Python OLS.summary方法代码示例

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
    def test_OLSsummary_rsquared_label(self):
        # Check that the "uncentered" label is correctly added after rsquared
        x = [1, 5, 7, 3, 5, 2, 5, 3]
        y = [6, 4, 2, 7, 4, 9, 10, 2]
        reg_with_constant = OLS(y, x, hasconst=True).fit()
        assert 'R-squared:' in str(reg_with_constant.summary2())
        assert 'R-squared:' in str(reg_with_constant.summary())

        reg_without_constant = OLS(y, x, hasconst=False).fit()
        assert 'R-squared (uncentered):' in str(reg_without_constant.summary2())
        assert 'R-squared (uncentered):' in str(reg_without_constant.summary())

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
    def test_regression_with_tuples(self):
        i = pandas.Series([1, 2, 3, 4] * 10, name="i")
        y = pandas.Series([1, 2, 3, 4, 5] * 8, name="y")
        x = pandas.Series([1, 2, 3, 4, 5, 6, 7, 8] * 5, name="x")

        df = pandas.DataFrame(index=i.index)
        df = df.join(i)
        endo = df.join(y)
        exo = df.join(x)
        endo_groups = endo.groupby("i")
        exo_groups = exo.groupby("i")
        exo_df = exo_groups.agg([np.sum, np.max])
        endo_df = endo_groups.agg([np.sum, np.max])
        reg = OLS(exo_df[[("x", "sum")]], endo_df).fit()
        interesting_lines = []
        import warnings
        with warnings.catch_warnings():
            # Catch ominormal warning, not interesting here
            warnings.simplefilter("ignore")
            for line in str(reg.summary()).splitlines():
                if "_" in line:
                    interesting_lines.append(line[:38])

        desired = ["Dep. Variable:                  x_sum ",
                   "y_sum          1.4595      0.209      ",
                   "y_amax         0.2432      0.035      "]

        assert_equal(sorted(desired), sorted(interesting_lines))

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def test_ols_summary_rsquared_label():
    # Check that the "uncentered" label is correctly added after rsquared
    x = [1, 5, 7, 3, 5, 2, 5, 3]
    y = [6, 4, 2, 7, 4, 9, 10, 2]
    reg_with_constant = OLS(y, add_constant(x)).fit()
    r2_str = 'R-squared:'
    with pytest.warns(UserWarning):
        assert r2_str in str(reg_with_constant.summary2())
    with pytest.warns(UserWarning):
        assert r2_str in str(reg_with_constant.summary())

    reg_without_constant = OLS(y, x, hasconst=False).fit()
    r2_str = 'R-squared (uncentered):'
    with pytest.warns(UserWarning):
        assert r2_str in str(reg_without_constant.summary2())
    with pytest.warns(UserWarning):
        assert r2_str in str(reg_without_constant.summary())

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def test_fvalue_only_constant():
    # if only constant in model, return nan see #3642
    nobs = 20
    np.random.seed(2)
    x = np.ones(nobs)
    y = np.random.randn(nobs)

    from statsmodels.regression.linear_model import OLS, WLS

    res = OLS(y, x).fit(cov_type='hac', cov_kwds={'maxlags': 3})
    assert_(np.isnan(res.fvalue))
    assert_(np.isnan(res.f_pvalue))
    res.summary()

    res = WLS(y, x).fit(cov_type='HC1')
    assert_(np.isnan(res.fvalue))
    assert_(np.isnan(res.f_pvalue))
    res.summary()

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def test_fvalue_implicit_constant():
    nobs = 100
    np.random.seed(2)
    x = np.random.randn(nobs, 1)
    x = ((x > 0) == [True, False]).astype(int)
    y = x.sum(1) + np.random.randn(nobs)

    from statsmodels.regression.linear_model import OLS, WLS

    res = OLS(y, x).fit(cov_type='HC1')
    assert_(np.isnan(res.fvalue))
    assert_(np.isnan(res.f_pvalue))
    res.summary()

    res = WLS(y, x).fit(cov_type='HC1')
    assert_(np.isnan(res.fvalue))
    assert_(np.isnan(res.f_pvalue))
    res.summary()

