def api_get_prior(project_id): # noqa: F401
"""Get all papers classified as prior documents
"""
lock_fp = get_lock_path(project_id)
with SQLiteLock(lock_fp, blocking=True, lock_name="active"):
label_history = read_label_history(project_id)
indices = [x[0] for x in label_history]
records = read_data(project_id).record(indices)
payload = {"result": []}
for i, record in enumerate(records):
payload["result"].append({
"id": int(record.record_id),
"title": record.title,
"abstract": record.abstract,
"authors": record.authors,
"keywords": record.keywords,
"included": int(label_history[i][1])
})
response = jsonify(payload)
response.headers.add('Access-Control-Allow-Origin', '*')
return response
def api_get_prior(project_id): # noqa: F401
"""Get all papers classified as prior documents
"""
subset = request.args.get('subset', default=None, type=str)
# check if the subset exists
if subset is not None and subset not in ["included", "excluded"]:
message = "Unkown subset parameter"
return jsonify(message=message), 400
lock_fp = get_lock_path(project_id)
with SQLiteLock(lock_fp, blocking=True, lock_name="active"):
label_history = read_label_history(project_id, subset=subset)
indices = [x[0] for x in label_history]
records = read_data(project_id).record(indices)
payload = {"result": []}
for i, record in enumerate(records):
payload["result"].append({
"id": int(record.record_id),
"title": record.title,
"abstract": record.abstract,
"authors": record.authors,
"keywords": record.keywords,
"included": int(label_history[i][1])
})
response = jsonify(payload)
response.headers.add('Access-Control-Allow-Origin', '*')
return response
def search_data(project_id, q, n_max=100):
"""Get the title/authors/abstract for a paper."""
# read the dataset
as_data = read_data(project_id)
# search for the keywords
paper_ids = as_data.fuzzy_find(q, max_return=n_max, exclude=[])
# return full information on the records
return as_data.record(paper_ids)
def get_data_statistics(project_id):
"""Get the title/authors/abstract for a paper."""
# read the dataset
as_data = read_data(project_id)
result = {
"n_rows": as_data.df.shape[0],
"n_cols": as_data.df.shape[1],
}
# return full information on the records
return result
def api_random_prior_papers(project_id): # noqa: F401
"""Get a selection of random papers to find exclusions.
This set of papers is extracted from the pool, but without
the already labeled items.
"""
lock_fp = get_lock_path(project_id)
with SQLiteLock(lock_fp,
blocking=True,
lock_name="active",
project_id=project_id):
pool = read_pool(project_id)
# with open(get_labeled_path(project_id, 0), "r") as f_label:
# prior_labeled = json.load(f_label)
# excluded the already labeled items from our random selection.
# prior_labeled_index = [int(label) for label in prior_labeled.keys()]
# pool = [i for i in pool if i not in prior_labeled_index]
# sample from the pool (this is already done atm of initializing
# the pool. But doing it again because a double shuffle is always
# best)
try:
pool_random = np.random.choice(pool, 1, replace=False)[0]
except Exception:
raise ValueError("Not enough random indices to sample from.")
try:
record = read_data(project_id).record(pool_random, by_index=False)
payload = {"result": []}
payload["result"].append({
"id": int(record.record_id),
"title": record.title,
"abstract": record.abstract,
"authors": record.authors,
"keywords": record.keywords,
"included": None
})
except Exception as err:
logging.error(err)
return jsonify(message="Failed to load random documents."), 500
response = jsonify(payload)
response.headers.add('Access-Control-Allow-Origin', '*')
return response
def train_model(project_id, label_method=None):
"""Add the new labels to the review and do the modeling.
It uses a lock to ensure only one model is running at the same time.
Old results directories are deleted after 4 iterations.
It has one argument on the CLI, which is the base project directory.
"""
logging.info(f"Project {project_id} - Train a new model for project")
# get file locations
asr_kwargs_file = get_kwargs_path(project_id)
lock_file = get_lock_path(project_id)
# Lock so that only one training run is running at the same time.
# It doesn't lock the flask server/client.
with SQLiteLock(lock_file,
blocking=False,
lock_name="training",
project_id=project_id) as lock:
# If the lock is not acquired, another training instance is running.
if not lock.locked():
logging.info("Project {project_id} - "
"Cannot acquire lock, other instance running.")
