def smSolution(M1, M2, M3):
'''Solution with the tools from statsmodels'''
import statsmodels.api as sm
import C2_8_mystyle
Res1 = sm.OLS(y, M1).fit()
Res2 = sm.OLS(y, M2).fit()
Res3 = sm.OLS(y, M3).fit()
print(Res1.summary2())
print(Res2.summary2())
print(Res3.summary2())
# Plot the data
plt.plot(x,y, '.', label='Data')
plt.plot(x, Res1.fittedvalues, 'r--', label='Linear Fit')
plt.plot(x, Res2.fittedvalues, 'g', label='Quadratic Fit')
plt.plot(x, Res3.fittedvalues, 'y', label='Cubic Fit')
plt.legend(loc='upper left', shadow=True)
C2_8_mystyle.printout('linearModel.png', xlabel='x', ylabel='y')
def main():
'''Demonstrate the generation of different statistical standard plots'''
# Univariate data -------------------------
# Generate data that are normally distributed
x = np.random.randn(500)
# Set the fonts the way I like them
sns.set_context('poster')
sns.set_style('ticks')
C2_8_mystyle.set(fs=32)
# Scatter plot
plt.scatter(np.arange(len(x)), x)
plt.xlim([0, len(x)])
# Save and show the data, in a systematic format
C2_8_mystyle.printout('scatterPlot.png', xlabel='x', ylabel='y', title='Scatter')
# Histogram
plt.hist(x)
C2_8_mystyle.printout('histogram_plain.png', xlabel='Data Values', ylabel='Frequency', title='Histogram, default settings')
plt.hist(x,25)
C2_8_mystyle.printout('histogram.png', xlabel='Data Values', ylabel='Frequency', title='Histogram, 25 bins')
# Cumulative probability density
numbins = 20
plt.plot(stats.cumfreq(x,numbins)[0])
C2_8_mystyle.printout('CumulativeFrequencyFunction.png', xlabel='Data Values', ylabel='CumFreq', title='Cumulative Frequncy')
# KDE-plot
sns.kdeplot(x)
C2_8_mystyle.printout('kde.png', xlabel='Data Values', ylabel='Density',
title='KDE_plot')
# Boxplot
# The ox consists of the first, second (middle) and third quartile
plt.boxplot(x, sym='*')
C2_8_mystyle.printout('boxplot.png', xlabel='Values', title='Boxplot')
plt.boxplot(x, sym='*', vert=False)
plt.title('Boxplot, horizontal')
plt.xlabel('Values')
plt.show()
# Errorbars
x = np.arange(5)
y = x**2
errorBar = x/2
plt.errorbar(x,y, yerr=errorBar, fmt='o', capsize=5, capthick=3)
plt.xlim([-0.2, 4.2])
plt.ylim([-0.2, 19])
C2_8_mystyle.printout('Errorbars.png', xlabel='Data Values', ylabel='Measurements', title='Errorbars')
# Violinplot
nd = stats.norm
data = nd.rvs(size=(100))
nd2 = stats.norm(loc = 3, scale = 1.5)
data2 = nd2.rvs(size=(100))
# Use pandas and the seaborn package for the violin plot
df = pd.DataFrame({'Girls':data, 'Boys':data2})
sns.violinplot(df)
C2_8_mystyle.printout('violinplot.png', title='Violinplot')
# Barplot
df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df.plot(kind='bar', grid=False)
C2_8_mystyle.printout('barplot.png', title='Barplot')
# Grouped Boxplot
sns.set_style('whitegrid')
sns.boxplot(df)
C2_8_mystyle.set(fs=28)
C2_8_mystyle.printout('groupedBoxplot.png', title='sns.boxplot')
# Bivariate Plots
df2 = pd.DataFrame(np.random.rand(50, 4), columns=['a', 'b', 'c', 'd'])
df2.plot(kind='scatter', x='a', y='b', s=df['c']*300);
C2_8_mystyle.printout('bivariate.png')
# Pieplot
series = pd.Series(3 * np.random.rand(4), index=['a', 'b', 'c', 'd'], name='series')
oldPalette = sns.color_palette()
sns.set_palette("husl")
series.plot(kind='pie', figsize=(6, 6))
