def trainBDT(self, targetSample):
originDF = self.getTrainDataFrame()
targetDF = targetSample.getTrainDataFrame()
if self.observables.keys() != targetSample.observables.keys():
print 'Error observables for target and origin data sets do not match. Exiting...'
print 'Origin:', self.observables.keys()
print 'Target:', targetSample.observables.keys()
exit(-1)
originPreWeights = originDF["preweight"]
targetPreWeights = targetDF["preweight"]
originDF = originDF[self.observables.keys()]
targetDF = targetDF[targetSample.observables.keys()]
reweighter = GBReweighter(n_estimators=200,
learning_rate=.1,
max_depth=3,
min_samples_leaf=1000,
loss_regularization=1.0)
reweighter.fit(original=originDF,
target=targetDF,
original_weight=originPreWeights,
target_weight=targetPreWeights)
with open(self.gbrwPath(), "wb") as f:
pickle.dump(reweighter, f)
def train_reweighter():
extra_vars = [
gcm().ltime_var
]
all_vars = gcm().phsp_vars + extra_vars
columns = [v.var for v in all_vars if 'phi' not in v.var]
columns += ['cosphi', 'sinphi']
# Current mode stuff
data = gcm().get_data([f.var for f in extra_vars])
add_variables.append_phsp(data)
data['cosphi'] = np.cos(data.phi1)
data['sinphi'] = np.sin(data.phi1)
df_sel = final_selection.get_final_selection()
df_sel &= selection.delta_mass_signal_region()
gen = get_model()
gen['cosphi'] = np.cos(gen.phi1)
gen['sinphi'] = np.sin(gen.phi1)
limits = {v.var: v.binning[1:] for v in all_vars}
limits['cosphi'] = (-1., 1)
limits['sinphi'] = (-1., 1)
for c in columns:
mi, ma = limits[c]
data[c] = (data[c] - mi) / (ma - mi) + 2.
gen[c] = (gen[c] - mi) / (ma - mi) + 2.
log.info('Training BDT reweighter for {}'.format(', '.join(columns)))
reweighter = GBReweighter(n_estimators=300, max_depth=5, learning_rate=0.2)
reweighter.fit(original=gen[columns].sample(n=250000),
target=data[columns][df_sel].sample(n=250000))
bdt_utils.dump_reweighter(reweighter)
def gbreweight(weighttree, originaltree, name, variables, n=None):
'''Use Hep_ml GBReweighter to calculate weights for weighttree to match originaltree in the given variables.
Adds a friend with branch named 'name' of length 2: the first element is the calculated weight, the second is
the product of that weight with any existing weight used for the weighttree (from the selection).'''
from hep_ml.reweight import GBReweighter
originalweights, originalvals = get_weights_and_vals(
originaltree, variables, n)
weightedweights, weightedvals = get_weights_and_vals(
weighttree, variables, n)
weighter = GBReweighter()
print('Fit GBReweighter', name)
weighter.fit(original=originalvals,
original_weight=originalweights,
target=weightedvals,
target_weight=weightedweights)
weight = weighttree.selection_functor()
vals = weighttree.get_functor_list(variables)
def get_weight():
_w = weighter.predict_weights([vals()])[0]
return [_w, _w * weight()]
print('Add weights for GBReweighter', name)
weighttree.add_friend_tree(name,
{name: dict(function=get_weight, length=2)})
reweighterEst20 = GBReweighter(n_estimators=20,
#learning_rate=params['learning_rate'],
max_depth=5,
#min_samples_leaf=params['min_samples_leaf'],
#loss_regularization=params['loss_regularization']
)
reweighterEst40 = GBReweighter(n_estimators=40,
#learning_rate=params['learning_rate'],
max_depth=5,
#min_samples_leaf=params['min_samples_leaf'],
#loss_regularization=params['loss_regularization']
)
log.info(f"Fitting weights...")
