def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
def run_strategy(cfg, sample_file):
rec = Recommender(cfg)
repo_size = rec.items_repository.get_doccount()
results = ExperimentResults(repo_size)
label = get_label(cfg)
population_sample = []
sample_str = sample_file.split('/')[-1]
with open(sample_file, 'r') as f:
for line in f.readlines():
user_id = line.strip('\n')
population_sample.append(
os.path.join(cfg.popcon_dir, user_id[:2], user_id))
sample_dir = ("results/roc-sample/%s" % sample_str)
if not os.path.exists(sample_dir):
os.makedirs(sample_dir)
log_file = os.path.join(sample_dir, label["values"])
# n iterations per population user
for submission_file in population_sample:
user = PopconSystem(submission_file)
user.filter_pkg_profile(cfg.pkgs_filter)
user.maximal_pkg_profile()
for n in range(iterations):
# Fill sample profile
profile_len = len(user.pkg_profile)
item_score = {}
for pkg in user.pkg_profile:
item_score[pkg] = user.item_score[pkg]
sample = {}
sample_size = int(profile_len * 0.9)
for i in range(sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
iteration_user = User(item_score)
recommendation = rec.get_recommendation(iteration_user, repo_size)
if hasattr(recommendation, "ranking"):
results.add_result(recommendation.ranking, sample)
plot_roc(results, log_file)
plot_roc(results, log_file, 1)
with open(log_file + "-roc.jpg.comment", 'w') as f:
f.write("# %s\n# %s\n\n" %
(label["description"], label["values"]))
f.write("# roc AUC\n%.4f\n\n" % results.get_auc())
f.write(
"# threshold\tmean_fpr\tdev_fpr\t\tmean_tpr\tdev_tpr\t\tcoverage\n") # noqa
for size in results.thresholds:
f.write("%4d\t\t%.4f\t\t%.4f\t\t%.4f\t\t%.4f\t\t%.4f\n" %
(size, numpy.mean(results.fpr[size]),
numpy.std(results.fpr[size]),
numpy.mean(results.recall[size]),
numpy.std(results.recall[size]),
numpy.mean(results.coverage(size))))
def run_strategy(cfg, user):
for weight in weighting:
cfg.weight = weight[0]
cfg.bm25_k1 = weight[1]
rec = Recommender(cfg)
repo_size = rec.items_repository.get_doccount()
for proportion in sample_proportions:
results = ExperimentResults(repo_size)
label = get_label(cfg, proportion)
log_file = "results/strategies/" + label["values"]
for n in range(iterations):
# Fill sample profile
profile_size = len(user.pkg_profile)
item_score = {}
for pkg in user.pkg_profile:
item_score[pkg] = user.item_score[pkg]
sample = {}
sample_size = int(profile_size * proportion)
for i in range(sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
iteration_user = User(item_score)
recommendation = rec.get_recommendation(
iteration_user, repo_size)
write_recall_log(
label, n, sample, recommendation, profile_size, repo_size,
log_file)
if hasattr(recommendation, "ranking"):
results.add_result(recommendation.ranking, sample)
with open(log_file, 'w') as f:
precision_10 = sum(results.precision[10]) / len(
results.precision[10])
f1_10 = sum(results.f1[10]) / len(results.f1[10])
f05_10 = sum(results.f05[10]) / len(results.f05[10])
f.write("# %s\n# %s\n\ncoverage %d\n\n" %
(label["description"], label["values"],
recommendation.size))
f.write("# best results (recommendation size; metric)\n")
f.write(
"precision (%d; %.2f)\nf1 (%d; %.2f)\nf05 (%d; %.2f)\n\n" %
(results.best_precision()[0], results.best_precision()[1],
results.best_f1()[0], results.best_f1()[1],
results.best_f05()[0], results.best_f05()[1]))
f.write("# recommendation size 10\nprecision (10; %.2f)\nf1 (10; %.2f)\nf05 (10; %.2f)" % # noqa
(precision_10, f1_10, f05_10))
precision = results.get_precision_summary()
recall = results.get_recall_summary()
f1 = results.get_f1_summary()
f05 = results.get_f05_summary()
accuracy = results.get_accuracy_summary()
plot_summary(precision, recall, f1, f05, accuracy, log_file)
def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
class AppRecommender:
def __init__(self):
self.recommender = Recommender()
self.config = Config()
def make_recommendation(self, reference_pkgs=None,
print_recommendation=True):
begin_time = datetime.datetime.now()
logging.info("Computation started at %s" % begin_time)
if not reference_pkgs:
reference_pkgs = []
user = LocalSystem(reference_pkgs)
recommendation_size = Config().num_recommendations
