def main(): predictor = MFUPredictor() db_helper = ApeicDBHelper() users = db_helper.get_users() for user in users: logs = db_helper.get_logs(user) sessions = db_helper.get_sessions(user) training_logs, testing_logs = split(sessions, aggregated=True) predictor.train(training_logs) launches = map(lambda x: x['application'], testing_logs) predictions = map(lambda x: predictor.predict(x), testing_logs) hr, mrr = predictor.test(launches, predictions) print hr, mrr
def main():
predictor = MFUPredictor()
db_helper = ApeicDBHelper()
users = db_helper.get_users()
for user in users:
logs = db_helper.get_logs(user)
sessions = db_helper.get_sessions(user)
training_logs, testing_logs = split(sessions, aggregated=True)
predictor.train(training_logs)
launches = map(lambda x: x['application'], testing_logs)
predictions = map(lambda x: predictor.predict(x), testing_logs)
hr, mrr = predictor.test(launches, predictions)
print hr, mrr
def main():
predictor = LUPredictor()
db_helper = ApeicDBHelper()
users = db_helper.get_users()
for user in users:
sessions = db_helper.get_sessions(user)
training_logs, testing_logs = split(sessions, aggregated=True)
predictor.train(training_logs)
launches = map(lambda x: x['application'], testing_logs[2:])
predictions = map(lambda i: predictor.predict(\
{'lu1': testing_logs[i-1]['application'], 'lu2': testing_logs[i-2]['application']}), \
xrange(2, len(testing_logs)))
hr, mrr = predictor.test(launches, predictions)
print hr, mrr
def main():
predictor = LUPredictor()
db_helper = ApeicDBHelper()
users = db_helper.get_users()
for user in users:
sessions = db_helper.get_sessions(user)
training_logs, testing_logs = split(sessions, aggregated=True)
predictor.train(training_logs)
launches = map(lambda x: x['application'], testing_logs[2:])
predictions = map(lambda i: predictor.predict(\
{'lu1': testing_logs[i-1]['application'], 'lu2': testing_logs[i-2]['application']}), \
xrange(2, len(testing_logs)))
hr, mrr = predictor.test(launches, predictions)
print hr, mrr
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler
##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=100,
centers=centers,
cluster_std=0.4,
random_state=0)
X = StandardScaler().fit_transform(X)
from numpy import array
from predictor.predictor import Predictor, split
db_helper = ApeicDBHelper()
for user in db_helper.get_users()[7:]:
sessions = db_helper.get_sessions(user)
training_logs, testing_logs = split(sessions, aggregated=True)
training_logs = filter(
lambda x: x['latitude'] != 0 and x['longitude'] != 0, training_logs)
latlng_pairs = list(
set(map(lambda x: (x['latitude'], x['longitude']), training_logs)))
print latlng_pairs
print len(latlng_pairs)
# X = array(latlng_pairs)
# print X.size
# print X
result = []
for la1, ln1 in latlng_pairs:
from predictor.preprocessor import Preprocessor
from predictor.mfu_predictor import MFUPredictor
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.naive_bayes import GaussianNB
from sklearn.feature_extraction import DictVectorizer
from sklearn import tree
def split(sessions, ratio=0.8):
split_index = int(len(sessions) * ratio)
return sessions[:split_index], sessions[split_index:]
import sys
if __name__ == '__main__':
db_helper = ApeicDBHelper()
users = db_helper.get_users()
accuracies = []
for user in users:
print colored(user, attrs=['blink'])
sessions = db_helper.get_sessions(user)
training_sessions, testing_sessions = split(sessions, 0.8)
preprocessor = Preprocessor([])
start = 0
tesiting_sessions = filter(lambda x: len(x) > start, testing_sessions)
logs = preprocessor.aggregate_sessions(\
training_sessions + \
map(lambda x: [x[start]], tesiting_sessions))
from predictor.preprocessor import Preprocessor from predictor.mfu_predictor import MFUPredictor from sklearn.naive_bayes import MultinomialNB, BernoulliNB from sklearn.naive_bayes import GaussianNB from sklearn.feature_extraction import DictVectorizer from sklearn import tree def split(sessions, ratio=0.8): split_index = int(len(sessions)*ratio) return sessions[:split_index], sessions[split_index:] import sys if __name__ == '__main__': db_helper = ApeicDBHelper() users = db_helper.get_users() accuracies = [] for user in users: print colored(user, attrs=['blink']) sessions = db_helper.get_sessions(user) training_sessions, testing_sessions = split(sessions, 0.8) preprocessor = Preprocessor([]) start = 0 tesiting_sessions = filter(lambda x: len(x) > start, testing_sessions) logs = preprocessor.aggregate_sessions(\ training_sessions + \ map(lambda x: [x[start]], tesiting_sessions))
from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler
##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=100, centers=centers, cluster_std=0.4,
random_state=0)
X = StandardScaler().fit_transform(X)
from numpy import array
from predictor.predictor import Predictor, split
db_helper = ApeicDBHelper()
for user in db_helper.get_users()[7:]:
sessions = db_helper.get_sessions(user)
training_logs, testing_logs = split(sessions, aggregated=True)
training_logs = filter(lambda x: x['latitude'] != 0 and x['longitude']!= 0, training_logs)
latlng_pairs = list(set(map(lambda x: (x['latitude'], x['longitude']), training_logs)))
print latlng_pairs
print len(latlng_pairs)
# X = array(latlng_pairs)
# print X.size
# print X
result = []
for la1, ln1 in latlng_pairs:
dists = []