def test_dates_from_range():
results = [datetime(1959, 3, 31, 0, 0),
datetime(1959, 6, 30, 0, 0),
datetime(1959, 9, 30, 0, 0),
datetime(1959, 12, 31, 0, 0),
datetime(1960, 3, 31, 0, 0),
datetime(1960, 6, 30, 0, 0),
datetime(1960, 9, 30, 0, 0),
datetime(1960, 12, 31, 0, 0),
datetime(1961, 3, 31, 0, 0),
datetime(1961, 6, 30, 0, 0),
datetime(1961, 9, 30, 0, 0),
datetime(1961, 12, 31, 0, 0),
datetime(1962, 3, 31, 0, 0),
datetime(1962, 6, 30, 0, 0)]
dt_range = dates_from_range('1959q1', '1962q2')
npt.assert_(results == dt_range)
# test with starting period not the first with length
results = results[2:]
dt_range = dates_from_range('1959q3', length=len(results))
npt.assert_(results == dt_range)
# check month
results = [datetime(1959, 3, 31, 0, 0),
datetime(1959, 4, 30, 0, 0),
datetime(1959, 5, 31, 0, 0),
datetime(1959, 6, 30, 0, 0),
datetime(1959, 7, 31, 0, 0),
datetime(1959, 8, 31, 0, 0),
datetime(1959, 9, 30, 0, 0),
datetime(1959, 10, 31, 0, 0),
datetime(1959, 11, 30, 0, 0),
datetime(1959, 12, 31, 0, 0),
datetime(1960, 1, 31, 0, 0),
datetime(1960, 2, 28, 0, 0),
datetime(1960, 3, 31, 0, 0),
datetime(1960, 4, 30, 0, 0),
datetime(1960, 5, 31, 0, 0),
datetime(1960, 6, 30, 0, 0),
datetime(1960, 7, 31, 0, 0),
datetime(1960, 8, 31, 0, 0),
datetime(1960, 9, 30, 0, 0),
datetime(1960, 10, 31, 0, 0),
datetime(1960, 12, 31, 0, 0),
datetime(1961, 1, 31, 0, 0),
datetime(1961, 2, 28, 0, 0),
datetime(1961, 3, 31, 0, 0),
datetime(1961, 4, 30, 0, 0),
datetime(1961, 5, 31, 0, 0),
datetime(1961, 6, 30, 0, 0),
datetime(1961, 7, 31, 0, 0),
datetime(1961, 8, 31, 0, 0),
datetime(1961, 9, 30, 0, 0),
datetime(1961, 10, 31, 0, 0)]
dt_range = dates_from_range("1959m3", length=len(results))
def test_acovf2d():
dta = sunspots.load_pandas().data
dta.index = Index(dates_from_range('1700', '2008'))
del dta["YEAR"]
res = acovf(dta)
assert_equal(res, acovf(dta.values))
X = np.random.random((10,2))
assert_raises(ValueError, acovf, X)
def test_acovf2d():
dta = sunspots.load_pandas().data
dta.index = Index(dates_from_range('1700', '2008'))
del dta["YEAR"]
res = acovf(dta)
assert_equal(res, acovf(dta.values))
X = np.random.random((10, 2))
assert_raises(ValueError, acovf, X)
def test_hpfilter_pandas():
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
cycle, trend = hpfilter(dta["realgdp"])
ndcycle, ndtrend = hpfilter(dta['realgdp'].values)
assert_equal(cycle.values, ndcycle)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.name, "realgdp")
def test_hpfilter_pandas():
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
cycle, trend = hpfilter(dta["realgdp"])
ndcycle, ndtrend = hpfilter(dta['realgdp'].values)
assert_equal(cycle.values, ndcycle)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.name, "realgdp")
def test_dates_from_range():
results = [datetime(1959, 3, 31, 0, 0),
datetime(1959, 6, 30, 0, 0),
datetime(1959, 9, 30, 0, 0),
datetime(1959, 12, 31, 0, 0),
datetime(1960, 3, 31, 0, 0),
datetime(1960, 6, 30, 0, 0),
datetime(1960, 9, 30, 0, 0),
datetime(1960, 12, 31, 0, 0),
datetime(1961, 3, 31, 0, 0),
datetime(1961, 6, 30, 0, 0),
datetime(1961, 9, 30, 0, 0),
datetime(1961, 12, 31, 0, 0),
datetime(1962, 3, 31, 0, 0),
datetime(1962, 6, 30, 0, 0)]
dt_range = dates_from_range('1959q1', '1962q2')
npt.assert_(results == dt_range)
def setupClass(cls):
if not _have_x13:
raise SkipTest('X13/X12 not available')
import pandas as pd