user_recommendation = (self.recommender.get_recommendation(
user, recommendation_size))
logging.info("Recommending applications for user %s" % user.user_id)
if print_recommendation:
print(user_recommendation)
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)
return user_recommendation
class AppRecommender:
def __init__(self):
self.recommender = Recommender()
self.config = Config()
def make_recommendation(self, print_recommendation=True):
begin_time = datetime.datetime.now()
logging.info("Computation started at %s" % begin_time)
# user = RandomPopcon(cfg.popcon_dir,os.path.join(cfg.filters_dir,
# "desktopapps"))
user = LocalSystem()
recommendation_size = Config().num_recommendations
user_recommendation = (self.recommender.get_recommendation(
user, recommendation_size))
logging.info("Recommending applications for user %s" % user.user_id)
if print_recommendation:
print(user_recommendation)
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)
return user_recommendation
def run_strategy(cfg, user):
rec = Recommender(cfg)
repo_size = rec.items_repository.get_doccount()
results = ExperimentResults(repo_size)
label = get_label(cfg)
user_dir = ("results/roc-suite/%s/%s" % (user.user_id[:8], cfg.strategy))
if not os.path.exists(user_dir):
os.makedirs(user_dir)
log_file = os.path.join(user_dir, label["values"])
for n in range(iterations):
# Fill sample profile
profile_len = len(user.pkg_profile)
item_score = {}
for pkg in user.pkg_profile:
item_score[pkg] = user.item_score[pkg]
sample = {}
sample_size = int(profile_len * 0.9)
for i in range(sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
iteration_user = User(item_score)
recommendation = rec.get_recommendation(iteration_user, repo_size)
write_recall_log(
label, n, sample, recommendation, profile_len, repo_size, log_file)
if hasattr(recommendation, "ranking"):
results.add_result(recommendation.ranking, sample)
with open(log_file + "-roc.jpg.comment", 'w') as f:
f.write("# %s\n# %s\n\n" %
(label["description"], label["values"]))
f.write("# roc AUC\n%.4f\n\n" % results.get_auc())
f.write("# threshold\tprecision\trecall\t\tf05\t\tcoverage\n")
for size in results.thresholds:
f.write("%4d\t\t%.4f\t\t%.4f\t\t%.4f\t\t%.4f\n" %
(size, numpy.mean(results.precision[size]),
numpy.mean(results.recall[size]),
numpy.mean(results.f05[size]),
numpy.mean(results.coverage(size))))
shutil.copy(log_file + "-roc.jpg.comment", log_file + ".jpg.comment")
shutil.copy(log_file + "-roc.jpg.comment",
log_file + "-logscale.jpg.comment")
plot_roc(results, log_file)
plot_summary(results, log_file)
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.sample_size = int(
len(self.user.pkg_profile) * params['sample'])
class AppRecommender:
def __init__(self):
self.recommender = Recommender()
def make_recommendation(self,
recommendation_size,
no_auto_pkg_profile=False):
begin_time = datetime.datetime.now()
logging.info("Computation started at %s" % begin_time)
# user = RandomPopcon(cfg.popcon_dir,os.path.join(cfg.filters_dir,
# "desktopapps"))
user = self.get_user(no_auto_pkg_profile)
user_reccomendation = (self.recommender.get_recommendation(
user, recommendation_size))
logging.info("Recommending applications for user %s" % user.user_id)
logging.info(user_reccomendation)
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)
return user_reccomendation
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
class AppRecommender:
def __init__(self):
self.recommender = Recommender()
def make_recommendation(self, recommendation_size,
no_auto_pkg_profile=False):
begin_time = datetime.datetime.now()
logging.info("Computation started at %s" % begin_time)
# user = RandomPopcon(cfg.popcon_dir,os.path.join(cfg.filters_dir,
# "desktopapps"))
user = self.get_user(no_auto_pkg_profile)
user_reccomendation = (self.recommender.get_recommendation(
user, recommendation_size))
logging.info("Recommending applications for user %s" % user.user_id)
logging.info(user_reccomendation)
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)
return user_reccomendation
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
import sys
sys.path.insert(0, '../')
import logging
