def shist(self,data,sflag,spath,sname,pflag):
g.tprinter('Running sist',pflag)
xdata=data[:,0]
ydata=data[:,1]
plt.plot(xdata,ydata,'ro')
plt.savefig(os.path.join(spath,str(sname))+'.pdf')
plt.close()
def plot2D(x,y,x_ex,y_ex,ylabl):
#static variable counter
plot2D.fig_num += 1
plt.subplot(2,2,plot2D.fig_num)
plt.xlabel('$x$ (cm)')
plt.ylabel(ylabl)
plt.plot(x,y,"b+-",label="Lagrangian")
plt.plot(x_ex,y_ex,"r--",label="Exact")
plt.savefig("var_"+str(plot2D.fig_num)+".pdf")
def plot(self, output):
plt.figure(figsize=output.fsize, dpi=output.dpi)
for ii in range(0, len(self.v)):
imsize = [self.t[0], self.t[-1], self.x[ii][-1], self.x[ii][0]]
lim = amax(absolute(self.v[ii])) / output.scale_sat
plt.imshow(self.v[ii], extent=imsize, vmin=-lim, vmax=lim, cmap=cm.gray, origin='upper', aspect='auto')
plt.title("%s-Velocity for Trace #%i" % (self.comp.upper(), ii))
plt.xlabel('Time (s)')
plt.ylabel('Offset (km)')
#plt.colorbar()
plt.savefig("Trace_%i_v%s.pdf" % (ii, self.comp))
plt.clf()
def viz_losses(filename, losses):
if '.' not in filename: filename += '.png'
x = history['epoch']
legend = losses.keys
for v in losses.values: plt.plot(np.arange(len(v)) + 1, v, marker='.')
plt.title('Loss over epochs')
plt.xlabel('Epochs')
plt.xticks(history['epoch'], history['epoch'])
plt.legend(legend, loc = 'upper right')
plt.savefig(filename)
def plot_hist(a,b):
v = np.random.beta(a, b, 10000)
s = np.zeros(v.shape[0])
for i in range(v.shape[0]):
s[i] = np.random.binomial(20,v[i])
figure()
center = scipy.stats.itemfreq(s)[:,0]
hist = scipy.stats.itemfreq(s)[:,1]
plt.bar(center, hist, align = 'center', width = 0.7)
plt.savefig('../Figures/a'+str(a)+'_b'+str(int(b))+'.pdf')
def plot2D(x,y,ylabl,x_ex=None,y_ex=None):
#static variable counter
plot2D.fig_num += 1
plt.subplot(2,2,plot2D.fig_num)
plt.xlabel('$x$ (cm)')
plt.ylabel(ylabl)
plt.plot(x,y,"b+-",label="Numerical")
if (x_ex != None):
plt.plot(x_ex,y_ex,"r-x",label="Exact")
plt.savefig("var_"+str(plot2D.fig_num)+".pdf")
def plot_confusion_matrix(cm, labels, title='Confusion matrix', cmap=plt.cm.Blues, save=False):
plt.figure()
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(labels))
plt.xticks(tick_marks, labels, rotation=45)
plt.yticks(tick_marks, labels)
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.show()
if save:
plt.savefig(save)
def print_scatter_data():
import matplotlib.pylab as plt
filename = Par.dirname + ('/Scatter.dat')
fitnesses = []
self_reliences = []
life_times = []
self_reliences_dead = []
for Agent in Par.Agents:
if Agent.dead != True:
fitnesses.append(Agent.fitness)
Needs = Agent.needs
Production = Agent.production
selfReli = [0.0]*Par.num_resources
for i in range(Par.num_resources):
selfReli[i] = Production[i]*Needs[i]
self_reliences.append(abs(sum(selfReli)))
else:
life_time = Agent.t_death - Agent.t_discovery
life_times.append(life_time)
Needs = Agent.needs
Production = Agent.production
selfReli = [0.0]*Par.num_resources
for i in range(Par.num_resources):
selfReli[i] = Production[i]*Needs[i]
self_reliences_dead.append(abs(sum(selfReli)))
file =open(filename, 'w')
for i in range(len(fitnesses)):
s= str(fitnesses[i]) +' '+ str(self_reliences[i])
file.write(s)
file.write('\n')
file.close()
plt.scatter(self_reliences, fitnesses)
plt.ylabel('Fitness')
plt.xlabel('self_reliences')
plt.savefig('FitnessVSR.png')
plt.close()
plt.scatter(self_reliences_dead, life_times)
plt.ylabel('LifeTimes')
plt.xlabel('self_reliences')
plt.savefig('LifeTimeVSR.png')
plt.close()
def dataSet(temps, motorFreqs, durations=10.0, numMeas=10, pauseTime=1, sampRates=2048, tempTime=120, motorTime=60, printDataBool=False, plotResults = True, substance='Water' ):
initialize(substance) #Initialize ports, files, and constants (see below)
for temp in temps:
stirFreq = 400.0 #Set stirring speed for bath
setBath(temp, stirFreq, minStableTime=tempTime) #Set temperature and wait for stability (see below)
for i in range(motorFreqs.size): #Cycle through motorFreqs
motorFreq = motorFreqs[i]
print 'motorFreq is ' + str(motorFreq) + ' deg/sec.'
sampRate = sampRates[i]
print 'sampRate is ' + str(sampRate) + ' samples/sec.'
duration = durations[i]
# before each measurement, we reset the chains by stirring them up, and then letting them reform
print 'Spinning rotor for ' + str(motorTime) + ' seconds.'
setMotorFreq(stirFreq, sleepTime=motorTime) # Prevent sedimentation
print 'Pausing rotor for ' + str(pauseTime) + ' seconds.'
