import warnings
warnings.filterwarnings("ignore")

import itertools
import pandas as pd
import numpy as np

import statsmodels.api as sm
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
%matplotlib inline

# 한글폰트 
import matplotlib.font_manager as fm
# 폰트 적용
font_location = '/usr/share/fonts/truetype/nanum/NanumBarunGothic.ttf'
font_name = fm.FontProperties(fname=font_location).get_name()

from matplotlib import rc
rc('font', family=font_name)

import pandas_datareader.data as web
from datetime import datetime

# 대한항공 2015. 1. 1.부터 현재까지의 주가 

start = datetime( 2015, 1, 1 )
end = datetime.now()

# yahoo 파이낸스 
KA = web.DataReader('003490.KS', 'yahoo', start, end)

KA.head()

KA['Close'].plot(
    style='--',
    figsize=(12, 6)
)
pd.rolling_mean( KA['Close'], 7).plot( lw=2 )
plt.title('대한항공 종가 시세')
plt.legend( ['종가시세', '이동평균선(7일)' ] )
plt.show()

start = datetime( 2010, 1, 1 )
end = datetime.now()

SamSung = web.DataReader('005930.KS', 'yahoo', start, end)
SamSung['Close'].plot(
    style='--',
    figsize=(12, 6)
)
pd.rolling_mean( KA['Close'], 7).plot( lw=2 )
plt.title('삼성전자')
plt.legend( ['종가시세', '이동평균선(7일)' ] )
plt.show()

SamSung.head(3)

len(SamSung)

from pylab import rcParams
rcParams['figure.figsize'] = 12, 8

# 삼성전자 주식 종가에 대한 분해
y = SamSung['Close'][ 1600 : ] 

decomposition = sm.tsa.seasonal_decompose(  y, freq=12 )

fig = decomposition.plot()
plt.show()

# Define the p, d and q parameters to take any value between 0 and 2
p = d = q = range(0, 2)

# Generate all different combinations of p, q and d triplets
pdq = list( itertools.product(p, d, q))

# Generate all different combinations of seasonal p, q and d triplets
seasonal_pdq = [ (x[0], x[1], x[2], 12)  for x in pdq ]

print('Example 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]) )

warnings.filterwarnings("ignore")

y = SamSung['Close']

select_candi = 10000000
param_candi = ( 0, 0, 0 )
param_seasonal_candi = ( 0, 0, 0)

count=0
end_count = len(pdq)

for param in pdq:   
    for param_seasonal in seasonal_pdq:
        try:
            mod = sm.tsa.statespace.SARIMAX( 
                                            y,
                                            order=param,
                                            seasonal_order=param_seasonal,
                                            enforce_stationarity=False,
                                            enforce_invertibility=False
                                           )
            results = mod.fit()
            count += 1
            if count <= 5:
                print('ARIMA{}x{}12 - AIC:{}'.format(param, param_seasonal, results.aic))
            
            if results.aic < select_candi:
                select_candi = results.aic
                param_candi = param
                param_seasonal_candi = param_seasonal
        except:
            continue
            
print(param_candi, param_seasonal_candi, select_candi)            

mod = sm.tsa.statespace.SARIMAX(
    y,
    order=(1, 1, 1),
    seasonal_order=(0, 0, 1, 12),
    enforce_stationarity=False,
    enforce_invertibility=False
)

results = mod.fit()

print( results.summary().tables[1] )

results.plot_diagnostics( figsize=(12, 10) )
plt.show()

pred = results.get_prediction(
    start=pd.to_datetime('2015-1-2'),
    dynamic=False
)

pred_ci = pred.conf_int()