import datetime
from apprecommender.config import Config
from apprecommender.recommender import Recommender
from apprecommender.user import LocalSystem
from apprecommender.error import Error
if __name__ == '__main__':
try:
cfg = Config()
rec = Recommender(cfg)
user = LocalSystem()
user.no_auto_pkg_profile()
# user.maximal_pkg_profile()
begin_time = datetime.datetime.now()
logging.debug("Recommendation computation started at %s" % begin_time)
print rec.get_recommendation(user)
end_time = datetime.datetime.now()
logging.debug("Recommendation computation completed at %s" % end_time)
delta = end_time - begin_time
logging.info("Time elapsed: %d seconds." % delta.seconds)
except Error:
class RecommenderTests(unittest.TestCase):
@classmethod
def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
def test_set_strategy(self):
self.rec.set_strategy("cb")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "mix")
self.rec.set_strategy("cbt")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "tag")
self.rec.set_strategy("cbd")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "desc")
self.rec.set_strategy("cbtm")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "time")
self.rec.set_strategy("mlbva")
self.assertIsInstance(self.rec.strategy, MachineLearningBVA)
self.assertEqual(self.rec.strategy.content, "mlbva_mix")
self.rec.set_strategy("mlbow")
self.assertIsInstance(self.rec.strategy, MachineLearningBOW)
self.assertEqual(self.rec.strategy.content, "mlbow_mix")
self.rec.set_strategy("mlbva_eset")
self.assertIsInstance(self.rec.strategy, MachineLearningBVA)
self.assertEqual(self.rec.strategy.content, "mlbva_mix_eset")
self.rec.set_strategy("mlbow_eset")
self.assertIsInstance(self.rec.strategy, MachineLearningBOW)
self.assertEqual(self.rec.strategy.content, "mlbow_mix_eset")
self.rec.set_strategy("cbpkg")
self.assertIsInstance(self.rec.strategy, PackageReference)
self.assertEqual(self.rec.strategy.content, "mix")
def test_get_recommendation(self):
user = User({"inkscape": 1, "gimp": 1, "eog": 1, "vim": 1})
result = self.rec.get_recommendation(user)
self.assertIsInstance(result, RecommendationResult)
self.assertGreater(len(result.item_score), 0)
import sys
sys.path.insert(0, '../')
import logging
import datetime
from apprecommender.config import Config
from apprecommender.evaluation import (Precision, Recall, F1, Accuracy,
SimpleAccuracy, CrossValidation)
from apprecommender.recommender import Recommender
from apprecommender.user import LocalSystem
from apprecommender.error import Error
if __name__ == '__main__':
try:
cfg = Config()
rec = Recommender(cfg)
print "\nRecommender strategy: ", rec.strategy.description
user = LocalSystem()
# user.app_pkg_profile(rec.items_repository)
user.no_auto_pkg_profile()
begin_time = datetime.datetime.now()
logging.debug("Cross-validation started at %s" % begin_time)
metrics = []
metrics.append(Precision())
metrics.append(Recall())
metrics.append(F1())
metrics.append(Accuracy())
metrics.append(SimpleAccuracy())
validation = CrossValidation(0.9, 10, rec, metrics, 0.1)
validation.run(user)
class RecommenderTests(unittest.TestCase):
@classmethod
def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
def test_set_strategy(self):
self.rec.set_strategy("cb")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "mix")
self.rec.set_strategy("cbt")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "tag")
self.rec.set_strategy("cbd")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "desc")
self.rec.set_strategy("cbtm")
self.assertIsInstance(self.rec.strategy, ContentBased)
self.assertEqual(self.rec.strategy.content, "time")
self.rec.set_strategy("mlbva")
self.assertIsInstance(self.rec.strategy, MachineLearningBVA)
self.assertEqual(self.rec.strategy.content, "mlbva_mix")
self.rec.set_strategy("mlbow")
self.assertIsInstance(self.rec.strategy, MachineLearningBOW)
self.assertEqual(self.rec.strategy.content, "mlbow_mix")
self.rec.set_strategy("mlbva_eset")
self.assertIsInstance(self.rec.strategy, MachineLearningBVA)
self.assertEqual(self.rec.strategy.content, "mlbva_mix_eset")
self.rec.set_strategy("mlbow_eset")
self.assertIsInstance(self.rec.strategy, MachineLearningBOW)