setMotorFreq(0, sleepTime=pauseTime) # Pause, perhaps to wait for chains to form
breakBool = setMotorFreq(motorFreq, sleepTime=motorTime)
#Set motor and checks if motorFreq is too high
#(high value may be changed in method setMotorFreq) (see below)
if breakBool: break #Break if motorFreq is above threshold
rotorFreqs = getData(numMeas, countTime=duration, sampRate=sampRate, printDataBool=printDataBool)
#Data retrieval (see below)
plt.savefig('Figs/'+time.strftime("%y-%m-%d-%H-%M-%S", time.localtime())+'-'+str(motorFreq)+'.png')
data = processData(temp, motorFreq, rotorFreqs) #Data processing (see below)
# calculate the std. error:
#se = numpy.std(rotorFreqs) / sqrt(numpy.size(rotorFreqs))
# Data recording: temp. - motorFreq. - avg. rotor Freq. - std. err. - sampRate - duration
writeToFile( data )
print 'Measurements at ' + str(temp) + ' degrees C completed.'
closeUp()
if plotResults and len(data) > 1:
kplt.plotData(os.getcwd(), Filename, writeFile=True, fit=False)
def plot_data():
import matplotlib.pylab as plt
t, suffering = np.loadtxt('suffering.dat', unpack= True, usecols = (0,1))
t, fitness = np.loadtxt('fitness.dat', unpack = True, usecols = (0,1))
plt.plot(t, suffering)
plt.xlabel('t')
plt.ylabel('suffering')
plt.savefig('suffering.png')
plt.close()
plt.plot(t, fitness)
plt.xlabel('t')
plt.ylabel('fitness')
plt.savefig('fitness.png')
plt.close()
def Transit(lc, PGpoints, intrans, starpos):
#Takes in shape. Draws it as array. Moves it across the Star. Draws lightcurve. Compares with known ligthcurve
movie=0
#Drawing star
star = DrawStar(starpos)
#Normalising total flux to 1.0
star/=np.sum(star)
#Turning the polygon into an array
from PIL import Image, ImageDraw
img = Image.new('L', (800, 800), 0)
ImageDraw.Draw(img).polygon(PGpoints, outline=1, fill=1)
objbox=np.array(img)
objbox=1-objbox
#Setting animation to step 4 pixels at a time
step=4.0
lc=lc[lc[:, 0].argsort(), :]
timearr=np.linspace(lc[0,0],lc[-1,0],1600)
print timearr
print lc[:, 0]
lightcurvemodel=[]
#Drawing initial plots
fig=plt.figure(figsize=(6, 12))
ax1=fig.add_subplot(211)
ax1.imshow(star[:, :800],cmap='hot');
ax2=fig.add_subplot(212)
ax2.plot(lc[:,0],lc[:,1],'--k')
ax2.plot(timearr, np.tile(1.0, 1600),'--', color='#CCCCCC')
plt.pause(0.002)
#Sweep across the star, keeping the object fixed
for pix in range(400,2000, step):
#Draw an 800x800 box from the star
starbox=star[:,(pix-400):(pix+400)]
total=objbox*starbox
#if np.sum(starbox)!=0:#skipping to where there is some of the star on the screen
ax1.cla()
ax1.imshow(total,cmap='hot');
#plotting lightcurve
rest=np.sum(star[:,:(pix-400)])+np.sum(star[:, (pix+400):])
lightcurvemodel+=[np.sum(total)+np.sum(rest)]
ax2.plot(timearr[pix-400],np.array(lightcurvemodel)[-1],'.r')
plt.pause(0.002)
movie=1 #Setting to record pngs as movie
if movie==1:
plt.savefig('TransitMovie/Movie'+str(pix)+'.png')
plt.pause(1)
np.savetxt('OutLightcurve.txt',np.column_stack((timearr[0:len(lightcurvemodel)],np.array(lightcurvemodel))))
def __save(self,n,plot,sfile):
p.figure(figsize=sfile)
p.xlabel(plot.xlabel)
p.ylabel(plot.ylabel)
p.xscale(plot.xscale)
p.yscale(plot.yscale)
p.grid()
for curve in plot.curves:
if curve[1] == None: p.plot(curve[0],curve[2], label=curve[3])
else: p.plot(curve[0], curve[1], curve[2], label=curve[3])
p.rc('legend', fontsize='small')
p.legend(shadow=0, loc='best')
p.axes().set_aspect(plot.aspect)
if not plot.dir: plot.dir = './plots/'
if not plot.name: plot.name = self.__global_name+'_%0*i'%(2,n)
if not os.path.isdir(plot.dir): os.mkdir(plot.dir)
if plot.pgf: p.savefig(plot.dir+plot.name+'.pgf')
else: p.savefig(plot.dir+plot.name+'.pdf', bbox_inches='tight')
p.close()
def task4(save=False):
knot = [0, 0, 0, 0.3, 0.5, 0.5, 0.6, 1, 1, 1]
control = np.array([[0, 0], [2, 3], [7, 5], [9, 2], [13, 1], [10, 1],
[7, 1]])
A = spline(knot, 2)
for i in range(len(knot) - 1):
X = linspace(knot[i], knot[i + 1], 20)
Y = A.evalvector(control, X)
plt.plot(Y[:, 0], Y[:, 1])
plt.scatter(control[:, 0], control[:, 1])
plt.scatter(6, 3, s=300)
plt.scatter(6.1, 3, s=50, color="black")
