def compute_top_n_tokens_for_each_doc(top_n, first_id, last_id):
models.connect_to_db(conf.DATABASE_FILENAME)
cleaner = Cleaner()
top_n_tokens_per_paper = {}
for i in range(first_id, last_id + 1, increments):
papers_to_process = ids_to_query(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers_NR.select().where(
models.Papers.id == paper_id)
if DEBUG:
print(paper_query)
print(len(paper_query))
if len(paper_query) > 0:
paper_content = paper_query[0].paper_text
pdf_name = paper_query[0].paper_name
tokens = cleaner.tokenize(paper_content)
token_frequencies = {}
for token in tokens:
if token not in token_frequencies:
token_frequencies[token] = 1
else:
token_frequencies[token] = token_frequencies[token] + 1
sorted_tokens = [(k, token_frequencies[k]) for k in sorted(
token_frequencies, key=token_frequencies.get, reverse=True)
]
top_n_tokens_per_paper[pdf_name] = sorted_tokens[:top_n]
models.close_connection()
printer = Printer()
printer.print_dict(top_n_tokens_per_paper)
def insert_title_column_to_nr_nsw_table():
models.connect_to_db(DATABASE_FILENAME)
last_id_query = models.Papers_NR.select().order_by(models.Papers_NR.id.desc()).limit(1)
first_id = 1
last_id = last_id_query[0].id
last_id = 100
increments = 50
for i in range(first_id, last_id + 1, increments):
papers_to_process = create_list_of_ids(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers_NR.select().where(models.Papers_NR.id == paper_id)
if len(paper_query) > 0:
paper_pdf_name = paper_query[0].pdf_name
title = paper_pdf_name.split(".pdf")[0]
print("Title before replace: {0}".format(title))
title = title.replace("-", " ")
print("Title after replace: {0}".format(title))
new_entry = models.Papers_NR_NSW.create(id=paper_id,
pdf_name=paper_pdf_name,
paper_text=cleaned_content)
new_entry.save()
counter += increments
print("Number of documents cleaned: {0}".format(counter))
print("Sleeping for one second ...")
time.sleep(1)
models.close_connection()
def clean_papers_from_db():
models.connect_to_db(DATABASE_FILENAME)
last_id_query = models.Papers.select().order_by(
models.Papers.id.desc()).limit(1)
first_id = 1
last_id = last_id_query[0].id
increments = 10
for i in range(first_id, last_id + 1, increments):
papers_to_process = create_list_of_ids(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers.select().where(
models.Papers.id == paper_id)
print(paper_query)
print(len(paper_query))
if (len(paper_query) > 0):
paper_content = paper_query[0].paper_text
paper_pdf_name = paper_query[0].pdf_name
print("Removing reference section from paper id: {0}".format(
paper_id))
new_content = remove_reference_section(paper_content)
print("Saving new paper_text into papers_for_index")
new_entry = models.Papers_NR.create(id=paper_id,
pdf_name=paper_pdf_name,
paper_text=new_content)
print("Number of rows modified: {0}".format(new_entry.save()))
print("Sleeping for one second ...")
time.sleep(1)
models.close_connection()
def save_cleaned_files(input_directory):
filenames = io.list_files_in_dir(input_directory)
models.connect_to_db(conf.DATABASE_FILENAME)
for filename in filenames:
print("Saving {} into DB".format(filename))
paper_id = extract_id_from_filename(filename)
paper_pdf_name = create_pdf_filename(filename)
file_path = conf.IRREGULAR_PAPERS_DIRECTORY + "/" + filename
paper_content = io.load_file_rows(file_path)
new_entry = models.Papers_NR.create(id=paper_id,
pdf_name=paper_pdf_name,
paper_text=paper_content)
print("Number of rows modified: {0}".format(new_entry.save()))
models.close_connection()
def clean_papers():
models.connect_to_db(conf.DATABASE_FILENAME)
last_id_query = models.Papers_NR.select().order_by(
models.Papers_NR.id.desc()).limit(1)
first_id = 1
last_id = last_id_query[0].id
increments = 50
paper_cleaner = text_cleaner.Cleaner()
counter = 0
for i in range(first_id, last_id + 1, increments):
papers_to_process = create_list_of_ids(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers_NR.select().where(
models.Papers_NR.id == paper_id)
if len(paper_query) > 0:
paper_content = paper_query[0].paper_text
paper_pdf_name = paper_query[0].pdf_name
title = paper_pdf_name.split(".pdf")[0]
title = title.replace("-", " ")
#print("Cleaning content for paper id: {0}".format(paper_id))
rows_to_clean = paper_content.split("\n")
cleaned_content = ""
cleaner = text_cleaner.Cleaner()
for row in rows_to_clean:
cleaned_row = cleaner.clean_text(row)
if len(cleaned_row) > 0:
cleaned_content += cleaned_row + "\n"
#print("Saving new paper_text into papers_NR_NSW")
new_entry = models.Papers_NR_NSW.create(
id=paper_id,
pdf_name=paper_pdf_name,
paper_text=cleaned_content,
paper_title=title)
new_entry.save()
#print("Number of rows modified: {0}".format(new_entry.save()))
counter += increments
print("Number of documents cleaned: {0}".format(counter))
print("Sleeping for one second ...")
