def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
exh.create_directory(DIRECTORY)
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
display.display_ok("Loading publications done")
n = CONFIG['NGRAMS']
subsets_dida = []
subsets_notdida = []
covers = []
for i in range(1, n+1):
print("Starting analysis for {0}-grams".format(i))
# Process on DIDA class
subset, set_cover = process_ngrams(i, dida_data, "dida")
subsets_dida.extend(subset)
covers.extend(set_cover)
# Process on Not-DIDA class
subset, set_cover = process_ngrams(i, notdida_data, "notdida")
subsets_notdida.extend(subset)
covers.extend(set_cover)
display.display_ok("Analysis for {0}-grams done".format(i))
print("Searching set cover with all grams for DIDA")
set_cover = get_set_cover(subsets_dida)
scores = check_score(set_cover, subsets_dida, subsets_dida, dida_data)
exh.write_text(scores, SCORE_FILENAME.format("dida", "all"))
display.display_ok("Done")
print("Searching set cover with all grams for NotDIDA")
set_cover = get_set_cover(subsets_notdida)
scores = check_score(set_cover, subsets_notdida, subsets_notdida, notdida_data)
exh.write_text(scores, SCORE_FILENAME.format("notdida", "all"))
display.display_ok("Done")
save_topwords(covers)
display.display_info("All results were saved in {0} directory".format(DIRECTORY))
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
exh.create_directory(DIRECTORY)
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(
FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
display.display_ok("Loading publications done")
n = CONFIG['NGRAMS']
for i in range(1, n + 1):
print("Starting analysis for {0}-grams".format(i))
print("Couting occurrences for DIDA")
dida_occurrences = ngh.count_occurrences(i, dida_data)
dida_normalized = ngh.normalize_occurrences(dida_occurrences,
len(dida_data))
display.display_ok("Counting occurrences for DIDA done")
print("Couting occurrences for NotDIDA")
notdida_occurrences = ngh.count_occurrences(i, notdida_data)
notdida_normalized = ngh.normalize_occurrences(notdida_occurrences,
len(notdida_data))
display.display_ok("Counting occurrences for NotDIDA done")
# Merge n-grams in the same list
merged = merge_ngrams(dida_normalized, notdida_normalized)
# Order n-grams by difference
merged = ordered(merged, score)
# Save results
save_to_file(merged, i)
display.display_ok("Analysis for {0}-grams done".format(i))
def read_file(filename, extension):
"""Returns publications based on a text file containing PMIDs or a JSON file
containing publications
Parameters
----------
filename : str
The name of the file to read
extension : str
The extension of the file
Returns
-------
list
a list of publications at JSON format
"""
if extension == "txt":
print("Received a text file - Reading PMIDs list")
# Read each PMID in the file
f = open(filename)
lines = f.readlines()
pmids = []
for line in lines:
pmids.append(line.replace('\n', ''))
f.close()
# Downloads and returns publications
print("Downloading publications")
return pbmdh.download_publications(pmids)
elif extension == "json":
print("Received a JSON file - Getting publications")
return exh.load_json(filename)
def run(dida_pmids):
"""Executes the main process of the script
Parameters
----------
dida_pmids : str
The file name of the file containing the PMIDs in DIDA
"""
global CONFIG
# Load configuration
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
# Get DIDA PMIDs
known_pmids = get_dida_pmids(dida_pmids)
# Get Not-DIDA PMIDs
pmids = get_pmids_by_dates()
notdida_pmids = filter(pmids, known_pmids)
display.display_info("Total PMIDs between {0} and {1} : {2}".format(
CONFIG['START_YEAR'], CONFIG['SPLIT_YEAR'], len(pmids)))
display.display_info("Total PMIDs in DIDA : {0}".format(len(known_pmids)))
display.display_info("Total PMIDs in Not-DIDA : {0}".format(
len(notdida_pmids)))
# Download Not-DIDA publications
download_doc(notdida_pmids)
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
exh.create_directory(DIRECTORY)
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(
FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
display.display_ok("Loading publications done")
n = CONFIG['NGRAMS']
for i in range(1, n + 1):
extract_ngrams(i, deepcopy(dida_data), deepcopy(notdida_data))