plt.plot((7, 6), (1, 0))
plt.grid()
if save:
plt.savefig("interpol2.pdf")
plt.show()
def plot_top_M_fisherfaces(eigenvec,M,Mpca,mode):
if mode == 'None':
return None
cols = 10
rows = M/cols
index = 1
font_size = 10
plt.figure(figsize=(20,20))
for i in range(0,M):
plt.subplot(rows,cols,index),plt.imshow(np.reshape(eigenvec[:,i],(46,56)).T, cmap = 'gist_gray')
face_title = str("M="+str(i+1))
plt.title(face_title, fontsize=font_size).set_position([0.5,1.05]), plt.xticks([]), plt.yticks([]) # set_position([a,b]) adjust b for height
index = index+1
if mode == 'show':
plt.show()
plt.close()
if mode == 'save':
title = str("Top 50 Fisherfaces for Mpca="+str(Mpca))
plt.savefig(title)
plt.close()
def print_save_all_mean_faces(x_class_mean,global_mean,show,save):
rows = 4
cols = 14
index = 1
font_size = 10
plt.figure(figsize=(20,10))
plt.subplot(rows,cols,index), plt.imshow(np.reshape(global_mean,(46,56)).T, cmap = 'gist_gray')
title = str("Global Mean")
plt.title(title, fontsize=font_size).set_position([0.5,0.95]), plt.xticks([]), plt.yticks([])
index=index+1
for i in range(0,x_class_mean.shape[1]):
title = str("Class Mean "+str(i+1))
plt.subplot(rows,cols,index), plt.imshow(np.reshape(x_class_mean[:,i],(46,56)).T, cmap = 'gist_gray')
plt.title(title, fontsize=font_size).set_position([0.5,0.95]), plt.xticks([]), plt.yticks([])
index = index+1
if show == 'yes':
plt.show()
if save == 'yes':
plt.savefig('Global and Class Mean')
plt.close()
def plot_confusion_matrix(cm, classes,
normalize=False, title='Confusion matrix',
cmap=plt.cm.Blues, filename='viz\\confusion_matrix.png'):
plt.figure()
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
if normalize: cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j], horizontalalignment="center", color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.savefig(filename)
def make_hists(self, X, y):
colors = [
'red', 'tan', 'lime', 'orange', 'black', 'yellow', 'green', 'pink',
'red', 'brown', 'grey', 'purple', 'navy'
]
features = (set(self.train_df.keys()) -
{'Vote'}) - set(categorical_features)
for feature in features:
df = pd.DataFrame({
"x": X[feature].values,
"class": y.values.flatten()
})
_, edges = np.histogram(df["x"], bins=15)
histdata = []
labels = []
for n, group in df.groupby("class"):
histdata.append(np.histogram(group["x"], bins=edges)[0])
labels.append(n)
hist = np.array(histdata)
histcum = np.cumsum(hist, axis=0)
plt.bar(edges[:-1],
hist[0, :],
width=np.diff(edges)[0],
label=labels[0],
align="edge")
for i in range(1, len(hist)):
plt.bar(edges[:-1],
hist[i, :],
width=np.diff(edges)[0],
bottom=histcum[i - 1, :],
color=colors[i],
label=labels[i],
align="edge")
plt.legend(title="class")
plt.savefig('hists_label/' + feature + '.jpeg')
def cmp_overall_qoe_per_region(regions, regionName):
google_QoE_folder = geographical_data_folder + "google/dataQoE/"
azure_QoE_folder = geographical_data_folder + "azure/dataQoE/"
amazon_QoE_folder = geographical_data_folder + "amazon/dataQoE/"
qoogle_regional_qoes = load_all_session_qoes_per_region(google_QoE_folder)
azure_regional_qoes = load_all_session_qoes_per_region(azure_QoE_folder)
amazon_regional_qoes = load_all_session_qoes_per_region(amazon_QoE_folder)
google_to_draw = []
azure_to_draw = []
amazon_to_draw = []
for r in regions:
google_to_draw.extend(qoogle_regional_qoes[r])
azure_to_draw.extend(azure_regional_qoes[r])
amazon_to_draw.extend(amazon_regional_qoes[r])
fig, ax = plt.subplots()
draw_cdf(google_to_draw, styles[0], "Google Cloud CDN")
draw_cdf(azure_to_draw, styles[1], "Azure CDN (Verizon)")
draw_cdf(amazon_to_draw, styles[2], "Amazon CloudFront")
ax.set_xlabel(r'Session QoE (0-5)', fontsize=18)
ax.set_ylabel(r'Percentage of PlanetLab users', fontsize=18)
plt.xlim([0, 5])
plt.ylim([0, 1])
plt.legend(loc=2)
imgName = img_folder + "compare_cloud_cdns_QoE_region_" + regionName
plt.savefig(imgName + ".jpg")
plt.savefig(imgName + ".pdf")
plt.savefig(imgName + ".png")
plt.show()
def rader_plot(x, y):
pi = 3.1415
# number of variable
plt.figure(figsize=(8,8))
categories=x.values.tolist()
N = len(categories)
