def test_tsfi(): tsfi = timeseriescv.tsfi(20,ntraining=10,ntest=2,nvalidation=2) for x in tsfi: assert len(x.training) >= 10 assert len(x.test) == 2 assert len(x.validation) == 2 tsfi = timeseriescv.tsfi(20,ntraining=5,ntest=3,nvalidation=3) for x in tsfi: assert len(x.training) >= 5 assert len(x.test) == 3 assert len(x.validation) == 3
def test_tsfi():
tsfi = timeseriescv.tsfi(20, ntraining=10, ntest=2, nvalidation=2)
for x in tsfi:
assert len(x.training) >= 10
assert len(x.test) == 2
assert len(x.validation) == 2
tsfi = timeseriescv.tsfi(20, ntraining=5, ntest=3, nvalidation=3)
for x in tsfi:
assert len(x.training) >= 5
assert len(x.test) == 3
assert len(x.validation) == 3
def test_bivariate_optimise():
w_spams = FistaFlat(**{
"intercept": True,
"loss":"square",
"regul":"l1"
})
u_spams = FistaFlat(**{
"intercept": True,
"loss":"square",
"regul":"l1"
})
learner = BatchBivariateLearner(w_spams,u_spams)
gen = RandomBiGen()
ndays = 20
Xt,Y = gen.generate(n=ndays)
Xt = vstack(Xt)
Y = vstack(Y)
folds = [x for x in tscv.tsfi(ndays,ntest=2)]
lrng = np.arange(0.1,1,0.1)
fold = folds[0]
X = ssp.csc_matrix(Xt.transpose())
Xparts,Yparts = BatchBivariateLearner.XYparts(fold,X,Y)
learner.optimise_lambda(lrng,lrng,Yparts,Xparts)
print w_spams.params
print u_spams.params
def test_bivariate_optimise():
w_spams = FistaFlat(**{"intercept": True, "loss": "square", "regul": "l1"})
u_spams = FistaFlat(**{"intercept": True, "loss": "square", "regul": "l1"})
learner = BatchBivariateLearner(w_spams, u_spams)
gen = RandomBiGen()
ndays = 20
Xt, Y = gen.generate(n=ndays)
Xt = vstack(Xt)
Y = vstack(Y)
folds = [x for x in tscv.tsfi(ndays, ntest=2)]
lrng = np.arange(0.1, 1, 0.1)
fold = folds[0]
X = ssp.csc_matrix(Xt.transpose())
Xparts, Yparts = BatchBivariateLearner.XYparts(fold, X, Y)
learner.optimise_lambda(lrng, lrng, Yparts, Xparts)
print w_spams.params
print u_spams.params
})
u_spams = FistaFlat(**{
"intercept": True,
"loss":"square",
"regul":"elastic-net",
"max_it":1000,
"lambda2":0.5,
"lambda1":0.3
})
es.exp("randomExp",fake=False)
es.state("random")
gen = randomgen.RandomBiGen(noise=0.01,brng=(100,1000),ntasks=1,wu_sparcity=0.6,wrng=(2,3),urng=(2,3),nusers=100,nwords=400)
x,y = gen.generate(n=1000)
x = ssp.csc_matrix(vstack(x).T)
y = array(y)
fold = [f for f in tscv.tsfi(y.shape[0],ntest=100,ntraining=900)][0]
Xparts,Yparts = BatchBivariateLearner.XYparts(fold,x,y)
learner = BatchBivariateLearner(w_spams,u_spams,bivar_max_it=10)
learner.process(Yparts.train_all,Xparts.train_all,tests={"test":(Xparts.test,Yparts.test)})
print learner.w.todense()
print gen._w
print learner.u.todense()
print gen._u
print learner.w_bias
print learner.u_bias
print gen._bias
embed()
def experiment(o):
logger.info("Reading initial data")
start = o["start"];ndays = o["ndays"];end = start + ndays
folds = tscv.tsfi(ndays,ntest=o['f_ntest'],nvalidation=o['f_nval'],ntraining=o['f_ntrain'])
