from ailever.utils import source
source('ST-0000')




time series

TS( N,N) - Simple Exponential Smoothing 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY']
target.plot(marker='o', color='black', legend=True, figsize=(12,5))

# TS(N,N) : Simple Exponential Smoothing
model = smt.SimpleExpSmoothing(target).fit(smoothing_level=0.9, optimized=False)
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.SimpleExpSmoothing]
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level:(float)
TS( A,N) - Holt Linear Method 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# Holt TS(A,N)
model = smt.Holt(target).fit()
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.Holt]
# exponential :(bool)
# damped_trend :(bool)
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level :(float)
# initial_trend :(float)
TS(Ad,N) - Additive Damped Trend Method 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# Holt TS(Ad,N)
model = smt.Holt(target, exponential=True, damped_trend=True).fit()
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.Holt]
# exponential :(bool)
# damped_trend :(bool)
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level :(float)
# initial_trend :(float)
TS( A,A) - Additive Holt-Winters' Method 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# Holt-Winter's TS(A,A)
model = smt.ExponentialSmoothing(target, seasonal_periods=24, trend='add', seasonal='add', damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ExponentialSmoothing]
# trend :(str) “add”, “mul”, “additive”, “multiplicative”, None
# damped_trend :(bool) 
# seasonal :(str) “add”, “mul”, “additive”, “multiplicative”, None
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level :(float)
# initial_trend :(float)
# initial_seasonal :(array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds :(dict)[str, tuple[float, float]]
# dates :(array_like) of datetime
# freq :(str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing :(str)  ‘none’, ‘drop’, and ‘raise’
TS( A,M) - Multiplicative Holt-Winters' Method 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# Holt-Winter's TS(A,M)
model = smt.ExponentialSmoothing(target, seasonal_periods=24, trend='add', seasonal='mul', damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ExponentialSmoothing]
# trend :(str) “add”, “mul”, “additive”, “multiplicative”, None
# damped_trend :(bool) 
# seasonal :(str) “add”, “mul”, “additive”, “multiplicative”, None
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level :(float)
# initial_trend :(float)
# initial_seasonal :(array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds :(dict)[str, tuple[float, float]]
# dates :(array_like) of datetime
# freq :(str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing :(str)  ‘none’, ‘drop’, and ‘raise’
TS(Ad,M) - Holt-Winters Damped Method 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# Holt-Winter's TS(Ad,M)
model = smt.ExponentialSmoothing(target, seasonal_periods=24, trend='add', seasonal='mul', damped_trend=True).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast = model.forecast(24).rename(r'$\alpha=%s$'%model.model.params['smoothing_level'])
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ExponentialSmoothing]
# trend :(str) “add”, “mul”, “additive”, “multiplicative”, None
# damped_trend :(bool) 
# seasonal :(str) “add”, “mul”, “additive”, “multiplicative”, None
# initialization_method :(str) None, ‘estimated’, ‘heuristic’, ‘legacy-heuristic’, ‘known’
# initial_level : (float)
# initial_trend : (float)
# initial_seasonal : (array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds : (dict)[str, tuple[float, float]]
# dates : (array_like) of datetime
# freq : (str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing : (str)  ‘none’, ‘drop’, and ‘raise’
ETS(A,N,N) - Simple Exponential Smoothing with Additive Errors 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# ETS(A,N,N)
model = smt.ETSModel(target, seasonal_periods=24, error='add', trend=None, seasonal=None, damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$ETS$')
forecast = model.forecast(24).rename(r'$ETS$')
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ETSModel]
# error :(str) “add”-default or “mul”.
# trend :(str) “add”, “mul”, or None-default
# damped_trend :(bool) True, False-Default 
# seasonal :(str) “add”, “mul”, or None-default
# seasonal_periods :(int)
# initialization_method :(str) None, ‘estimated’-default, ‘heuristic’, ‘known’
# initial_level : (float)
# initial_trend : (float)
# initial_seasonal : (array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds : (dict)[str, tuple[float, float]]
# - “smoothing_level”
# - “smoothing_trend”
# - “smoothing_seasonal”
# - “damping_trend”
# - “initial_level”
# - “initial_trend”
# - “initial_seasonal.0”, …, “initial_seasonal.(m-1)”
# dates : (array_like) of datetime
# freq : (str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing : (str)  ‘none’, ‘drop’, and ‘raise’
ETS(M,N,N) - Simple Exponential Smoothing with Multiplicative Errors 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# ETS(M,N,N)
model = smt.ETSModel(target, seasonal_periods=24, error='mul', trend=None, seasonal=None, damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$ETS$')
forecast = model.forecast(24).rename(r'$ETS$')
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ETSModel]
# error :(str) “add”-default or “mul”.
# trend :(str) “add”, “mul”, or None-default
# damped_trend :(bool) True, False-Default 
# seasonal :(str) “add”, “mul”, or None-default
# seasonal_periods :(int)
# initialization_method :(str) None, ‘estimated’-default, ‘heuristic’, ‘known’
# initial_level : (float)
# initial_trend : (float)
# initial_seasonal : (array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds : (dict)[str, tuple[float, float]]
# - “smoothing_level”
# - “smoothing_trend”
# - “smoothing_seasonal”
# - “damping_trend”
# - “initial_level”
# - “initial_trend”
# - “initial_seasonal.0”, …, “initial_seasonal.(m-1)”
# dates : (array_like) of datetime
# freq : (str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing : (str)  ‘none’, ‘drop’, and ‘raise’
ETS(A,A,N) - Holt’s Linear Method with Additive Errors 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# ETS(A,A,N)
model = smt.ETSModel(target, seasonal_periods=24, error='add', trend='add', seasonal=None, damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$ETS$')
forecast = model.forecast(24).rename(r'$ETS$')
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ETSModel]
# error :(str) “add”-default or “mul”.
# trend :(str) “add”, “mul”, or None-default
# damped_trend :(bool) True, False-Default 
# seasonal :(str) “add”, “mul”, or None-default
# seasonal_periods :(int)
# initialization_method :(str) None, ‘estimated’-default, ‘heuristic’, ‘known’
# initial_level : (float)
# initial_trend : (float)
# initial_seasonal : (array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds : (dict)[str, tuple[float, float]]
# - “smoothing_level”
# - “smoothing_trend”
# - “smoothing_seasonal”
# - “damping_trend”
# - “initial_level”
# - “initial_trend”
# - “initial_seasonal.0”, …, “initial_seasonal.(m-1)”
# dates : (array_like) of datetime
# freq : (str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing : (str)  ‘none’, ‘drop’, and ‘raise’
ETS(M,A,N) - Holt’s Linear Method with Multiplicative Errors 
import statsmodels.api as sm
import statsmodels.tsa.api as smt
import matplotlib.pyplot as plt