reweighterEst10.fit(original = np.array([data_train['pho_eta'][trainMask & (data_train["label"] < 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] < 0.5)]]).T,
target = np.array([data_train['pho_eta'][trainMask & (data_train["label"] >= 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] >= 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] >= 0.5)]]).T)
reweighterEst20.fit(original = np.array([data_train['pho_eta'][trainMask & (data_train["label"] < 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] < 0.5)]]).T,
target = np.array([data_train['pho_eta'][trainMask & (data_train["label"] >= 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] >= 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] >= 0.5)]]).T)
reweighterEst40.fit(original = np.array([data_train['pho_eta'][trainMask & (data_train["label"] < 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] < 0.5)]]).T,
target = np.array([data_train['pho_eta'][trainMask & (data_train["label"] >= 0.5)],
data_train['pho_et'][trainMask & (data_train["label"] >= 0.5)],
data_train['correctedScaledActualMu'][trainMask & (data_train["label"] >= 0.5)]]).T)
log.info(f"Fitting of weights is done (time: {timedelta(seconds=time() - t)})")
signal_reweight_data = reweight_data_small.where(reweight_data['Signal'] == 1)
signal_reweight_data_s_dropped = signal_reweight_data.drop(['Signal'], axis=1)
signal_reweight_data_nan_s_dropped = signal_reweight_data_s_dropped.dropna(
axis=0)
background_reweight_data = reweight_data_small.where(
reweight_data['Signal'] == 0)
background_reweight_data_s_dropped = background_reweight_data.drop(['Signal'],
axis=1)
background_reweight_data_nan_s_dropped = background_reweight_data_s_dropped.dropna(
axis=0)
ratio = len(signal_reweight_data_nan_s_dropped) / len(
background_reweight_data_nan_s_dropped)
reweighter = GBReweighter(n_estimators=40)
reweighter.fit(background_reweight_data_nan_s_dropped,
signal_reweight_data_nan_s_dropped)
weights = reweighter.predict_weights(background_reweight_data_nan_s_dropped)
print(weights)
total_weights = ratio * weights / np.mean(weights)
#reweighted_background = background_reweight_data.multiply(weights, axis=0)
fig_weight, ax_weight = plt.subplots(3, 2, figsize=(15, 15))
ax_weight[0, 0].hist(signal_reweight_data_nan_s_dropped.p_et_calo.ravel(),
bins=50,
range=(0, 100000),
color='r',
alpha=0.5,
label="Signal")
pre_separation.fit(subtrain[reweight_feats],
subtrain[['isE']],
sample_weight=subtrain.weight)
test_proba = pre_separation.predict_proba(subtest[reweight_feats])[:, 1]
roc_pre = roc_curve(subtest[['isE']],
test_proba,
sample_weight=subtest.weight)[:2]
auc_pre = roc_auc_score(subtest[['isE']],
test_proba,
sample_weight=subtest.weight)
#run reweighting -- not working on MC for some reason
reweighter = GBReweighter(n_estimators=1 if debug else 30,
max_depth=4,
learning_rate=0.1)
reweighter.fit(subtrain[subtrain.isE == 1][reweight_feats], subtrain[
subtrain.isE == 0][reweight_feats]) #make electrons look like tracks
#run weights FOR EVERYTHING!
