df = pd.read_excel("./input/Superstore.xls")
df.head()

df.shape

furniture = df.loc[df.Category == 'Furniture']
furniture.head()

print('시점 :', furniture['Order Date'].min())
print('종점 :', furniture['Order Date'].max())

type(furniture['Order Date'].min())

furniture.head()

furniture.isnull().sum()

furniture.groupby('Order Date').count().sort_values(by='Sales', ascending=False).head()

furniture = furniture.groupby('Order Date').agg({'Sales': 'sum'}).reset_index()
furniture.head()

furniture = furniture.set_index('Order Date', drop=True)
furniture.index

x = furniture['Sales'].resample('MS').mean()
x.head(5)

x.head()

x.plot(figsize=(15, 6))

decomposition = sm.tsa.seasonal_decompose(x, model='additive')
mpl.rcParams['figure.figsize'] = (18, 8)
fig = decomposition.plot()

pdq

seasonal_pdq

print('Examples of parameter combinations for Seasonal ARIMA...')
print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[1]))
print('SARIMAX: {} x {}'.format(pdq[1], seasonal_pdq[2]))
print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[3]))
print('SARIMAX: {} x {}'.format(pdq[2], seasonal_pdq[4]))

for param in pdq:
    for param_seasonal in seasonal_pdq:
        try:
            mod = sm.tsa.statespace.SARIMAX(x,
                                            order=param,
                                            seasonal_order=param_seasonal,
                                            enforce_stationarity=False,
                                            enforce_invertibility=False)
            results = mod.fit(missing = 'drop')
            print('ARIMA{}x{}12 - AIC:{}'
                  .format(param, param_seasonal, results.aic))
        except Exception:
#             print(results.mle_retvals)
            continue

mod = sm.tsa.statespace.SARIMAX(x,
                                order=(1, 1, 1),
                                seasonal_order=(1, 1, 0, 12),
                                enforce_stationarity=False,
                                enforce_invertibility=False)
results = mod.fit()
print(results.summary().tables[1])

results.plot_diagnostics(figsize=(16, 8))
plt.show()

ax = x['2014':].plot(label='observed')
pred.predicted_mean.plot(ax=ax, label='One-step ahead Forecast', alpha=.7, figsize=(14, 7))
ax.fill_between(pred_ci.index,
                pred_ci.iloc[:, 0],
                pred_ci.iloc[:, 1], color='k', alpha=.2)
ax.set_xlabel('Date')
ax.set_ylabel('Furniture Sales')
plt.legend()
plt.show()

x_forecasted = pred.predicted_mean
x_truth = x['2017-01-01':]
mse = ((x_forecasted - x_truth) ** 2).mean()
print('The Mean Squared Error of our forecasts is {}'.format(round(mse, 2)))

print('The Root Mean Squared Error of our forecasts is {}'.format(round(np.sqrt(mse), 2)))

pred_uc = results.get_forecast(steps=100)
pred_ci = pred_uc.conf_int()
ax = x.plot(label='observed', figsize=(14, 7))
pred_uc.predicted_mean.plot(ax=ax, label='Forecast')
ax.fill_between(pred_ci.index,
                pred_ci.iloc[:, 0],
                pred_ci.iloc[:, 1], color='k', alpha=.25)
ax.set_xlabel('Date')
ax.set_ylabel('Furniture Sales')
plt.legend()
plt.show()

print(furniture.shape)
print(office.shape)

store = furniture.merge(
    office, how='inner', on='Order Date'
)
store.head()

plt.figure(figsize=(20, 8))
plt.plot(store['Order Date'], store['furniture_sales'], 'b-', label = 'furniture')
plt.plot(store['Order Date'], store['office_sales'], 'r-', label = 'office supplies')
plt.xlabel('Date')
plt.ylabel('Sales')
plt.title('Sales of Furniture and Office Supplies')
plt.legend()

print("Office supplies first time produced higher sales than furniture is {}.".format(first_date.date()))

furniture_model = Prophet(interval_width=0.95)
furniture_model.fit(furniture)

office_model = Prophet(interval_width=0.95)
office_model.fit(office)

plt.figure(figsize=(18, 6))
furniture_model.plot(furniture_forecast, xlabel = 'Date', ylabel = 'Sales')
plt.title('Furniture Sales')

plt.figure(figsize=(18, 6))
office_model.plot(office_forecast, xlabel = 'Date', ylabel = 'Sales')
plt.title('Office Supplies Sales')

forecast = forecast.rename(columns={'furniture_ds': 'Date'}).drop('office_ds', axis=1)
forecast.head()

plt.figure(figsize=(10, 7))
plt.plot(forecast['Date'], forecast['furniture_trend'], 'b-')
plt.plot(forecast['Date'], forecast['office_trend'], 'r-')
plt.legend(); plt.xlabel('Date'); plt.ylabel('Sales')
plt.title('Furniture vs. Office Supplies Sales Trend')

plt.figure(figsize=(10, 7))
plt.plot(forecast['Date'], forecast['furniture_yhat'], 'b-')
plt.plot(forecast['Date'], forecast['office_yhat'], 'r-')
plt.legend(); plt.xlabel('Date'); plt.ylabel('Sales')
plt.title('Furniture vs. Office Supplies Estimate')

furniture_model.plot_components(furniture_forecast)

office_model.plot_components(office_forecast)