def run():
table = get_data(get_data_path('taxonomy.csv'))
group_id = species_id = 1
for index in range(1, len(table)):
row = table[index]
kwargs = {
'id': group_id,
'order': row[5],
'family': row[6].split('(')[0].strip(),
'genus': row[3].split(' ')[0],
}
if 'en' in get_languages() and '(' in row[6]:
kwargs['name_en'] = row[6].split('(')[1][:-1].strip()
group, created = SpeciesGroup.objects.get_or_create(**kwargs)
if created:
group_id += 1
Species.objects.create(
id=species_id,
include=False,
order=species_id,
rank=Rank.objects.get(slug=row[1]),
group=group,
standard_name=row[4],
scientific_name=row[3],
)
if created:
species_id += 1
def init_settings(data_path):
global _db_path
global _db_conn
db_dir = os.path.join(data_path, 'data')
_db_path = os.path.join(db_dir, 'settings.sqlite')
if not os.path.exists(db_dir):
os.makedirs(db_dir)
if not os.path.exists(_db_path):
_db_conn = sqlite3.connect(_db_path)
_db_conn.execute("""
CREATE TABLE IF NOT EXISTS lang_settings(
lang VARCHAR(25) UNIQUE NOT NULL,
tab_width INTEGER(2) NOT NULL,
use_spaces INTEGER(1) NOT NULL
)
""")
for lang in get_languages():
_db_conn.execute('INSERT INTO lang_settings(\
lang, tab_width, use_spaces)\
VALUES("' + lang + '", 4, 1)')
_db_conn.commit()
else:
_db_conn = sqlite3.connect(_db_path)
def GET(self):
i = web.input(q="", limit=5)
i.limit = safeint(i.limit, 5)
languages = [
lang for lang in utils.get_languages()
if lang.name.lower().startswith(i.q.lower())
]
return to_json(languages[:i.limit])
def search_engine_3(data_frame, tfidf_vocabulary, query, vocabulary):
se3 = data_frame
languages = utils.get_languages(se3)
# ask user for the language
print("Choose a language from: ")
print(languages)
l = input("Select language: ")
print("You selected: " + l)
if (l not in languages):
print("Sorry, your language is not in our dataset")
# add column with new ranking
se3['Similarity'] = se3.apply(utils.cosSim,
axis=1,
tfidf_vocabulary=tfidf_vocabulary,
query=query,
vocabulary=vocabulary)
# add a column to checking the language
se3['sel_lan'] = se3.apply(utils.selected_films, axis=1, language=l)
# create tuples with similarity and film id
list_tuples = []
for i in range(30000):
list_tuples.append(
(list(se3[se3['film_id'] == i]['Similarity'])[0], i))
# order tuples and take top 15th
heapq.heapify(list_tuples)
largest_sim = nlargest(15, list_tuples)
# create a data frame with the top 15th results
res_sim = pd.DataFrame(columns=[
'title', 'intro', 'Wikipedia_link', 'Running time', 'Similarity'
])
for elem in largest_sim:
res_sim = res_sim.append(se3[se3['film_id'] == elem[1]][[
'title', 'intro', 'Wikipedia_link', 'Running time', 'Similarity'
]])
# add column ranking running tima
res_sim['rank_duration'] = res_sim.apply(utils.R_time_score, axis=1)
res_sim.sort_values(by=['rank_duration'], inplace=True, ascending=True)
print(res_sim[['title', 'intro', 'Wikipedia_link',
'rank_duration']].to_string())
def GET(self):
i = web.input(q="", limit=5)
i.limit = safeint(i.limit, 5)
languages = [lang for lang in utils.get_languages() if lang.name.lower().startswith(i.q.lower())]
return to_json(languages[:i.limit])