tasks = billdata.taskvals(o["task_file"])
ndays_total = tasks.yvalues.shape[0]
if o["user_file_corrected"] is None or not os.path.exists(o["user_file_corrected"]):
logger.info("...Loading and correcting from source")
if "voc_file" in o and not o["word_subsample"] < 1:
logger.info("...Reading vocabulary")
voc = billdata.voc(o["voc_file"]).voc()
# voc = None
else:
voc = None
logger.info("...Reading user days")
user_col, word_col = billdata.suserdayword(
o["user_file"],ndays_total,
nwords=billdata.count_cols_h5(o["word_file"])
).mat(
days=(start,end),
voc=voc
)
if o["user_file_corrected"] is not None:
logger.info("...Saving corrected user_mat")
sio.savemat(o["user_file_corrected"],{"data":user_col.data,"indices":user_col.indices,"indptr":user_col.indptr,"shape":user_col.shape})
else:
logger.info("...Loading corrected user_mat")
# csc_matrix((data, indices, indptr), [shape=(M, N)])
user_col_d = sio.loadmat(o["user_file_corrected"])
user_col = ssp.csc_matrix((user_col_d["data"][:,0],user_col_d["indices"][:,0],user_col_d["indptr"][:,0]),shape=user_col_d["shape"])
logger.info("...User Col read, dimensions: %s"%str(user_col.shape))
logger.info("...Reading task data")
tasks = tasks.mat(days=(start,end),cols=[3,4,5])
logger.info("...Reading tree file")
tree = billdata.tree(o["tree_file"]).spamsobj()
if o["word_subsample"] < 1 or o["user_subsample"] < 1:
user_col=billdata.subsample(user_col,word_subsample=o["word_subsample"],user_subsample=o["user_subsample"],ndays=ndays)
# At this point we've just loaded all the data
# Prepare the optimisation functions
u_lambdas = [float(x) for x in o['u_lambdas_str'].split(",")]
w_lambdas = [float(x) for x in o['w_lambdas_str'].split(",")]
u_lambdas = np.arange(*u_lambdas)
w_lambdas = np.arange(*w_lambdas)
spams_avail = {
"tree":FistaTree(tree,**{
"intercept": True,
"loss":"square",
"regul":"multi-task-tree",
"it0":10,
"lambda2":1000,
"max_it":1000,
"verbose":True
}),
"treecheck":FistaTree(tree,**{
"intercept": True,
"loss":"square",
"regul":"multi-task-tree",
"it0":10,
"max_it":100,
"lambda2":1000,
"verbose":True
}),
"flatcheck":FistaFlat(**{
"intercept": True,
"loss":"square",
"regul":"l1l2",
"it0":50,
"max_it":100,
"verbose":True
}),
"flat":FistaFlat(**{
"intercept": True,
"loss":"square",
"regul":"l1l2",
"it0":50,
"max_it":1000,
"verbose":True
})
}
w_spams = copy.deepcopy(spams_avail[o["w_spams"]])
u_spams = copy.deepcopy(spams_avail[o["u_spams"]])
lambda_set = False
if o["lambda_file"] is not None and os.path.exists(o["lambda_file"]):
logger.info("... loading existing lambda")
lambda_d = sio.loadmat(o["lambda_file"])
w_spams.params["lambda1"] = lambda_d["w_lambda"][0][0]
u_spams.params["lambda1"] = lambda_d["u_lambda"][0][0]
lambda_set = True
# Prepare the learner
learner = BatchBivariateLearner(w_spams,u_spams,bivar_max_it=o["bivar_max_it"])
fold_i = 0
es.exp(os.sep.join([o['exp_out'],"ds:politics_word:l1_user:l1_task:multi"]),fake=False)