for df in [data, subtrain, subtest]:
weights = reweighter.predict_weights(
df[df.isE == 1][reweight_feats]) #1/w to be used
df.loc[df.isE == 1, 'weight'] = weights
#save reweighter
joblib.dump(reweighter, reweight_model_file, compress=True)
# Check that sepratation vanishes
post_separation = GradientBoostingClassifier(
n_estimators=1 if debug else 50,
max_depth=4,
random_state=42,
str_to_parent_folder=str(Path(__file__).resolve().parent.parent)
tree = uproot.open(str_to_parent_folder+"/forward_MC/user.lehrke.mc16_13TeV.361106.Zee.EGAM8.e3601_e5984_s3126_r10724_r10726_p3648.ePID18_NTUP3_v01_myOutput.root/user.lehrke.17118381._000003.myOutput.root")[b'tree;1']
reweight_data = tree.pandas.df(["averageInteractionsPerCrossing","p_et_calo","p_eta","p_TruthType"])
reweight_data_small = reweight_data.sample(frac=1,replace=False, random_state=42)
p_TruthType_reweight_data = reweight_data_small.where(reweight_data_small['p_TruthType'] == 2)
p_TruthType_reweight_data_s_dropped = p_TruthType_reweight_data.drop(['p_TruthType'], axis=1)
p_TruthType_reweight_data_nan_s_dropped = p_TruthType_reweight_data_s_dropped.dropna(axis=0)
background_reweight_data = reweight_data_small.where(reweight_data['p_TruthType'] !=2)
background_reweight_data_s_dropped = background_reweight_data.drop(['p_TruthType'], axis=1)
background_reweight_data_nan_s_dropped =background_reweight_data_s_dropped.dropna(axis=0)
ratio=len(p_TruthType_reweight_data_nan_s_dropped)/len(background_reweight_data_nan_s_dropped)
reweighter = GBReweighter(n_estimators=40)
reweighter.fit(background_reweight_data_nan_s_dropped, p_TruthType_reweight_data_nan_s_dropped)
weights = reweighter.predict_weights(background_reweight_data_nan_s_dropped)
print(weights)
total_weights=ratio*weights /np.mean(weights)
np.savetxt('../weights/weights_MC_03.csv', total_weights, delimiter=',')
#reweighted_background = background_reweight_data.multiply(weights, axis=0)
""" fig_weight, ax_weight = plt.subplots(3,2, figsize=(15,15))
ax_weight[0,0].hist(p_TruthType_reweight_data_nan_s_dropped.p_et_calo.ravel(),bins=50,range=(0,100000), color = 'r', alpha = 0.5, label = "p_TruthType")
ax_weight[0,0].hist(background_reweight_data_nan_s_dropped.p_et_calo.ravel(), bins=50,range=(0,100000), color = 'blue', alpha = 0.5, label = "Background")
ax_weight[0,0].legend(loc="upper right")
ax_weight[0,0].set_title('P_et_calo (before weight)')
n_estimators=17,
#learning_rate=params['learning_rate'],
max_depth=5,
#min_samples_leaf=params['min_samples_leaf'],
#loss_regularization=params['loss_regularization']
)
# Create weight estimators and fit them to the data
log.info(f"Fitting weights...")
reweighterEst10.fit(
original=np.array([
data_train['muo_eta'][trainMask & (data_train["label"] < 0.5)],
data_train['muo_pt'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledAverageMu'][trainMask
& (data_train["label"] < 0.5)]
]).T,
target=np.array([
data_train['muo_eta'][trainMask & (data_train["label"] >= 0.5)],
data_train['muo_pt'][trainMask & (data_train["label"] >= 0.5)],
data_train['correctedScaledAverageMu'][trainMask
& (data_train["label"] >= 0.5)]
]).T)
reweighterEst20.fit(
original=np.array([
data_train['muo_eta'][trainMask & (data_train["label"] < 0.5)],
data_train['muo_pt'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledAverageMu'][trainMask
& (data_train["label"] < 0.5)]
]).T,
target=np.array([
data_train['muo_eta'][trainMask & (data_train["label"] >= 0.5)],
# Read the decay times from the LHCb simulation - I've serialised it here
print("reading pickle")
with open("mc_times.pickle", "rb") as f:
mc_times = pickle.load(f)
# Generate some random numbers from an exponential distribution with the right decay constant
d_lifetime_ps = 0.49
N = len(mc_times)
print("gen times")
exp_times = np.random.exponential(d_lifetime_ps, N)
mc_train, mc_test, model_train, model_test = train_test_split(
mc_times, exp_times)
bdt = GBReweighter()
print("Training bdt")
bdt.fit(original=model_train, target=mc_train)