# We are going to plot the first line of the data frame.
# But we need to repeat the first value to close the circular graph:
values = [s for s in y.values.tolist()]
# What will be the angle of each axis in the plot? (we divide the plot / number of variable)
angles = [n / float(N) * 2 * pi for n in range(N)]
# Initialise the spider plot
ax = plt.subplot(111, polar=True)
# Draw one axe per variable + add labels labels yet
plt.xticks(angles, categories, color='grey', size=25)
# Draw ylabels
ax.set_rlabel_position(0)
plt.yticks([0.25, 0.5, 0.75, 1], ["25%","50%","75%","100%"], color="grey", size=7)
plt.ylim(0,1)
angles.append(angles[0])
values.append(values[0])
# Plot data
ax.plot(angles, values, linewidth=1, linestyle='solid')
# Fill area
ax.fill(angles, values, 'b', alpha=0.1)
filename = f"{uid}_{status_id}.png"
plt.savefig(filename)
plt.close()
return filename
def main():
df = pd.read_csv(sys.argv[1])
df_fraud = df.loc[df['Class'] == 1]
# Only sample 50,000 data points
df_gen = df.loc[df['Class'] == 0].head(50000)
df_new = pd.concat([df_fraud, df_gen])
# Drop uninformative features
df_new = df_new.drop('Time', axis=1).drop("V13", axis=1).drop(
"V15", axis=1).drop("V20", axis=1).drop("V22", axis=1).drop(
"V23", axis=1).drop("V24",
axis=1).drop("V25",
axis=1).drop("V26",
axis=1).drop("V28",
axis=1)
t0 = time()
# Execute t-sne
X_tsne = manifold.TSNE(learning_rate=500, n_iter=600,
verbose=4).fit_transform(
df_new.drop('Class', axis=1))
plt.figure()
plt.scatter(X_tsne[:, 0], X_tsne[:, 1], c=df_new['Class'])
plt.xlabel("x-tsne")
plt.ylabel("y-tsne")
plt.title('T-SNE on Reduced Credit Card Fraud Detection Dataset')
purple_patch = mpatches.Patch(color='purple', label='Genuine')
yellow_patch = mpatches.Patch(color='yellow', label='Fraudulent')
plt.legend(handles=[purple_patch, yellow_patch])
t1 = time()
plt.savefig('tsne_50kpoints_600iterations_partialfeature.png',
bbox_inches='tight')
print(t1 - t0)
plt.show()
def cmp_overall_qoe_cps():
google_QoE_folder = geographical_data_folder + "google/dataQoE/"
azure_QoE_folder = geographical_data_folder + "azure/dataQoE/"
amazon_QoE_folder = geographical_data_folder + "amazon/dataQoE/"
qoogle_session_qoes = load_all_session_qoes(google_QoE_folder)
azure_session_qoes = load_all_session_qoes(azure_QoE_folder)
amazon_session_qoes = load_all_session_qoes(amazon_QoE_folder)
fig, ax = plt.subplots()
draw_cdf(qoogle_session_qoes, styles[0], "Google Cloud CDN")
draw_cdf(azure_session_qoes, styles[1], "Azure CDN (Verizon)")
draw_cdf(amazon_session_qoes, styles[2], "Amazon CloudFront")
ax.set_xlabel(r'Session QoE (0-5)', fontsize=18)
ax.set_ylabel(r'Percentage of PlanetLab users', fontsize=18)
plt.xlim([0, 5])
plt.ylim([0, 1])
plt.legend(loc=2)
imgName = img_folder + "compare_cloud_cdns_QoE_overall"
plt.savefig(imgName + ".jpg")
plt.savefig(imgName + ".pdf")
plt.savefig(imgName + ".png")
plt.show()
def plot_df(
df1, plot_title, x_axis, y_axis, plot, save
): # function for plotting high-dimension and low-dimension eigenvalues
y1 = df1[df1.columns[1]]
x1 = df1[df1.columns[0]]
plt.figure(figsize=(8, 8))
plt.plot(x1, y1, color='red')
plt.grid(color='black', linestyle='-',
linewidth=0.1) # parameters for plot grid
plt.xticks(np.arange(0,
max(x1) * 1.1,
int(max(x1) / 10))) # adjusting the intervals to 250
plt.yticks(np.arange(0, max(y1) * 1.1, int(max(y1) / 10)))
plt.title(plot_title).set_position([0.5, 1.05])
plt.xlabel(x_axis)
plt.ylabel(y_axis)
plt.legend(loc='best') # creating legend and placing in at the top right
if save == 'yes':
plt.savefig(plot_title)
if plot == 'yes':
plt.show()
plt.close()
def draw_3D(csvfile, savename, x_name, y_name, z_name1, z_name2):
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
from scipy.interpolate import griddata
csv = pd.read_csv(csvfile)
x = csv[x_name]
y = csv[y_name]
z1 = csv[z_name1]
z2 = csv[z_name2]
# xx, yy = np.meshgrid(x, y)
# zz = griddata(x, y, z, xx, yy)
ax = plt.subplot(111, projection='3d')
ax.scatter(x, y, z1)
ax.scatter(x, y, z2)
# ax.plot_trisurf(x, y, z)
ax.set_xlabel('k')
ax.set_ylabel('alpha')
ax.set_zlabel('acc')
plt.savefig('../eps/' + savename)
plt.show()
def ecdf_sca(data,
attribute,
aggregate=False,
datalinks=range(0, NUM_DATA_LINK),
save=False):
if aggregate:
selected_ds = data[data.name.isin([
attribute + '-' + str(i) for i in datalinks
])].groupby('run').mean()
else:
selected_ds = data[data.name == attribute]
plot_ecdf(selected_ds.value.to_numpy())
plt.title("ECDF for " + attribute +
(" (aggregated mean)" if aggregate else ""))
if save:
plt.savefig("ecdf_" + attribute + ".pdf", bbox_inches="tight")
plt.clf()
else:
plt.show()
return
def udaljenost_tocke(x1,y1,x2,y2,r):
plt.xlim([0,10])
plt.ylim([0,10])
kruznica = plt.Circle((x2,y2),r,color='r')
plt.gca().add_artist(kruznica)
plt.plot(x1,y1, 'bo')
x = (x1-x2)**2 + (y1-y2)**2
d = sqrt(x)
nacin = int(input('Unesi 1 za prikaz slike, 2 za spremanje'))
if znak ==1:
plt.show()
elif znak ==2:
naziv = input('Unesite naziv slike:')
plt.savefig(f'{naziv}.pdf')
epsilon = 0.01
if d < r:
print(f'Točka je unutar kružnice, a udaljenost je {d}.')
