def get_timeline_count(tweets_file, keywords=None, timezones=None):
# get dataframe
l = Loader(tweets_file)
data = l.get_dataframe()
def valid_keyword(x):
for keyword in keywords:
if keyword in x:
return True
return False
def valid_timezone(t):
for timezone in timezones:
if timezone in t:
return True
return False
if not keywords is None:
data = data[data["text"].apply(valid_keyword) == True]
if not timezones is None:
data = data[data["user_time_zone"].apply(valid_timezone) == True]
print len(data.index)
data["created_at"] = data["created_at"].astype("datetime64")
a = data["created_at"].groupby(data["created_at"].dt.date).count()
print a
a = a.to_frame()
return np.array(date2num(a.index)), np.array(a.values)
def test3():
l = Loader("./data/weight.json")
print l.get_dataframe()
day = dates_set[i]
for key in keys:
if key in tweet:
try:
counts[day] += 1
except:
counts[day] = 1
df = df.drop(idx)
break
return df, counts
l = Loader("./data/May_16.csv")
df = l.get_dataframe()
df["created_at"] = pandas.to_datetime(df["created_at"])
dates = df["created_at"].dt.date.to_frame()
dates = np.array(date2num(dates)).flatten()
print "==== Size : {} ====".format(len(df.index))
# Remove tweets containing keywords mapped to a fixed sentiment
df, counts_leave = count_for_set(df, dates, leave_keys)
df, counts_other = count_for_set(df, dates, other_keys)
df, counts_stay = count_for_set(df, dates, stay_keys)
print "==== Size : {} ====".format(len(df.index))
print "Days : ", dates
print "==== Leave ===="