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

wip

Browse Source
This commit is contained in:
wea_ondara
2020-04-08 12:28:52 +02:00
parent e926ea5b22
commit 813d5edf24
2 changed files with 73 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
its.py
View File

@@ -1,14 +1,13 @@
import sys
import matplotlib.pyplot as plt
import numpy as np
import os
import statsmodels.api as sm
import sys
from datetime import datetime
from datetime import timedelta
from dateutil.relativedelta import relativedelta
from common import calc_intervals, printnoln, rprint, DAYS_NEW_USER
from common import calc_intervals, printnoln, rprint, DAYS_NEW_USER, difftime
from loader import load, dmt, cms
from sentiments import readtoxleveltxt
@@ -58,7 +57,7 @@ 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")
@@ -120,7 +119,7 @@ def main(folder, intervl):
file.write(str(res.summary()))
fig = plt.figure(figsize=(16, 12))
plt.plot([i[0] for i in intervals], data, label="average sentiment")
plt.plot([difftime(i[0]) for i in intervals], data, label="average sentiment")
plt.grid(True)
for i in range(len(data)):
va = "center"
@@ -139,12 +138,12 @@ def main(folder, intervl):
va = "bottom"
else:
va = "top"
plt.text(intervals[i][0], data[i], ("n=" if i == 0 else "") + str(len(datasingle[i])), ha="center", va=va)
plt.plot([intervals[i][0] for i in range(len(datasingle)) for j in datasingle[i]], its2ols, label="sm single ITS (pvalues " + str(p2) + ")")
plt.text(difftime(intervals[i][0]), data[i], ("n=" if i == 0 else "") + str(len(datasingle[i])), ha="center", va=va)
plt.plot([difftime(intervals[i][0]) for i in range(len(datasingle)) for j in datasingle[i]], its2ols, label="sm single ITS (pvalues " + str(p2) + ")")
# print("shape: " + str(np.shape(thresdata)))
for (ti, t) in enumerate(thresholds):
# print("shape1: " + str(np.shape(thresdata[ti])))
plt.plot([thresiv[ti][i][0] for i in range(len(thresdata[ti])) for j in thresdata[ti][i]], thresols[ti], label="thres ITS " + str(t) + " months (pvalues " + str(thresp[ti]) + ")")
plt.plot([difftime(thresiv[ti][i][0]) for i in range(len(thresdata[ti])) for j in thresdata[ti][i]], thresols[ti], label="thres ITS " + str(t) + " months (pvalues " + str(thresp[ti]) + ")")
plt.title("Average sentiments for new users")
plt.xticks(rotation=90)
plt.xlabel("months")