elif r-epsilon < d < r+epsilon:
print(f'Točka se nalazi na kružnici.')
else:
print(f'Točka je izvan kružnice, a udaljenost je {d}.')
def draw_line_chart12(
csvfile,
savename,
x_name,
y_name_1,
y_name_2,
):
import matplotlib.pyplot as plt
import pandas as pd
csv = pd.read_csv(csvfile)
x = csv[x_name]
y1 = csv[y_name_1]
y2 = csv[y_name_2]
plt.figure()
plt.plot(x, y1, marker='o')
plt.plot(x, y2, marker='^')
plt.xlabel('number of maps')
plt.ylabel('accuracy')
plt.grid()
plt.legend()
plt.savefig('../eps/' + savename)
plt.show()
def display(self, data, candidates, fname, display):
finallist=[]
for c in candidates:
finallist.append(c[0])
#print finallist
part1 = finallist[:len(finallist)/2]
part2 = finallist[len(finallist)/2:]
meandiff=int(np.sqrt(np.power(np.mean(part2),2)-np.power(np.mean(part1),2)))
rangeA = max(part1)-min(part1)
rangeB = max(part2)-min(part2)
span = int((rangeA+rangeB)/2)
dspan = int(meandiff/span)
theta = float(meandiff/(rangeA+rangeB))
oneortwo=""
if dspan >3 and meandiff > 20 or meandiff>36:
oneortwo = "Two distributions \n\n MD: %d \n Span: %d \n Dspan: %d \n theta: %d" % (meandiff, span, dspan, theta)
else:
oneortwo = "One distribution \n\n MD: %d \n Span: %d \n Dspan: %d \n theta: %d" % (meandiff, span, dspan, theta)
cans = np.array(candidates)
plt.plot(cans[:,0],cans[:,1],'ro')
plt.axhline(max(cans[:,1])/4, color='r')
plt.axhline(max(cans[:,1]/2), color='r')
plt.axhline(int(max(cans[:,1]))*0.75, color='r')
red_patch = mpatches.Patch(color='red', label='75%, 50% and 25% \nof maximum frequency')
plt.legend(handles=[red_patch])
plt.ylabel('Frequency of occurence')
plt.xlabel('separate items')
plt.title('Frequency distribution estimation graph: %s' %(fname))
plt.text(max(data)*1.1, max(cans[:,1])*0.62, oneortwo, fontsize = 11, color = 'r')
plt.hist(data,range(int(min(data)),int(max(data)),1))
ofile = fname[0:-3]+"png"
print ("Writing outfile: %s") % (ofile)
plt.savefig(ofile, bbox_inches='tight')
if display == True:
plt.show()
return;
def plot_board(self):
X = self.X
fig = plt.figure(figsize=(5, 5))
plt.xlim(-1, 1)
plt.ylim(-1, 1)
if self.mu and self.clusters:
mu = self.mu
clus = self.clusters
K = self.K
for m, clu in clus.items():
cs = cm.spectral(1. * m / self.K)
plt.plot(mu[m][0],
mu[m][1],
'o',
marker='*',
markersize=12,
color=cs)
plt.plot(zip(*clus[m])[0],
zip(*clus[m])[1],
'.',
markersize=8,
color=cs,
alpha=0.5)
else:
plt.plot(zip(*X)[0], zip(*X)[1], '.', alpha=0.5)
if self.method == '++':
tit = 'K-means++'
else:
tit = 'K-means with random initialization'
pars = 'N=%s, K=%s' % (str(self.N), str(self.K))
plt.title('\n'.join([pars, tit]), fontsize=16)
plt.savefig('kpp_N%s_K%s.png' % (str(self.N), str(self.K)),
bbox_inches='tight',
dpi=200)
def forward(self, x):
# polar plot
rr = self.rr.data.cpu().detach().numpy()
theta = self.theta.data.cpu().detach().numpy()
ax = plt.subplot(1, 1, 1, projection='polar')
ax.scatter(0, 1, c='black')
# unactive poles
ax.scatter(theta, rr)
ax.scatter(-theta, rr)
ax.scatter(np.pi - theta, rr)
ax.scatter(theta - np.pi, rr)
#
ax.set_rmax(1.2)
ax.set_title("Dictionary", va='bottom')
plt.savefig('usedPolesDCT_NFRAMES.png')
plt.show()
plt.close()
dic = creatRealDictionary(self.T, self.rr, self.theta, self.gid)
sparsecode = fista(dic, x, 0.05, 100, self.gid)
return Variable(sparsecode)
def plot_scores(scores):
plt.figure(figsize=(15, 6))
names, val_scores = [name for name, _, _, _, _, _, _ in scores
], [score for _, score, _, _, _, _, _ in scores]
ax = sns.barplot(x=names, y=val_scores)
for p, score in zip(ax.patches, val_scores):
height = p.get_height()
ax.text(p.get_x() + p.get_width() / 2.,
height + 0.005,
'{:1.3f}'.format(score),
ha="center",
fontsize=14)
plt.xlabel('method', fontsize=18)
plt.ylabel('Mean Val. Accuracy', fontsize=18)
plt.xticks(rotation=90, fontsize=16)
plt.yticks(fontsize=16)
plt.ylim(0.6, 1)
path = WORKING_PATH + "/___comparison.png"
plt.savefig(path)
plt.clf()
return path
def plotdata(trl, tel, tea):
xlist = range(len(trl))
ax1 = plt.subplot(2, 1, 1)
plt.plot(xlist, trl, 'r-', label='train loss')
plt.plot(xlist, tel, 'b-', label='validation loss')
plt.ylabel('loss value')
plt.title('loss graph')
plt.legend(loc=1)
ax2 = plt.subplot(2, 1, 2)
plt.plot(xlist, tea, 'b-', label='validation acc')
#plt.ylim(0, 100)
#plt.xlim(0, 100)
plt.yticks(range(0, 101, 10))
plt.grid(True)
plt.ylabel('acc(%)')
plt.title('acc graph')
plt.legend(loc=1)
plt.tight_layout()
plt.savefig('batchNorWithxavier.png', dpi=300)
plt.close()
def draw_line_chart14(csvfile, savename, x_name, y_name1, y_name2):
import matplotlib.pyplot as plt
import pandas as pd
csv = pd.read_csv(csvfile)
x = csv[x_name]
y1 = csv[y_name1]
y2 = csv[y_name2]
csv2 = pd.read_csv("../log/mnist_mapid_acc10.csv")
y3 = csv2[y_name1]
y4 = csv2[y_name2]
plt.figure()
plt.plot(x, y1, marker=".")
