def setUp(self):
self.dataset = {
'Lisa Rose': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'Superman Returns': 3.5,
'You, Me and Dupree': 2.5,
'The Night Listener': 3.0
},
'Gene Seymour': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 3.5,
'Just My Luck': 1.5,
'Superman Returns': 5.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 3.5
},
'Michael Phillips': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.0,
'Superman Returns': 3.5,
'The Night Listener': 4.0
},
'Claudia Puig': {
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'The Night Listener': 4.5,
'Superman Returns': 4.0,
'You, Me and Dupree': 2.5
},
'Mick LaSalle': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'Just My Luck': 2.0,
'Superman Returns': 3.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 2.0
},
'Jack Matthews': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'The Night Listener': 3.0,
'Superman Returns': 5.0,
'You, Me and Dupree': 3.5
},
'Toby': {
'Snakes on a Plane': 4.5,
'You, Me and Dupree': 1.0,
'Superman Returns': 4.0
}
}
self.wrapper = DataWrapper(self.dataset)
def __init__(self,
data=dict(),
numRecommendations=1,
db=None,
metric="rating",
school="gatech"):
self.dataset = DataWrapper(instances=data,
db=db,
school=school,
metric=metric)
self.updated = False
self.sparsedata = None
self.sparseifyData()
try:
self.svd = TruncatedSVD(n_components=numRecommendations)
self.model = self.svd.inverse_transform(
self.svd.fit_transform(self.sparsedata))
except ValueError:
self.svd = None
self.model = None
raise ValueError("Not enough ratings for predictions")
def __init__(self, data=dict(), numRecommendations=1, db=None, metric="rating", school="gatech"):
self.dataset = DataWrapper(instances=data, db=db, school=school, metric=metric)
self.updated = False
self.sparsedata = None
self.sparseifyData()
try:
self.svd = TruncatedSVD(n_components=numRecommendations)
self.model = self.svd.inverse_transform(self.svd.fit_transform(self.sparsedata))
except ValueError:
self.svd = None
self.model = None
raise ValueError("Not enough ratings for predictions")
def setUp(self):
self.dataset = {
'Lisa Rose': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'Superman Returns': 3.5,
'You, Me and Dupree': 2.5,
'The Night Listener': 3.0
},
'Gene Seymour': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 3.5,
'Just My Luck': 1.5,
'Superman Returns': 5.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 3.5
},
'Michael Phillips': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.0,
'Superman Returns': 3.5,
'The Night Listener': 4.0
},
'Claudia Puig': {
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'The Night Listener': 4.5,
'Superman Returns': 4.0,
'You, Me and Dupree': 2.5
},
'Mick LaSalle': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'Just My Luck': 2.0,
'Superman Returns': 3.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 2.0
},
'Jack Matthews': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'The Night Listener': 3.0,
'Superman Returns': 5.0,
'You, Me and Dupree': 3.5
},
'Toby': {
'Snakes on a Plane':4.5,
'You, Me and Dupree':1.0,
'Superman Returns':4.0
}
}
self.wrapper = DataWrapper(self.dataset)
class CollaborativeFilter:
#This takes in a matrix
def __init__(self,
data=dict(),
numRecommendations=1,
db=None,
metric="rating",
school="gatech"):
self.dataset = DataWrapper(instances=data,
db=db,
school=school,
metric=metric)
self.updated = False
self.sparsedata = None
self.sparseifyData()
try:
self.svd = TruncatedSVD(n_components=numRecommendations)
self.model = self.svd.inverse_transform(
self.svd.fit_transform(self.sparsedata))
except ValueError:
self.svd = None
self.model = None
raise ValueError("Not enough ratings for predictions")
def getRecommendation(self, instances):
if (self.updated):
self.sparseifyData()
self.model = self.svd.inverse_transform(
self.svd.fit_transform(self.sparsedata))
self.updated = False
ret = {}
for instance in instances:
values = {}
for feature in instances[instance]:
try:
row = self.dataset.getRow(instance)
column = self.dataset.getColumn(feature)
values[feature] = self.model[row][column]
except KeyError:
values[feature] = None
ret[instance] = values
return ret
def updateValues(self, instances):
self.dataset.addData(instances)
self.updated = True
def forceModelUpdate(self):
self.updated = False
self.sparseifyData()
self.model = self.svd.inverse_transform(
self.svd.fit_transform(self.sparsedata))
def sparseifyData(self):
data = self.dataset.getData()
sparsematrix = sparse.dok_matrix((len(data), len(data[0])))
for i in range(len(data)):
for j in range(len(data[i])):
if data[i][j] is not None:
sparsematrix[i, j] = data[i][j]
self.sparsedata = sparsematrix
def getSparseData(self):
return self.sparsedata
def getModel(self):
return self.model
def getData(self, *args):
if len(args) == 2:
return self.dataset.getData(args[0], args[1])
else:
return self.dataset.getData()
def getUpdated(self):
return self.updated
def getDataDict(self):
return self.dataset.getDataDict()
class TestDataWrapper(unittest.TestCase):
def setUp(self):
self.dataset = {
'Lisa Rose': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'Superman Returns': 3.5,
'You, Me and Dupree': 2.5,
'The Night Listener': 3.0
},
'Gene Seymour': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 3.5,
'Just My Luck': 1.5,
'Superman Returns': 5.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 3.5
},
'Michael Phillips': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.0,
'Superman Returns': 3.5,
'The Night Listener': 4.0
},
'Claudia Puig': {
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'The Night Listener': 4.5,
'Superman Returns': 4.0,
'You, Me and Dupree': 2.5
},
'Mick LaSalle': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'Just My Luck': 2.0,
'Superman Returns': 3.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 2.0
},
'Jack Matthews': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'The Night Listener': 3.0,
'Superman Returns': 5.0,
'You, Me and Dupree': 3.5
},
'Toby': {
'Snakes on a Plane': 4.5,
'You, Me and Dupree': 1.0,
'Superman Returns': 4.0
}
}
self.wrapper = DataWrapper(self.dataset)
def test_create_lookups(self):
temp = {}
self.assertIsInstance(self.wrapper.getInstanceLookup(), type(temp))
self.assertIsInstance(self.wrapper.getFeatureLookup(), type(temp))
def test_getters(self):
temp = {}
self.assertIsInstance(self.wrapper.getInstanceLookup(), type(temp))
self.assertNotEqual(self.wrapper.getInstanceLookup(), type(temp))
self.assertIsInstance(self.wrapper.getFeatureLookup(), type(temp))
self.assertNotEqual(self.wrapper.getFeatureLookup(), type(temp))
self.assertEqual(self.wrapper.getDataDict(), self.dataset)
self.assertNotEqual(
self.wrapper.getData(),
[[None], [None], [None], [None], [None], [None], [None]])
def test_add_data(self):
tempData = copy.deepcopy(self.wrapper.getData())
tempDataDict = copy.deepcopy(self.wrapper.getDataDict())
instance = {
'Casey': {
'Snakes on a Plane': 5.0,
'Superman Returns': 3.4
}
}
instance['Lisa Rose'] = {'The Night Listener': 5.0}
self.wrapper.addData(instance)
self.assertNotEqual(tempDataDict, self.wrapper.getDataDict())
self.assertNotEqual(tempData, self.wrapper.getData())
def test_convert_data(self):
self.assertNotEqual(
self.wrapper.getData(),
[[None], [None], [None], [None], [None], [None], [None]])
class CollaborativeFilter:
#This takes in a matrix
def __init__(self, data=dict(), numRecommendations=1, db=None, metric="rating", school="gatech"):
self.dataset = DataWrapper(instances=data, db=db, school=school, metric=metric)
self.updated = False
self.sparsedata = None
self.sparseifyData()
try:
