def test_PriceEstimator_compute_product_occurrence_matrix():
"Test construction of matrix for linear least square algorithm."
from clair.coredata import DataStore
from clair.prices import PriceEstimator
print "start"
data = DataStore()
data.read_data(relative("../../example-data"))
test_listings = data.listings.ix[0:20]
print test_listings
print test_listings.to_string(columns=["products", "price"])
product_ids = [u'nikon-d70', u'nikon-d90', u'nikon-sb-24', u'nikon-sb-26',
u'nikon-18-70-f/3.5-4.5--1', u'nikon-18-105-f/3.5-5.6--1',
u'nikon-28-85-f/3.5-4.5--1']
estimator = PriceEstimator()
matrix, prices, listing_ids, product_ids = \
estimator.compute_product_occurrence_matrix(test_listings, product_ids)
print
print "matrix:\n", matrix
print "matrix rank:", np.linalg.matrix_rank(matrix)
print "number products:", len(product_ids)
print "prices:\n", prices
print "listing_ids:\n", listing_ids
print "product_ids:\n", product_ids
#TODO: assertions
print "finshed"
def test_PriceEstimator_create_prices_lstsq_soln_1():
"Test creation of price records with real data."
from clair.coredata import DataStore
from clair.prices import PriceEstimator
print "start"
data = DataStore()
data.read_data(relative("../../example-data"))
#Use all data as test data
# listings = data.listings
product_ids = [p.id for p in data.products
if not p.id.startswith("xxx-unknown")]
# #Take a small amount of test data.
listings = data.listings.ix[0:200]
# product_ids = [u'nikon-d70', u'nikon-d90', u'nikon-sb-24', u'nikon-sb-26',
# u'nikon-18-70-f/3.5-4.5--1', u'nikon-18-105-f/3.5-5.6--1',
# u'nikon-28-85-f/3.5-4.5--1']
print listings
# print listings.to_string(columns=["products", "price"])
estimator = PriceEstimator()
#Create matrix and vectors for linear least square
matrix, listing_prices, listing_ids, product_ids = \
estimator.compute_product_occurrence_matrix(listings, product_ids)
# print
# print "matrix:\n", matrix
# print "matrix rank:", np.linalg.matrix_rank(matrix)
# print "number products:", len(product_ids)
# print "listing_prices:\n", listing_prices
# print "listing_ids:\n", listing_ids
# print "product_ids:\n", product_ids
#Compute average product prices
product_prices, good_rows, good_cols, problem_products = \
estimator.solve_prices_lstsq(matrix, listing_prices,
listing_ids, product_ids)
#Create price records
prices = estimator.create_prices_lstsq_soln(matrix,
listing_prices, listing_ids,
product_prices, product_ids,
good_rows, good_cols, listings)
# print prices.to_string()
#TODO: assertions
print "finshed"
def test_PriceEstimator_solve_prices_lstsq_1():
"Test linear least square algorithm with real data."
from clair.coredata import DataStore
from clair.prices import PriceEstimator
print "start"
data = DataStore()
data.read_data(relative("../../example-data"))
#Take a small amount of test data.
listings = data.listings.ix[0:50]
# listings = data.listings
# product_ids = [p.id for p in data.products]
product_ids = [u'nikon-d70', u'nikon-d90', u'nikon-sb-24', u'nikon-sb-26',
u'nikon-18-70-f/3.5-4.5--1', u'nikon-18-105-f/3.5-5.6--1',
u'nikon-28-85-f/3.5-4.5--1']
print listings
print listings.to_string(columns=["products", "price"])
estimator = PriceEstimator()
#Create matrix and vectors for linear least square
matrix, listing_prices, listing_ids, product_ids = \
estimator.compute_product_occurrence_matrix(listings, product_ids)
print
print "matrix:\n", matrix
print "matrix rank:", np.linalg.matrix_rank(matrix)
print "number products:", len(product_ids)
print "listing_prices:\n", listing_prices
print "listing_ids:\n", listing_ids
print "product_ids:\n", product_ids
product_prices, good_rows, good_cols, problem_products = \
estimator.solve_prices_lstsq(matrix, listing_prices,
listing_ids, product_ids)
print "product_prices:\n", product_prices * 0.7
#TODO: assertions
print "finshed"
