Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jesterhazy merged 3 commits into from
Apr 30, 2019
Merged

Add document embedding support to Object2Vec algorithm #772

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
85f392f
Add document embedding support to Object2Vec algorithm
pnpnpn Apr 29, 2019
c20340e
Merge branch 'master' into o2v-doc-embedding-r3
jesterhazy Apr 30, 2019
d10fa95
Merge branch 'master' into o2v-doc-embedding-r3
jesterhazy Apr 30, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions src/sagemaker/amazon/object2vec.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
valid_superset = set(valid_super_list)

def validate(value):
if not isinstance(value, str):
return False

val_list = [s.strip() for s in value.split(',')]
return set(val_list).issubset(valid_superset)

return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
'A float in [1e-06, 1.0]', float)

negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
'One of "dense", "row_sparse"', str)

enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
'One of "hcnn", "bilstm", "pooled_embedding"', str)
enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
output_layer=None,
optimizer=None,
learning_rate=None,
negative_sampling_rate=None,
comparator_list=None,
tied_token_embedding_weight=None,
token_embedding_storage_type=None,
enc0_network=None,
enc1_network=None,
enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
output_layer(str): Optional. Type of output layer
optimizer(str): Optional. Type of optimizer for training
learning_rate(float): Optional. Learning rate for SGD training
negative_sampling_rate(int): Optional. Negative sampling rate
comparator_list(str): Optional. Customization of comparator operator
tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
token_embedding_storage_type(str): Optional. Type of token embedding storage
enc0_network(str): Optional. Network model of encoder "enc0"
enc1_network(str): Optional. Network model of encoder "enc1"
enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
self.output_layer = output_layer
self.optimizer = optimizer
self.learning_rate = learning_rate

self.negative_sampling_rate = negative_sampling_rate
self.comparator_list = comparator_list
self.tied_token_embedding_weight = tied_token_embedding_weight
self.token_embedding_storage_type = token_embedding_storage_type

self.enc0_network = enc0_network
self.enc1_network = enc1_network
self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down
4 changes: 4 additions & 0 deletions tests/integ/test_object2vec.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
enc0_vocab_size=45000,
enc_dim=16,
num_classes=3,
negative_sampling_rate=0,
comparator_list='hadamard,concat,abs_diff',
tied_token_embedding_weight=False,
token_embedding_storage_type='dense',
sagemaker_session=sagemaker_session)

record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down
15 changes: 13 additions & 2 deletions tests/unit/test_object2vec.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
output_layer='softmax',
optimizer='adam',
learning_rate=0.0001,
negative_sampling_rate=1,
comparator_list='hadamard, abs_diff',
tied_token_embedding_weight=True,
token_embedding_storage_type='row_sparse',
enc0_network='bilstm',
enc1_network='hcnn',
enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
('optimizer', 0),
('enc0_cnn_filter_width', 'string'),
('weight_decay', 'string'),
('learning_rate', 'string')
('learning_rate', 'string'),
('negative_sampling_rate', 'some_string'),
('comparator_list', 0),
('comparator_list', ['foobar']),
('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
('weight_decay', 200000),
('enc0_cnn_filter_width', 2000),
('learning_rate', 0),
('learning_rate', 2)
('learning_rate', 2),
('negative_sampling_rate', -1),
('comparator_list', 'hadamard,foobar'),
('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
with pytest.raises(ValueError):
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Add document embedding support to Object2Vec algorithm#772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jesterhazy
merged 3 commits into

from

Apr 30, 2019
 Merged


Add document embedding support to Object2Vec algorithm
#772
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


3 commits


Select commit
Hold shift + click to select a range
85f392f

Add document embedding support to Object2Vec algorithm


pnpnpn Apr 29, 2019
c20340e

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019
d10fa95

Merge branch 'master' into o2v-doc-embedding-r3


jesterhazy Apr 30, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


35 changes: 35 additions & 0 deletions
src/sagemaker/amazon/object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -21,6 +21,19 @@
from sagemaker.vpc_utils import VPC_CONFIG_DEFAULT


def _list_check_subset(valid_super_list):
 valid_superset = set(valid_super_list)

 def validate(value):
 if not isinstance(value, str):
 return False

 val_list = [s.strip() for s in value.split(',')]
 return set(val_list).issubset(valid_superset)

 return validate


class Object2Vec(AmazonAlgorithmEstimatorBase):

 repo_name = 'object2vec'
Expand DownExpand Up@@ -57,6 +70,14 @@ class Object2Vec(AmazonAlgorithmEstimatorBase):
 'One of "adagrad", "adam", "rmsprop", "sgd", "adadelta"', str)
 learning_rate = hp('learning_rate', (ge(1e-06), le(1.0)),
 'A float in [1e-06, 1.0]', float)