# 관측 데이터  1973년 부터 끝까지 
ax = y[ '2000' : ].plot( label='observed', figsize=(12, 8) )

# 예측
pred.predicted_mean.plot(
    ax=ax,
    label='One-step ahead Forecast',
    alpha=.7
)

ax.fill_between(
    pred_ci.index,
    pred_ci.iloc[ : , 0 ],
    pred_ci.iloc[ : , 1 ],
    color='k',
    alpha=.2
)

ax.fill_betweenx(
    ax.get_ylim(),
    pd.to_datetime('2015-01-01'),
    y.index[-1],
    alpha=.3,
)

ax.set_xlabel('Date')
ax.set_ylabel('best')
plt.legend()

plt.show()

y = SamSung['Close'].resample('MS').mean()

warnings.filterwarnings("ignore")

select_candi = 10000000
param_candi = ( 0, 0, 0 )
param_seasonal_candi = ( 0, 0, 0)

count=0
end_count = len(pdq)

for param in pdq:   
    for param_seasonal in seasonal_pdq:
        try:
            mod = sm.tsa.statespace.SARIMAX( 
                                            y,
                                            order=param,
                                            seasonal_order=param_seasonal,
                                            enforce_stationarity=False,
                                            enforce_invertibility=False
                                           )
            results = mod.fit()
            count += 1
            if count <= 5:
                print('ARIMA{}x{}12 - AIC:{}'.format(param, param_seasonal, results.aic))
            
            if results.aic < select_candi:
                select_candi = results.aic
                param_candi = param
                param_seasonal_candi = param_seasonal
        except:
            continue
            
print(param_candi, param_seasonal_candi, select_candi)        

mod = sm.tsa.statespace.SARIMAX(
    y,
    order=( 0, 1, 1 ),
    seasonal_order=( 1, 1, 1, 12 ),
    enforce_stationarity=False,
    enforce_invertibility=False
)

results = mod.fit()

print( results.summary().tables[1] )

results.plot_diagnostics( figsize=(12, 10) )
plt.show()

pred = results.get_prediction(
    start=pd.to_datetime('2015-01-01'),
    dynamic=False
)

pred_ci = pred.conf_int()

# 관측 데이터  2003년 부터 끝까지 
ax = y[ '2003' : ].plot( label='observed', figsize=(12, 8) )

# 예측
pred.predicted_mean.plot(
    ax=ax,
    label='One-step ahead Forecast',
    alpha=.7
)

ax.fill_between(
    pred_ci.index,
    pred_ci.iloc[ : , 0 ],
    pred_ci.iloc[ : , 1 ],
    color='k',
    alpha=.2
)

ax.fill_betweenx(
    ax.get_ylim(),
    pd.to_datetime('2015-01-01'),
    y.index[-1],
    alpha=.3,
)

ax.set_xlabel('Date')
plt.legend()

plt.show()

import warnings
warnings.filterwarnings("ignore")

import itertools
import pandas as pd
import numpy as np

import statsmodels.api as sm
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
%matplotlib inline
import pandas_datareader.data as web
from datetime import datetime

# 한글폰트 
import matplotlib.font_manager as fm
# 폰트 적용
font_location = '/usr/share/fonts/truetype/nanum/NanumBarunGothic.ttf'
font_name = fm.FontProperties(fname=font_location).get_name()

from matplotlib import rc
rc('font', family=font_name)


from fbprophet import Prophet

start = datetime( 1990, 1, 1 )
end = datetime( 2017, 6, 30 )

# 기아자동차 주식
KIA = web.DataReader('000270.KS', 'yahoo', start, end )
KIA.head()

KIA['Close'].plot()

# 2016-12-31까지 

KIA_trunc = KIA[ : '2016-12-31' ]
KIA_trunc.head(3)

df = pd.DataFrame(
    {
        'ds': KIA_trunc.index,
        'y'  : KIA_trunc['Close']
    }    
)

df.reset_index( inplace=True )

del df['Date']

df.head(3)

m = Prophet()
m.fit(df)

future = m.make_future_dataframe( periods=365 )
future.tail(3)

forecast = m.predict( future )
forecast[ [ 'ds', 'yhat', 'yhat_lower', 'yhat_upper' ] ].tail()

plt.figure( figsize=( 12, 8) )
plt.plot( KIA['Close'] )
plt.show()

m.plot(forecast)

m.plot_components( forecast )

df = pd.read_csv( './data_science/07. example_wp_R.csv' )
df['y' ] = np.log( df['y'] )

df['cap'] = 8.5

m = Prophet( growth='logistic' )
m.fit(df)

future = m.make_future_dataframe( periods=1826 )
future['cap'] = 8.5
fcst = m.predict( future )
m.plot( fcst )