def get_cohorts_for_article(article_id):
"""
Gets all the cohorts for this article
"""
article = Article.find_by_id(article_id)
return json.dumps(CohortArticleMap.get_cohorts_for_article(article))
def add_article_to_cohort():
"""
Gets all the articles of this teacher
"""
cohort = Cohort.find(request.form.get("cohort_id"))
check_permission_for_cohort(cohort.id)
article = Article.find_by_id(request.form.get("article_id"))
if not CohortArticleMap.find(cohort.id, article.id):
now = datetime.now()
new_mapping = CohortArticleMap(cohort, article, now)
db.session.add(new_mapping)
db.session.commit()
return "OK"
def delete_article_from_cohort():
"""
Gets all the articles of this teacher
"""
cohort = Cohort.find(request.form.get("cohort_id"))
check_permission_for_cohort(cohort.id)
article = Article.find_by_id(request.form.get("article_id"))
mapping = CohortArticleMap.find(cohort.id, article.id)
if mapping:
db.session.delete(mapping)
db.session.commit()
return "OK"
else:
return make_error(401, "That article does not belong to the cohort!")
def more_like_this_article(user, count, article_id):
"""
Given a article ID find more articles like that one via Elasticsearchs "more_like_this" method
"""
article = Article.find_by_id(article_id)
query_body = build_more_like_this_query(count, article.content,
article.language)
es = Elasticsearch(ES_CONN_STRING)
res = es.search(index=ES_ZINDEX, body=query_body) # execute search
hit_list = res["hits"].get("hits")
# TODO need to make sure either that the searched on article is always a part of the list \
# or that it is never there.
# it could be used to show on website; you searched on X, here is what we found related to X
final_article_mix = _to_articles_from_ES_hits(hit_list)
return [
UserArticle.user_article_info(user, article)
for article in final_article_mix
]
def articles_correlations():
articles_df = pd.DataFrame(columns=[
"id", "lang", "difficulty", "word_count", "title_length", "opened",
"translated", "spoken", "liked", "closed"
])
all_users = User.find_all()
print(len(all_users))
for reading_language in languages_to_analyze:
print("\nLANGUAGE:", reading_language)
language_id = Language.find(reading_language).id
for user in tqdm(all_users):
if user.learned_language_id == language_id:
events = UserActivityData.find(user)
for event in events:
article_id = event.article_id
if article_id:
article_data = Article.find_by_id(article_id)
if article_data.language_id == language_id:
if not (articles_df['id'] == article_id).any():
title_len = len(article_data.title.split())
df = {
"id": article_id,
"lang": article_data.language_id,
"difficulty": article_data.fk_difficulty,
"word_count": article_data.word_count,
"title_length": title_len,
"opened": 0,
"translated": 0,
"spoken": 0,
"liked": 0,
"closed": 0
}
articles_df = articles_df.append(
df, ignore_index=True)
if event.event == "UMR - OPEN ARTICLE":
articles_df.loc[articles_df.id == article_id,
'opened'] += 1
if event.event == "UMR - TRANSLATE TEXT":
articles_df.loc[articles_df.id == article_id,
'translated'] += 1
if event.event == "UMR - SPEAK TEXT":
articles_df.loc[articles_df.id == article_id,
'spoken'] += 1
if event.event == "UMR - LIKE ARTICLE":
articles_df.loc[articles_df.id == article_id,
'liked'] += 1
if event.event == "UMR - ARTICLE CLOSED":
articles_df.loc[articles_df.id == article_id,
'closed'] += 1
print("Articles:", len(articles_df))
correlation_variables = [
"word_count", "difficulty", "liked", "translated", "spoken",
"opened", "closed", "title_length"
]
# word count & fk_difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[0]],
articles_df[correlation_variables[1]])
print(correlation_variables[0], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# liked & fk_difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[2]],
articles_df[correlation_variables[1]])
print(correlation_variables[2], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# number of translations & difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[3]],
articles_df[correlation_variables[1]])
print(correlation_variables[3], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# number of spoken words & difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[4]],
articles_df[correlation_variables[1]])
print(correlation_variables[4], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# number of times article is opened & difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[5]],
articles_df[correlation_variables[1]])
print(correlation_variables[5], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# number of times article is closed & difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[6]],
articles_df[correlation_variables[1]])
print(correlation_variables[6], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# title length & fk_difficulty
spearman_corr = stats.spearmanr(articles_df[correlation_variables[7]],
articles_df[correlation_variables[1]])
print(correlation_variables[7], correlation_variables[1],
spearman_corr[0], spearman_corr[1])
# title length & number of times article is opened
spearman_corr = stats.spearmanr(articles_df[correlation_variables[5]],
articles_df[correlation_variables[7]])
print(correlation_variables[5], correlation_variables[7],
spearman_corr[0], spearman_corr[1])
def _to_articles_from_ES_hits(hits):
articles = []
for hit in hits:
articles.append(Article.find_by_id(hit.get("_id")))
return articles