# Go through the folds!
for fold in folds:
es.state("fold_%d"%fold_i)
logger.info("Working on fold: %d"%fold_i)
logger.info("... preparing fold parts")
Xparts,Yparts = BatchBivariateLearner.XYparts(fold,user_col,tasks)
if not o["optimise_lambda_once"] or (o["optimise_lambda_once"] and not lambda_set):
logger.debug("... Setting max it to optimisation mode: %d"%o["opt_maxit"])
w_spams.params["max_it"] = o["opt_maxit"]
u_spams.params["max_it"] = o["opt_maxit"]
logger.info("... optimising fold lambda")
ulambda,wlambda = learner.optimise_lambda(
w_lambdas,u_lambdas,Yparts,Xparts,
w_lambda=o["w_lambda"],u_lambda=o["u_lambda"]
)
lambda_set = True
if o["lambda_file"] is not None:
logger.info("... saving optimised lambdas")
sio.savemat(o["lambda_file"],{"w_lambda":wlambda[1],"u_lambda":ulambda[1]})
logger.info("... training fold")
logger.debug("... Setting max it to training mode: %d"%o["train_maxit"])
w_spams.params["max_it"] = o["train_maxit"]
u_spams.params["max_it"] = o["train_maxit"]
learner.process(
Yparts.train_all,Xparts.train_all,
tests={
"test":(Xparts.test,Yparts.test),
"val_it":(Xparts.val_it,Yparts.val_it)
}
)
es.add(locals(),"fold_i","w_lambdas","u_lambdas","fold","Yparts","o")
es.state()["w_spams_params"] = w_spams.params
es.state()["u_spams_params"] = u_spams.params
logger.info("... Saving output")
es.flush()
fold_i += 1
if o["f_maxiter"] is not None and fold_i >= o["f_maxiter"]: break
data_home = "%s/Dropbox/Experiments/twitter_uk_users_MATLAB" % home
user_mat_file = "user_vsr_for_polls_day_%d_%d_t.mat"
word_mat_file = "user_vsr_for_polls_day_%d_%d.mat"
task_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/UK_data_for_experiment_PartII.mat" % home
tree_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/UK_data_for_experiment_PartI.mat" % home
voc_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/voc_matching_v2.mat" % home
start = 81
ndays = 20
end = start + ndays
user_file = os.sep.join([data_home, user_mat_file % (start, end)])
word_file = os.sep.join([data_home, word_mat_file % (start, end)])
folds = tscv.tsfi(ndays, ntest=2)
logger.info("Reading task data")
tasks = billdata.taskvals(task_file).mat(days=(start, end))
# tree = billdata.tree(tree_file).spamsobj()
logger.info("Reading vocabulary")
voc = billdata.voc(voc_file).voc()
user_col, word_col = billdata.suserdayword(user_file, word_file,
ndays).mat(voc=voc)
user_col, word_col = billdata.subsample(user_col,
word_subsample=0.001,
user_subsample=0.001,
ndays=ndays)
# At this point we've just loaded all the data
# Prepare the optimisation functions
u_lambdas = np.arange(0.1, 1, 0.1)
es.exp("randomExp", fake=False)
es.state("random")
gen = randomgen.RandomBiGen(noise=0.01,
brng=(100, 1000),
ntasks=1,
wu_sparcity=0.6,
wrng=(2, 3),
urng=(2, 3),
nusers=100,
nwords=400)
x, y = gen.generate(n=1000)
x = ssp.csc_matrix(vstack(x).T)
y = array(y)
fold = [f for f in tscv.tsfi(y.shape[0], ntest=100, ntraining=900)][0]
Xparts, Yparts = BatchBivariateLearner.XYparts(fold, x, y)
learner = BatchBivariateLearner(w_spams, u_spams, bivar_max_it=10)
learner.process(Yparts.train_all,
Xparts.train_all,
tests={"test": (Xparts.test, Yparts.test)})
print learner.w.todense()
print gen._w
print learner.u.todense()
print gen._u
print learner.w_bias
print learner.u_bias
print gen._bias
embed()
logger.info("Reading initial data")
home = os.environ['HOME']
data_home = "%s/Dropbox/Experiments/twitter_uk_users_MATLAB"%home
user_mat_file = "user_vsr_for_polls_day_%d_%d_t.mat"
word_mat_file = "user_vsr_for_polls_day_%d_%d.mat"
task_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/UK_data_for_experiment_PartII.mat"%home
tree_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/UK_data_for_experiment_PartI.mat"%home
voc_file = "%s/Dropbox/TrendMiner/Collaboration/EMNLP_2013/MATLAB_v2/voc_matching_v2.mat"%home
start = 81;ndays = 20;end = start + ndays
user_file = os.sep.join([data_home,user_mat_file%(start,end)])
word_file = os.sep.join([data_home,word_mat_file%(start,end)])
folds = tscv.tsfi(ndays,ntest=2)
logger.info("Reading task data")
tasks = billdata.taskvals(task_file).mat(days=(start,end))
# tree = billdata.tree(tree_file).spamsobj()
logger.info("Reading vocabulary")
voc = billdata.voc(voc_file).voc()
user_col, word_col = billdata.suserdayword(
user_file,word_file,ndays
).mat(voc=voc)
user_col,word_col=billdata.subsample(user_col,word_subsample=0.001,user_subsample=0.001,ndays=ndays)
# At this point we've just loaded all the data
# Prepare the optimisation functions
u_lambdas = np.arange(0.1,1,0.1)
w_lambdas = np.arange(0.1,2,0.1)
w_spams = FistaFlat(**{
