def test_kalman_filter_pickle(data):
# Construct the statespace representation
true = results_kalman_filter.uc_uni
k_states = 4
model = KalmanFilter(k_endog=1, k_states=k_states)
model.bind(data['lgdp'].values)
model.design[:, :, 0] = [1, 1, 0, 0]
model.transition[([0, 0, 1, 1, 2, 3],
[0, 3, 1, 2, 1, 3],
[0, 0, 0, 0, 0, 0])] = [1, 1, 0, 0, 1, 1]
model.selection = np.eye(model.k_states)
# Update matrices with given parameters
(sigma_v, sigma_e, sigma_w, phi_1, phi_2) = np.array(
true['parameters']
)
model.transition[([1, 1], [1, 2], [0, 0])] = [phi_1, phi_2]
model.state_cov[
np.diag_indices(k_states) + (np.zeros(k_states, dtype=int),)] = [
sigma_v ** 2, sigma_e ** 2, 0, sigma_w ** 2
]
# Initialization
initial_state = np.zeros((k_states,))
initial_state_cov = np.eye(k_states) * 100
# Initialization: modification
initial_state_cov = np.dot(
np.dot(model.transition[:, :, 0], initial_state_cov),
model.transition[:, :, 0].T
)
model.initialize_known(initial_state, initial_state_cov)
pkl_mod = cPickle.loads(cPickle.dumps(model))
results = model.filter()
pkl_results = pkl_mod.filter()
assert_allclose(results.llf_obs[true['start']:].sum(),
pkl_results.llf_obs[true['start']:].sum())
assert_allclose(results.filtered_state[0][true['start']:],
pkl_results.filtered_state[0][true['start']:])
assert_allclose(results.filtered_state[1][true['start']:],
pkl_results.filtered_state[1][true['start']:])
assert_allclose(results.filtered_state[3][true['start']:],
pkl_results.filtered_state[3][true['start']:])
def main1():
for equity in os.listdir(rawDataDir):
infp = PurePath(str(rawDataDir) + "/" + equity)
df = pd.read_parquet(infp)
volume_M = df.volume.sum() / df.shape[0]
# produce the volume bar
vbar = volume_bar_df(df, 'volume', volume_M)
vbar.set_index('dates', inplace=True)
# return
vbar['retClose'] = vbar['price'] / vbar['price'].shift(1) - 1
# daily vol
vbar['dailyVol'] = getDailyVol(vbar['price'])
# normOI and VPIN
vbar = orderFlow(vbar)
# kf setting, assume random walk
kf = KalmanFilter(1, 1)
sigma_h = 0.0001 # hidden
sigma_e = 0.001 # obs
kf.obs_cov = np.array([sigma_e])
kf.state_cov = np.array([sigma_h])
kf.design = np.array([1.0])
kf.transition = np.array([1.0])
kf.selection = np.array([1.0])
kf.initialize_known(np.array([vbar.price[0]]), np.array([[sigma_h]]))
kf.bind(np.array(vbar.price.copy()))
r = kf.filter()
vbar['forecasts'] = pd.DataFrame(r.forecasts[0], index=vbar.index)
vbar['forecasts_error'] = pd.DataFrame(r.forecasts_error[0],
index=vbar.index)
vbar['error_std'] = pd.DataFrame(np.sqrt(r.forecasts_error_cov[0][0]),
index=vbar.index)
vbar = vbar.dropna()
# srl_corr
vbar['srl_corr'] = df_rolling_autocorr(vbar['price'],
window=100).rename('srl_corr')
vbar = vbar.dropna()
## output
tmpPath = str(interimDataDir) + "/" + equity
outfp = PurePath(tmpPath)
print(outfp)
vbar.to_parquet(outfp)
print("Success: save")
return
#y = a + e #If we can only observe y, what can we say about α? #This acts like a filter trying to recover a signal by filtering out noise. #A linear filter. # a is the state and y is the observation (equations) import statsmodels.tsa.statespace.kalman_filter from statsmodels.tsa.statespace.kalman_filter import KalmanFilter kf = KalmanFilter(1,1) kf.obs_cov = np.array([sigma_e]) # H kf.state_cov = np.array([sigma_h]) # Q kf.design = np.array([1.0]) # Z kf.transition = np.array([1.0]) # T kf.selection = np.array([1.0]) # R ys, ah = kf.simulate(100)
