def get_author_details():
if request.method == 'GET':
author_id = request.args.get('author_id')
doc_num = request.args.get('doc_num')
if author_id is None and doc_num is None:
return render_template('data_visualize/select_author.html',
title='Select an author',
content=u'Select an author in the following list and the system will display the '
u'details of that author you selected',
authors_list=data_warehouse.get_all_author_id_and_name()
)
if request.method == 'POST':
try:
author_id = int(request.form['author_id'])
doc_num = data_warehouse.get_num_of_doc_written_by_an_author(author_id)
except ValueError:
abort(403)
try:
author_id = int(author_id)
doc_num = int(doc_num)
except ValueError:
abort(403)
author_name = data_warehouse.get_author_name_by_id(author_id)
return render_template('data_visualize/author_details.html',
title=author_name,
content=Markup(u'You are now looking at <strong>{}</strong>. There are <strong>{}</strong> '
u'of documents written by {} stored in our database.'
.format(author_name, doc_num, author_name)),
doc_list=data_warehouse.get_all_docs_by_author_id(author_id)
)
def get_author_details():
if request.method == 'GET':
author_id = request.args.get('author_id')
doc_num = request.args.get('doc_num')
if author_id is None and doc_num is None:
return render_template('data_visualize/select_author.html',
title='Select an author',
content=u'Select an author in the following list and the system will display the '
u'details of that author you selected',
authors_list=data_warehouse.get_all_author_id_and_name()
)
if request.method == 'POST':
try:
author_id = int(request.form['author_id'])
doc_num = data_warehouse.get_num_of_doc_written_by_an_author(author_id)
except ValueError:
abort(403)
try:
author_id = int(author_id)
doc_num = int(doc_num)
except ValueError:
abort(403)
author_name = data_warehouse.get_author_name_by_id(author_id)
return render_template('data_visualize/author_details.html',
title=author_name,
content=Markup(u'You are now looking at <strong>{}</strong>. There are <strong>{}</strong> '
u'of documents written by {} stored in our database.'
.format(author_name, doc_num, author_name)),
doc_list=data_warehouse.get_all_docs_by_author_id(author_id)
)
def get_knn_statics():
if request.method != 'POST':
abort(403)
results = []
prefix_path = '/var/tmp/stylometric_app/knn_upload/'
f = request.files['file']
path = os.path.join(prefix_path, secure_filename(f.filename))
f.save(path)
if not os.path.exists(path):
abort(403)
qp = plaintext_data_etl.read_file_and_get_doc_list(path)
author_hash = dict([(row['author_id'], row['author_name']) for row in data_warehouse.get_all_author_id_and_name()])
try:
authors = session['authors']
feature_list, author_list = data_warehouse.get_features_from_database_fact_by_list_of_author_id(authors)
except KeyError:
feature_list, author_list = data_warehouse.get_all_features_from_database_fact()
knn_proba = cknn.get_query_set_probabilistic(feature_list, author_list, qp)
authors = list(set(author_list))
for idx in range(len(set(authors))):
results.append((author_hash.get(authors[idx]), knn_proba[idx]))
session.clear()
return jsonify(dict(results))
def get_knn_statics():
if request.method != 'POST':
abort(403)
results = []
prefix_path = '/var/tmp/stylometric_app/knn_upload/'
f = request.files['file']
path = os.path.join(prefix_path, secure_filename(f.filename))
f.save(path)
if not os.path.exists(path):
abort(403)
qp = plaintext_data_etl.read_file_and_get_doc_list(path)
author_hash = dict([(row['author_id'], row['author_name']) for row in data_warehouse.get_all_author_id_and_name()])
try:
authors = session['authors']
feature_list, author_list = data_warehouse.get_features_from_database_fact_by_list_of_author_id(authors)
except KeyError:
feature_list, author_list = data_warehouse.get_all_features_from_database_fact()
knn_proba = cknn.get_query_set_probabilistic(feature_list, author_list, qp)
authors = list(set(author_list))
for idx in range(len(set(authors))):
results.append((author_hash.get(authors[idx]), knn_proba[idx]))
session.clear()
return jsonify(dict(results))
def get_chars():
return render_template('data_visualize/charts.html',
title='Stylometric Charts',
content=Markup(u'In this page, you can compare the writing styles of <strong>at most 3 '
u'documents</strong> in terms of stylometric features. Firstly, you need to '
u'select an author from the drop-down list. Afterwards, another drop-down '
u'list is shown for you to select the document. Finally, click the button '
u'<mark>Add to Table</mark> to add the document into the cache. You will '
u'need to repeat the steps until there are at least 2 documents.'),
authors_list=data_warehouse.get_all_author_id_and_name()
)
def upload_file():
return render_template('data_visualize/upload.html',
title='KNN Authorship Determination',
content=Markup(u'In this page, you may upload a txt file to the server. The '
u'application will search the entire database to find an author with the '
u'closest writing style by using the Probabilistic K-Nearest Neighbor '
u'Algorithm. Drag and Drop a txt file to the box in order to '
u'upload the txt file to the server. The display of probabilistic values '
u'is provided in the form of CSV file.'),
authors_list=data_warehouse.get_all_author_id_and_name()
)
def get_chars():
return render_template('data_visualize/charts.html',
title='Stylometric Charts',
content=Markup(u'In this page, you can compare the writing styles of <strong>at most 3 '
u'documents</strong> in terms of stylometric features. Firstly, you need to '
u'select an author from the drop-down list. Afterwards, another drop-down '
u'list is shown for you to select the document. Finally, click the button '
u'<mark>Add to Table</mark> to add the document into the cache. You will '
u'need to repeat the steps until there are at least 2 documents.'),
authors_list=data_warehouse.get_all_author_id_and_name()
)
def upload_file():
return render_template('data_visualize/upload.html',
title='KNN Authorship Determination',
content=Markup(u'In this page, you may upload a txt file to the server. The '
u'application will search the entire database to find an author with the '
u'closest writing style by using the Probabilistic K-Nearest Neighbor '
u'Algorithm. Drag and Drop a txt file to the box in order to '
u'upload the txt file to the server. The display of probabilistic values '
u'is provided in the form of CSV file.'),
authors_list=data_warehouse.get_all_author_id_and_name()
)
def running_self_defined_distance():
return render_template('data_visualize/selfdistance.html',
title='Self-defined Distance',
content='TBC',
authors_list=data_warehouse.get_all_author_id_and_name()
)
def running_self_defined_distance():
return render_template('data_visualize/selfdistance.html',
title='Self-defined Distance',
content='TBC',
authors_list=data_warehouse.get_all_author_id_and_name()
)