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def test_summary_as_latex():
    # GH#734
    import re
    dta = longley.load_pandas()
    X = dta.exog
    X["constant"] = 1
    y = dta.endog
    res = OLS(y, X).fit()
    with pytest.warns(UserWarning):
        table = res.summary().as_latex()
    # replace the date and time
    table = re.sub("(?<=\n\\\\textbf\\{Date:\\}             &).+?&",
                   " Sun, 07 Apr 2013 &", table)
    table = re.sub("(?<=\n\\\\textbf\\{Time:\\}             &).+?&",
                   "     13:46:07     &", table)

    expected = """\\begin{center}
\\begin{tabular}{lclc}
\\toprule
\\textbf{Dep. Variable:}    &      TOTEMP      & \\textbf{  R-squared:         } &     0.995   \\\\
\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.992   \\\\
\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     330.3   \\\\
\\textbf{Date:}             & Sun, 07 Apr 2013 & \\textbf{  Prob (F-statistic):} &  4.98e-10   \\\\
\\textbf{Time:}             &     13:46:07     & \\textbf{  Log-Likelihood:    } &   -109.62   \\\\
\\textbf{No. Observations:} &          16      & \\textbf{  AIC:               } &     233.2   \\\\
\\textbf{Df Residuals:}     &           9      & \\textbf{  BIC:               } &     238.6   \\\\
\\textbf{Df Model:}         &           6      & \\textbf{                     } &             \\\\
\\bottomrule
\\end{tabular}
\\begin{tabular}{lcccccc}
                  & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\
\\midrule
\\textbf{GNPDEFL}  &      15.0619  &       84.915     &     0.177  &         0.863        &     -177.029    &      207.153     \\\\
\\textbf{GNP}      &      -0.0358  &        0.033     &    -1.070  &         0.313        &       -0.112    &        0.040     \\\\
\\textbf{UNEMP}    &      -2.0202  &        0.488     &    -4.136  &         0.003        &       -3.125    &       -0.915     \\\\
\\textbf{ARMED}    &      -1.0332  &        0.214     &    -4.822  &         0.001        &       -1.518    &       -0.549     \\\\
\\textbf{POP}      &      -0.0511  &        0.226     &    -0.226  &         0.826        &       -0.563    &        0.460     \\\\
\\textbf{YEAR}     &    1829.1515  &      455.478     &     4.016  &         0.003        &      798.788    &     2859.515     \\\\
\\textbf{constant} &   -3.482e+06  &      8.9e+05     &    -3.911  &         0.004        &     -5.5e+06    &    -1.47e+06     \\\\
\\bottomrule
\\end{tabular}
\\begin{tabular}{lclc}
\\textbf{Omnibus:}       &  0.749 & \\textbf{  Durbin-Watson:     } &    2.559  \\\\
\\textbf{Prob(Omnibus):} &  0.688 & \\textbf{  Jarque-Bera (JB):  } &    0.684  \\\\
\\textbf{Skew:}          &  0.420 & \\textbf{  Prob(JB):          } &    0.710  \\\\
\\textbf{Kurtosis:}      &  2.434 & \\textbf{  Cond. No.          } & 4.86e+09  \\\\
\\bottomrule
\\end{tabular}
%\\caption{OLS Regression Results}
\\end{center}

Warnings: \\newline
 [1] Standard Errors assume that the covariance matrix of the errors is correctly specified. \\newline
 [2] The condition number is large, 4.86e+09. This might indicate that there are \\newline
 strong multicollinearity or other numerical problems."""
    assert_equal(table, expected)

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def test_summary():
    # test 734
    import re
    dta = longley.load_pandas()
    X = dta.exog
    X["constant"] = 1
    y = dta.endog
    with warnings.catch_warnings(record=True):
        res = OLS(y, X).fit()
        table = res.summary().as_latex()
    # replace the date and time
    table = re.sub("(?<=\n\\\\textbf\{Date:\}             &).+?&",
                   " Sun, 07 Apr 2013 &", table)
    table = re.sub("(?<=\n\\\\textbf\{Time:\}             &).+?&",
                   "     13:46:07     &", table)