# dataset
target = sm.datasets.sunspots.load_pandas().data['SUNACTIVITY'] + 10
target.plot(marker='o', color='black', legend=True, figsize=(12,5)) 

# ETS(M,A,N)
model = smt.ETSModel(target, seasonal_periods=24, error='mul', trend='add', seasonal=None, damped_trend=False).fit(use_boxcox=True)
model.fittedvalues.plot(style='--',  color='blue', label=r'$ETS$')
forecast = model.forecast(24).rename(r'$ETS$')
forecast.plot(marker='o', color='blue')

plt.legend()
plt.show()

# [smt.ETSModel]
# error :(str) “add”-default or “mul”.
# trend :(str) “add”, “mul”, or None-default
# damped_trend :(bool) True, False-Default 
# seasonal :(str) “add”, “mul”, or None-default
# seasonal_periods :(int)
# initialization_method :(str) None, ‘estimated’-default, ‘heuristic’, ‘known’
# initial_level : (float)
# initial_trend : (float)
# initial_seasonal : (array_like)
# use_boxcox : {True, False, ‘log’, float}
# bounds : (dict)[str, tuple[float, float]]
# - “smoothing_level”
# - “smoothing_trend”
# - “smoothing_seasonal”
# - “damping_trend”
# - “initial_level”
# - “initial_trend”
# - “initial_seasonal.0”, …, “initial_seasonal.(m-1)”
# dates : (array_like) of datetime
# freq : (str) ‘B’, ‘D’, ‘W’, ‘M’, ‘A’, or ‘Q’
# missing : (str)  ‘none’, ‘drop’, and ‘raise’




TITLE2













　



　



　
















Reference

    
  
  1. 
  
  2. 
  
  3. 









  Edit







				
				

					
					
					

					
ailever