plt.plot(x, y2, marker=".")
plt.plot(x, y3, marker=".")
plt.plot(x, y4, marker='.')
plt.xlabel('number of maps')
plt.ylabel('accuracy')
plt.grid()
plt.legend()
plt.savefig('../eps/' + savename)
plt.show()
def plot3d(data):
fig = plt.figure()
ax = fig.gca(projection='3d')
Z, T1, T2, T3, X, Y = zip(*data)
X = np.array(X)
Y = np.array(Y)
Z = np.array(Z)
print X, Y, Z
print "XYZ printed"
print X.shape
print Y.shape
print Z.shape
ax.plot_surface(X, Y, Z) #,rstride=8, cstride=8, alpha=0.3)
#cset = ax.contour(X, Y, Z, zdir='z', offset=-100)
#cset = ax.contour(X, Y, Z, zdir='x', offset=-40)
#cset = ax.contour(X, Y, Z, zdir='y', offset=40)
ax.set_xlabel('Latitude')
#ax.set_xlim3d(-40, 40)
ax.set_ylabel('Longitude')
#ax.set_ylim3d(-40, 40)
ax.set_zlabel('Time')
#ax.set_zlim3d(-100, 100)
plt.savefig("fig1.ps")
def cm_plot(original_label, predict_label, kunm, pic=None):
cm = confusion_matrix(original_label, predict_label)
print('kappa:', kappa(cm))
plt.figure()
plt.matshow(cm, cmap=plt.cm.Blues)
plt.colorbar()
for x in range(len(cm)):
for y in range(len(cm)):
plt.annotate(cm[x, y],
xy=(x, y),
horizontalalignment='center',
verticalalignment='center')
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.title('confusion matrix')
if pic is not None:
plt.savefig(str(pic) + '.svg')
# plt.xticks(('Wake','N1','N2','N3','REM'))
# plt.yticks(('Wake','N1','N2','N3','REM'))
plt.savefig(savepath + "cnnmatrix" + str(kunm) + ".svg")
plt.show()
def plotFeatImportance(pathOut,
imp,
oob,
oos,
method,
tag=0,
simNum=0,
**kargs):
#plot mean imp bars with std
import matplotlib as mpl
mpl.figure(figsize=(10, imp.shape[0] / 5.))
imp = imp.sort_values('mean', ascending=True)
ax = imp['mean'].plot(kind='barh',
color='b',
alpha=.25,
xerr=imp['std'],
error_kw={'ecolor': 'r'})
if method == 'MDI':
mpl.xlim([0, imp.sum(axis=1).max()])
mpl.axvline(1. / imp.shape[0],
linewidth=1,
color='r',
linestyle='dotted')
ax.get_yaxis().set_visible(False)
for i, j in zip(ax.patches, imp.index):
ax.text(i.get_width() / 2,
i.get_y() + i.get_height() / 2,
j,
ha='center',
va='center',
color='black')
mpl.title = ('tag=' + tag + '|simNum=' + str(simNum) + '|oob=' +
str(round(oob, 4)) + '|oos=' + str(round(oos, 4)))
mpl.savefig(pathOut + 'featImportance_' + str(simNum) + '.png', dpi=100)
mpl.clf()
mpl.close()
return
def plot_response_time_variousT():
dataframe = pd.DataFrame()
index = []
for k in capacity_change_time:
for mode in modes:
index.append(f"{mode},t={k}s")
dataframe['index'] = index
for mode in modes:
index = []
meanResponseTime = []
for i in capacity_change_time:
df = scalar_df_parse(
f"C:\\Users\\Leonardo Poggiani\\Documents\\GitHub\\PECSNproject\\csv\\pool_classico_varia_T\\{mode}{i}.csv"
)
response = df[df.name == "responseTime"]
meanResponseTime.append(response.value.mean())
index.append(i)
plt.bar(index, meanResponseTime)
plt.title(f"{mode}")
plt.rcParams["figure.figsize"] = (12, 10)
plt.xticks(rotation=25)
plt.show()
plt.xlabel("Value of t")
plt.ylabel("Response time")
plt.title("Comparison of various values of t")
plt.legend(loc='best')
plt.savefig(
"C:\\Users\\Leonardo Poggiani\\Documents\\GitHub\\PECSNproject\\analysis\\variandoT\\responseTimeAlVariareDiT2.png"
)
def plot_per_historgram(per_path:str, save_path:str=None):
"""
This function plots PER values as a histogram. The plot is saved to `save_path`.
