Я пытаюсь прогнозировать несколько значений, используя модель ARIMA. Я получаю следующую ошибку. Я попытался убрать стационарность и другие необходимые условия для прогнозирования. Может кто-нибудь указать мне, почему эта ошибка генерируется и как это исправить? Я новичок в Python. Заранее спасибо.
Ошибка завершает дерево ошибок следующим образом.
MissingDataError Traceback (most recent call last)
<ipython-input-7-35993c1e078a> in <module>
37 from statsmodels.tsa.stattools import adfuller
38 print("Results of Dickey-Fuller Test:")
---> 39 dftest = adfuller(indexedDataset["like"], autolag='AIC')
40
41 dfoutput = pd.Series(dftest[0:4],index=['Test Statistics','p-value',
'#Lags Used','#Number of observations used'])
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\tsa\stattools.py in adfuller(x, maxlag, regression, autolag, store, regresults)
239 if not regresults:
240 icbest, bestlag = _autolag(OLS, xdshort, fullRHS, startlag,
--> 241 maxlag, autolag)
242 else:
243 icbest, bestlag, alres = _autolag(OLS, xdshort, fullRHS,
startlag,
~\AppData\Local\Continuum\anaconda3\lib\site-
packages\statsmodels\tsa\stattools.py in _autolag(mod, endog, exog,
startlag, maxlag, method, modargs, fitargs, regresults)
84 method = method.lower()
85 for lag in range(startlag, startlag + maxlag + 1):
---> 86 mod_instance = mod(endog, exog[:, :lag], *modargs)
87 results[lag] = mod_instance.fit()
88
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
815 **kwargs):
816 super(OLS, self).__init__(endog, exog, missing=missing,
--> 817 hasconst=hasconst, **kwargs)
818 if "weights" in self._init_keys:
819 self._init_keys.remove("weights")
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
661 weights = weights.squeeze()
662 super(WLS, self).__init__(endog, exog, missing=missing,
--> 663 weights=weights, hasconst=hasconst, **kwargs)
664 nobs = self.exog.shape[0]
665 weights = self.weights
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, endog, exog, **kwargs)
177 """
178 def __init__(self, endog, exog, **kwargs):
--> 179 super(RegressionModel, self).__init__(endog, exog, **kwargs)
180 self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog',
'weights'])
181
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\model.py in __init__(self, endog, exog, **kwargs)
210
211 def __init__(self, endog, exog=None, **kwargs):
--> 212 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
213 self.initialize()
214
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\model.py in __init__(self, endog, exog, **kwargs)
62 hasconst = kwargs.pop('hasconst', None)
63 self.data = self._handle_data(endog, exog, missing, hasconst,
---> 64 **kwargs)
65 self.k_constant = self.data.k_constant
66 self.exog = self.data.exog
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
85
86 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
---> 87 data = handle_data(endog, exog, missing, hasconst, **kwargs)
88 # kwargs arrays could have changed, easier to just attach here
89 for key in kwargs:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
631 klass = handle_data_class_factory(endog, exog)
632 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
--> 633 **kwargs)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
77
78 # this has side-effects, attaches k_constant and const_idx
---> 79 self._handle_constant(hasconst)
80 self._check_integrity()
81 self._cache = resettable_cache()
