def api_get_project_info(project_id): # noqa: F401 """Get info on the article""" logging.info("get project info") try: # read the file with project info with open(get_project_file_path(project_id), "r") as fp: project_info = json.load(fp) # check if there is a dataset try: get_data_file_path(project_id) project_info["projectHasDataset"] = True except Exception: project_info["projectHasDataset"] = False # check if there is a prior knowledge (check if there is a model set), # if this is the case, the reviewer past the prior knowledge screen. project_info["projectHasPriorKnowledge"] = \ get_kwargs_path(project_id).exists() # check if there is a prior knowledge (check if there is a model set), # if this is the case, the reviewer past the prior knowledge screen. project_info["projectHasAlgorithms"] = \ get_kwargs_path(project_id).exists() # backwards support <0.10 if "projectInitReady" not in project_info: if project_info["projectHasPriorKnowledge"]: project_info["projectInitReady"] = True else: project_info["projectInitReady"] = False response = jsonify(project_info) except FileNotFoundError as err: logging.error(err) response = jsonify(message="Project not found.") return response, 400 except Exception as err: logging.error(err) response = jsonify(message="Internal Server Error.") return response, 500 return response
def remove_dataset_to_project(project_id, file_name): """Remove dataset from project """ project_file_path = get_project_file_path(project_id) fp_lock = get_lock_path(project_id) with SQLiteLock(fp_lock, blocking=True, lock_name="active", project_id=project_id): # open the projects file with open(project_file_path, "r") as f_read: project_dict = json.load(f_read) # remove the path from the project file data_fn = project_dict["dataset_path"] del project_dict["dataset_path"] with open(project_file_path, "w") as f_write: json.dump(project_dict, f_write) # files to remove data_path = get_data_file_path(project_id, data_fn) pool_path = get_pool_path(project_id) labeled_path = get_labeled_path(project_id) os.remove(str(data_path)) os.remove(str(pool_path)) os.remove(str(labeled_path))
def read_data(project_id, use_cache=True, save_cache=True): """Get ASReviewData object from file. Parameters ---------- project_id: str, iterable The project identifier. use_cache: bool Use the pickle file if available. save_cache: bool Save the file to a pickle file if not available. Returns ------- ASReviewData: The data object for internal use in ASReview. """ # use cache file if use_cache: try: return _read_data_from_cache(project_id) except CacheDataError: pass # load from file fp_data = get_data_file_path(project_id) data_obj = ASReviewData.from_file(fp_data) # save a pickle version if save_cache: _write_data_to_cache(project_id, data_obj) return data_obj
def api_get_project_data(project_id): # noqa: F401 """Get info on the article""" if not is_project(project_id): response = jsonify(message="Project not found.") return response, 404 try: filename = get_data_file_path(project_id).stem # get statistics of the dataset statistics = get_data_statistics(project_id) statistics["filename"] = filename except FileNotFoundError as err: print(err) statistics = {"filename": None} except Exception as err: print(err) message = f"Failed to get file. {err}" return jsonify(message=message), 400 response = jsonify(statistics) response.headers.add('Access-Control-Allow-Origin', '*') return response
def api_get_project_info(project_id): # noqa: F401 """Get info on the article""" try: # read the file with project info with open(get_project_file_path(project_id), "r") as fp: project_info = json.load(fp) # check if there is a dataset try: get_data_file_path(project_id) project_info["projectHasDataset"] = True except Exception: project_info["projectHasDataset"] = False # check if there is a prior knowledge (check if there is a model set), # if this is the case, the reviewer past the prior knowledge screen. project_info["projectHasPriorKnowledge"] = \ get_kwargs_path(project_id).exists() # check if there is a prior knowledge (check if there is a model set), # if this is the case, the reviewer past the prior knowledge screen. project_info["projectHasAlgorithms"] = \ get_kwargs_path(project_id).exists() # backwards support <0.10 if "projectInitReady" not in project_info: if project_info["projectHasPriorKnowledge"]: project_info["projectInitReady"] = True else: project_info["projectInitReady"] = False except FileNotFoundError: raise ProjectNotFoundError() return jsonify(project_info)
def read_data(project_id, save_tmp=True): """Get ASReviewData object from file. Parameters ---------- project_id: str, iterable The project identifier. save_tmp: bool Save the file to a pickle file if not available. Returns ------- ASReviewData: The data object for internal use in ASReview. """ fp_data = get_data_file_path(project_id) fp_data_pickle = Path(fp_data).with_suffix(fp_data.suffix + ".pickle") try: # get the pickle data with open(fp_data_pickle, 'rb') as f_pickle_read: data_obj = pickle.load(f_pickle_read) return data_obj except FileNotFoundError: # file not available data_obj = ASReviewData.from_file(fp_data) except pickle.PickleError: # problem loading pickle file # remove the pickle file os.remove(fp_data_pickle) data_obj = ASReviewData.from_file(fp_data) # save a pickle version if save_tmp: logging.info("Store a copy of the data in a pickle file.") with open(fp_data_pickle, 'wb') as f_pickle: pickle.dump(data_obj, f_pickle) return data_obj
def read_data(project_id): """Get ASReviewData object of the dataset""" dataset = get_data_file_path(project_id) return ASReviewData.from_file(dataset)
def _get_cache_data_path(project_id): fp_data = get_data_file_path(project_id) return get_data_file_path(project_id) \ .with_suffix(fp_data.suffix + ".pickle")
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)