time.sleep(1)
models.close_connection()
def add_data(text):
paper_text = text
#new_paper_text = stemming(paper_text)
models.connect_to_db(conf.DATABASE_FILENAME)
last_id_query = models.Papers_NR_NSW_STE.select().order_by(
models.Papers_NR_NSW_STE.id.desc()).limit(1)
first_id = 1
last_id = last_id_query[0].id
increments = 10
for i in range(first_id, last_id + 1, increments):
papers_to_process = create_list_of_ids(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers_NR_NSW_STE.select().where(
models.Papers_NR_NSW_STE.id == paper_id)
paper_pdf_name = paper_query[0].pdf_name
# is update the statement to use?
new_entry = models.Papers_NR_NSW.update(id=paper_id,
pdf_name=paper_pdf_name,
paper_text=new_paper_text)
print("Number of rows modified: {0}".format(new_entry.save()))
models.close_connection()
def compute_document_frequencies():
models.connect_to_db(conf.DATABASE_FILENAME)
first_id = 1
last_id_query = papers.select().order_by(papers.id.desc()).limit(1)
last_id = last_id_query[0].id
increments = 10
token_frequencies = {}
for i in range(first_id, last_id + 1, increments):
papers_to_process = ids_to_query(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = papers.select().where(papers.id == paper_id)
unique_tokens = set()
if DEBUG:
print(paper_query)
print(len(paper_query))
if len(paper_query) > 0:
paper_content = paper_query[0].paper_text
paper_pdf_name = paper_query[0].pdf_name
tokens = paper_content.strip().split()
for token in tokens:
#print(token)
unique_tokens.add(token.lower())
for i, token in enumerate(unique_tokens):
#print(token)
if token not in token_frequencies:
token_frequencies[token] = 1
else:
token_frequencies[token] = token_frequencies[token] + 1
models.close_connection()
sorted_tokens = [(k, token_frequencies[k]) for k in sorted(token_frequencies, key=token_frequencies.get)]
printer = Printer()
printer.print_token_frequency(sorted_tokens)
def compute_top_n_tokens_for_collection(top_n):
models.connect_to_db(conf.DATABASE_FILENAME)
first_id = 1
last_id_query = models.Papers_NR.select().order_by(
models.Papers_NR.id.desc()).limit(1)
last_id = last_id_query[0].id
increments = 10
cleaner = Cleaner()
token_frequencies = {}
for i in range(first_id, last_id + 1, increments):
papers_to_process = ids_to_query(i, increments, last_id)
for paper_id in papers_to_process:
paper_query = models.Papers.select().where(
models.Papers.id == paper_id)
if DEBUG:
print(paper_query)
print(len(paper_query))
if len(paper_query) > 0:
paper_content = paper_query[0].paper_text
paper_pdf_name = paper_query[0].pdf_name
tokens = cleaner.tokenize(paper_content)
for token in tokens:
if token not in token_frequencies:
token_frequencies[token] = 1
else:
token_frequencies[token] = token_frequencies[token] + 1
models.close_connection()
sorted_tokens = [(k, token_frequencies[k]) for k in sorted(
token_frequencies, key=token_frequencies.get, reverse=True)]
top_n_tokens = sorted_tokens[:top_n]
printer = Printer()
printer.print_token_frequency(top_n_tokens)
def retrieve_papers():
io.create_directory(conf.IRREGULAR_PAPERS_DIRECTORY)
models.connect_to_db(conf.DATABASE_FILENAME)
# retrieve papers with reference not separated
query = models.Papers.select().where(
models.Papers.id.in_(conf.ids_reference_not_separated))
for paper in query:
filename = create_paper_newname(conf.IRREGULAR_PAPERS_DIRECTORY,
paper.pdf_name)
content = paper.paper_text
io.save_file(content, filename)
# retrieve papers with poorly defined reference section
query = models.Papers.select().where(
models.Papers.id.in_(conf.ids_poorly_defined_reference))
for paper in query:
filename = create_paper_newname(conf.IRREGULAR_PAPERS_DIRECTORY,
paper.pdf_name)
content = paper.paper_text
io.save_file(content, filename)
models.close_connection()
def drop_papers_nr_nsw_table():
models.connect_to_db(conf.DATABASE_FILENAME)
models.Papers_NR_NSW_STE.drop_table()
models.close_connection()
def drop_papers_nr_table():
models.connect_to_db(DATABASE_FILENAME)
models.Papers_NR.drop_table()
models.close_connection()