    expected = """\\begin{center}
\\begin{tabular}{lclc}
\\toprule
\\textbf{Dep. Variable:}    &      TOTEMP      & \\textbf{  R-squared:         } &     0.995   \\\\
\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.992   \\\\
\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     330.3   \\\\
\\textbf{Date:}             & Sun, 07 Apr 2013 & \\textbf{  Prob (F-statistic):} &  4.98e-10   \\\\
\\textbf{Time:}             &     13:46:07     & \\textbf{  Log-Likelihood:    } &   -109.62   \\\\
\\textbf{No. Observations:} &          16      & \\textbf{  AIC:               } &     233.2   \\\\
\\textbf{Df Residuals:}     &           9      & \\textbf{  BIC:               } &     238.6   \\\\
\\textbf{Df Model:}         &           6      & \\textbf{                     } &             \\\\
\\bottomrule
\\end{tabular}
\\begin{tabular}{lccccc}
                  & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$>$$|$t$|$} & \\textbf{[95.0\\% Conf. Int.]}  \\\\
\\midrule
\\textbf{GNPDEFL}  &      15.0619  &       84.915     &     0.177  &         0.863        &      -177.029   207.153       \\\\
\\textbf{GNP}      &      -0.0358  &        0.033     &    -1.070  &         0.313        &        -0.112     0.040       \\\\
\\textbf{UNEMP}    &      -2.0202  &        0.488     &    -4.136  &         0.003        &        -3.125    -0.915       \\\\
\\textbf{ARMED}    &      -1.0332  &        0.214     &    -4.822  &         0.001        &        -1.518    -0.549       \\\\
\\textbf{POP}      &      -0.0511  &        0.226     &    -0.226  &         0.826        &        -0.563     0.460       \\\\
\\textbf{YEAR}     &    1829.1515  &      455.478     &     4.016  &         0.003        &       798.788  2859.515       \\\\
\\textbf{constant} &   -3.482e+06  &      8.9e+05     &    -3.911  &         0.004        &      -5.5e+06 -1.47e+06       \\\\
\\bottomrule
\\end{tabular}
\\begin{tabular}{lclc}
\\textbf{Omnibus:}       &  0.749 & \\textbf{  Durbin-Watson:     } &    2.559  \\\\
\\textbf{Prob(Omnibus):} &  0.688 & \\textbf{  Jarque-Bera (JB):  } &    0.684  \\\\
\\textbf{Skew:}          &  0.420 & \\textbf{  Prob(JB):          } &    0.710  \\\\
\\textbf{Kurtosis:}      &  2.434 & \\textbf{  Cond. No.          } & 4.86e+09  \\\\
\\bottomrule
\\end{tabular}
%\\caption{OLS Regression Results}
\\end{center}"""
    assert_equal(table, expected)

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
    def test_OLSsummary(self):
        # Test that latex output of regular OLS output still contains
        # multiple tables

        x = [1,5,7,3,5]
        x = add_constant(x)
        y1 = [6,4,2,7,4]
        reg1 = OLS(y1,x).fit()
        with warnings.catch_warnings():
            warnings.simplefilter("ignore")
            actual = reg1.summary().as_latex()
        string_to_find = r'''\end{tabular}
\begin{tabular}'''
        result = string_to_find in actual
        assert(result is True)

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
def regression(aspects, dataset):
    asps = list(set(dataset.columns).intersection(aspects))
    asps.sort()
    
    aspsMP = list()
    for asp in asps:
        minus = asp+'_minus'
        dataset[minus] = dataset.apply(lambda x: 1 if x[asp] and x[asp+'sent'] == -1 else 0, axis=1)    
        aspsMP.append(minus)
         
        plus = asp+'_plus'
        dataset[plus] = dataset.apply(lambda x: 1 if x[asp] and x[asp+'sent'] == 1 else 0, axis=1)    
        aspsMP.append(plus)
         
#         overall = 'a_'+asp
#         dataset[overall] = dataset.apply(lambda x: x[asp]*x[asp+'sent'], axis=1)    
#         aspsMP.append(overall)

        neutral = asp+'_neutral'
        dataset[neutral] = dataset.apply(lambda x: 1 if x[asp] and x[asp+'sent'] == 0 else 0, axis=1)    
        aspsMP.append(neutral)
        
#         aspsMP.append(asp+'sent')
        
        
#     MINUS
#     PLUS
    
    aspsMP.sort()
    dataset['intercept'] = np.ones(len(dataset))
    aspsMP = ['intercept'] + aspsMP
#     print(len(aspects),len(asps))
    model = OLS(dataset['stars'], dataset[aspsMP]).fit()
#     model.summary
#     print(model.params)
#     print(model.pvalues)
    
    return model.summary()

