def train(X, Y, valX=None, valY=None, testX=None, testY=None):
feats = formatFeatures(X, Y)
trainer = pycrfsuite.Trainer(verbose=False)
for xseq, yseq in pycrfInstances(feats, labeled=True):
trainer.append(xseq, yseq)
os_handle, tmp_file = tempfile.mkstemp(dir=tmp_dir, suffix="crf_temp")
trainer.train(tmp_file)
model = ''
with open(tmp_file, 'rb') as f:
model = f.read()
os.close(os_handle)
os.remove(tmp_file)
scores = {}
train_pred = predict(model, X)
train_stats = compute_performance_stats('train', train_pred, Y)
scores['train'] = train_stats
if valX:
val_pred = predict(model, valX)
val_stats = compute_performance_stats('dev', val_pred, valY)
scores['dev'] = val_stats
if testX:
test_pred = predict(model, testX)
test_stats = compute_performance_stats('test', test_pred, testY)
scores['test'] = test_stats
scores['hyperparams'] = {}
enabled_mods = enabledModules()
for module, enabled in enabled_mods.items():
e = bool(enabled)
scores['hyperparams'][module] = e
return model, scores
def train(X, Y, val_X=None, val_Y=None, test_X=None, test_Y=None):
'''
train()
Train a Conditional Random Field for sequence tagging.
@param X. List of sparse-matrix sequences. Each sequence is one sentence.
@param Y. List of sequence tags. Each sequence is the sentence's per-token tags.
@param val_X. More X data, but a heldout dev set.
@param val_Y. More Y data, but a heldout dev set.
@return A tuple of encoded parameter weights and hyperparameters for predicting.
'''
# Sanity Check detection: features & label
#with open('a','w') as f:
# for xline,yline in zip(X,Y):
# for x,y in zip(xline,yline):
# print >>f, y, '\t', x.nonzero()[1][0]
# print >>f
# Format features fot crfsuite
feats = format_features(X, Y)
# Create a Trainer object.
trainer = pycrfsuite.Trainer(verbose=False)
for xseq, yseq in pycrf_instances(feats, labeled=True):
trainer.append(xseq, yseq)
# Train the model
os_handle, tmp_file = tempfile.mkstemp(dir='/tmp', suffix="crf_temp")
trainer.train(tmp_file)
# Read the trained model into a string (so it can be pickled)
model = ''
with open(tmp_file, 'rb') as f:
model = f.read()
os.close(os_handle)
# Remove the temporary file
os.remove(tmp_file)
######################################################################
# information about fitting the model
scores = {}
# how well does the model fir the training data?
train_pred = predict(model, X)
train_stats = compute_performance_stats('train', train_pred, Y)
scores['train'] = train_stats
if val_X:
val_pred = predict(model, val_X)
val_stats = compute_performance_stats('dev', val_pred, val_Y)
scores['dev'] = val_stats
if test_X:
test_pred = predict(model, test_X)
test_stats = compute_performance_stats('test', test_pred, test_Y)
scores['test'] = test_stats
# keep track of which external modules were used for building this model!
scores['hyperparams'] = {}
enabled_mods = enabled_modules()
for module, enabled in enabled_mods.items():
e = bool(enabled)
scores['hyperparams'][module] = e
return model, scores
def train(X, Y, val_X=None, val_Y=None, test_X=None, test_Y=None):
'''
train()
Train a Conditional Random Field for sequence tagging.
@param X. List of sparse-matrix sequences. Each sequence is one sentence.
@param Y. List of sequence tags. Each sequence is the sentence's per-token tags.
@param val_X. More X data, but a heldout dev set.
@param val_Y. More Y data, but a heldout dev set.
@return A tuple of encoded parameter weights and hyperparameters for predicting.
'''
# Sanity Check detection: features & label
#with open('a','w') as f:
# for xline,yline in zip(X,Y):
# for x,y in zip(xline,yline):
# print >>f, y, '\t', x.nonzero()[1][0]
# print >>f
# Format features fot crfsuite
feats = format_features(X,Y)
# print(feats)# [... ,'' ,t12193=1\t12199=1', ...]
# Create a Trainer object.
trainer = pycrfsuite.Trainer(verbose=False)
trainer.select(algorithm= 'pa') # algorithm:{‘lbfgs’, ‘l2sgd’, ‘ap’, ‘pa’, ‘arow’}
# print(trainer.params()) # ['feature.minfreq', 'feature.possible_states', 'feature.possible_transitions', 'c1', 'c2', 'max_iterations', 'num_memories', 'epsilon', 'period', 'delta', 'linesearch', 'max_linesearch']
# print(trainer.get_params())
'''
{'feature.minfreq': 0.0, 'feature.possible_states': False, 'feature.possible_transitions': False, 'type': 1, 'c': 1.0, 'error_sensitive': True, 'averaging': True, 'max_iterations': 100,
'epsilon': 0.0}
'''
for xseq, yseq in pycrf_instances(feats, labeled=True):
trainer.append(xseq, yseq)
# Train the model
os_handle,tmp_file = tempfile.mkstemp(dir=tmp_dir, suffix="crf_temp") #how is tmp_file created?
