Skip to content
Snippets Groups Projects
Commit 1862b2cc authored by Guillaume Di Fatta's avatar Guillaume Di Fatta
Browse files

Merge branch 'testBranch' into 'main'

Test branch

See merge request !7
parents 6d024a58 19e51f25
No related branches found
No related tags found
1 merge request!7Test branch
......@@ -18,6 +18,7 @@ tweetNumber = 100
for i, tweet in enumerate(sntwitter.TwitterSearchScraper(query=construct_query(terms, negativeTerms, filters, negativeFilters)).get_items()):
if i > tweetNumber:
break
if (tweet.lang in languages):
dict = {'date': convert_date_str(
tweet.date), 'tweet': supress_n(tweet.rawContent)}
......@@ -27,7 +28,7 @@ for i, tweet in enumerate(sntwitter.TwitterSearchScraper(query=construct_query(t
print(round(i/tweetNumber*100, 1), " %")
print(calc_frequency(table))
print(calc_frequency(table["date"]))
table = table.drop_duplicates(subset=["tweet"]).sort_values(by=["tweet"])
table.to_json("output/twitter_data.json", orient="split")
This diff is collapsed.
......@@ -29,10 +29,14 @@ def convert_date_str(date):
"%m/%d/%Y, %H:%M:%S"))
def time_to_num(time_str):
hh, mm, ss = map(int, time_str.split(':'))
def time_to_num(date):
clean_date = date[12:]
hh, mm, ss = int(clean_date[:2]), int(
clean_date[3:5]), int(clean_date[6:8])
return ss + 60*(mm+60*hh)
def calc_frequency(table_tweets):
return (abs(time_to_num(table_tweets["date"][0])-time_to_num(table_tweets["date"][-1]))/len(table_tweets["date"]))
table_tweets_list = list(table_tweets)
return (len(table_tweets)/abs(time_to_num(table_tweets_list[0])-time_to_num(table_tweets_list[-1])))
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment