def dcToDf(dc_file, df_out):
dc = DataCollection()
dc.readFromFile(dc_file)
NENT = 1 # Can skip some events
filelist = []
i = 0
storeInputs = True
count = 0
feature_names = dc.dataclass.branches[1]
spectator_names = dc.dataclass.branches[0]
labels_names = dc.getUsedTruth()
labels_names = ['truth' + l for l in labels_names]
for s in dc.samples:
if count > 1000000: break
spath = dc.getSamplePath(s)
filelist.append(spath)
h5File = h5py.File(spath)
f = h5File
features_val_i = [
h5File['x%i' % j][()]
for j in range(0, h5File['x_listlength'][()][0])
]
features_val_i = features_val_i[0][::NENT, 0, :]
#predict_test_i = model.predict(features_val)
weights_val_i = h5File['w0'][()]
labels_val_i = h5File['y0'][()][::NENT, :]
spectators_val_i = h5File['z0'][()][::NENT, 0, :]
if storeInputs: raw_features_val_i = h5File['z1'][()][::NENT, 0, :]
if i == 0:
#predict_test = predict_test_i
weights_val = weights_val_i
labels_val = labels_val_i
spectators_val = spectators_val_i
features_val = features_val_i
if storeInputs: raw_features_val = raw_features_val_i
else:
#predict_test = np.concatenate((predict_test,predict_test_i))
weights_val = np.concatenate((weights_val, weights_val_i))
labels_val = np.concatenate((labels_val, labels_val_i))
features_val = np.concatenate((features_val, features_val_i))
spectators_val = np.concatenate((spectators_val, spectators_val_i))
if storeInputs:
raw_features_val = np.concatenate(
(raw_features_val, raw_features_val_i))
i += 1
count += labels_val.shape[0]
entries = np.hstack((raw_features_val, spectators_val, labels_val,
weights_val.reshape((len(weights_val), 1))))
df = pd.DataFrame(entries,
columns=feature_names + spectator_names + labels_names +
['weight'])
#df = pd.DataFrame(raw_features_val+spectators_val , columns = feature_names+spectator_names)
#print df
if df_out != None:
df.to_pickle(df_out)
print "Saved df to", df_out
def evaluate(testd, trainData, model, outputDir, storeInputs=False, adv=False):
NENT = 1 # Can skip some events
filelist = []
i = 0
for s in testd.samples:
#for s in testd.samples[0:1]:
spath = testd.getSamplePath(s)
filelist.append(spath)
h5File = h5py.File(spath)
f = h5File
#features_val = [h5File['x%i_shape'%j][()] for j in range(0, h5File['x_listlength'][()][0])]
features_val = [
h5File['x%i' % j][()]
for j in range(0, h5File['x_listlength'][()][0])
]
#features_val=testd.getAllFeatures()
predict_test_i = model.predict(features_val)
labels_val_i = h5File['y0'][()][::NENT, :]
spectators_val_i = h5File['z0'][()][::NENT, 0, :]
if storeInputs: raw_features_val_i = h5File['z1'][()][::NENT, 0, :]
if i == 0:
predict_test = predict_test_i
labels_val = labels_val_i
spectators_val = spectators_val_i
if storeInputs: raw_features_val = raw_features_val_i
else:
predict_test = np.concatenate((predict_test, predict_test_i))
labels_val = np.concatenate((labels_val, labels_val_i))
spectators_val = np.concatenate((spectators_val, spectators_val_i))
if storeInputs:
raw_features_val = np.concatenate(
(raw_features_val, raw_features_val_i))
i += 1
# Value
#labels_val=testd.getAllLabels()[0][::NENT,:]
#features_val=testd.getAllFeatures()[0][::NENT,0,:]
#spectators_val = testd.getAllSpectators()[0][::NENT,0,:]
#if storeInputs: raw_features_val = testd.getAllSpectators()[-1][::NENT,0,:]
# Labels
print testd.dataclass.branches
feature_names = testd.dataclass.branches[1]
spectator_names = testd.dataclass.branches[0]
#truthnames = testd.getUsedTruth()