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
exh.create_directory(DIRECTORY)
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
# docs = [deepcopy(dida_data), deepcopy(notdida_data)]
docs = [deepcopy(notdida_data), deepcopy(dida_data)]
display.display_ok("Loading publications done")
print("Starting extraction of words information")
extract_words_information(docs)
display.display_ok("Extraction of words information done")
print("Computing joint probability distribution")
joint_probability_distribution()
display.display_ok("Computing joint probability distribution done")
print("Starting IB method")
all_clusters = ib.cluster(deepcopy(Pcw), deepcopy(Pw))
display.display_ok("IB method finished")
save_clusters(all_clusters)
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
# Extension of the input file
extension = args.FILE.split('.')[-1]
if extension in LEGAL_EXTENSIONS:
exh.create_directory(DIRECTORY)
# Get publications
print("Getting publications")
documents_l = read_file(args.FILE, extension)
display.display_ok("Getting publications done")
# Save publications
filename = BACK_FILENAME.format(args.OUTPUT)
exh.write_json(documents_l, filename)
display.display_info("Publications saved in {0}".format(filename))
# Insert PubTator annotations in the abstracts
print("Inserting PubTator annotations in abstracts")
docs = pbmdh.extract_features(documents_l)
display.display_ok("Inserting PubTator annotations in abstracts done")
# Extract n-grams
print("Extracting n-grams")
ngh.extract_ngrams(docs, CONFIG['NGRAMS'])
display.display_ok("Extracting n-grams done")
# Save publications and their n-grams
filename = NGRAMS_FILENAME.format(args.OUTPUT)
exh.write_json(docs, filename)
display.display_info("Publications and n-grams saved in {0}".format(filename))
else:
# The input file has not a valid extension
display.display_fail("Extension of input file not supported. Required : txt or json. Received : {0}".format(extension))
sys.exit(0)
* download_publications - downloads publications based on a PMIDs list
* extract_features - inserts PubTator annotations inside the publications abstracts
* get_pmids - gets a PMIDs list based on a particular query
"""
import json
import urllib.request as req
import xml.etree.ElementTree as ET
from copy import deepcopy
from nltk.stem import PorterStemmer
from string import punctuation
import explorer_helper as exh
STOPWORDS = exh.load_json("config/stopwords.json")['stopwords']
URL_DOWNLOAD = "https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/RESTful/tmTool.cgi/BioConcept/{0}/JSON/"
URL_PMIDS = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term={0}&retmax={1}"
def clean_text(text, stopwords=STOPWORDS):
"""Lowerizes and stems publications abstracts
Parameters
----------
text : str
The abstract to lowerize and stem
stopwords: list
A list of stopwords
Returns
-------
def classification(docs, Ndw, W, directory, true_predictions):
strict_result = {
"n_clusters": [],
"tn": [],
"fp": [],
"fn": [],
"tp": [],
"score": []
}
doublon_result = {
"n_clusters": [],
"tn": [],
"fp": [],
"fn": [],
"tp": [],
"score": []
}
print("Documents replacement")
converted_docs = converter.init(deepcopy(docs), deepcopy(W))
display.display_ok("Documents replacement done")
clusters_directory = directory + "/clusters"
max_clusters = len(W)
print("Evaluating classifier")
a = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
a.extend(range(100, 8500, 100))
a.extend([8417])
for n_clusters in a: #range(1, max_clusters+1,100):
print("Processing for {0} clusters (Total : {1})".format(
n_clusters, max_clusters))
# Load clusters
clusters = exh.load_json(clusters_directory +
"/{0}.json".format(n_clusters))
# Prepare classifier
classifier = NaiveBayesCluster(deepcopy(clusters), deepcopy(Ndw),
deepcopy(W))
print("Classifier ready")
print("Converting documents")
strict_converted_docs = converter.convert_all(deepcopy(converted_docs),
deepcopy(clusters))
doublon_converted_docs = converter.convert_all(
deepcopy(converted_docs), deepcopy(clusters), method='d')
print("Converting documents done")
print("Evaluate Strict Predictions")
strict_predictions = classifier.evaluate(strict_converted_docs)
print("Evaluate Doublon Predictions")
doublon_predictions = classifier.evaluate(doublon_converted_docs)