return
# Lock the current state. We want to have a consistent active state.
# This does communicate with the flask backend; it prevents writing and
# reading to the same files at the same time.
with SQLiteLock(lock_file,
blocking=True,
lock_name="active",
project_id=project_id) as lock:
# Get the all labels since last run. If no new labels, quit.
new_label_history = read_label_history(project_id)
data_fp = str(get_data_file_path(project_id))
as_data = read_data(project_id)
state_file = get_state_path(project_id)
# collect command line arguments and pass them to the reviewer
with open(asr_kwargs_file, "r") as fp:
asr_kwargs = json.load(fp)
asr_kwargs['state_file'] = str(state_file)
reviewer = get_reviewer(dataset=data_fp, mode="minimal", **asr_kwargs)
with open_state(state_file) as state:
old_label_history = get_label_train_history(state)
diff_history = get_diff_history(new_label_history, old_label_history)
if len(diff_history) == 0:
logging.info(
"Project {project_id} - No new labels since last run.")
return
query_idx = np.array([x[0] for x in diff_history], dtype=int)
inclusions = np.array([x[1] for x in diff_history], dtype=int)
# Classify the new labels, train and store the results.
with open_state(state_file) as state:
reviewer.classify(query_idx,
inclusions,
state,
method=label_method)
reviewer.train()
reviewer.log_probabilities(state)
new_query_idx = reviewer.query(reviewer.n_pool()).tolist()
reviewer.log_current_query(state)
proba = state.pred_proba.tolist()
with SQLiteLock(lock_file,
blocking=True,
lock_name="active",
project_id=project_id) as lock:
current_pool = read_pool(project_id)
in_current_pool = np.zeros(len(as_data))
in_current_pool[current_pool] = 1
new_pool = [x for x in new_query_idx if in_current_pool[x]]
write_pool(project_id, new_pool)
write_proba(project_id, proba)
def train_model(project_id, label_method=None):
"""Add the new labels to the review and do the modeling.
It uses a lock to ensure only one model is running at the same time.
Old results directories are deleted after 4 iterations.
It has one argument on the CLI, which is the base project directory.
"""
logging.info(f"Project {project_id} - Train a new model for project")
# get file locations
asr_kwargs_file = get_kwargs_path(project_id)
lock_file = get_lock_path(project_id)
# Lock so that only one training run is running at the same time.
# It doesn't lock the flask server/client.
with SQLiteLock(
lock_file, blocking=False, lock_name="training",
project_id=project_id) as lock:
# If the lock is not acquired, another training instance is running.
if not lock.locked():
logging.info("Project {project_id} - "
"Cannot acquire lock, other instance running.")
return
# Lock the current state. We want to have a consistent active state.
# This does communicate with the flask backend; it prevents writing and
# reading to the same files at the same time.
with SQLiteLock(
lock_file,
blocking=True,
lock_name="active",
project_id=project_id) as lock:
# Get the all labels since last run. If no new labels, quit.
new_label_history = read_label_history(project_id)
data_fp = str(get_data_file_path(project_id))
as_data = read_data(project_id)
state_file = get_state_path(project_id)
# collect command line arguments and pass them to the reviewer
with open(asr_kwargs_file, "r") as fp:
asr_kwargs = json.load(fp)
try:
del asr_kwargs["abstract_only"]
except KeyError:
pass
asr_kwargs['state_file'] = str(state_file)
reviewer = get_reviewer(dataset=data_fp, mode="minimal", **asr_kwargs)
with open_state(state_file) as state:
old_label_history = _get_label_train_history(state)
diff_history = _get_diff_history(new_label_history, old_label_history)
if len(diff_history) == 0:
logging.info(
"Project {project_id} - No new labels since last run.")
return
query_record_ids = np.array([x[0] for x in diff_history], dtype=int)
inclusions = np.array([x[1] for x in diff_history], dtype=int)
query_idx = convert_id_to_idx(as_data, query_record_ids)
# Classify the new labels, train and store the results.
with open_state(state_file) as state:
reviewer.classify(
query_idx, inclusions, state, method=label_method)
reviewer.train()
reviewer.log_probabilities(state)
new_query_idx = reviewer.query(reviewer.n_pool()).tolist()
reviewer.log_current_query(state)
# write the proba to a pandas dataframe with record_ids as index
proba = pd.DataFrame(
{"proba": state.pred_proba.tolist()},
index=pd.Index(as_data.record_ids, name="record_id")
)
# update the pool and output the proba's
# important: pool is sorted on query
with SQLiteLock(
lock_file,
blocking=True,
lock_name="active",
project_id=project_id) as lock:
# read the pool
current_pool = read_pool(project_id)
# diff pool and new_query_ind
current_pool_idx = convert_id_to_idx(as_data, current_pool)
current_pool_idx = frozenset(current_pool_idx)
new_pool_idx = [x for x in new_query_idx if x in current_pool_idx]
# convert new_pool_idx back to record_ids
new_pool = convert_idx_to_id(as_data, new_pool_idx)
# write the pool and proba
write_pool(project_id, new_pool)
write_proba(project_id, proba)