from statsmodels.datasets import macrodata, co2
dta = macrodata.load_pandas().data
dates = dates_from_range('1959Q1', '2009Q3')
index = pd.DatetimeIndex(dates)
dta.index = index
cls.quarterly_data = dta.dropna()
dta = co2.load_pandas().data
dta['co2'] = dta.co2.interpolate()
cls.monthly_data = dta.resample('M')
cls.monthly_start_data = dta.resample('MS')
def setupClass(cls):
if not _have_x13:
raise SkipTest("X13/X12 not available")
import pandas as pd
from statsmodels.datasets import macrodata, co2
dta = macrodata.load_pandas().data
dates = dates_from_range("1959Q1", "2009Q3")
index = pd.DatetimeIndex(dates)
dta.index = index
cls.quarterly_data = dta.dropna()
dta = co2.load_pandas().data
dta["co2"] = dta.co2.interpolate()
cls.monthly_data = dta.resample("M")
cls.monthly_start_data = dta.resample("MS")
def test_bking_pandas():
# 1d
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
filtered = bkfilter(dta["infl"])
nd_filtered = bkfilter(dta['infl'].values)
assert_equal(filtered.values, nd_filtered)
assert_equal(filtered.index[0], datetime(1962, 3, 31))
assert_equal(filtered.index[-1], datetime(2006, 9, 30))
assert_equal(filtered.name, "infl")
#2d
filtered = bkfilter(dta[["infl","unemp"]])
nd_filtered = bkfilter(dta[['infl', 'unemp']].values)
assert_equal(filtered.values, nd_filtered)
assert_equal(filtered.index[0], datetime(1962, 3, 31))
assert_equal(filtered.index[-1], datetime(2006, 9, 30))
assert_equal(filtered.columns.values, ["infl", "unemp"])
def test_cfitz_pandas():
# 1d
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
cycle, trend = cffilter(dta["infl"])
ndcycle, ndtrend = cffilter(dta['infl'].values)
assert_allclose(cycle.values, ndcycle, rtol=1e-14)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.name, "infl")
#2d
cycle, trend = cffilter(dta[["infl","unemp"]])
ndcycle, ndtrend = cffilter(dta[['infl', 'unemp']].values)
assert_allclose(cycle.values, ndcycle, rtol=1e-14)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.columns.values, ["infl", "unemp"])
def test_bking_pandas():
# 1d
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
filtered = bkfilter(dta["infl"])
nd_filtered = bkfilter(dta['infl'].values)
assert_equal(filtered.values, nd_filtered)
assert_equal(filtered.index[0], datetime(1962, 3, 31))
assert_equal(filtered.index[-1], datetime(2006, 9, 30))
assert_equal(filtered.name, "infl")
#2d
filtered = bkfilter(dta[["infl","unemp"]])
nd_filtered = bkfilter(dta[['infl', 'unemp']].values)
assert_equal(filtered.values, nd_filtered)
assert_equal(filtered.index[0], datetime(1962, 3, 31))
assert_equal(filtered.index[-1], datetime(2006, 9, 30))
assert_equal(filtered.columns.values, ["infl", "unemp"])
def test_cfitz_pandas():
# 1d
dta = macrodata.load_pandas().data
index = Index(dates_from_range('1959Q1', '2009Q3'))
dta.index = index
cycle, trend = cffilter(dta["infl"])
ndcycle, ndtrend = cffilter(dta['infl'].values)
assert_allclose(cycle.values, ndcycle, rtol=1e-14)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.name, "infl")
#2d
cycle, trend = cffilter(dta[["infl","unemp"]])
ndcycle, ndtrend = cffilter(dta[['infl', 'unemp']].values)
assert_allclose(cycle.values, ndcycle, rtol=1e-14)
assert_equal(cycle.index[0], datetime(1959, 3, 31))
assert_equal(cycle.index[-1], datetime(2009, 9, 30))
assert_equal(cycle.columns.values, ["infl", "unemp"])
def setupClass(cls):