print("Predictions done")
print("Perform scores")
strict_score = classifier.score(true_predictions, strict_predictions)
doublon_score = classifier.score(true_predictions, doublon_predictions)
print("Scores performed : ({0}, {1})".format(strict_score,
doublon_score))
add_result(n_clusters, strict_score, strict_result)
add_result(n_clusters, doublon_score, doublon_result)
display.display_ok("Evaluating classifier done")
return strict_result, doublon_result
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(
FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
# docs = [deepcopy(notdida_data), deepcopy(dida_data)]
docs = [deepcopy(dida_data), deepcopy(notdida_data)]
display.display_ok("Loading publications done")
data_directory = DIRECTORY + '/' + CONFIG['ALL_CLUSTERS_DIRECTORY']
Ndw = exh.load_json(data_directory + "/ndw.json")
W = exh.load_json(data_directory + "/W.json")
# Real labels of each publication
# y_true = np.append(np.zeros(len(notdida_data)), np.ones(len(dida_data)))
y_true = np.append(np.ones(len(dida_data)), np.zeros(len(notdida_data)))
strict_result, doublon_result = classification(docs, Ndw, W,
data_directory, y_true)
plt.plot_confusion_matrix(strict_result,
len(dida_data),
len(notdida_data),
"strict_",
"n_clusters",
"Number of clusters",
DIRECTORY,
step=1000)
exh.save_to_log(strict_result, "strict", "n_clusters",
LOG_FILENAME.format("strict"))
plt.plot_confusion_matrix(doublon_result,
len(dida_data),
len(notdida_data),
"doublon_",
"n_clusters",
"Number of clusters",
DIRECTORY,
step=1000)
exh.save_to_log(doublon_result, "doublon", "n_clusters",
LOG_FILENAME.format("doublon"))
scores = [strict_result['score'], doublon_result['score']]
classifiers_names = ["Strict converter", "Doublon converter"]
plt.plot_lines(strict_result['n_clusters'],
scores,
classifiers_names,
FSCORE_FILENAME,
"Number of clusters",
"F1-score",
step=1000)
def run(args):
"""Executes the main process of the script
Parameters
----------
args : ArgumentParser
The arguments of the command typed by the user
"""
global CONFIG
CONFIG = exh.load_json("config/{0}.json".format(args.CONFIG))
exh.create_directory(DIRECTORY)
print("Loading publications")
# Load DIDA publications
dida_data = exh.load_json(FILENAME_TEMPLATE.format(CONFIG['DIDA_DOCS']))
# Load Not-DIDA publications
notdida_data = exh.load_json(
FILENAME_TEMPLATE.format(CONFIG['NOTDIDA_DOCS']))
display.display_ok("Loading publications done")
n = CONFIG['NGRAMS']
csv_files = csv_filenames(n)
# Real labels of each publication
y_true = np.append(np.ones(len(dida_data)), np.zeros(len(notdida_data)))
data = deepcopy(dida_data)
data.extend(deepcopy(notdida_data))
scores = []
classifiers_names = []
print("Strict Classifier training")
results = train(StrictClassifier, deepcopy(data), csv_files, y_true)
plt.plot_confusion_matrix(results, len(dida_data), len(notdida_data),
'strict_', "threshold", "Threshold", DIRECTORY)
scores.append(results['score'])
exh.save_to_log(results, "strict", "threshold",
LOG_FILENAME.format("strict"))
classifiers_names.append("Strict Classifier")
display.display_ok("Strict Classifier training done")
print("Split Weighted Classifier training")
results = train(SplitWeightedClassifier, deepcopy(data), csv_files, y_true)
plt.plot_confusion_matrix(results, len(dida_data), len(notdida_data),
'splitweighted_', "threshold", "Threshold",
DIRECTORY)
scores.append(results['score'])
exh.save_to_log(results, "splitweighted", "threshold",
LOG_FILENAME.format("splitweighted"))
classifiers_names.append("Split Weighted Classifier")
display.display_ok("Split Weighted Classifier training done")
print("Weighted Classifier training")
results = train(WeightedClassifier, deepcopy(data), csv_files, y_true)
plt.plot_confusion_matrix(results, len(dida_data), len(notdida_data),
'weighted_', "threshold", "Threshold", DIRECTORY)
scores.append(results['score'])
exh.save_to_log(results, "weighted", "threshold",
LOG_FILENAME.format("weighted"))
classifiers_names.append("Weighted Classifier")
display.display_ok("Weighted Classifier training done")
plt.plot_lines(results['threshold'], scores, classifiers_names,
FSCORE_FILENAME, "Threshold", "F1-score")
display.display_info("Results saved in {0}".format(DIRECTORY))