Args:
per_path (str): path to per csv file with one column as the sample_id and the other the per value
save_path (str): path to save the histrogram plot
"""
import csv
import matplotlib.pyplot as plt
import numpy as np
with open(per_path, 'r') as fid:
reader = csv.reader(fid, delimiter=',')
per_list = [float(row[1]) for row in reader]
plt.hist(per_list, bins=10, range=(0.0, 1.0))
plt.title("histogram of 2020-10-29 model PER values")
plt.xlabel("PER bins")
plt.ylabel("# of records")
plt.xticks(np.arange(0, 1.1, step=0.1))
#plt.yticks(labels=per_list)
if save_path == None:
save_path = "PER_histogram.png"
plt.savefig(save_path)
def loss_store2(self, x_train, x_gene):
with open('./result/genefinalfig/x_train.pickle', 'wb') as fp:
pickle.dump(x_train, fp)
with open('./result/genefinalfig/generated.pickle', 'wb') as fp:
pickle.dump(x_gene, fp)
bins = 100
plt.hist(x_gene, bins, facecolor='red', alpha=0.5)
plt.title('Histogram of distribution of generated data')
plt.xlabel('Generated data value')
plt.ylabel('Frequency')
plt.savefig(
'./result/genefinalfig/WGAN-Generated-data-distribution.jpg')
plt.close()
with open('./result/lossfig/wdis.pickle', 'wb') as fp:
pickle.dump(self.wdis_store, fp)
t = arange(len(self.wdis_store))
plt.plot(t, self.wdis_store, 'r--')
plt.xlabel('Iterations')
plt.ylabel('Wasserstein distance')
plt.savefig('./result/lossfig/WGAN-W-distance.jpg')
plt.close()
rv_pre, gv_pre, rv_pro, gv_pro = dwp(x_train, x_gene, self.testX,
self.db)
print 'Totally ' + str(len(rv_pre)) + ' of coordinates are left'
with open('./result/genefinalfig/rv_pre.pickle', 'wb') as fp:
pickle.dump(rv_pre, fp)
with open('./result/genefinalfig/gv_pre.pickle', 'wb') as fp:
pickle.dump(gv_pre, fp)
with open('./result/genefinalfig/rv_pro.pickle', 'wb') as fp:
pickle.dump(rv_pro, fp)
with open('./result/genefinalfig/gv_pro.pickle', 'wb') as fp:
pickle.dump(gv_pro, fp)
rv_pre, gv_pre, rv_pro, gv_pro = fig_add_noise(rv_pre), fig_add_noise(
gv_pre), fig_add_noise(rv_pro), fig_add_noise(gv_pro)
plt.scatter(rv_pre, gv_pre)
plt.title('Dimension-wise prediction, lr')
plt.xlabel('Real data')
plt.ylabel('Generated data')
plt.savefig('./result/genefinalfig/WGAN-dim-wise-prediction.jpg')
plt.close()
plt.scatter(rv_pro, gv_pro)
plt.title('Dimension-wise probability, lr')
plt.xlabel('Real data')
plt.ylabel('Generated data')
plt.savefig('./result/genefinalfig/WGAN-dim-wise-probability.jpg')
plt.close()
def img_gen(img,
zca=False,
rotation=0.,
w_shift=0.,
h_shift=0.,
shear=0.,
zoom=0.,
h_flip=False,
v_flip=False,
preprocess_fcn=None,
batch_size=9):
"""
define function to generate images
"""
datagen = ImageDataGenerator(zca_whitening=zca,
rotation_range=rotation,
width_shift_range=w_shift,
height_shift_range=h_shift,
shear_range=shear,
zoom_range=zoom,
fill_mode='nearest',
horizontal_flip=h_flip,
vertical_flip=v_flip,
preprocessing_function=preprocess_fcn,
data_format=K.image_data_format())
datagen.fit(img)
i = 0
for img_batch in datagen.flow(img, batch_size=9, shuffle=False):
for img in img_batch:
plt.subplot(330 + 1 + i)
plt.imshow(img)
i += 1
if i >= batch_size:
break
# plt.show()
plt.savefig('img/trans/cats.png')
def show_hough_line(img, accumulator, thetas, rhos, save_path=None):
'''
set up show image with matplotlib
'''
fig, ax = plt.pyplot.subplots(1, 2, figsize=(10, 10))
ax[0].imshow(img, cmap=plt.cm.gray)
ax[0].set_title('Input image')
ax[0].axis('image')
ax[1].imshow(
accumulator, cmap='jet',
extent=[np.rad2deg(thetas[-1]), np.rad2deg(thetas[0]), rhos[-1], rhos[0]])
ax[1].set_aspect('equal', adjustable='box')
ax[1].set_title('Hough transform')
ax[1].set_xlabel('Angles')
ax[1].set_ylabel('Distance')
ax[1].axis('image')
# plt.axis('off')
if save_path is not None:
plt.savefig(save_path, bbox_inches='tight')
plt.show()
def show_image(img_ndarray, id):
'''
Visualize images resulted from calling vis_smpl_params in Jupyternotebook
:param img_ndarray: Nx400x400x3
'''
import matplotlib as plt
import os
import numpy as np
import cv2
fig = plt.figure(figsize=(4, 4), dpi=300)
ax = fig.gca()
img = img_ndarray.astype(np.uint8)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
ax.imshow(img)
plt.axis('off')
if not os.path.isdir("images"):
os.makedirs("images")
fig_name = "images/fig" + str(id) + ".png"
plt.savefig(fig_name)
plt.close()
def draw_bar(savename):
import matplotlib.pyplot as plt
size = 3
x = np.arange(size)
a = [34.89, 33.87, 72.37]
b = [551.72, 552.87, 698.34]
xl = [
'training time \n on MNIST', 'training time on \n Fashion-MNIST',
'training time \n on CIFAR-10'
]
total_width, n = 0.54, 2
width = total_width / n
x = x - (total_width - width)
plt.figure()
plt.bar(x, a, width=width)
plt.bar(x + width, b, width=width)
plt.ylabel('time(s)')
plt.xticks(
x,
xl,
)
plt.legend()
plt.savefig('../eps/' + savename)
plt.show()
def plotdatatree(treeID, scale1, mass1):
plot_title="Mass Accretion History Tree " + str(treeID) #Can code the number in with treemax
x_axis="scale time"
y_axis="total mass"
figure_name=os.path.expanduser('~/figureTree' + str(treeID))
#Choose which type of plot you would like: Commented out.