weights = bdt.predict_weights(model_test)
kw = {"bins": np.linspace(0.0, 9.0, 100), "alpha": 0.3, "density": True}
plt.figure(figsize=(12.0, 9.0))
plt.hist(mc_test, label="Original", **kw)
plt.hist(model_test, label="Target", **kw)
plt.hist(model_test, label="Target Weighted", weights=weights, **kw)
plt.legend()
plt.xlabel("Time /ps")
plt.ylabel("Counts")
plt.savefig("mwe.png")
print "Performing train-test split"
original_train, original_test = train_test_split(original)
else:
original_train = original
original_test = original
original_weight_distribution_train = original_train[original_weights] if original_weights != None else None
target_weight_distribution = target[target_weights] if target_weights != None else None
#Start the training
gb = GBReweighter(**gb_settings)
print( "Doing training of GBReweighter..." )
print( "Re-weighting variables: {}".format(reweighting_branches) )
begin = time.time()
gb_output = gb.fit(original_train[reweighting_branches], target[reweighting_branches],
original_weight = original_weight_distribution_train, target_weight = target_weight_distribution)
print( "Settings: {}".format(gb_output) )
print( "Training of GBReweighter took {:.2f} seconds".format(time.time()-begin) )
#Save the classifier as pickle if applicable
if options.Save:
ensure_dir(options.Save)
with open(options.Save, 'wb') as handle:
pickle_file = {"GBReweighter" : gb, "Branches" : reweighting_branches}
pickle.dump(pickle_file, handle)
print( "GBReweighter saved to {}".format(options.Save) )
axis=1)
# CREATING SAMPLE WEIGHTS # (https://arogozhnikov.github.io/hep_ml/reweight.html)
res_cols = list(tm_revenue.reset_index().columns)
resampling_b = datab[['Segment Knicks'] + res_cols]
resampling_h = datah[['Segment Rangers'] + res_cols]
sampleb = resampling_b.dropna(subset=['Segment Knicks']).drop(
['Segment Knicks'], axis=1).set_index('email')
fullb = resampling_b[pd.isnull(resampling_b['Segment Knicks'])].drop(
['Segment Knicks'], axis=1).set_index('email')
sampleh = resampling_h.dropna(subset=['Segment Rangers']).drop(
['Segment Rangers'], axis=1).set_index('email')
fullh = resampling_h[pd.isnull(resampling_h['Segment Rangers'])].drop(
['Segment Rangers'], axis=1).set_index('email')
reweighter = GBReweighter()
sampleb['weight'] = reweighter.fit(
original=sampleb, target=fullb).predict_weights(sampleb).round(3)
sampleh['weight'] = reweighter.fit(
original=sampleh, target=fullh).predict_weights(sampleh).round(3)
# LOGIT MODELING #
modeling_bball = pd.merge(data[data['vspt'] == 'basketball'],
sampleb['weight'].reset_index(),
on='email').drop(
['vspt', 'Sample', 'email', 'Segment Rangers'],
axis=1).set_index('uid')
modeling_hockey = pd.merge(data[data['vspt'] == 'hockey'],
sampleh['weight'].reset_index(),
on='email').drop(
['vspt', 'Sample', 'email', 'Segment Knicks'],
axis=1).set_index('uid')
n_estimators=params['n_estimators'],
learning_rate=params['learning_rate'],
max_depth=params['max_depth'],
min_samples_leaf=params['min_samples_leaf'],
loss_regularization=params['loss_regularization'])
# Create weight estimators and fit them to the data
log.info(f"Fitting weights...")
reweighter.fit(
original=np.array([
data_train['eta'][trainMask & (data_train["label"] < 0.5)],
data_train['pt'][trainMask & (data_train["label"] < 0.5)],
data_train['invM'][trainMask & (data_train["label"] < 0.5)],
data_train['correctedScaledActualMu'][
trainMask & (data_train["label"] < 0.5)]
]).T,
target=np.array([
data_train['eta'][trainMask & (data_train["label"] >= 0.5)],
data_train['pt'][trainMask & (data_train["label"] >= 0.5)],
data_train['invM'][trainMask & (data_train["label"] >= 0.5)],
data_train['correctedScaledActualMu'][
trainMask & (data_train["label"] >= 0.5)]
]).T)
log.info(
f"Fitting of weights is done (time: {timedelta(seconds=time() - t)})"
)
# Get weights
log.info(f"Get weights for training, validation and test set")
weight_train = getRegularWeights("train", reweighter,
data_train[trainMask])