if not _have_x13:
raise SkipTest('X13/X12 not available')
import pandas as pd
from statsmodels.datasets import macrodata, co2
dta = macrodata.load_pandas().data
dates = dates_from_range('1959Q1', '2009Q3')
index = pd.DatetimeIndex(dates)
dta.index = index
cls.quarterly_data = dta.dropna()
dta = co2.load_pandas().data
dta['co2'] = dta.co2.interpolate()
cls.monthly_data = dta.resample('M')
# change in pandas 0.18 resample is deferred object
if not isinstance(cls.monthly_data, (pd.DataFrame, pd.Series)):
cls.monthly_data = cls.monthly_data.mean()
cls.monthly_start_data = dta.resample('MS')
if not isinstance(cls.monthly_start_data, (pd.DataFrame, pd.Series)):
cls.monthly_start_data = cls.monthly_start_data.mean()
def setupClass(cls):
if not _have_x13:
raise SkipTest('X13/X12 not available')
import pandas as pd
from statsmodels.datasets import macrodata, co2
dta = macrodata.load_pandas().data
dates = dates_from_range('1959Q1', '2009Q3')
index = pd.DatetimeIndex(dates)
dta.index = index
cls.quarterly_data = dta.dropna()
dta = co2.load_pandas().data
dta['co2'] = dta.co2.interpolate()
cls.monthly_data = dta.resample('M')
# change in pandas 0.18 resample is deferred object
if not isinstance(cls.monthly_data, (pd.DataFrame, pd.Series)):
cls.monthly_data = cls.monthly_data.mean()
cls.monthly_start_data = dta.resample('MS')
if not isinstance(cls.monthly_start_data, (pd.DataFrame, pd.Series)):
cls.monthly_start_data = cls.monthly_start_data.mean()
from statsmodels.datasets.macrodata import load_pandas
from statsmodels.tsa.base.datetools import dates_from_range
from statsmodels.tsa.arima_model import ARIMA
import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm
plt.interactive(False)
# let's examine an ARIMA model of CPI
cpi = load_pandas().data["cpi"]
dates = dates_from_range("1959q1", "2009q3")
cpi.index = dates
res = ARIMA(cpi, (1,1,1), freq='Q').fit()
print res.summary()
# we can look at the series
cpi.diff().plot()
# maybe logs are better
log_cpi = np.log(cpi)
# check the ACF and PCF plots
acf, confint_acf = sm.tsa.acf(log_cpi.diff().values[1:], confint=95)
# center the confidence intervals about zero
#confint_acf -= confint_acf.mean(1)[:,None]
pacf = sm.tsa.pacf(log_cpi.diff().values[1:], method='ols')
# confidence interval is now an option to pacf
from scipy import stats
confint_pacf = stats.norm.ppf(1-.025) * np.sqrt(1/202.)
#print newdf.head()
#===========================
# TIME SERIES ANALYSIS
#===========================
# Building ARIMA model
from statsmodels.tsa.base.datetools import dates_from_range
trainWTI = newdf[:int(0.95 * len(newdf))]
# 2012m12 means to start counting months from the 12th month of 2012
# To know the starting month, print trainWTI.head()
dates1 = dates_from_range('2012m1', length=len(trainWTI.WTI))
trainWTI.index = dates1
trainWTI = trainWTI[['WTI']]
print trainWTI.tail()
# Determine whether AR or MA terms are needed to correct any
# autocorrelation that remains in the series.
# Looking at the autocorrelation function (ACF) and partial autocorrelation (PACF) plots of the series,
# it's possible to identify the numbers of AR and/or MA terms that are needed
# In this example, the autocorrelations are significant for a large number of lags,
# but perhaps the autocorrelations at lags 2 and above are merely due to the propagation of the autocorrelation at lag 1.