from DeepJetCore.DataCollection import DataCollection
traind = DataCollection()
traind.readFromFile(trainData)
truthnames = traind.getUsedTruth()
# Store features
print "Coulmns", spectator_names
df = pd.DataFrame(spectators_val, columns=spectator_names)
if storeInputs:
for i, tname in enumerate(feature_names):
df[tname] = raw_features_val[:, i]
# Add predictions
print truthnames
print predict_test.shape
for i, tname in enumerate(truthnames):
df['truth' + tname] = labels_val[:, i]
#print "Mean 0th label predict predict of ", tname, np.mean(predict_test[:,0]), ", Stats:", np.sum(labels_val[:,i]), "/", len(labels_val[:,i])
if adv:
df['predict' + tname] = predict_test[:, NBINS + i]
for j in range(NBINS):
df['predict_massbin%i' % j] = predict_test[:, j + i]
else:
df['predict' + tname] = predict_test[:, i]
print "Testing prediction:"
print "Total: ", len(predict_test[:, 0])
for lab in truthnames:
print lab, ":", sum(df['truth' + lab].values)
df.to_pickle(outputDir +
'/output.pkl') #to save the dataframe, df to 123.pkl
return df
print "Finished storing dataframe"
def evaluate(testd, trainData, model, outputDir):
NENT = 1 # Can skip some events
filelist = []
i = 0
for s in testd.samples:
spath = testd.getSamplePath(s)
filelist.append(spath)
h5File = h5py.File(spath)
f = h5File
#features_val = [h5File['x%i_shape'%j][()] for j in range(0, h5File['x_listlength'][()][0])]
features_val = [
h5File['x%i' % j][()]
for j in range(0, h5File['x_listlength'][()][0])
]
#features_val=testd.getAllFeatures()
predict_test_i = model.predict(features_val)
if i == 0:
predict_test = predict_test_i
else:
predict_test = np.concatenate((predict_test, predict_test_i))
i += 1
# Value
labels_val = testd.getAllLabels()[0][::NENT, :]
features_val = testd.getAllFeatures()[0][::NENT, 0, :]
spectators_val = testd.getAllSpectators()[0][::NENT, 0, :]
raw_features_val = testd.getAllSpectators()[-1][::NENT, 0, :]
# Labels
print testd.dataclass.branches
feature_names = testd.dataclass.branches[1]
spectator_names = testd.dataclass.branches[0]
#truthnames = testd.getUsedTruth()
from DeepJetCore.DataCollection import DataCollection
traind = DataCollection()
traind.readFromFile(trainData)
truthnames = traind.getUsedTruth()
# Store features
df = pd.DataFrame(spectators_val)
df.columns = [spectator_names]
for i, tname in enumerate(feature_names):
df[tname] = raw_features_val[:, i]
# Add predictions
print truthnames
print predict_test.shape
for i, tname in enumerate(truthnames):
df['truth' + tname] = labels_val[:, i]
df['predict' + tname] = predict_test[:, i]
df.to_pickle(outputDir +
'/output.pkl') #to save the dataframe, df to 123.pkl
print df
dt = pd.read_pickle(outputDir + '/output.pkl')
print dt
def dists(xdf, truthnames):
truths = truthnames
print truths
def distribution(xdf, predict="Hcc"):
plt.figure(figsize=(10, 7))
bins = np.linspace(0, 1, 70)
trus = []
for tru in truths:
trus.append(xdf['truth' + tru].values)
preds = [xdf['predict' + predict].values] * len(truths)
plt.hist(preds,
bins=bins,
weights=trus,
alpha=0.8,
normed=True,
label=truths,
stacked=True)
plt.xlabel("Probability " + predict)
plt.title("Stacked Distributions")
plt.semilogy()
plt.legend(title="True labels:")
plt.savefig(outputDir + '/dist' + predict + '.png', dpi=300)
for pred in truths:
distribution(xdf, predict=pred)
dists(df, truthnames)
print "Testing prediction:"
print "Total: ", len(predict_test[:, 0])
for lab in truthnames:
print lab, ":", sum(df['truth' + lab].values)
print "Finished"