def test_one_column_exog(self):
from statsmodels.formula.api import ols
res = ols("y~var1-1", data=self.data).fit()
fig = plot_regress_exog(res, "var1")
plt.close(fig)
res = ols("y~var1", data=self.data).fit()
fig = plot_regress_exog(res, "var1")
plt.close(fig)
def test_one_column_exog(self):
from statsmodels.formula.api import ols
res = ols("y~var1-1", data=self.data).fit()
plot_regress_exog(res, "var1")
plt.close('all')
res = ols("y~var1", data=self.data).fit()
plot_regress_exog(res, "var1")
plt.close('all')
def test_plot_oth(self, close_figures):
#just test that they run
res = self.res
plot_fit(res, 0, y_true=None)
plot_partregress_grid(res, exog_idx=[0,1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=0)
plot_ccpr_grid(res, exog_idx=[0])
fig = plot_ccpr_grid(res, exog_idx=[0,1])
for ax in fig.axes:
add_lowess(ax)
close_or_save(pdf, fig)
def test_plot_oth(self):
#just test that they run
res = self.res
endog = res.model.endog
exog = res.model.exog
plot_fit(res, 0, y_true=None)
plot_partregress(endog, exog, exog_idx=[0, 1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=[0])
plot_ccpr(res, exog_idx=[0, 1])
plt.close('all')
def test_plot_oth(self):
#just test that they run
res = self.res
endog = res.model.endog
exog = res.model.exog
plot_fit(res, 0, y_true=None)
plot_partregress(endog, exog, exog_idx=[0,1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=[0])
plot_ccpr(res, exog_idx=[0,1])
plt.close('all')
def test_plot_oth(self, close_figures):
#just test that they run
res = self.res
plot_fit(res, 0, y_true=None)
plot_partregress_grid(res, exog_idx=[0, 1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=0)
plot_ccpr_grid(res, exog_idx=[0])
fig = plot_ccpr_grid(res, exog_idx=[0, 1])
for ax in fig.axes:
add_lowess(ax)
close_or_save(pdf, fig)
def test_plot_oth(self):
#just test that they run
res = self.res
endog = res.model.endog
exog = res.model.exog
plot_fit(res, 0, y_true=None)
plot_partregress_grid(res, exog_idx=[0,1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=0)
plot_ccpr_grid(res, exog_idx=[0])
fig = plot_ccpr_grid(res, exog_idx=[0,1])
for ax in fig.axes:
add_lowess(ax)
plt.close('all')
def test_plot_oth(self):
#just test that they run
res = self.res
endog = res.model.endog
exog = res.model.exog
plot_fit(res, 0, y_true=None)
plot_partregress_grid(res, exog_idx=[0, 1])
plot_regress_exog(res, exog_idx=0)
plot_ccpr(res, exog_idx=0)
plot_ccpr_grid(res, exog_idx=[0])
fig = plot_ccpr_grid(res, exog_idx=[0, 1])
for ax in fig.axes:
add_lowess(ax)
plt.close('all')
x2beta = x2 * res.params[2]
plt.plot(x1, x1beta + res.resid, 'o')
plt.plot(x1, x1beta, '-')
ax.set_title('X_i beta_i plus residuals versus exog (CCPR)') # + namestr)
ax = fig6.add_subplot(2, 1, 2)
plt.plot(x2, x2beta + res.resid, 'o')
plt.plot(x2, x2beta, '-')
#print res.summary()
doplots = 1
if doplots:
fig1 = smrp.plot_fit(res, 0, y_true=None)
smrp.plot_fit(res, 1, y_true=None)
smrp.plot_partregress(y, exog0, exog_idx=[0, 1])
smrp.plot_regress_exog(res, exog_idx=0)
smrp.plot_ccpr(res, exog_idx=[0])
smrp.plot_ccpr(res, exog_idx=[0, 1])
from statsmodels.graphics.tests.test_regressionplots import TestPlot
