def test_import_data(self):
"""
Tests the import_data function
"""
#directory_path = r"C:/Users/Amir G/SP_Python220B_2019/students/amirg/" \
# r"lesson05/assignment/data"
directory_path = r"data"
linear.drop_data()
list1 = linear.import_data(directory_path, 'products.csv',
'customers.csv')
self.assertEqual(list1[0][0], 999)
self.assertEqual(list1[0][1], 0)
self.assertEqual(list1[0][2], 999)
self.assertTrue(list1[0][3] > 0)
self.assertEqual(list1[1][0], 999)
self.assertEqual(list1[1][1], 0)
self.assertEqual(list1[1][2], 999)
self.assertTrue(list1[1][3] > 0)
linear.drop_data()
list2 = linear.import_data(directory_path, 'products.csv',
'nothing.csv')
self.assertEqual(list2[0][0], 999)
self.assertEqual(list2[0][1], 0)
self.assertEqual(list2[0][2], 999)
self.assertTrue(list2[0][3] > 0)
self.assertEqual(len(list2), 1)
def test_import_data(self):
linear.drop_data()
good_import = linear.import_data('data', 'products.csv',
'customers.csv', 'rentals.csv')
self.assertEqual(good_import[0][0], 9999)
self.assertEqual(good_import[0][1], 0)
self.assertEqual(good_import[0][2], 9999)
self.assertEqual(type(good_import[0][3]), type(float(1.02)))
self.assertEqual(good_import[0], good_import[1])
def test_submission(_all_answers):
#linear cust/prod, parallel cust/prod
l.drop_data()
for answer in _all_answers:
# needs a few more
assert type(answer["processed"]) == int
assert type(answer["count_prior"]) == int
assert type(answer["count_new"]) == int
assert answer["count_prior"] + answer["processed"] == answer["count_new"]
assert type(answer["elapsed"]) == float
assert answer["elapsed"] > 0.0
def test_drop_data(self):
linear.drop_data()
# Populate the database
linear.import_data('data', 'products.csv', 'customers.csv', 'test.csv')
mongo = linear.MongoDBConnection()
with mongo:
database = mongo.connection.media
record_count = database['rentals'].count_documents({})
self.assertEqual(record_count, 4)
# Make sure the database successfully clears
linear.drop_data()
with mongo:
database = mongo.connection.media
record_count = database['rentals'].count_documents({})
self.assertEqual(record_count, 0)
def test_1_import(self):
"""
Test that the records are successfully imported.
"""
# Start fresh so we don't mess up all our tests...
linear.drop_data()
self.assertEqual(linear.show_available_products(), {})
# Check for proper error handling of import_data()
with self.assertRaises(FileNotFoundError):
result = linear.import_data('data2', 'p.csv', 'c.csv', 'r.csv')
# These tests are hard-coded to the expected values from the incluced CSV's.
# Your results may vary if the data sets change. :)
result = linear.import_data('data', 'products.csv', 'customers.csv', 'rentals.csv')
self.assertEqual(result[0][0], 1000)
self.assertEqual(result[0][1], 0)
self.assertEqual(result[0][2], 1000)
self.assertEqual(result[1][0], 1000)
self.assertEqual(result[1][1], 0)
self.assertEqual(result[1][2], 1000)
linear_available = linear.show_available_products()
# Run the parallel again -- we're going to grab the results of show_available_products()
# to consistency check later.
parallel.drop_data()
self.assertEqual(parallel.show_available_products(), {})
with self.assertRaises(FileNotFoundError):
result = linear.import_data('data2', 'p.csv', 'c.csv', 'r.csv')
result = parallel.import_data('data', 'products.csv', 'customers.csv', 'rentals.csv')
self.assertEqual(result[0][0], 1000)
self.assertEqual(result[0][1], 0)
self.assertEqual(result[0][2], 1000)
self.assertEqual(result[1][0], 1000)
self.assertEqual(result[1][1], 0)
self.assertEqual(result[1][2], 1000)
self.assertEqual(linear_available, parallel.show_available_products())
with mongo:
# mongodb database; it all starts here
d_b = mongo.connection.media
#import customer data
start1 = time.time()
cdb = d_b["customers"]
count_prior_i = cdb.count()
customer_entry = import_table(cdb, path + cust_file)
count_after_i = cdb.count()
#print_mdb_collection(cdb)
end1 = time.time()
time1 = end1 - start1
#import Product Data
start2 = time.time()
pdb = d_b["product"]
count_prior_j = pdb.count()
product_entry = import_table(pdb, path + prod_file)
count_after_j = pdb.count()
#print_mdb_collection(pdb)
end2 = time.time()
time2 = end2 - start2
return (customer_entry, count_prior_i, count_after_i, time1), \
(product_entry, count_prior_j, count_after_j, time2)
if __name__ == "__main__":
print(import_data('../data/', "product.csv", "customer.csv"))
drop_data()
"""
Run linear and parallel imports and provide time data.
"""
import datetime
import linear
import parallel
linear.drop_data()
print("--- Running linear import ---")
start_time = datetime.datetime.now()
results = linear.import_data('data', 'products.csv', 'customers.csv', 'rentals.csv')
print("Products:")
print(" Records: {} processed, {} imported".format(results[0][0], results[0][2] - results[0][1]))
print(" Runtime: {} seconds".format(results[0][3]))
print()
print("Customers:")
print(" Records: {} processed, {} imported".format(results[1][0], results[1][2] - results[1][1]))
print(" Runtime: {} seconds".format(results[1][3]))
print()
print("Linear import complete in {} seconds.".format(
(datetime.datetime.now() - start_time).total_seconds()))
print()
parallel.drop_data()
print("--- Running parallel import ---")
start_time = datetime.datetime.now()
results = parallel.import_data('data', 'products.csv', 'customers.csv', 'rentals.csv')
print("Products:")
print(" Records: {} processed, {} imported".format(results[0][0], results[0][2] - results[0][1]))