
# Date: 24/DEC/2014
# File: NBAStatsTeamPlayerDataProcessor.py
# Desc: the data downloaded from net isnt good, so need this
# file process it before used in models
#
# Produced By CSRGXTU
from Utility import loadMatrixFromFile, saveMatrixToFile, readmatricefromfile, loadSeasons, loadTeamIds, saveLstToFile
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
seasons = loadSeasons(DIR + 'seasons-18-Nov-2014.txt')
teamIds = loadTeamIds(DIR + 'teamidshortname.csv')
# noneWithAVG
# replace None with average value
#
# @param teamId
# @param season
# @return res list(list)
def noneWithAVG(teamId, season):
DIR = '/home/archer/Documents/maxent/data/basketball/leaguerank/'
mat = loadMatrixFromFile(DIR + teamId + "." + season + ".player.csv")
if len(mat) == 0:
return [[]]
heights = []
weights = []
ages = []
exps = []
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Author: Archer
# File: InsertTeamStats.py
# Date: 05/Jun/2015
# Desc: insert NBA.TeamStats table
#
# Produced By CSRGXTU
import MySQLdb as mdb
import sys
from Utility import loadMatrixFromFile, loadSeasons, loadTeamIds
teamIds = loadTeamIds(
'/home/archer/Documents/Python/maxent/data/basketball/leaguerank/teamidshortname.csv'
)
seasons = loadSeasons(
'/home/archer/Documents/Python/maxent/data/basketball/leaguerank/seasons-18-Nov-2014.txt'
)
TeamID2TeamShortNames = loadMatrixFromFile(
'/home/archer/Documents/Python/maxent/data/basketball/leaguerank/TeamID2TeamShortName.csv'
)
def findId(shortName):
for row in TeamID2TeamShortNames:
if row[1] == shortName:
return row[0]
return False
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Author: Archer
# File: InsertTeamStats.py
# Date: 05/Jun/2015
# Desc: insert NBA.TeamStats table
#
# Produced By CSRGXTU
import MySQLdb as mdb
import sys
from Utility import loadMatrixFromFile, loadSeasons, loadTeamIds
teamIds = loadTeamIds('/home/archer/Documents/Python/maxent/data/basketball/leaguerank/teamidshortname.csv')
seasons = loadSeasons('/home/archer/Documents/Python/maxent/data/basketball/leaguerank/seasons-18-Nov-2014.txt')
TeamID2TeamShortNames = loadMatrixFromFile('/home/archer/Documents/Python/maxent/data/basketball/leaguerank/TeamID2TeamShortName.csv')
def findId(shortName):
for row in TeamID2TeamShortNames:
if row[1] == shortName:
return row[0]
return False
def isHome(matchUpString):
if '@' in matchUpString:
return 1
else:
return 0
def none20(lst):
for i in range(len(lst)):
tmpLst.append(item['PTS'])
tmpLst.append(ranking['PPG'])
tmpLst.append(ranking['RPG'])
tmpLst.append(ranking['APG'])
tmpLst.append(ranking['OPPG'])
tmpLst.append(profile['Height'])
tmpLst.append(profile['Weight'])
tmpLst.append(profile['Age'])
appendlst2file(tmpLst, dataFile)
if __name__ == '__main__':
# first, load team id
teamIds = loadTeamIds('../../data/basketball/leaguerank/teamidname-18-Nov-2014.csv')
# second, load seasons
seasons = loadSeasons('../../data/basketball/leaguerank/seasons-18-Nov-2014.txt')
# seasonTypes
seasonTypes = ['Playoffs']
# leagueId
leagueId = "00"
"""
for teamId in teamIds:
dataFile = '../../data/basketball/leaguerank/' + teamId + '.playoff.csv'
for t in seasonTypes:
for s in seasons: