#, ['Halcyondays' , 'Caldera Ginger Beer', 4.0]] #testQueries = [['stcules', 'English Strong Ale',3.0]] actualToPredictedRating = [] for query in testQueries : testCustomer = query[0] testProduct = query[1] actualRating = query[2] print "****************************************" print "Test Query ", query #Step 1 : Find Similar customers for this customer print "Finding similar customers for : ", testCustomer similarCustomers = knnc.findSimilarCustomers(testCustomer, availableCustomerRows, availableBeerColumns); #Step 2 : Fnd all the beers which are similar to this one. print "Finding similar beers for : ", testProduct #similarBeers = kv.findSimiarityInParallel(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP) similarBeers = kv.findSimiarity(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP) #Step 3 : Predict rating for this query filteredRating = 0 overallRating = 0 try : #BeerName - 'Heavy Handed IPA' model = PredictionModel(testCustomer, similarCustomers, similarBeers, availableBeerColumns, availableCustomerRows) #Next for each of those products find the common reviewers.
#testQueries = [['stcules', 'English Strong Ale',3.0]]
actualToPredictedRating = []
for query in testQueries:
testCustomer = query[0]
testProduct = query[1]
actualRating = query[2]
print "****************************************"
print "Test Query ", query
#Step 1 : Find Similar customers for this customer
print "Finding similar customers for : ", testCustomer
similarCustomers = knnc.findSimilarCustomers(testCustomer,
availableCustomerRows,
availableBeerColumns)
#Step 2 : Fnd all the beers which are similar to this one.
print "Finding similar beers for : ", testProduct
#similarBeers = kv.findSimiarityInParallel(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP)
similarBeers = kv.findSimiarity(testProduct, availableBeerColumns,
availableCustomerRows, FIELD_MAP)
#Step 3 : Predict rating for this query
filteredRating = 0
overallRating = 0
try:
#BeerName - 'Heavy Handed IPA'
model = PredictionModel(testCustomer, similarCustomers, similarBeers,
def findSimilarCustomers(customerId) :
return knnc.findSimilarCustomers(customerId, availableCustomerRows, availableBeerColumns);
def processData(count, availableBeerColumns, availableCustomerRows, sumOfBeerRatingsOverall):
MEAN_PRODUCT_RATING=round((sumOfBeerRatingsOverall/count), 1)
print ("Mean Beer rating for any beer : ", MEAN_PRODUCT_RATING)
print ("# of beers = ", len(availableBeerColumns))
print ("# of customers = ", len(availableCustomerRows))
#availableBeerColumns = csvLoader.getAvailableBeerColumns()
#availableCustomerRows = csvLoader.getAvailableCustomerRows()
#Demo - combined run
#testQueries = [['rawthar' , 'Caldera Ginger Beer', 4.0], ['Halcyondays' , 'Caldera Ginger Beer', 4.0],['rawthar' , 'Heavy Handed IPA', 4.0] ]
#Demo - quick run
testQueries = [['hopdog' , 'Iron Hill Northern English Brown Ale', 3.0]]
#Demo - large data
#testQueries = [['rawthar' , 'Heavy Handed IPA', 4.0]]
#, ['Halcyondays' , 'Caldera Ginger Beer', 4.0]]
#testQueries = [['stcules', 'English Strong Ale',3.0]]
actualToPredictedRating = []
for query in testQueries :
testCustomer = query[0]
testProduct = query[1]
actualRating = query[2]
print ("****************************************")
print ("Test Query ", query)
#Step 1 : Find Similar customers for this customer
print ("Finding similar customers for : ", testCustomer)
similarCustomers = knnc.findSimilarCustomers(testCustomer, availableCustomerRows, availableBeerColumns);
print ("SIMILAR Customers *****", len(similarCustomers))
#Step 2 : Fnd all the beers which are similar to this one.
print ("Finding similar beers for : ", testProduct)
similarBeers = kv.findSimiarityInParallel(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP)
#similarBeers = kv.findSimiarity(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP)
#print ("SIMILAR ONES *****", similarBeers[0])
#Step 3 : Predict rating for this query
filteredRating = 0
overallRating = 0
try :
#BeerName - 'Heavy Handed IPA'
model = PredictionModel(testCustomer, similarCustomers, similarBeers, availableBeerColumns, availableCustomerRows)
#Next for each of those products find the common reviewers.