C2_8_mystyle.printout('piePlot.png', title='pie-plot')
sns.set_palette(oldPalette)
def simplePlots():
'''Demonstrate the generation of different statistical standard plots'''
# Univariate data -------------------------
# Make sure that always the same random numbers are generated
np.random.seed(1234)
# Generate data that are normally distributed
x = np.random.randn(500)
# Other graphics settings
sns.set(context='poster', style='ticks', palette=sns.color_palette('muted'))
# Set the fonts the way I like them
C2_8_mystyle.set(fs=32)
# Scatter plot
plt.scatter(np.arange(len(x)), x)
plt.xlim([0, len(x)])
# Save and show the data, in a systematic format
C2_8_mystyle.printout('scatterPlot.png', xlabel='Datapoints', ylabel='Values', title='Scatter')
# Histogram
plt.hist(x)
C2_8_mystyle.printout('histogram_plain.png', xlabel='Data Values',
ylabel='Frequency', title='Histogram, default settings')
plt.hist(x,25)
C2_8_mystyle.printout('histogram.png', xlabel='Data Values', ylabel='Frequency',
title='Histogram, 25 bins')
# Cumulative probability density
numbins = 20
plt.plot(stats.cumfreq(x,numbins)[0])
C2_8_mystyle.printout('CumulativeFrequencyFunction.png', xlabel='Data Values',
ylabel='CumFreq', title='Cumulative Frequency')
# KDE-plot
sns.kdeplot(x)
C2_8_mystyle.printout('kde.png', xlabel='Data Values', ylabel='Density',
title='KDE_plot')
# Boxplot
# The ox consists of the first, second (middle) and third quartile
plt.boxplot(x, sym='*')
C2_8_mystyle.printout('boxplot.png', xlabel='Values', title='Boxplot')
plt.boxplot(x, sym='*', vert=False)
plt.title('Boxplot, horizontal')
plt.xlabel('Values')
plt.show()
# Errorbars
x = np.arange(5)
y = x**2
errorBar = x/2
plt.errorbar(x,y, yerr=errorBar, fmt='o', capsize=5, capthick=3)
plt.xlim([-0.2, 4.2])
plt.ylim([-0.2, 19])
C2_8_mystyle.printout('Errorbars.png', xlabel='Data Values', ylabel='Measurements', title='Errorbars')
# Violinplot
nd = stats.norm
data = nd.rvs(size=(100))
nd2 = stats.norm(loc = 3, scale = 1.5)
data2 = nd2.rvs(size=(100))
# Use pandas and the seaborn package for the violin plot
df = pd.DataFrame({'Girls':data, 'Boys':data2})
sns.violinplot(df)
C2_8_mystyle.printout('violinplot.png', title='Violinplot')
# Barplot
# The font-size is set such that the legend does not overlap with the data
np.random.seed(1234)
C2_8_mystyle.set(20)
df = pd.DataFrame(np.random.rand(10, 4), columns=['a', 'b', 'c', 'd'])
df.plot(kind='bar', grid=False, color=sns.color_palette('muted'))
C2_8_mystyle.printout_plain('barplot.png')
C2_8_mystyle.set(28)
# Bivariate Plots
df2 = pd.DataFrame(np.random.rand(50, 3), columns=['a', 'b', 'c'])
df2.plot(kind='scatter', x='a', y='b', s=df2['c']*500);
plt.axhline(0, ls='--', color='#999999')
plt.axvline(0, ls='--', color='#999999')
C2_8_mystyle.printout('bivariate.png')
# Grouped Boxplot
sns.set_style('whitegrid')
sns.boxplot(df)
C2_8_mystyle.set(fs=28)
C2_8_mystyle.printout('groupedBoxplot.png', title='sns.boxplot')
sns.set_style('ticks')
# Pieplot
txtLabels = 'Cats', 'Dogs', 'Frogs', 'Others'
fractions = [45, 30, 15, 10]
offsets =(0, 0.05, 0, 0)
plt.pie(fractions, explode=offsets, labels=txtLabels,
autopct='%1.1f%%', shadow=True, startangle=90,
colors=sns.color_palette('muted') )
plt.axis('equal')
C2_8_mystyle.printout('piePlot.png', title=' ')
