def reset(self, params, rep):
if params['name'].startswith("content"):
cfg = Config()
# if the index was not built yet
# app_axi = AppAptXapianIndex(cfg.axi,"results/arnaldo/AppAxi")
cfg.axi = "data/AppAxi"
cfg.index_mode = "old"
cfg.weight = params['weight']
self.rec = Recommender(cfg)
self.rec.set_strategy(params['strategy'])
self.repo_size = self.rec.items_repository.get_doccount()
self.user = LocalSystem()
self.user.app_pkg_profile(self.rec.items_repository)
self.user.no_auto_pkg_profile()
self.sample_size = int(
len(self.user.pkg_profile) * params['sample'])
def get_user(self, no_auto_pkg_profile):
config = Config()
user = LocalSystem()
user.filter_pkg_profile(
os.path.join(config.filters_dir, "desktopapps"))
user.maximal_pkg_profile()
if no_auto_pkg_profile:
user.no_auto_pkg_profile()
return user
def reset(self, params, rep):
if params['name'].startswith("content"):
cfg = Config()
#if the index was not built yet
#app_axi = AppAptXapianIndex(cfg.axi,"results/arnaldo/AppAxi")
cfg.axi = "data/AppAxi"
cfg.index_mode = "old"
cfg.weight = params['weight']
self.rec = Recommender(cfg)
self.rec.set_strategy(params['strategy'])
self.repo_size = self.rec.items_repository.get_doccount()
self.user = LocalSystem()
self.user.app_pkg_profile(self.rec.items_repository)
self.user.no_auto_pkg_profile()
self.sample_size = int(len(self.user.pkg_profile)*params['sample'])
"""
import os
import sys
sys.path.insert(0,'../')
import logging
import random
import datetime
from config import Config
from recommender import Recommender
from user import LocalSystem, RandomPopcon
if __name__ == '__main__':
begin_time = datetime.datetime.now()
cfg = Config()
rec = Recommender(cfg)
logging.info("Computation started at %s" % begin_time)
#user = RandomPopcon(cfg.popcon_dir,os.path.join(cfg.filters_dir,"desktopapps"))
user = LocalSystem()
user.filter_pkg_profile(os.path.join(cfg.filters_dir,"desktopapps"))
user.maximal_pkg_profile()
logging.info("Recommending applications for user %s" % user.user_id)
logging.info(rec.get_recommendation(user,20))
end_time = datetime.datetime.now()
logging.info("Computation completed at %s" % end_time)
delta = end_time - begin_time
logging.info("Time elapsed: %d seconds." % delta.seconds)
class ContentBasedSuite(expsuite.PyExperimentSuite):
def reset(self, params, rep):
if params['name'].startswith("content"):
cfg = Config()
# if the index was not built yet
# app_axi = AppAptXapianIndex(cfg.axi,"results/arnaldo/AppAxi")
cfg.axi = "data/AppAxi"
cfg.index_mode = "old"
cfg.weight = params['weight']
self.rec = Recommender(cfg)
self.rec.set_strategy(params['strategy'])
self.repo_size = self.rec.items_repository.get_doccount()
self.user = LocalSystem()
self.user.app_pkg_profile(self.rec.items_repository)
self.user.no_auto_pkg_profile()
self.sample_size = int(
len(self.user.pkg_profile) * params['sample'])
# iteration should be set to 10 in config file
# self.profile_size = range(10,101,10)
def iterate(self, params, rep, n):
if params['name'].startswith("content"):
item_score = dict.fromkeys(self.user.pkg_profile, 1)
# Prepare partition
sample = {}
for i in range(self.sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
# Get full recommendation
user = User(item_score)
recommendation = self.rec.get_recommendation(user, self.repo_size)
# Write recall log
recall_file = "results/content/recall/%s-%s-%.2f-%d" % \
(params['strategy'], params[
'weight'], params['sample'], n)
output = open(recall_file, 'w')
output.write("# weight=%s\n" % params['weight'])
output.write("# strategy=%s\n" % params['strategy'])
output.write("# sample=%f\n" % params['sample'])
output.write("\n%d %d %d\n" %
(self.repo_size, len(item_score), self.sample_size))
notfound = []
ranks = []
for pkg in sample.keys():
if pkg in recommendation.ranking:
ranks.append(recommendation.ranking.index(pkg))
else:
notfound.append(pkg)
for r in sorted(ranks):
output.write(str(r) + "\n")
if notfound:
output.write("Out of recommendation:\n")
for pkg in notfound:
output.write(pkg + "\n")
output.close()
# Plot metrics summary
accuracy = []
precision = []
recall = []
f1 = []
g = Gnuplot.Gnuplot()
g('set style data lines')
g.xlabel('Recommendation size')
for size in range(1, len(recommendation.ranking) + 1, 100):
predicted = RecommendationResult(
dict.fromkeys(recommendation.ranking[:size], 1))
real = RecommendationResult(sample)
evaluation = Evaluation(predicted, real, self.repo_size)
accuracy.append([size, evaluation.run(Accuracy())])
precision.append([size, evaluation.run(Precision())])
recall.append([size, evaluation.run(Recall())])
f1.append([size, evaluation.run(F1())])
g.plot(Gnuplot.Data(accuracy, title="Accuracy"),
Gnuplot.Data(precision, title="Precision"),
Gnuplot.Data(recall, title="Recall"),
Gnuplot.Data(f1, title="F1"))
g.hardcopy(recall_file + "-plot.ps", enhanced=1, color=1)
# Iteration log
result = {'iteration': n,
'weight': params['weight'],
'strategy': params['strategy'],
'accuracy': accuracy[20],
'precision': precision[20],
'recall:': recall[20],
'f1': f1[20]}
return result