# This is confirmed by the PACF plot.
# RULES OF THUMB:
# Rule 1: If the PACF of the differenced series displays a sharp cutoff and/or the lag-1 autocorrelation is positive,
# then consider adding an AR term to the model. The lag at which the PACF cuts off is the indicated number of AR terms.
from statsmodels.datasets.macrodata import load_pandas
from statsmodels.tsa.base.datetools import dates_from_range
from statsmodels.tsa.arima_model import ARIMA
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
import statsmodels.api as sm
plt.interactive(False)
# 让我们以 CPI 的 ARIMA 模型来举例
cpi = load_pandas().data['cpi']
dates = dates_from_range('1959q1', '2009q3')
cpi.index = dates
res = ARIMA(cpi, (1, 1, 1), freq='Q').fit()
print(res.summary())
# 我们可以画图查看序列
cpi.diff().plot()
# 或许查看日志会更好
log_cpi = np.log(cpi)
# 检查 ACF 和 PCF 图
acf, confint_acf = sm.tsa.acf(log_cpi.diff().values[1:], confint=95)
# 将置信区间定为零
# TODO: demean? --> confint_acf -= confint_acf.mean(1)[:, None]
pacf = sm.tsa.pacf(log_cpi.diff().values[1:], method='ols')
# 置信区间是 pacf 的一个选项
confint_pacf = stats.norm.ppf(1 - .025) * np.sqrt(1 / 202.)
#===========================
# TIME SERIES ANALYSIS
#===========================
# Building ARIMA model
from statsmodels.tsa.base.datetools import dates_from_range
trainWTI = newdf[:int(0.95*len(newdf))]
# 2012m12 means to start counting months from the 12th month of 2012
# To know the starting month, print trainWTI.head()
dates1 = dates_from_range('2012m1', length=len(trainWTI.WTI))
trainWTI.index = dates1
trainWTI = trainWTI[['WTI']]
print trainWTI.tail()
# Determine whether AR or MA terms are needed to correct any
# autocorrelation that remains in the series.
# Looking at the autocorrelation function (ACF) and partial autocorrelation (PACF) plots of the series,
# it's possible to identify the numbers of AR and/or MA terms that are needed
# In this example, the autocorrelations are significant for a large number of lags,
# but perhaps the autocorrelations at lags 2 and above are merely due to the propagation of the autocorrelation at lag 1.
# This is confirmed by the PACF plot.
# RULES OF THUMB:
# Rule 1: If the PACF of the differenced series displays a sharp cutoff and/or the lag-1 autocorrelation is positive,
# then consider adding an AR term to the model. The lag at which the PACF cuts off is the indicated number of AR terms.
from __future__ import print_function
from statsmodels.datasets.macrodata import load_pandas
from statsmodels.tsa.base.datetools import dates_from_range
from statsmodels.tsa.arima_model import ARIMA
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
import statsmodels.api as sm
plt.interactive(False)
# let's examine an ARIMA model of CPI
cpi = load_pandas().data['cpi']
dates = dates_from_range('1959q1', '2009q3')
cpi.index = dates
res = ARIMA(cpi, (1, 1, 1), freq='Q').fit()
print(res.summary())
# we can look at the series
cpi.diff().plot()
# maybe logs are better
log_cpi = np.log(cpi)
# check the ACF and PCF plots
acf, confint_acf = sm.tsa.acf(log_cpi.diff().values[1:], confint=95)
# center the confidence intervals about zero
# TODO: demean? --> confint_acf -= confint_acf.mean(1)[:, None]
pacf = sm.tsa.pacf(log_cpi.diff().values[1:], method='ols')
# confidence interval is now an option to pacf
