if __name__ == '__main__':
tPolls = 2
tTwitter = 14
startTrain = 52
addFake = False
m.setFonts('timeseries')
### Load in data and normalise
twitterColumns = [0, 2]
pollColumns = [1, 3, 4, 5, 6, 7, 8,
9] # avdate, Remain (norm), Leave (norm)
lh, rh, p = m.getPanda(twitterColumns, pollColumns)
h_agg, p_agg, p_var = m.aggregate(lh,
rh,
p,
splitPolls=False,
interpolate=True)
p_orig = p_agg.copy()
h_orig = h_agg.copy()
p_agg = m.shift_polls(p_agg, tPolls, addFake=addFake)
h_agg = m.shift_tweets(h_agg, tTwitter)
kalmanData = m.getKalmanData(p_agg, h_agg)
startDate = kalmanData.index[0] + dt.timedelta(days=startTrain)
endDate = dt.datetime(day=23, month=6, year=2016)
### FIND KF VARIABLES: 1) R and 2) P0
# find R
preds = []
R_r = p_var['Remain'].mean()
if __name__ == '__main__':
### GET DATA ###
m.setFonts('timeseries')
startDate = dt.datetime(year=2016, month=3, day=1)
endDate = dt.datetime(year=2016, month=6, day=1)
interpolate = False
m.longPrint()
### Load in data and normalise
twitterColumns = [0, 2]
pollColumns = [1, 3, 4, 5, 6, 7, 8,
9] # avdate, Remain (norm), Leave (norm)
lh, rh, p = m.getPanda(twitterColumns, pollColumns)
h_agg, p_agg, p_var = m.aggregate(lh,
rh,
p,
splitPolls=False,
interpolate=interpolate)
_, p_onl, p_tel = m.aggregate(lh,
rh,
p,
splitPolls=True,
interpolate=interpolate)
kalmanData = m.getKalmanData(p_agg, h_agg)
kalmanData_o = m.getKalmanData(p_onl, h_agg)
kalmanData_t = m.getKalmanData(p_tel, h_agg)
# 1. Moving Average
df_orig = kalmanData
df_ma = df_orig.rolling(3, center=True, closed='both').mean()