import sys
import numpy
import matplotlib
import powerlaw
matplotlib.use("GTK3Agg")
import matplotlib.pyplot as plt
from wallhack.rankingexp.DatasetUtils import DatasetUtils
"""
Do some basic analysis on the recommendation datasets.
"""
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
#X, U, V = DatasetUtils.syntheticDataset1()
#X = DatasetUtils.syntheticDataset2()
X = DatasetUtils.movieLens(quantile=100)
#X = DatasetUtils.flixster(quantile=100)
#X = DatasetUtils.mendeley(quantile=50)
print(X.shape)
m, n = X.shape
userCounts = X.sum(1)
itemCounts = X.sum(0)
results = powerlaw.Fit(itemCounts, discrete=True, xmax=n)
print(results.power_law.alpha)
print(results.power_law.xmin)
print(results.power_law.xmax)
u = 5
dataArgs = argparse.Namespace()
# Arguments related to the algorithm
defaultAlgoArgs = argparse.Namespace()
# data args parser #
dataParser = argparse.ArgumentParser(description="", add_help=False)
dataParser.add_argument("-h", "--help", action="store_true", help="show this help message and exit")
devNull, remainingArgs = dataParser.parse_known_args(namespace=dataArgs)
if dataArgs.help:
helpParser = argparse.ArgumentParser(description="", add_help=False, parents=[dataParser, RankingExpHelper.newAlgoParser(defaultAlgoArgs)])
helpParser.print_help()
exit()
#Load/create the dataset
X = DatasetUtils.movieLens()
(m, n) = X.shape
defaultAlgoArgs.u = 0.1
defaultAlgoArgs.ks = numpy.array([32, 64, 128])
dataArgs.extendedDirName = ""
dataArgs.extendedDirName += "MovieLens"
# print args #
logging.info("Running on " + dataArgs.extendedDirName)
logging.info("Data params:")
keys = list(vars(dataArgs).keys())
keys.sort()
for key in keys:
logging.info(" " + str(key) + ": " + str(dataArgs.__getattribute__(key)))