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
    def split(self,X,Y,max_splits=1000):
        """
        - we don't actually need X but we take it for consistency
        """

        nsubs=len(Y)

        # cycle through until we find a split that is good enough

        runctr=0
        best_pval=0.
        while 1:
            runctr+=1
            cv=KFold(n_splits=self.nfolds,shuffle=True)

            idx=N.zeros((nsubs,self.nfolds)) # this is the design matrix
            folds=[]
            ctr=0
            for train,test in cv.split(Y):
                idx[test,ctr]=1
                folds.append([train,test])
                ctr+=1

            lm_y=OLS(Y-N.mean(Y),idx).fit()

            if lm_y.f_pvalue>best_pval:
                best_pval=lm_y.f_pvalue
                best_folds=folds

            if lm_y.f_pvalue>self.pthresh:
                if self.verbose:
                    print(lm_y.summary())
                return iter(folds)

            if runctr>max_splits:
                print('no sufficient split found, returning best (p=%f)'%best_pval)
                return iter(best_folds)

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
    def test_regression_with_tuples(self):
        i = pandas.Series( [1,2,3,4]*10 , name="i")
        y = pandas.Series( [1,2,3,4,5]*8, name="y")
        x = pandas.Series( [1,2,3,4,5,6,7,8]*5, name="x")

        df = pandas.DataFrame( index=i.index )
        df = df.join( i )
        endo = df.join( y )
        exo = df.join( x )
        endo_groups = endo.groupby( ("i",) )
        exo_groups = exo.groupby( ("i",) )
        exo_Df = exo_groups.agg( [np.sum, np.max] )
        endo_Df = endo_groups.agg( [np.sum, np.max] )
        reg = OLS(exo_Df[[("x", "sum")]],endo_Df).fit()
        interesting_lines = []
        for line in str( reg.summary() ).splitlines():
            if "('" in line:
                interesting_lines.append( line[:38] )
        
        desired = ["Dep. Variable:           ('x', 'sum') ",
                   "('y', 'sum')      1.4595      0.209   ",
                   "('y', 'amax')     0.2432      0.035   "]
        
        self.assertEqual( desired, interesting_lines  )

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
import numpy as np
from statsmodels.regression.linear_model import OLS, GLSAR
from statsmodels.tools.tools import add_constant
from statsmodels.datasets import macrodata
import statsmodels.regression.tests.results.results_macro_ols_robust as res


d2 = macrodata.load(as_pandas=False).data
g_gdp = 400*np.diff(np.log(d2['realgdp']))
g_inv = 400*np.diff(np.log(d2['realinv']))
exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1]], prepend=False)
res_olsg = OLS(g_inv, exogg).fit()



print(res_olsg.summary())
res_hc0 = res_olsg.get_robustcov_results('HC1')
print('\n\n')
print(res_hc0.summary())
print('\n\n')
res_hac4 = res_olsg.get_robustcov_results('HAC', maxlags=4, use_correction=True)
print(res_hac4.summary())


print('\n\n')
tt = res_hac4.t_test(np.eye(len(res_hac4.params)))
print(tt.summary())
print('\n\n')
print(tt.summary_frame())

res_hac4.use_t = False

# 需要导入模块: from statsmodels.regression.linear_model import OLS [as 别名]
# 或者: from statsmodels.regression.linear_model.OLS import summary [as 别名]
import numpy as np
from statsmodels.regression.linear_model import OLS, GLSAR
from statsmodels.tools.tools import add_constant
from statsmodels.datasets import macrodata
import statsmodels.regression.tests.results.results_macro_ols_robust as res


d2 = macrodata.load().data
g_gdp = 400*np.diff(np.log(d2['realgdp']))
g_inv = 400*np.diff(np.log(d2['realinv']))
exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1]], prepend=False)
res_olsg = OLS(g_inv, exogg).fit()



print res_olsg.summary()
res_hc0 = res_olsg.get_robustcov_results('HC1')
print '\n\n'
print res_hc0.summary()
print '\n\n'
res_hac4 = res_olsg.get_robustcov_results('HAC', maxlags=4, use_correction=True)
print res_hac4.summary()


print '\n\n'
tt = res_hac4.t_test(np.eye(len(res_hac4.params)))
print tt.summary()
print '\n\n'
print tt.summary_frame()

res_hac4.use_t = False