def generate_dataset_ARIMA(pun, first_day, meteo, varn): vector_date = np.array(pun[pun.columns[0]]) vector_ore = np.array(pun[pun.columns[1]]) target = np.array(pun[varn]) global_dates = temp.dates(pd.Series(vector_date)) vac_glob = temp.add_holidays(global_dates) all_days = temp.generate_days(vector_ore, first_day) MD = replicate_meteo_variables(meteo, global_dates) aad = np.array([temp.convert_day_to_angle(v) for v in all_days]) aore = np.sin(vector_ore*np.pi/24) all_dict = {'holiday' : vac_glob, 'day' : aad, 'ora' : aore} all_dict.update(MD) FDF = pd.DataFrame(all_dict) return FDF, target
sep="\t") ################################################################### ###### find missing dates ######################################### ################################################################### vector_dates = np.concatenate([ np.array(data[data.columns[0]]), np.array(data2[data2.columns[0]]), np.array(data3[data3.columns[0]]), np.array(data4[data4.columns[0]]), np.array(data5[data5.columns[0]]), np.array(data6[data6.columns[0]]) ]) global_dates = temp.dates(pd.Series(vector_dates)) missing = Functions_for_TSP.finding_missing_dates(global_dates, milano) missing2 = Functions_for_TSP.finding_missing_dates(global_dates, torino) test = Functions_for_TSP.update_meteo(milano, torino) test.to_csv('storico_milano_aggiornato.txt', sep="\t", index=False) missing2 = Functions_for_TSP.finding_missing_dates(global_dates, test) missingca = Functions_for_TSP.finding_missing_dates(global_dates, ca) missingpa = Functions_for_TSP.finding_missing_dates(global_dates, pa) missingrc = Functions_for_TSP.finding_missing_dates(global_dates, rc) missingfi = Functions_for_TSP.finding_missing_dates(global_dates, fi) diffmiro = Functions_for_TSP.simulate_meteo(milano, roma) difffiro = Functions_for_TSP.simulate_meteo(fi, roma)
import statsmodels.api as sm #from statsmodels.tsa import stattools #from statsmodels.graphics import tsaplots import pandas as pd import numpy as np import matplotlib.pyplot as plt import Functions_for_TSP import statsmodels.tsa.arima_model data = pd.read_excel("C:/Users/d_floriello/Documents/PUN/Anno 2010.xlsx") import temp pun = data["PUN"] pun = data["CSUD"] dates = temp.dates(data[data.columns[0]]) prova = pd.to_datetime(dates) df = pd.DataFrame(pun) df = df.set_index(prova) dec = sm.tsa.seasonal_decompose(df, freq=24) dec.plot() min_season = np.array(dec.seasonal.ix[0:24]) plt.plot(min_season) D, Y = temp.create_dataset(data, "ven") Y = np.array(Y) acf, Q, P, = statsmodels.tsa.stattools.acf(Y, nlags=48, qstat=True) statsmodels.graphics.tsaplots.plot_acf(Y, lags=1000)
ca = pd.read_table("C:/Users/d_floriello/Documents/PUN/storico_cagliari.txt", sep="\t") pa = pd.read_table("C:/Users/d_floriello/Documents/PUN/storico_palermo.txt", sep="\t") rc = pd.read_table("C:/Users/d_floriello/Documents/PUN/storico_reggiocalabria.txt", sep="\t") fi = pd.read_table("C:/Users/d_floriello/Documents/PUN/storico_firenze.txt", sep="\t") ################################################################### ###### find missing dates ######################################### ################################################################### vector_dates = np.concatenate([np.array(data[data.columns[0]]), np.array(data2[data2.columns[0]]), np.array(data3[data3.columns[0]]), np.array(data4[data4.columns[0]]), np.array(data5[data5.columns[0]]), np.array(data6[data6.columns[0]])]) global_dates = temp.dates(pd.Series(vector_dates)) missing = Functions_for_TSP.finding_missing_dates(global_dates, milano) missing2 = Functions_for_TSP.finding_missing_dates(global_dates, torino) test = Functions_for_TSP.update_meteo(milano, torino) test.to_csv('storico_milano_aggiornato.txt', sep="\t", index = False) missing2 = Functions_for_TSP.finding_missing_dates(global_dates, test) missingca = Functions_for_TSP.finding_missing_dates(global_dates, ca) missingpa = Functions_for_TSP.finding_missing_dates(global_dates, pa) missingrc = Functions_for_TSP.finding_missing_dates(global_dates, rc) missingfi = Functions_for_TSP.finding_missing_dates(global_dates, fi) diffmiro = Functions_for_TSP.simulate_meteo(milano,roma) difffiro = Functions_for_TSP.simulate_meteo(fi,roma)
import statsmodels.api as sm #from statsmodels.tsa import stattools #from statsmodels.graphics import tsaplots import pandas as pd import numpy as np import matplotlib.pyplot as plt import Functions_for_TSP import statsmodels.tsa.arima_model data = pd.read_excel("C:/Users/d_floriello/Documents/PUN/Anno 2010.xlsx") import temp pun = data["PUN"] pun = data["CSUD"] dates = temp.dates(data[data.columns[0]]) prova = pd.to_datetime(dates) df = pd.DataFrame(pun) df = df.set_index(prova) dec = sm.tsa.seasonal_decompose(df, freq=24) dec.plot() min_season = np.array(dec.seasonal.ix[0:24]) plt.plot(min_season) D,Y = temp.create_dataset(data, "ven") Y = np.array(Y) acf, Q, P, = statsmodels.tsa.stattools.acf(Y, nlags = 48, qstat = True) statsmodels.graphics.tsaplots.plot_acf(Y, lags=1000)