wea_ondara/master
1
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

wip

Browse Source
This commit is contained in:
wea_ondara
2021-03-22 20:30:32 +01:00
parent 316fed8283
commit 52d7ddb7fc
9 changed files with 270 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
its.py
View File

@@ -7,13 +7,12 @@ from datetime import datetime
from datetime import timedelta
from dateutil.relativedelta import relativedelta
from common import calc_intervals, printnoln, rprint, DAYS_NEW_USER, FIG_SIZE, difftime
from common import calc_intervals, printnoln, rprint, DAYS_NEW_USER, FIG_SIZE, CHANGE_DATE, difftime
from loader import load, dmt, cms
from sentiments import readtoxleveltxt
colors = ['red', 'green', 'blue', 'orange', 'deeppink']
thresholds = [6, 9, 12, 15]
changedate = datetime.fromisoformat("2018-09-01T00:00:00")
def main(folder, intervl):
@@ -42,9 +41,9 @@ def main(folder, intervl):
# avg sentiments
filtered = (dmt(posts).map(lambda p: [cachedsentiments[a['Id']]['compound']
for a in p['Answers']
if option_date_from <= p['CreationDate'] < option_date_to #post in interval
and firstcontrib[p['OwnerUserId']] + timedelta(days=DAYS_NEW_USER) > p['CreationDate'] # post created withon 1 week of 1st contrib
and p['CreationDate'] + timedelta(days=DAYS_NEW_USER) > a['CreationDate']]) # answer within 1 week of post creation
if option_date_from <= p['CreationDate'] < option_date_to # post in interval
and firstcontrib[p['OwnerUserId']] + timedelta(days=DAYS_NEW_USER) > p['CreationDate'] # post created withon 1 week of 1st contrib
and p['CreationDate'] + timedelta(days=DAYS_NEW_USER) > a['CreationDate']]) # answer within 1 week of post creation
.filter(lambda p: p != [])
.reduce(lambda a, b: a + b, lambda a, b: a + b, lambda: [])
@@ -57,7 +56,7 @@ def main(folder, intervl):
avgcount = np.mean([x for x in count if str(x) != "nan"])
stdcount = np.std([x for x in count if str(x) != "nan"])
for i in range(len(count)):
if str(count[i]) == "nan": # or np.abs((count[i] - avgcount) / stdcount) > 3:
if str(count[i]) == "nan": # or np.abs((count[i] - avgcount) / stdcount) > 3:
datasingle[i] = float("nan")
data[i] = float("nan")
count[i] = float("nan")