~\AppData\Local\Continuum\anaconda3\lib\site-packages\statsmodels\base\data.py in _handle_constant(self, hasconst)
131 ptp_ = self.exog.ptp(axis=0)
132 if not np.isfinite(ptp_).all():
--> 133 raise MissingDataError('exog contains inf or nans')
134 const_idx = np.where(ptp_ == 0)[0].squeeze()
135 self.k_constant = const_idx.size
MissingDataError: exog contains inf or nans
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
%matplotlib inline
from matplotlib.pylab import rcParams
rcParams['figure.figsize'] = 10, 6
dataset = pd.read_csv("data.csv")
#Parse strings to datetime type
dataset['Date'] = pd.to_datetime(dataset['Date'],
infer_datetime_format=True)
indexedDataset = dataset.set_index(['Date'])
from datetime import datetime
indexedDataset.tail(5)
#plot graph
plt.xlabel("Date")
plt.ylabel("Number of Likes")
plt.plot(indexedDataset)
#Determining the rolling statistics
rolmean = indexedDataset.rolling(window=12).mean()
rolstd = indexedDataset.rolling(window=12).std()
print(rolmean, rolstd)
#plot tolling statistics
orig = plt.plot(indexedDataset, color="blue", label="original")
mean = plt.plot(rolmean, color="red", label="Rolling Mean")
std = plt.plot(rolstd, color="black", label= "Rolling std")
plt.legend(loc="best")
plt.title=("Rolling Mean and Standard Deviation")
#Perform Dickey-Fuller test
from statsmodels.tsa.stattools import adfuller
print("Results of Dickey-Fuller Test:")
dftest = adfuller(indexedDataset["like"], autolag='AIC')
dfoutput = pd.Series(dftest[0:4],index=['Test Statistics','p-value', '#Lags
Used','#Number of observations used'])
for key, value in dftest[4].items():
dfoutput['Critical Value (%s)' %key] = value
print(dfoutput)
#Estimating trend
indexedDataset_logScale = np.log(indexedDataset)
plt.plot(indexedDataset_logScale)
movingAverage = indexedDataset_logScale.rolling(window=12).mean()
movingSTD = indexedDataset_logScale.rolling(window=12).std()
plt.plot(indexedDataset_logScale)
plt.plot(movingAverage, color="red")
datasetLogScaleMinusMovingAverage = indexedDataset_logScale - movingAverage
datasetLogScaleMinusMovingAverage.head(12)
#remove Nan Values
datasetLogScaleMinusMovingAverage.dropna(inplace=True)
datasetLogScaleMinusMovingAverage.head(10)
from statsmodels.tsa.stattools import adfuller
def test_stationarity(timeseries):
#determing rolling statistics
movingAverage = timeseries.rolling(window=12).mean()
movingSTD = timeseries.rolling(window=12).std()
#plot rolling statistics
orig = plt.plot(timeseries, color='blue',label='Original')
mean = plt.plot(movingAverage, color='red', label='Rolling Mean')
std = plt.plot(movingSTD, color='black', label= 'Rolling std')
plt.legend(loc='best')
plt.title=("Rolling Mean and Standard Deviation")
plt.show(block=False)
#Perform Dickey-Fuller test:
print('Results of Dickey-Fuller Test:')
dftest = adfuller(indexedDataset["like"], autolag='AIC')
dfoutput = pd.Series(dftest[0:4],index=['Test Statistics','p-value', '#Lags
Used','#Number of observations used'])
for key,value in dftest[4].items():
dfoutput['Critical Value (%s)'%key] = value
print(dfoutput)
test_stationarity(datasetLogScaleMinusMovingAverage)
exponentialDecayWeightAverage =
indexedDataset_logScale.ewm(halflife=12,min_periods=0,adjust=True).mean()
plt.plot(indexedDataset_logScale)
plt.plot(exponentialDecayWeightAverage, color='red')
datasetLogScaleMinusMovingAverageExponentialDecayAverage =
indexedDataset_logScale - exponentialDecayWeightAverage
