import pandas as pd
import seaborn as sns
import numpy as np
import os
from matplotlib import pyplot as plt
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error
from pandas.plotting import autocorrelation_plot
import datetime
import matplotlib.patches as mpatches
from pmdarima.arima import auto_arima
import statsmodels.api as sm
from statsmodels.tsa.stattools import adfuller
from numpy import log

ig, axes = plt.subplots(2, 1, figsize=(10,5), dpi=100, sharex=True)

bikes = pd.read_csv('D:\PracaDomowa3-master\data\\newbikes6years.csv')
bikes['Trip Date'] = pd.to_datetime(bikes['Trip Date'])
bikes.set_index('Trip Date', inplace=True)
print(bikes)
print(type(bikes))

test = bikes.loc['2019-01-01':]
data = bikes.loc[:'2018-12-31']


# Usual Differencing
axes[0].plot(data[:], label='Original Series')
axes[0].plot(data[:].diff(1), label='Usual Differencing')
axes[0].set_title('Usual Differencing')
axes[0].legend(loc='upper left', fontsize=10)

axes[1].plot(data[:], label='Original Series')
axes[1].plot(data[:].diff(7), label='Seasonal Differencing', color='green')
axes[1].set_title('Seasonal Differencing')
plt.legend(loc='upper left', fontsize=10)
plt.suptitle('Amount of trips per day', fontsize=16)
plt.show()


smodel = auto_arima(data,
                    test='adf',
                    m=7,
                    seasonal=True,
                    D=1, trace=True,
                    error_action='ignore',
                    suppress_warnings=True,
                    stepwise=True)

smodel.summary()
print(smodel.summary())


n_periods = 365
fitted, confint = smodel.predict(n_periods=n_periods, return_conf_int=True)
index_of_fc = pd.date_range(data.index[-1], periods = n_periods, freq='D')

fitted_series = pd.Series(fitted, index=index_of_fc)
lower_series = pd.Series(confint[:, 0], index=index_of_fc)
upper_series = pd.Series(confint[:, 1], index=index_of_fc)

rolling_test = test.rolling(window=30).mean()
rolling_mean = data.rolling(window=30).mean()
plt.plot(rolling_mean)
plt.plot(rolling_test, color = 'g')
plt.plot(fitted_series, color='darkgreen')
plt.fill_between(lower_series.index,
                 lower_series,
                 upper_series,
                 color='r', alpha=.15)

plt.title("SARIMA - Final Forecast")
plt.show()

#SARIMAX(2,0,1)x(0,1,1,7)