def test():
# create a random matrix in the file
gen_random.gen_random_array(1000000, 25, "matrix.txt")
# splits the matrix into training and test data
split_file("matrix.txt", "matrix_train.txt", "matrix_test.txt")
start = time.time()
coefs = linreg.get_coefficients("matrix_train.txt")
predict_buy, predict_sell = get_recommended_buys("matrix_test.txt", coefs)
print time.time() - start
def test_parallel(rows, cols, num_threads):
"""
returns time of linear regression using parallel choelsky
"""
gen_random.gen_random_array(rows, cols, "parallel_matrix.txt")
split_file("parallel_matrix.txt", "parallel_matrix_train.txt", "parallel_matrix_test.txt")
start = time.time()
coefs = linreg.parallel_get_coefficients(file_name="parallel_matrix_train.txt", num_threads=num_threads)
reg_time = time.time() - start
# return time in seconds of lin reg
return reg_time
def get_data(request):
rows = int(request.POST.get("rows"))
cols = int(request.POST.get("columns"))
#create a random matrix in the file
gen_random.gen_random_array(rows, cols, home_dir + "matrix.txt")
#splits the matrix into training and test data
test_regression.split_file(home_dir + "matrix.txt", home_dir + "matrix_train.txt", home_dir + "matrix_test.txt")
start = time.time()
coefs = get_coefficients(home_dir + "matrix_train.txt")
#tests the coefs
predict_buy, predict_sell = test_regression.get_recommended_buys(home_dir + "matrix_test.txt", coefs)
elapsed = time.time() - start
#gets the top buys and sells
top_buys = sorted(predict_buy, key=lambda x: x["change"], reverse=True)[:50]
top_sells = sorted(predict_sell, key=lambda x: x["change"], reverse=True)[:50]
#gets the (simulated) event names for the buys and sells
event_names = os.listdir(home_dir + "../../snapshots_by_event")
event_names = [home_dir + "../../snapshots_by_event/" + x for x in event_names if x[-4:]==".txt"]
top_buys = test_regression.get_events_from_simulation(top_buys, event_names)
top_sells = test_regression.get_events_from_simulation(top_sells, event_names)
#resorts (as prices may have been updated with true ticket prices)
top_buys = sorted(top_buys, key=lambda x: x["change"], reverse=True)
top_sells = sorted(top_sells, key=lambda x: x["change"], reverse=True)
response = {}
response['time'] = elapsed
response["buy_events"] = top_buys
response["sell_events"] = top_sells
'''
#read random data for each of the rows
files = os.listdir("../../snapshots_by_event")
files = ["../../snapshots_by_event/" + x for x in files if x[-4:]==".txt"]
#gets metadata
#metadata = ['event_id', 'last_chance', 'act_primary', 'venue_name', 'eventLocation_facet_str', 'zip']
for i in range(len(predict_buy[:50])):
cur_file = np.random.choice(files)
with open(cur_file, "r+") as inputfile:
metadata = inputfile.next().split("\t")
predict_buy_events.append(metadata)
for i in range(len(predict_sell[:50])):
cur_file = np.random.choice(files)
with open(cur_file, "r+") as inputfile:
metadata = inputfile.next().split("\t")
predict_sell_events.append(metadata)
response["buy_events"] = predict_buy_events
response["sell_events"] = predict_sell_events
#gets the times, in index 1
for x in response["buy_events"]:
cur_time = x[1]
parsed_time = datetime.datetime.strptime(cur_time, "%Y-%m-%dT%XZ")
formatted_time = parsed_time.strftime("%c")
x[1] = formatted_time
for x in response["sell_events"]:
cur_time = x[1]
parsed_time = datetime.datetime.strptime(cur_time, "%Y-%m-%dT%XZ")
formatted_time = parsed_time.strftime("%c")
x[1] = formatted_time
'''
#return HttpResponse(json.dumps(response), content_type="application/json")
return render(request, "mysite/events.html", response)