test_stationarity(datasetLogScaleMinusMovingAverageExponentialDecayAverage)
datasetLogDiffShifting = indexedDataset_logScale -
indexedDataset_logScale.shift()
plt.plot(datasetLogDiffShifting)
datasetLogDiffShifting.dropna(inplace=True)
test_stationarity(datasetLogDiffShifting)
from statsmodels.tsa.seasonal import seasonal_decompose
decomposition = seasonal_decompose(indexedDataset_logScale)
trend = decomposition.trend
seasonal = decomposition.seasonal
residual = decomposition.resid
plt.subplot(411)
plt.plot(indexedDataset_logScale, label='Original')
plt.legend(loc='best')
plt.subplot(412)
plt.plot(trend, label='Trend')
plt.legend(loc='best')
plt.subplot(413)
plt.plot(seasonal,label="Seasonality")
plt.legend(loc='best')
plt.subplot(414)
plt.plot(residual, label='Residuals')
plt.legend(loc='best')
plt.tight_layout()
decomposedLogData = residual
decomposedLogData.dropna(inplace=True)
test_stationarity(decomposedLogData)
decomposedLogData = residual
decomposedLogData.dropna(inplace=True)
test_stationarity(decomposedLogData)
#ACF and PACF plates
from statsmodels.tsa.stattools import acf, pacf
lag_acf = acf(datasetLogDiffShifting, nlags=20)
lag_pacf = pacf(datasetLogDiffShifting, nlags=20, method="ols")
#plot ACF
plt.subplot(121)
plt.plot(lag_acf)
plt.axhline(y=0,linestyle='--',color='gray')
plt.axhline(y=-1.96/np.sqrt(len(datasetLogDiffShifting)),linestyle='--
',color='gray')
plt.axhline(y=1.96/np.sqrt(len(datasetLogDiffShifting)),linestyle='--
',color='gray')
# plt.title("Autocorrelation Function")
#Plot PACF
plt.subplot(122)
plt.plot(lag_pacf)
plt.axhline(y=0,linestyle='--',color='gray')
plt.axhline(y=-1.96/np.sqrt(len(datasetLogDiffShifting)),linestyle='--',color='gray')
plt.axhline(y=1.96/np.sqrt(len(datasetLogDiffShifting)),linestyle='--',color='gray')
# plt.title("Partial Autocorrelation Function")
plt.tight_layout()
from statsmodels.tsa.arima_model import ARIMA
#AR MODEL
model = ARIMA(indexedDataset_logScale, order=(2, 1, 2))
result_AR = model.fit(disp=-1)
plt.plot(datasetLogDiffShifting)
plt.plot(result_AR.fittedvalues, color='red')
print('RSS: %.4f'% sum((result_AR.fittedvalues-
datasetLogDiffShifting["like"])**2))
print('Plotting AR model')
#MA MODEL
model = ARIMA(indexedDataset_logScale, order=(2,1,2))
results_MA = model.fit(disp=-1)
plt.plot(datasetLogDiffShifting)
plt.plot(results_MA.fittedvalues, color='red')
print('RSS: %.4f'% sum((results_MA.fittedvalues-
datasetLogDiffShifting["like"])**2))
print('Plotting AR model')
model = ARIMA(indexedDataset_logScale, order=(2,1,2))
results_ARIMA = model.fit(disp=-1)
plt.plot(datasetLogDiffShifting)
plt.plot(results_ARIMA.fittedvalues, color="red")
print('RSS: %.4f'% sum((results_MA.fittedvalues-
datasetLogDiffShifting["like"])**2))
predictions_ARIMA_diff = pd.Series(results_ARIMA.fittedvalues, copy=True)
print(predictions_ARIMA_diff.head())
#Convert to cumulative sum
predictions_ARIMA_diff_cumsum = predictions_ARIMA_diff.cumsum()
print(predictions_ARIMA_diff_cumsum.head())
predictions_ARIMA_log = pd.Series(indexedDataset_logScale["like"].iloc[0],
index=indexedDataset_logScale.index)
predictions_ARIMA_log =
predictions_ARIMA_log.add(predictions_ARIMA_diff_cumsum,fill_value=0)
predictions_ARIMA_log.head()
predictions_ARIMA = np.exp(predictions_ARIMA_log)
plt.plot(indexedDataset)
plt.plot(predictions_ARIMA)
indexedDataset_logScale
results_ARIMA.plot_predict(1,264)
# x=results_ARIMA.forecast(steps=120)