tp = TestPlot()
tp.test_plot_fit()
fig1 = smrp.plot_partregress(y, exog0, exog_idx=[0, 1])
#add lowess
ax = fig1.axes[0]
y0 = ax.get_lines()[0]._y
x0 = ax.get_lines()[0]._x
lres = sm.nonparametric.lowess(y0, x0, frac=0.2)
ax.plot(lres[:, 0], lres[:, 1], 'r', lw=1.5)
ax = fig1.axes[1]
def test_one_column_exog(self, close_figures):
from statsmodels.formula.api import ols
res = ols("y~var1-1", data=self.data).fit()
fig = plot_regress_exog(res, "var1")
res = ols("y~var1", data=self.data).fit()
fig = plot_regress_exog(res, "var1")
def test_graphs(self, res):
col_num = self.X.shape[1]
rp.plot_fit(res, exog_idx=col_num - 3)
rp.plot_regress_exog(res, exog_idx=col_num - 1, fig=None)
rp.plot_leverage_resid2(res) # squared
"""
# /// Graphical Diagnostic Tools /// ---------------------------------
import statsmodels.graphics.regressionplots as regplot
"""
まず、以下のinfluence_plot()は、サンプルの中にはずれ値的な動きをした期間があるかを検出してくれます。
"""
# Checking Outlier effect
regplot.influence_plot(rlt) # Studentized Residual
regplot.plot_leverage_resid2(rlt) # Leverage vs. resid^2
"""
また、plot_regress_exog()は、個別の説明変数ごとに、誤差項と説明変数の関係や、他の要因をコントロールした上での当該変数の説明力を見る偏回帰プロットが表示されます。誤差や説明力が説明変数の値に連動して変化するなら、他変数からの影響や非線形性が現れていると考えられます。
"""
# Selected exog vs. other things controlled endog plot
regplot.plot_regress_exog(rlt, 1)
N = DD.shape[0]
x = DD['Pic'].values * 100
y = DD['GAP'].values * 100
radii = np.random.random(size=N) / 10
colors = [
"#%02x%02x%02x" % (r, g, 150)
for r, g in zip(np.floor(50 + 2 * x), np.floor(30 + 2 * y))
]
output_file("color_scatter.html", title="color_scatter.py example")
scatter(x,
plt.plot(x1, x1beta + res.resid, 'o')
plt.plot(x1, x1beta, '-')
ax.set_title('X_i beta_i plus residuals versus exog (CCPR)')# + namestr)
ax = fig6.add_subplot(2,1,2)
plt.plot(x2, x2beta + res.resid, 'o')
plt.plot(x2, x2beta, '-')
#print res.summary()
doplots = 1
if doplots:
fig1 = smrp.plot_fit(res, 0, y_true=None)
smrp.plot_fit(res, 1, y_true=None)
smrp.plot_partregress_grid(res, exog_idx=[0,1])
smrp.plot_regress_exog(res, exog_idx=0)
smrp.plot_ccpr(res, exog_idx=0)
smrp.plot_ccpr_grid(res, exog_idx=[0,1])
from statsmodels.graphics.tests.test_regressionplots import TestPlot
tp = TestPlot()
tp.test_plot_fit()
fig1 = smrp.plot_partregress_grid(res, exog_idx=[0,1])
#add lowess
ax = fig1.axes[0]
y0 = ax.get_lines()[0]._y
x0 = ax.get_lines()[0]._x
lres = sm.nonparametric.lowess(y0, x0, frac=0.2)
ax.plot(lres[:,0], lres[:,1], 'r', lw=1.5)
ax = fig1.axes[1]
"""
まず、以下のinfluence_plot()は、サンプルの中にはずれ値的な動きをした期間があるかを検出してくれます。
"""
# Checking Outlier effect
regplot.influence_plot(rlt) # Studentized Residual
regplot.plot_leverage_resid2(rlt) # Leverage vs. resid^2
"""
また、plot_regress_exog()は、個別の説明変数ごとに、誤差項と説明変数の関係や、他の要因をコントロールした上での当該変数の説明力を見る偏回帰プロットが表示されます。誤差や説明力が説明変数の値に連動して変化するなら、他変数からの影響や非線形性が現れていると考えられます。
"""
# Selected exog vs. other things controlled endog plot
regplot.plot_regress_exog(rlt,1)
N = DD.shape[0]
x = DD['Pic'].values*100
y = DD['GAP'].values*100
radii = np.random.random(size=N)/10
colors = ["#%02x%02x%02x" % (r, g, 150) for r, g in zip(np.floor(50+2*x), np.floor(30+2*y))]
output_file("color_scatter.html", title="color_scatter.py example")
