def test_s_fmt_lineoptions(self, close_figures):
qqline(self.ax,
"s",
x=self.x,
y=self.y,
fmt=self.fmt,
**self.lineoptions)
def test_q_fmt_lineoptions(self, close_figures):
qqline(
self.ax,
"q",
dist=stats.norm,
x=self.x,
y=self.y,
fmt=self.fmt,
**self.lineoptions,
)
def test_q_fmt(self, close_figures):
qqline(self.ax, "q", dist=stats.norm, x=self.x, y=self.y, fmt=self.fmt)
def test_q(self, close_figures):
nchildren = len(self.ax.get_children())
qqline(self.ax, "q", dist=stats.norm, x=self.x, y=self.y)
assert len(self.ax.get_children()) > nchildren
def test_s(self, close_figures):
nchildren = len(self.ax.get_children())
qqline(self.ax, "s", x=self.x, y=self.y)
assert len(self.ax.get_children()) > nchildren
def test_s_fmt(self, close_figures):
qqline(self.ax, "s", x=self.x, y=self.y, fmt=self.fmt)
def test_45_fmt(self, close_figures):
qqline(self.ax, "45", fmt=self.fmt)
def test_45_fmt_lineoptions(self, close_figures):
qqline(self.ax, "45", fmt=self.fmt, **self.lineoptions)
def test_non45_no_x_no_y(self, close_figures):
with pytest.raises(ValueError):
qqline(self.ax, "s")
def test_45(self, close_figures):
nchildren = len(self.ax.get_children())
qqline(self.ax, "45")
assert len(self.ax.get_children()) > nchildren
def test_badline(self):
with pytest.raises(ValueError):
qqline(self.ax, "junk")
# Build a regression model for 'stay' versus 't'
model1 = smf.ols('stay ~ t', data=brexit).fit()
# Examine the model output
model1.summary()
model1.summary2()
# Produce the following diagnostic plots:
# * Predicted versus observed
sns.jointplot(brexit.stay, model1.fittedvalues)
# * Residuals versus predicted
sns.jointplot(model1.fittedvalues, model1.resid)
# * Residuals versus 't'
sns.pointplot(brexit.t, model1.resid, join=False)
# * Autocorrelation plot
autocorrelation_plot(model1.resid)
# * Normal Q-Q plot for (Studentised) residuals
st_resid = model1.get_influence().get_resid_studentized_external()
qq = smg.qqplot(st_resid)
smg.qqline(qq.gca(), '45')
# BONUS: Build a second regression model for 'stay' versus 't' and 'pollster',
# and re-run all of the above
model2 = smf.ols('stay ~ t + pollster', data=brexit).fit()
'''
Import the food expenditure dataset. Plot annual food expenditure on
x-axis and household income on y-axis. Use qqline to add regression line
into the plot.
'''
import matplotlib.pyplot as plt
import statsmodels.api as sm
from statsmodels.graphics.gofplots import qqline
foodexp = sm.datasets.engel.load()
x = foodexp.exog
y = foodexp.endog
ax = plt.subplot(111)
plt.scatter(x, y)
ax.set_xlabel(foodexp.exog_name[0])
ax.set_ylabel(foodexp.endog_name)
qqline(ax, 'r', x, y)
plt.show()
plt.boxplot(fat)
plt.show()
# (c)
plt.scatter(age, fat, c="green", alpha=0.5)
plt.show()
stats.probplot(age, dist="norm", plot=pylab)
stats.probplot(fat, dist="norm", plot=pylab)
pylab.show()
ax = plt.subplot(111)
plt.scatter(age, fat)
qqline(ax, 'r', age, fat)
plt.show()
#########################################################
# 4.
# (a)
def cos_sim(A, B):
return dot(A, B) / (norm(A) * norm(B))
print(cos_sim((1.5, 1.7), (1.4, 1.6)))
print(cos_sim((2.0, 1.9), (1.4, 1.6)))
print(cos_sim((1.6, 1.8), (1.4, 1.6)))
'''
Import the food expenditure dataset. Plot annual food expendeture on
x-axis and household income on y-axis. Use qqline to add regression line
into the plot.
'''
import statsmodels.api as sm
import matplotlib.pyplot as plt
from statsmodels.graphics.gofplots import qqline
foodexp = sm.datasets.engel.load(as_pandas=False)
x = foodexp.exog
y = foodexp.endog
ax = plt.subplot(111)
plt.scatter(x, y)
ax.set_xlabel(foodexp.exog_name[0])
ax.set_ylabel(foodexp.endog_name)
qqline(ax, 'r', x, y)
plt.show()
