tr = StandardScaler()
pca = PCA(n_components=10)
lr = LinearSVC(penalty='l1',dual=False)
pipe = Pipeline([('tr',tr),('pca',pca),('lr',lr)])
clf = GridSearchCV(pipe, parms, scoring='f1', n_jobs=5)
clf.fit(X,Y)
import pickle
f = open('%s.model' % __fname__,'wb')
pickle.dump(clf, f)
f.close()
pred = clf.predict(X)
summary.clf_summary(clf, feature_names)
summary.summary(Y, pred)
F1, P, R = TestModel()
util.notify_me('%s.F1:%.2f,P:%.2f,R:%.2f' % (__fname__, F1*100, P*100, R*100))
# load need to be recommanded item
fo = open(fout, 'wb')
fw = csv.writer(fo, delimiter=',')
fw.writerow(['user_id','item_id'])
rec_set = set()
pool = mp.Pool(com.__n_process)
re_str = r'feature_total\.merge\.\d+\.csv$'
f_list = util.FilterFile(re_str)
rec_set_list = pool.map(GenRecDataFromFeatureFile,[(sys.argv[1], f) for f in f_list])
for r in rec_set_list:
rec_set |= r
for uid, tid in rec_set:
fw.writerow([uid, tid])
fo.close()
nrows = len(rec_set)
print 'recommand %d record.' % nrows
util.notify_me('recommand data are done! %d record.' % nrows)
elif shelter == "lerefugefmv":
present_value = check_lerefugefmv(url)
elif shelter == "spcamontreal":
present_value = check_spcamontreal(url)
logger.info("%s: %s chiens" % (shelter, present_value))
if present_value > previous_value and not is_first_run:
title = "Refuge %s" % shelter
diff = present_value - previous_value
if diff == 1:
msg = "%s nouveau chien\n%s" % (diff, url)
elif diff > 1:
msg = "%s nouveaux chiens\n%s" % (diff, url)
logger.critical(msg.strip())
util.notify_me(title, msg)
new_dict[shelter] = present_value
except util.MyException as e:
new_dict[shelter] = previous_value
logger.error(e)
#util.notify_me("Adoptions", e)
time.sleep(1)
util.write_prec_values(new_dict)
logger.debug("")
X, Y = GetData()
samples = (np.random.rand(len(Y)) < 0.1) | (Y == 1)
X = X[samples]
Y = Y[samples]
feature_names = X.columns
parms = {
'C': [1.05], #np.logspace(-1,0,4), #
# 'class_weight':[{0:1,1:1}] #[{0:1,1:50},{0:1,1:70},{0:1,1:85},{0:1,1:100},{0:1,1:120},{0:1,1:150}]
}
lr = LogisticRegression(penalty='l1')
clf = GridSearchCV(lr, parms, scoring='f1', n_jobs=1)
clf.fit(X, Y)
import pickle
f = open('%s.model' % __fname__, 'wb')
pickle.dump(clf, f)
f.close()
pred = clf.predict(X)
summary.clf_summary(clf, feature_names)
summary.summary(Y, pred)
TestModel()
util.notify_me('%s is finished' % __fname__)
feature_names = X.columns
parms = {
'C': np.logspace(-1,0,4), #
#'class_weight':[{0:1,1:10}] #[{0:1,1:50},{0:1,1:70},{0:1,1:85},{0:1,1:100},{0:1,1:120},{0:1,1:150}]
}
lr = LogisticRegression(penalty='l1')
clf = GridSearchCV(lr, parms, scoring='f1', n_jobs=10)
clf.fit(X,Y)
import pickle
f = open('%s.model' % __fname__,'wb')
pickle.dump(clf, f)
f.close()
print __doc__
pred = clf.predict(X)
summary.clf_summary(clf, feature_names)
summary.summary(Y, pred)
TestModel()
util.notify_me('%s is finished' % __fname__)