self.svd = TruncatedSVD(n_components=numRecommendations)
self.model = self.svd.inverse_transform(self.svd.fit_transform(self.sparsedata))
except ValueError:
self.svd = None
self.model = None
raise ValueError("Not enough ratings for predictions")
def getRecommendation(self, instances):
if(self.updated):
self.sparseifyData()
self.model = self.svd.inverse_transform(self.svd.fit_transform(self.sparsedata))
self.updated = False
ret = {}
for instance in instances:
values = {}
for feature in instances[instance]:
try:
row = self.dataset.getRow(instance)
column = self.dataset.getColumn(feature)
values[feature] = self.model[row][column]
except KeyError:
values[feature] = None
ret[instance] = values
return ret
def updateValues(self, instances):
self.dataset.addData(instances)
self.updated = True
def forceModelUpdate(self):
self.updated = False
self.sparseifyData()
self.model = self.svd.inverse_transform(self.svd.fit_transform(self.sparsedata))
def sparseifyData(self):
data = self.dataset.getData()
sparsematrix = sparse.dok_matrix((len(data), len(data[0])))
for i in range(len(data)):
for j in range(len(data[i])):
if data[i][j] is not None:
sparsematrix[i, j] = data[i][j]
self.sparsedata = sparsematrix
def getSparseData(self):
return self.sparsedata
def getModel(self):
return self.model
def getData(self, *args):
if len(args) == 2:
return self.dataset.getData(args[0], args[1])
else:
return self.dataset.getData()
def getUpdated(self):
return self.updated
def getDataDict(self):
return self.dataset.getDataDict()
class TestDataWrapper(unittest.TestCase):
def setUp(self):
self.dataset = {
'Lisa Rose': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'Superman Returns': 3.5,
'You, Me and Dupree': 2.5,
'The Night Listener': 3.0
},
'Gene Seymour': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 3.5,
'Just My Luck': 1.5,
'Superman Returns': 5.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 3.5
},
'Michael Phillips': {
'Lady in the Water': 2.5,
'Snakes on a Plane': 3.0,
'Superman Returns': 3.5,
'The Night Listener': 4.0
},
'Claudia Puig': {
'Snakes on a Plane': 3.5,
'Just My Luck': 3.0,
'The Night Listener': 4.5,
'Superman Returns': 4.0,
'You, Me and Dupree': 2.5
},
'Mick LaSalle': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'Just My Luck': 2.0,
'Superman Returns': 3.0,
'The Night Listener': 3.0,
'You, Me and Dupree': 2.0
},
'Jack Matthews': {
'Lady in the Water': 3.0,
'Snakes on a Plane': 4.0,
'The Night Listener': 3.0,
'Superman Returns': 5.0,
'You, Me and Dupree': 3.5
},
'Toby': {
'Snakes on a Plane':4.5,
'You, Me and Dupree':1.0,
'Superman Returns':4.0
}
}
self.wrapper = DataWrapper(self.dataset)
def test_create_lookups(self):
temp = {}
self.assertIsInstance(self.wrapper.getInstanceLookup(), type(temp))
self.assertIsInstance(self.wrapper.getFeatureLookup(), type(temp))
def test_getters(self):
temp = {}
self.assertIsInstance(self.wrapper.getInstanceLookup(), type(temp))
self.assertNotEqual(self.wrapper.getInstanceLookup(), type(temp))
self.assertIsInstance(self.wrapper.getFeatureLookup(), type(temp))
self.assertNotEqual(self.wrapper.getFeatureLookup(), type(temp))
self.assertEqual(self.wrapper.getDataDict(), self.dataset)
self.assertNotEqual(self.wrapper.getData(), [[None],[None],[None],[None],[None],[None],[None]])
def test_add_data(self):
tempData = copy.deepcopy(self.wrapper.getData())
tempDataDict = copy.deepcopy(self.wrapper.getDataDict())
instance = {'Casey' : { 'Snakes on a Plane': 5.0, 'Superman Returns' : 3.4}}
instance['Lisa Rose'] = {'The Night Listener' : 5.0}
self.wrapper.addData(instance)
self.assertNotEqual(tempDataDict, self.wrapper.getDataDict())
self.assertNotEqual(tempData, self.wrapper.getData())
def test_convert_data(self):
self.assertNotEqual(self.wrapper.getData(), [[None],[None],[None],[None],[None],[None],[None]])