#tmp_dir = cliner_dir/data/tmp #
trainer.train(tmp_file)# save temporary file to C:\Users\Anak\PycharmProjects\CliNER\data\tmp\tmp02nmns01crf_temp
# print(trainer.logparser.last_iteration)
#{'num': 54, 'scores': {}, 'loss': 49.276289, 'feature_norm': 5.78118, 'error_norm': 0.041626, 'active_features': 16870, 'linesearch_trials': 1, 'linesearch_step': 1.0, 'time': 0.003}
# Read the trained model into a string (so it can be pickled)
model = ''
with open(tmp_file, 'rb') as f:
model = f.read()
os.close(os_handle)
# print(model) # b'x01\x00\x00\x00\xd1D\x00\x00\x01\x00\x00\x00\xd2D\x00\x00\x01\x00\x00\x00\xd3D\x00
# print(X)
'''
[<2x12206 sparse matrix of type '<class 'numpy.float64'>'
with 70 stored elements in Compressed Sparse Row format>, <9x12206 sparse matrix of type '<class 'numpy.float64'>'
'''
# Remove the temporary file
os.remove(tmp_file)
######################################################################
# information about fitting the model
scores = {}
# how well does the model fit the training data?
train_pred = predict(model, X) # ANAK
train_stats = compute_performance_stats('train', train_pred, Y)
scores['train'] = train_stats
if val_X:
val_pred = predict(model, val_X)
val_stats = compute_performance_stats('dev', val_pred, val_Y)
scores['dev'] = val_stats
if test_X:
test_pred = predict(model, test_X)
test_stats = compute_performance_stats('test', test_pred, test_Y)
scores['test'] = test_stats
# keep track of which external modules were used for building this model!
scores['hyperparams'] = {}
enabled_mods = enabled_modules()
for module,enabled in enabled_mods.items():
e = bool(enabled)
scores['hyperparams'][module] = e
# print(len(scores)) # 3
return model, scores
def train(X, Y, val_X=None, val_Y=None):
'''
train()
Train a Conditional Random Field for sequence tagging.
@param X. List of sparse-matrix sequences. Each sequence is one sentence.
@param Y. List of sequence tags. Each sequence is the sentence's per-token tags.
@param val_X. More X data, but a heldout dev set.
@param val_Y. More Y data, but a heldout dev set.
@return A tuple of encoded parameter weights and hyperparameters for predicting.
'''
# Sanity Check detection: features & label
#with open('a','w') as f:
# for xline,yline in zip(X,Y):
# for x,y in zip(xline,yline):
# print >>f, y, '\t', x.nonzero()[1][0]
# print >>f
# Format features fot crfsuite
feats = format_features(X,Y)
# Create a Trainer object.
trainer = pycrfsuite.Trainer(verbose=False)
for xseq, yseq in pycrf_instances(feats, labeled=True):
trainer.append(xseq, yseq)
# Train the model
os_handle,tmp_file = tempfile.mkstemp(dir='/tmp', suffix="crf_temp")
trainer.train(tmp_file)
# Read the trained model into a string (so it can be pickled)
model = ''
with open(tmp_file, 'r') as f:
model = f.read()
os.close(os_handle)
# Remove the temporary file
os.remove(tmp_file)
######################################################################
# information about fitting the model
scores = {}
# how well does the model fir the training data?
train_pred = predict(model, X)
train_stats = compute_performance_stats('train', train_pred, Y)
scores['train'] = train_stats
if val_X:
val_pred = predict(model, val_X)
val_stats = compute_performance_stats('dev', val_pred, val_Y)
scores['dev'] = val_stats
# keep track of which external modules were used for building this model!
scores['hyperparams'] = {}
enabled_mods = enabled_modules()
for module,enabled in enabled_mods.items():
e = bool(enabled)
scores['hyperparams'][module] = e
return model, scores