def visualisation(vt0, vt1):
fig = plt.figure()
ax = plt.axes(xlim=(0, 250000), ylim=(3000, 9000))
line, = ax.plot([], [], lw=2)
datas = lexer.datas()
plt.xlabel("mileage (km)")
plt.ylabel("price (€)")
ttl = ax.text(0.32, 1.05, '', transform = ax.transAxes, va='center')
for data in datas:
plt.plot(data[0], data[1], 'ro')
def init():
ttl.set_text('')
line.set_data([], [])
return line, ttl
def animate(i):
ttl.set_text("number of iterations: " + str(i))
t0 = vt0[i]
t1 = vt1[i]
x = np.linspace(0,240000,100000)
y = t1 * x + t0
line.set_data(x, y)
return line, ttl
anim = animation.FuncAnimation(fig, animate, init_func=init,
frames=len(vt0), interval=20, blit=False)
plt.show()
def visualisation():
datas = lexer.datas()
for data in datas:
plt.plot(data[0], data[1], 'ro')
theta = lexer.thetas()
if theta[0] != 0 and theta[1] != 0:
x = np.linspace(0,240000,100000)
y = theta[0] * x + theta[1]
plt.plot(x, y, '-r')
plt.grid()
plt.xlabel("km")
plt.ylabel("price")
plt.show()
plt.close()
def describe(argv):
try:
datas = lexer.datas(sys.argv[1])
except:
print("Failed to read the file.")
exit()
tab = init_tab(datas)
tab, count_f = count_features(datas, tab)
tab, mean_f = mean_features(datas, tab, count_f)
tab, var_f, s_var_f = variance_features(datas, tab, count_f, mean_f)
tab = std_features(datas, tab, var_f, s_var_f)
tab, min_f = min_features(datas, tab)
tab, tf_f, sf_f = perce_features(datas, tab, count_f)
tab, max_f = max_features(datas, tab)
tab = range_features(datas, tab, min_f, max_f)
tab = iqr_features(datas, tab, tf_f, sf_f)
print(tab)
def precision():
datas = lexer.datas()
theta = lexer.thetas()
my = 0
for i, line in enumerate(datas):
n = i + 1
my += line[1]
my /= n
sse = 0
ssr = 0
for i, line in enumerate(datas):
fy = theta[0] + line[0] * theta[1]
sse += (fy - my) * (fy - my)
ssr += (line[1] - fy) * (line[1] - fy)
sst = sse + ssr
r2 = sse / sst
print("the precision of the algorithm is:", r2)
def minimisation(alpha0, alpha1, error):
datas = lexer.datas()
theta = lexer.thetas()
dt0, dt1 = 10, 10
t0, t1 = theta[0], theta[1]
vt0 = []
vt1 = []
while abs(dt0) > 0.01 and abs(dt1) > 0.01:
DT = update_thetas(datas, t0, t1)
dt0, dt1 = DT[0], DT[1]
t0 = t0 - alpha0*dt0
t1 = t1 - alpha1*dt1
if math.isnan(t0) or math.isnan(t1):
if error:
exit()
minimisation(alpha1, alpha0, 1)
vt0.append(t0)
vt1.append(t1)
ft_write(t0, t1)
visualisation(vt0, vt1)
def histogram(argv):
try:
datas = lexer.datas(sys.argv[1])
except:
print("Failed to read the file.")
exit()
# min_f = min_features(datas)
# max_f = max_features(datas)
# print (min_f[11])
# print (max_f[11])
f_h = feature_house(datas, 17)
# display (feat_house, datas[0][17], min_f[11], max_f[11])
print(plt.style.available[:6])
# Notez la taille de la figure
fig = plt.figure(figsize=(12, 8))
for i in range(6):
# On peut ajouter des sous graphes ainsi
fig.add_subplot(3, 2, i + 1)
# display(f_h,datas[0][17])
plt.style.use(plt.style.available[i])
plt.plot(x, y)
# Pour ajouter du texte
plt.text(s=plt.style.available[i], x=5, y=2, color='red')
# i = 6
# while i < 19:
# i += 1
# feat_house = feature_house(datas, i)
# ax = [0, 1, 2, 3, 4, 5, 6]
# np.random.seed(0)
# n_bins = 10
# x = np.random.randn(1000, 3)
# fh = feature_house(datas, 18)
# fig, axes = plt.subplots(nrows=5, ncols=4)
# ax = axes.flatten()
# colors = ['red', 'tan', 'lime']
# #ax0.hist(x, n_bins, normed=1, histtype='bar', color=colors, label=colors)
# ax[0].hist(fh[0], histtype = 'stepfilled', color = 'green', alpha = 0.25, label = 'Gryff')
# ax[0].hist(fh[1], histtype = 'stepfilled', color = 'blue', alpha = 0.25, label = 'Slith')
# ax[0].hist(fh[2], histtype = 'stepfilled', color = 'red', alpha = 0.25, label = 'Huffle')
# ax[0].hist(fh[3], histtype = 'stepfilled', color = 'yellow', alpha = 0.25, label = 'Ravenc')
# ax[0].legend(prop={'size': 10})
# ax[0].set_title('Histogram of '+ datas[0][18])
# ax[1].hist(x, n_bins, normed=1, histtype='bar', stacked=True)
# ax[1].set_title('stacked bar')
# ax[2].hist(x, n_bins, histtype='step', stacked=True, fill=False)
# ax[2].set_title('stack step (unfilled)')
# # Make a multiple-histogram of data-sets with different length.
# x_multi = [np.random.randn(n) for n in [10000, 5000, 2000]]
# ax[3].hist(x_multi, n_bins, histtype='bar')
# ax[3].set_title('different sample sizes')
# fig.tight_layout()
# plt.show()
# x1 = np.linspace(0.0, 5.0)
# y1 = np.cos(2 * np.pi * x1) * np.exp(-x1)
# x2 = np.linspace(0.0, 2.0)
# y2 = np.cos(2 * np.pi * x2)
# x3 = np.linspace(0.0, 4.0)
# y3 = np.cos(2 * np.pi * x3)
# x4 = np.linspace(-2.0, 2.0)
# y4 = np.cos(2 * np.pi * x4)
# x5 = np.linspace(-10.0, 20.0)
# y5 = np.cos(2 * np.pi * x5)
# i = 6
# while i < 7:
# #p = i - 5
# fh = feature_house(datas, i)
# plt.subplot(8, 4, i)
# plt.hist(fh[0], histtype = 'stepfilled', color = 'green', alpha = 0.25, label = 'Gryff')
# plt.hist(fh[1], histtype = 'stepfilled', color = 'blue', alpha = 0.25, label = 'Slith')
# #plt.legend(prop={'size': 10})
# plt.title('Histogram of '+ datas[0][i])
# i += 1
# plt.subplot(432)
# plt.plot(x2, y2, '.-')
# plt.xlabel('time (s)')
# plt.ylabel('Undamped')
# plt.subplot(433)
# plt.plot(x3, y4, '.-')
# plt.xlabel('3 (s)')
# plt.ylabel('3 ---------- stop')
plt.show()