self.assertEqual(self.rec.strategy.content, "mlbow_mix_eset")
# self.rec.set_strategy("knn")
# self.assertIsInstance(self.rec.strategy,Collaborative)
def test_get_recommendation(self):
user = User({"inkscape": 1, "gimp": 1, "eog": 1})
result = self.rec.get_recommendation(user)
self.assertIsInstance(result, RecommendationResult)
self.assertGreater(len(result.item_score), 0)
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.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
import os
import logging
import datetime
import sys
sys.path.insert(0, '../')
from apprecommender.config import Config
from apprecommender.evaluation import (CrossValidation, Precision, Recall,
F_score, FPR, Accuracy)
from apprecommender.recommender import Recommender
from apprecommender.user import PopconSystem
if __name__ == '__main__':
cfg = Config()
rec = Recommender()
# user = LocalSystem()
# user = RandomPopcon(cfg.popcon_dir)
# user = RandomPopcon(cfg.popcon_dir,os.path.join(cfg.filters_dir,
# "desktopapps"))
popcon_entries = "~/.app-recommender/popcon-entries/" \
"00/0001166d0737c6dffb083071e5ee69f5"
user = PopconSystem(os.path.expanduser(popcon_entries))
user.filter_pkg_profile(os.path.join(cfg.filters_dir, "desktopapps"))
user.maximal_pkg_profile()
begin_time = datetime.datetime.now()
metrics = []
metrics.append(Precision())
metrics.append(Recall())
def __init__(self):
self.recommender = Recommender()
self.config = Config()
"""
import sys
sys.path.insert(0, '../')
import logging
import datetime
from apprecommender.config import Config
from apprecommender.recommender import Recommender
from apprecommender.user import LocalSystem
from apprecommender.error import Error
if __name__ == '__main__':
try:
cfg = Config()
rec = Recommender(cfg)
user = LocalSystem()
begin_time = datetime.datetime.now()
logging.debug("Recommendation computation started at %s" % begin_time)
print rec.get_recommendation(user)
end_time = datetime.datetime.now()
logging.debug("Recommendation computation completed at %s" % end_time)
delta = end_time - begin_time
logging.info("Time elapsed: %d seconds." % delta.seconds)
except Error:
logging.critical("Aborting proccess. Use '--debug' for more details.")
def __init__(self):
self.recommender = Recommender()
f05_100_summary[size] = []
with open(log_file + "-%s%.3d" % (option_str, size), 'w') as f:
f.write("# sample %s\n" % sample_str)
f.write("# strategy %s-%s%.3d\n\n" %
(cfg.strategy, option_str, size))
f.write("# p_10\tf05_100\n\n")
# main loop per user
for submission_file in population_sample:
user = PopconSystem(submission_file)
user.filter_pkg_profile(cfg.pkgs_filter)
user.maximal_pkg_profile()
for size in sizes:
cfg.profile_size = size
cfg.k_neighbors = size
rec = Recommender(cfg)
repo_size = rec.items_repository.get_doccount()
p_10 = []
f05_100 = []
for n in range(iterations):
# Fill sample profile
profile_len = len(user.pkg_profile)
item_score = {}
for pkg in user.pkg_profile:
item_score[pkg] = user.item_score[pkg]
sample = {}
sample_size = int(profile_len * 0.9)
for i in range(sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
iteration_user = User(item_score)
def __init__(self):
self.recommender = Recommender()
precision_summary[k] = []
f05_summary[k] = []
mcc_summary[k] = []
with open(log_file + "-k%.3d" % k, 'w') as f:
f.write("# %s\n\n" % sample_file.split('/')[-1])
f.write("# strategy-k %s-k%.3d\n\n" % (cfg.strategy, k))
f.write("# roc_point \tprecision \tf05 \tmcc\n\n")
# main loop per user
for submission_file in population_sample:
user = PopconSystem(submission_file)
user.filter_pkg_profile(cfg.pkgs_filter)
user.maximal_pkg_profile()
for k in neighbors:
cfg.k_neighbors = k
rec = Recommender(cfg)
repo_size = rec.items_repository.get_doccount()
results = ExperimentResults(repo_size)
# n iterations for same recommender and user
for n in range(iterations):
# Fill sample profile
profile_len = len(user.pkg_profile)
item_score = {}
for pkg in user.pkg_profile:
item_score[pkg] = user.item_score[pkg]
sample = {}
sample_size = int(profile_len * 0.9)
for i in range(sample_size):
key = random.choice(item_score.keys())
sample[key] = item_score.pop(key)
iteration_user = User(item_score)