def plot5(self):
df1 = pd.read_csv('data/airline_passengers.csv',
index_col='Month',
parse_dates=True)
df1.index.freq = 'MS'
df2 = pd.read_csv('data/DailyTotalFemaleBirths.csv',
index_col='Date',
parse_dates=True)
df2.index.freq = 'D'
df = pd.DataFrame({'a': [13, 5, 11, 12, 9]})
arr = acovf(df['a'])
arr2 = acovf(df['a'], unbiased=True)
arr3 = acf(df['a'])
arr4 = pacf_yw(df['a'], nlags=4, method='mle')
lag_plot(df1['Thousands of Passengers'])
lag_plot(df2['Births'])
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.statespace.tools import diff
title = 'Autocorrelation: Daily Female Births'
lags = 40
plot_acf(df2, title=title, lags=lags)
title = 'Autocorrelation: Airline Passengers'
lags = 40
plot_acf(df1, title=title, lags=lags)
plt.interactive(False)
plt.show()
def test_ld(self):
pacfyw = pacf_yw(self.x, nlags=40, method="mle")
pacfld = pacf(self.x, nlags=40, method="ldb")
assert_almost_equal(pacfyw, pacfld, DECIMAL_8)
pacfyw = pacf(self.x, nlags=40, method="yw")
pacfld = pacf(self.x, nlags=40, method="ldu")
assert_almost_equal(pacfyw, pacfld, DECIMAL_8)
def test_ld(self):
pacfyw = pacf_yw(self.x, nlags=40, method="mle")
pacfld = pacf(self.x, nlags=40, method="ldb")
assert_almost_equal(pacfyw, pacfld, DECIMAL_8)
pacfyw = pacf(self.x, nlags=40, method="yw")
pacfld = pacf(self.x, nlags=40, method="ldu")
assert_almost_equal(pacfyw, pacfld, DECIMAL_8)
def test_pacf_burg():
rnd = np.random.RandomState(12345)
e = rnd.randn(10001)
y = e[1:] + 0.5 * e[:-1]
pacf, sigma2 = pacf_burg(y, 10)
yw_pacf = pacf_yw(y, 10)
assert_allclose(pacf, yw_pacf, atol=5e-4)
# Internal consistency check between pacf and sigma2
ye = y - y.mean()
s2y = ye.dot(ye) / 10000
pacf[0] = 0
sigma2_direct = s2y * np.cumprod(1 - pacf ** 2)
assert_allclose(sigma2, sigma2_direct, atol=1e-3)
def test_pacf_burg():
rnd = np.random.RandomState(12345)
e = rnd.randn(10001)
y = e[1:] + 0.5 * e[:-1]
pacf, sigma2 = pacf_burg(y, 10)
yw_pacf = pacf_yw(y, 10)
assert_allclose(pacf, yw_pacf, atol=5e-4)
# Internal consistency check between pacf and sigma2
ye = y - y.mean()
s2y = ye.dot(ye) / 10000
pacf[0] = 0
sigma2_direct = s2y * np.cumprod(1 - pacf ** 2)
assert_allclose(sigma2, sigma2_direct, atol=1e-3)
def test_yw(self):
pacfyw = pacf_yw(self.x, nlags=40, method="mle")
assert_almost_equal(pacfyw[1:], self.pacfyw, DECIMAL_8)
def test_pacf_yw():
pacfyw = tsa.pacf_yw(x100, 20, method='mle')
assert_array_almost_equal(mlpacf.pacf100.ravel(), pacfyw, 1)
pacfyw = tsa.pacf_yw(x1000, 20, method='mle')
assert_array_almost_equal(mlpacf.pacf1000.ravel(), pacfyw, 2)
def test_yw(self):
pacfyw = pacf_yw(self.x, nlags=40, method="mle")
assert_almost_equal(pacfyw[1:], self.pacfyw, DECIMAL_8)
#break
##
# Across all tracks
# Still not worrying about proper circular stats or differing time steps.
from statsmodels.tsa.stattools import pacf_yw
recs = []
for tag in df.index.values:
track = df.loc[tag, 'track']
rec = {}
seg = track[:-1]
nlag = min(len(seg) // 2 - 1, 20)
pa_hdg = pacf_yw(seg['swim_hdg_rel_uw'], nlags=nlag, method='mle')
pa_spd = pacf_yw(seg['swim_speed'], nlags=nlag, method='mle')
for l in range(len(pa_hdg)):
recs.append(
dict(lag=l, tag=tag, pacf_hdg=pa_hdg[l], pacf_spd=pa_spd[l]))
pacf_df = pd.DataFrame(recs)
plt.figure(70).clf()
fig, axs = plt.subplots(2, 1, num=70)
sns.boxplot(x='lag', y='pacf_hdg', data=pacf_df, ax=axs[0])
sns.boxplot(x='lag', y='pacf_spd', data=pacf_df, ax=axs[1])
fig.savefig(os.path.join(fig_dir, 'pacf_boxplot-hdg-speed.png'))
parse_dates=True)
df2.index.freq = 'D'
df1.head()
df2.head()
import warnings
warnings.filterwarnings('ignore') #to ignore the warnings which is unnecessary
df = pd.DataFrame({'a': [12, 5, 11, 12, 9]})
acf(df['a'])
pacf_yw(df['a'], nlags=4, method='mle')
pacf_yw(df['a'], nlags=4, method='unbiased')
pacf_ols(df['a'], nlags=4)
'''
Method in the above use different types of calculation corralation itself
'''
from pandas.plotting import lag_plot
lag_plot(df1['Thousands of Passengers'])
lag_plot(df2['Births'])
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
def test_pacf_yw():
pacfyw = tsa.pacf_yw(x100, 20, method='mle')
assert_array_almost_equal(mlpacf.pacf100.ravel(), pacfyw, 1)
pacfyw = tsa.pacf_yw(x1000, 20, method='mle')
assert_array_almost_equal(mlpacf.pacf1000.ravel(), pacfyw, 2)
file1 = r'C:\Damon\Udemy\Python for Time Series Data Analysis\TSA_COURSE_NOTEBOOKS\Data\airline_passengers.csv'
df1 = pd.read_csv(file1, index_col=0, parse_dates=True)
df1.rename(columns={'Thousands of Passengers': 'Pass_K'}, inplace=True)
df1.index.freq = 'MS'
file2 = r'C:\Damon\Udemy\Python for Time Series Data Analysis\TSA_COURSE_NOTEBOOKS\Data\DailyTotalFemaleBirths.csv'
df2 = pd.read_csv(file2, index_col='Date', parse_dates=True)
df2.index.freq = 'D'
df1.head()
df2.head()
df = pd.DataFrame({'a': [13, 5, 11, 12, 9]})
acf(df['a'])
pacf_yw(df['a'], nlags=4, method='mle')
pacf_ols(df['a'], nlags=4)
from pandas.plotting import lag_plot
lag_plot(df1['Pass_K']) # STRONG CORRELATION
lag_plot(df2['Births']) # WEAK/NO CORRELATION
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
plot_acf(df1, lags=40)
plot_acf(df2, lags=40)
plot_pacf(df2, lags=40, title='PACF BIRTHS')
plot_pacf(df1, lags=40, title='PACF Passengers')
def test_pacf_yw():
pacfyw = stattools.pacf_yw(x100, 20, method="mle")
assert_array_almost_equal(mlpacf.pacf100.ravel(), pacfyw, 1)
pacfyw = stattools.pacf_yw(x1000, 20, method="mle")
assert_array_almost_equal(mlpacf.pacf1000.ravel(), pacfyw, 2)