 negative_sampling_rate = hp('negative_sampling_rate', (ge(0), le(100)), 'An integer in [0, 100]', int)
 comparator_list = hp('comparator_list', _list_check_subset(["hadamard", "concat", "abs_diff"]),
 'Comma-separated of hadamard, concat, abs_diff. E.g. "hadamard,abs_diff"', str)
 tied_token_embedding_weight = hp('tied_token_embedding_weight', (), 'Either True or False', bool)
 token_embedding_storage_type = hp('token_embedding_storage_type', isin("dense", "row_sparse"),
 'One of "dense", "row_sparse"', str)

 enc0_network = hp('enc0_network', isin("hcnn", "bilstm", "pooled_embedding"),
 'One of "hcnn", "bilstm", "pooled_embedding"', str)
 enc1_network = hp('enc1_network', isin("hcnn", "bilstm", "pooled_embedding", "enc0"),
Expand DownExpand Up@@ -104,6 +125,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer=None,
 optimizer=None,
 learning_rate=None,
 negative_sampling_rate=None,
 comparator_list=None,
 tied_token_embedding_weight=None,
 token_embedding_storage_type=None,
 enc0_network=None,
 enc1_network=None,
 enc0_cnn_filter_width=None,
Expand DownExpand Up@@ -164,6 +189,10 @@ def __init__(self, role, train_instance_count, train_instance_type,
 output_layer(str): Optional. Type of output layer
 optimizer(str): Optional. Type of optimizer for training
 learning_rate(float): Optional. Learning rate for SGD training
 negative_sampling_rate(int): Optional. Negative sampling rate
 comparator_list(str): Optional. Customization of comparator operator
 tied_token_embedding_weight(bool): Optional. Tying of token embedding layer weight
 token_embedding_storage_type(str): Optional. Type of token embedding storage
 enc0_network(str): Optional. Network model of encoder "enc0"
 enc1_network(str): Optional. Network model of encoder "enc1"
 enc0_cnn_filter_width(int): Optional. CNN filter width
Expand DownExpand Up@@ -197,6 +226,12 @@ def __init__(self, role, train_instance_count, train_instance_type,
 self.output_layer = output_layer
 self.optimizer = optimizer
 self.learning_rate = learning_rate

 self.negative_sampling_rate = negative_sampling_rate
 self.comparator_list = comparator_list
 self.tied_token_embedding_weight = tied_token_embedding_weight
 self.token_embedding_storage_type = token_embedding_storage_type

 self.enc0_network = enc0_network
 self.enc1_network = enc1_network
 self.enc0_cnn_filter_width = enc0_cnn_filter_width
Expand Down

4 changes: 4 additions & 0 deletions
tests/integ/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -43,6 +43,10 @@ def test_object2vec(sagemaker_session):
 enc0_vocab_size=45000,
 enc_dim=16,
 num_classes=3,
 negative_sampling_rate=0,
 comparator_list='hadamard,concat,abs_diff',
 tied_token_embedding_weight=False,
 token_embedding_storage_type='dense',
 sagemaker_session=sagemaker_session)

 record_set = prepare_record_set_from_local_files(data_path, object2vec.data_location,
Expand Down

15 changes: 13 additions & 2 deletions
tests/unit/test_object2vec.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -111,6 +111,10 @@ def test_all_hyperparameters(sagemaker_session):
 output_layer='softmax',
 optimizer='adam',
 learning_rate=0.0001,
 negative_sampling_rate=1,
 comparator_list='hadamard, abs_diff',
 tied_token_embedding_weight=True,
 token_embedding_storage_type='row_sparse',
 enc0_network='bilstm',
 enc1_network='hcnn',
 enc0_cnn_filter_width=3,
Expand DownExpand Up@@ -161,7 +165,11 @@ def test_required_hyper_parameters_value(sagemaker_session, required_hyper_param
 ('optimizer', 0),
 ('enc0_cnn_filter_width', 'string'),
 ('weight_decay', 'string'),
 ('learning_rate', 'string')
 ('learning_rate', 'string'),
 ('negative_sampling_rate', 'some_string'),
 ('comparator_list', 0),
 ('comparator_list', ['foobar']),
 ('token_embedding_storage_type', 123),
])
def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand All@@ -182,7 +190,10 @@ def test_optional_hyper_parameters_type(sagemaker_session, optional_hyper_parame
 ('weight_decay', 200000),
 ('enc0_cnn_filter_width', 2000),
 ('learning_rate', 0),
 ('learning_rate', 2)
 ('learning_rate', 2),
 ('negative_sampling_rate', -1),
 ('comparator_list', 'hadamard,foobar'),
 ('token_embedding_storage_type', 'foobar'),
])
def test_optional_hyper_parameters_value(sagemaker_session, optional_hyper_parameters, value):
 with pytest.raises(ValueError):
Expand Down