def run(data, iter):
boots = []
for i in range(100, 100000, 1000):
boot = boostrap(data, data.shape[0], i, 95, 5)
boots.append([i, boot[0], "mean"])
boots.append([i, boot[1], "lower"])
boots.append([i, boot[2], "upper"])
df_boot = pd.DataFrame(boots,
columns=['Boostrap Iterations', 'Mean', "Value"])
sns_plot = sns.lmplot(df_boot.columns[0],
df_boot.columns[1],
data=df_boot,
fit_reg=False,
hue="Value")
sns_plot.axes[0, 0].set_ylim(0, )
sns_plot.axes[0, 0].set_xlim(0, 100000)
sns_plot.savefig("bootstrap_confidence{}.png".format(iter),
bbox_inches='tight')
sns_plot.savefig("bootstrap_confidence{}.pdf".format(iter),
bbox_inches='tight')
print("Mean: {}".format(np.mean(data)))
print("Var: {}".format(np.var(data)))
data = df.values.T[1][:79]
sns_plot2 = sns.distplot(data, bins=20, kde=False, rug=True).get_figure()
axes = plt.gca()
axes.set_xlabel('MPG of new vehicles')
axes.set_ylabel('Vehicle count')
sns_plot2.savefig("histogramNew.png", bbox_inches='tight')
sns_plot2.savefig("histogramNew.pdf", bbox_inches='tight')
plt.clf()
data_old = df.values.T[0]
sns_plot3 = sns.distplot(data_old, bins=20, kde=False,
rug=True).get_figure()
axes = plt.gca()
axes.set_xlabel('MPG of old vehicles')
axes.set_ylabel('Vehicle count')
sns_plot2.savefig("histogramOld.png", bbox_inches='tight')
sns_plot2.savefig("histogramOld.pdf", bbox_inches='tight')
old = np.array(data_old)
new = np.array(data)
print("Mean of old cars: %f" % np.mean(old))
print("Mean of new cars: %f" % np.mean(new))
old_bs_mean, old_bs_lower, old_bs_upper = bs.boostrap(
old, old.shape[0], 100000, 95)
new_bs_mean, new_bs_lower, new_bs_upper = bs.boostrap(
new, new.shape[0], 100000, 95)
print("Old lower: %f, Old mean: %f, Old upper: %f" %
(old_bs_lower, old_bs_mean, old_bs_upper))
print("New lower: %f, New mean: %f, New upper: %f" %
(new_bs_lower, new_bs_mean, new_bs_upper))
# ***** CODE *****
df = pd.read_csv('vehicles.csv')
# Creating Scaterplot and Histogram of fleets.
create_diagrams()
# ***** Standard deviation comparison via the boostrap *****
#std_current_fleet = np.std(df.values.T[0])
#std_proposed_fleet = np.std(df.dropna().values.T[0])
print("## Current fleet")
print("")
print("# Standard deviation")
boot = bootstrap.boostrap(np.std, 10000, df.values.T[0])
print("- upper = " + str(boot[2]))
print("- std-mean = " + str(boot[0]))
print("- lower = " + str(boot[1]))
print("")
print("Mean:")
print("- mean = " + str(np.mean(df.values.T[0])))
print("")
print("## Proposed fleet")
print("")
print("# Standard deviation:")
boot = bootstrap.boostrap(np.std, 10000, df.dropna().values.T[1])
print("- upper = " + str(boot[2]))
print("- std-mean = " + str(boot[0]))
print("- lower = " + str(boot[1]))
axes.set_ylabel('current fleet count')
sns_plot_cur.savefig("histogram_cur.png", bbox_inches='tight')
plt.clf()
sns_plot_new = sns.distplot(new_flt, bins=20, kde=False,
rug=True).get_figure()
axes = plt.gca()
axes.set_xlabel('new fleet')
axes.set_ylabel('new fleet count')
sns_plot_new.savefig("histogram_new.png", bbox_inches='tight')
#Exercise: The bootstrap(2)
mean_cur = np.mean(cur_flt)
mean_new = np.mean(new_flt)
boots_cur = boostrap(cur_flt, cur_flt.shape[0], 1000, 0.95)
boots_new = boostrap(new_flt, new_flt.shape[0], 1000, 0.95)
upper_cur = boots_cur[2]
lower_cur = boots_cur[1]
upper_new = boots_new[2]
lower_new = boots_new[1]
print("current fleet:")
print("mean: ", mean_cur)
print("upper: ", upper_cur)
print("lower: ", lower_cur)
print("-------------------------")
print("new fleet: ")
print((("Mean: %f") % (np.mean(data_new_fleet))))
print((("Median: %f") % (np.median(data_new_fleet))))
print((("Var: %f") % (np.var(data_new_fleet))))
print((("std: %f") % (np.std(data_new_fleet))))
print((("MAD: %f") % (mad(data_new_fleet))))
plt.clf()
vehicle_histogram = sns.distplot(data_new_fleet,
bins=20,
kde=False,
rug=True).get_figure()
axes = plt.gca()
axes.set_xlabel('New Fleet Vehicle MPG (Miles Per Gallon)')
axes.set_ylabel('Frequency')
vehicle_histogram.savefig("vehiclehistogram.png", bbox_inches='tight')
vehicle_histogram.savefig("vehiclehistogram.pdf", bbox_inches='tight')
mean_current_fleet = np.mean(data_current_fleet)
mean_new_fleet = np.mean(data_new_fleet)
boot_current = bootstrap.boostrap(data_current_fleet,
data_current_fleet.shape[0], 1000)
boot_new = bootstrap.boostrap(data_new_fleet, data_current_fleet.shape[0],
1000)
print("Current Fleet: Mean:{} Lower: {} Upper: {}".format(
mean_current_fleet, boot_current[1], boot_current[2]))
print("New Fleet: Mean:{} Lower: {} Upper: {}".format(
mean_new_fleet, boot_new[1], boot_new[2]))