print ("Finding Global BaseLine rating...")
baselineRating = model.computeGlobalBaseline(testProduct)
print ("Global BaseLine rating : ", baselineRating)
#Compute rating by Collaborative filtering.
print ("Finding filtered rating...")
filteredRating = model.computeFilteredRatingEstimate(testProduct)
#Now get the average overall rating
for k,v in filteredRating.items():
#print "rating for : ", k, " is " , v
overallRating += v;
if len(filteredRating) == 0 :
print ("Cannot predict overall rating, as filtered rating is zero!");
break
overallRating = (overallRating / len(filteredRating))
print ("Overall Rating : ", overallRating)
print ("****************************************")
actualToPredictedRating.append([actualRating] + [overallRating])
except Exception as e:
print (e)
pass
return actualToPredictedRating
def processData(count, availableBeerColumns, availableCustomerRows,
sumOfBeerRatingsOverall):
MEAN_PRODUCT_RATING = round((sumOfBeerRatingsOverall / count), 1)
print("Mean Beer rating for any beer : ", MEAN_PRODUCT_RATING)
print("# of beers = ", len(availableBeerColumns))
print("# of customers = ", len(availableCustomerRows))
#availableBeerColumns = csvLoader.getAvailableBeerColumns()
#availableCustomerRows = csvLoader.getAvailableCustomerRows()
#Demo - combined run
#testQueries = [['rawthar' , 'Caldera Ginger Beer', 4.0], ['Halcyondays' , 'Caldera Ginger Beer', 4.0],['rawthar' , 'Heavy Handed IPA', 4.0] ]
#Demo - quick run
testQueries = [['hopdog', 'Iron Hill Northern English Brown Ale', 3.0]]
#Demo - large data
#testQueries = [['rawthar' , 'Heavy Handed IPA', 4.0]]
#, ['Halcyondays' , 'Caldera Ginger Beer', 4.0]]
#testQueries = [['stcules', 'English Strong Ale',3.0]]
actualToPredictedRating = []
for query in testQueries:
testCustomer = query[0]
testProduct = query[1]
actualRating = query[2]
print("****************************************")
print("Test Query ", query)
#Step 1 : Find Similar customers for this customer
print("Finding similar customers for : ", testCustomer)
similarCustomers = knnc.findSimilarCustomers(testCustomer,
availableCustomerRows,
availableBeerColumns)
print("SIMILAR Customers *****", len(similarCustomers))
#Step 2 : Fnd all the beers which are similar to this one.
print("Finding similar beers for : ", testProduct)
similarBeers = kv.findSimiarityInParallel(testProduct,
availableBeerColumns,
availableCustomerRows,
FIELD_MAP)
#similarBeers = kv.findSimiarity(testProduct, availableBeerColumns, availableCustomerRows, FIELD_MAP)
#print ("SIMILAR ONES *****", similarBeers[0])
#Step 3 : Predict rating for this query
filteredRating = 0
overallRating = 0
try:
#BeerName - 'Heavy Handed IPA'
model = PredictionModel(testCustomer, similarCustomers,
similarBeers, availableBeerColumns,
availableCustomerRows)
#Next for each of those products find the common reviewers.
print("Finding Global BaseLine rating...")
baselineRating = model.computeGlobalBaseline(testProduct)
print("Global BaseLine rating : ", baselineRating)
#Compute rating by Collaborative filtering.
print("Finding filtered rating...")
filteredRating = model.computeFilteredRatingEstimate(testProduct)
#Now get the average overall rating
for k, v in filteredRating.items():
#print "rating for : ", k, " is " , v
overallRating += v
if len(filteredRating) == 0:
print(
"Cannot predict overall rating, as filtered rating is zero!"
)
break
overallRating = (overallRating / len(filteredRating))
print("Overall Rating : ", overallRating)
print("****************************************")
actualToPredictedRating.append([actualRating] + [overallRating])
except Exception as e:
print(e)
pass
return actualToPredictedRating
