%matplotlib inline
import numpy as np
import statsmodels.api as sm
import matplotlib.pyplot as plt
from statsmodels.sandbox.regression.predstd import wls_prediction_std
np.random.seed(9876789)

nsample = 100 #样本数量

x = np.linspace(0, 10, 100)
X = np.column_stack((x, x**2))

beta = np.array([1, 0.1, 10])
e = np.random.normal(size=nsample)
X = sm.add_constant(X)
y = np.dot(X, beta) + e

model = sm.OLS(y, X) 
results = model.fit()
print(results.summary())

print('Parameters: ', results.params)
print('R2: ', results.rsquared)

y_fitted = results.fittedvalues
fig, ax = plt.subplots(figsize=(8,6))
ax.plot(x, y, 'o', label='data')
ax.plot(x, y_fitted, 'r--.',label='OLS')
ax.legend(loc='best')

%matplotlib inline
import numpy as np
import statsmodels.api as sm
import pandas as pd
from statsmodels.tsa.arima_process import arma_generate_sample
np.random.seed(12345)

arparams = np.array([.75, -.25])
maparams = np.array([.65, .35])

arparams = np.r_[1, -arparams]
maparams = np.r_[1, maparams]
nobs = 250
y = arma_generate_sample(arparams, maparams, nobs)

dates = sm.tsa.datetools.dates_from_range('1980m1', length=nobs)
y = pd.Series(y, index=dates)
arma_mod = sm.tsa.ARMA(y, order=(2,2))
arma_res = arma_mod.fit(trend='nc', disp=-1)

import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(10,8))
fig = arma_res.plot_predict(start='1999-06-30', end='2001-05-31', ax=ax)
legend = ax.legend(loc='upper left')

%matplotlib inline
from statsmodels.compat import lzip
import numpy as np
import pandas as pd
import statsmodels.formula.api as smf
import statsmodels.stats.api as sms
import matplotlib.pyplot as plt

url = 'https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/HistData/Guerry.csv'
dat = pd.read_csv(url)

results = smf.ols('Lottery ~ Literacy + np.log(Pop1831)', data=dat).fit()

print(results.summary())

name = ['Jarque-Bera', 'Chi^2 two-tail prob.', 'Skew', 'Kurtosis']
test = sms.jarque_bera(results.resid)
lzip(name, test)
####结果
[('Jarque-Bera', 3.3936080248431666),
('Chi^2 two-tail prob.', 0.1832683123166337),
('Skew', -0.48658034311223375),
('Kurtosis', 3.003417757881633)]

name = ['Chi^2', 'Two-tail probability']
test = sms.omni_normtest(results.resid)
lzip(name, test)
####结果
[('Chi^2', 3.713437811597181), ('Two-tail probability', 0.15618424580304824)]

name = ['Lagrange multiplier statistic', 'p-value',
    'f-value', 'f p-value']
test = sms.het_breuschpagan(results.resid, results.model.exog)
lzip(name, test)
###结果
[('Lagrange multiplier statistic', 4.893213374093957),
('p-value', 0.08658690502352209),
('f-value', 2.503715946256434),
('f p-value', 0.08794028782673029)]
Goldfeld-Quandt test

np.linalg.cond(results.model.exog)