Residence Time_ADRL

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm
#Import the required modules for test statistic calculation:
import statsmodels.stats as sm_stat
#Import the required modules for model estimation:
import statsmodels.tsa as smt
#Import the required modules for optimization:
import scipy.optimize as optimize

#We also need additional data:
import statsmodels.formula.api as smf
from  statsmodels.tsa.vector_ar.vecm import *
from statsmodels.tsa.seasonal import seasonal_decompose


dataset=pd.read_csv('RBU_AIR.csv')
dataset.head(20)


def lag(x, n):
    if n == 0:
        return x
    if isinstance(x, pd.Series):
        return x.shift(n) 
    else:
        x = pd.Series(x)
        return x.shift(n) 

    x = x.copy()
    x[n:] = x[0:-n]
    x[:n] = np.nan
    return x
    
    
    mod_L4_est = smf.ols(formula = 'PM ~ 1 + lag(CO, 0) + lag(CO, 1) + lag(CO, 2) + lag(CO, 3) + lag(CO, 4) + lag(CO, 5) + lag(CO, 6) + lag(CO, 7) \
                     + lag(NO, 0) + lag(NO, 1) + lag(NO, 2) + lag(NO, 3) + lag(NO, 4) + lag(NO, 5) + lag(NO, 6) + lag(NO, 7) \
                     + lag(NO2, 0) + lag(NO2, 1) + lag(NO2, 2) + lag(NO2, 3) + lag(NO2, 4) + lag(NO2, 5) + lag(NO2, 6) + lag(NO2, 7) \
                     + lag(Nox, 0) + lag(Nox, 1) + lag(Nox, 2) + lag(Nox, 3) + lag(Nox, 4) + lag(Nox, 5) + lag(Nox, 6) + lag(Nox, 7) \
                     + lag(NH3, 0) + lag(NH3, 1) + lag(NH3, 2) + lag(NH3, 3) + lag(NH3, 4) + lag(NH3, 5) + lag(NH3, 6) + lag(NH3, 7) \
                     + lag(SO2, 0) + lag(SO2, 1) + lag(SO2, 2) + lag(SO2, 3) + lag(SO2, 4) + lag(SO2, 5) + lag(SO2, 6) + lag(SO2, 7) \
                     + lag(CO, 0) + lag(CO, 1) + lag(CO, 2) + lag(CO, 3) + lag(CO, 4) + lag(CO, 5) + lag(CO, 6) + lag(CO, 7) \
                     + lag(Ozone, 0) + lag(Ozone, 1) + lag(Ozone, 2) + lag(Ozone, 3) + lag(Ozone, 4) + lag(Ozone, 5) + lag(Ozone, 6) + lag(Ozone, 7) \
                     + lag(Benzene, 0) + lag(Benzene, 1) + lag(Benzene, 2) + lag(Benzene, 3) + lag(Benzene, 4) + lag(Benzene, 5) + lag(Benzene, 6) + lag(Benzene, 7) \
                     + lag(Toluene, 0) + lag(Toluene, 1) + lag(Toluene, 2) + lag(Toluene, 3) + lag(Toluene, 4) + lag(Toluene, 5) + lag(Toluene, 6) + lag(Toluene, 7) \
                     + lag(Temperature, 0) + lag(RH, 0) + lag(WS, 0) + lag(WD, 0) + lag(SR, 0) + lag(BP, 0) + lag(VWS, 0)', data = dataset)
mod_L4_fit = mod_L4_est.fit()
print(mod_L4_fit.summary())


print(np.round(mod_L4_fit.params, 4))
print(np.round(mod_L4_fit.pvalues, 4))