plt.plot(scale1, mass1, linestyle="-", marker="o")
#plt.scatter(scale1, mass1, label="first tree")
plt.title(plot_title)
plt.xlabel(x_axis)
plt.ylabel(y_axis)
#plt.yscale("log")
plt.savefig(figure_name)
#In order to Plot only a single tree on a plot must clear lists before loop.
#Comment out to over plot curves.
plt.clf()
clearmass = []
clearscale = []
return clearmass, clearscale
contour_font = 10
fig = plt.figure(figsize=(6, 5))
ax_ray = fig.add_subplot(111)
dist = [20, 60, 85, 95]
dist = [8, 27, 48, 67, 89, 99]
dist = [30, 60, 80, 95]
for i in range(len(dist)):
s = str(str(dist[i]) + "_SURF96.out")
data = np.loadtxt(s, usecols=(5, 6, 7))
ax_ray.plot(data[:, 0], data[:, 1], label=str(dist[i] * 10) + "km")
ax_ray.grid(True, linestyle='--', color='black', linewidth=0.15)
plt.xticks(fontsize=axes_label_font_size)
plt.yticks(fontsize=axes_label_font_size)
plt.xlabel('Time period ($s$)',
fontsize=axes_label_font_size,
fontweight='bold')
plt.ylabel('Phase velocity ($km/s$)',
fontsize=axes_label_font_size,
fontweight='bold')
plt.legend(fancybox=True,
shadow=True,
framealpha=0.5,
loc='lower right',
fontsize=legend_font_size)
plt.savefig('Rayleigh_Phase_dispersion.jpg', dpi=400)
plt.show()
exBestVersions = []
exNomaxfuse = []
orthBestVersions = []
orthNomaxfuse = []
N = 6 #number of matrix orders we consider: 50, 100, 250, 500, 1000, 2000
ind = np.arrange(N)
width = .20 #bar width
fig = pl.figure()
ax = fig.add_subplot(111) #add the bars to the figure along the axis
#define the bars in the bar graph
r1 = ax.bar(ind, gaNomaxfuse, width, color = 'b')
r2 = ax.bar(ind+width, gaBestVersions, width, color = 'y')
r3 = ax.bar(ind+(2*width), exNomaxfuse, width, color = 'b')
r4 = ax.bar(ind+(3*width), exBestVersions, width, color = 'y')
r5 = ax.bar(ind+(4*width), orthNomaxfuse, width, color = 'b')
r6 = ax.bar(ind+(5*width), orthBestVersions, width, color = 'y')
ax.set_ylabel('Time (sec)')
ax.set_xlabel('Nomaxfuse and best version by search strategy between n = 50 and n = 2000')
ax.set_title('Timing by search strategy and matrix size')
ax.set_xticks(ind+width)
ax.set_xticklabels( ('50', '100', '250', '500', '1000', '2000') )
ax.legend()
plt.savefig('searchstratsresults.pdf')
import pandas as pd
import matplotlib as plt
permutation3 = pd.read_csv('Results/Permutation_3.csv')
permutation4 = pd.read_csv('Results/Permutation_4.csv')
permutation5 = pd.read_csv('Results/Permutation_5.csv')
permutation3[' Median set size'].hist()
plt.savefig('dist_permutation_3.pdf')
#do the rest
axes[0,0].set_xlabel('u-g')
axes[0,0].set_xlabel('g-r')
axes[0,1].plot(g-r,r-i,marker='o',linestyle='')
axes[0,1].set_xlabel('g-r')
axes[0,1].set_xlabel('r-i')
axes[1,0].plot(r-i,i-z,marker='o',linestyle='')
axes[1,0].set_xlabel('r-i')
axes[1,0].set_xlabel('i-z')
axes[1,1].plot(u-g,r-i,marker='o',linestyle='')
axes[1,1].set_xlabel('u-g')
axes[1,1].set_xlabel('r-i')
plt.savefig('scatter_sdss_photometry.png')
#Here are the contour plots
#Step 1: use np.histogram2d to create "density" plots of the points
H1, xedges1, yedges1 = np.histogram2d((u-g), (g-r))
H2, xedges2, yedges2 = np.histogram2d((g-r),(r-i))
H3, xedges3, yedges3 = np.histogram2d((r-i),(i-z))
H4, xedges4, yedges4 = np.histogram2d((u-g),(r-i))
fig,axes = plt.subplots(2,2)
extent1 = [yedges1[0], yedges1[-1], xedges1[0], xedges1[-1]]
#This draws contours around the density
cset = axes[0,0].contour(H1,colors=['black','green','blue','red'],
linewidths=(1.9, 1.6, 1.5, 1.4),extent=extent1)
#Label the contours!
##
sc = SparkContext( appName="Wikipedia Count" )
lines = sc.textFile(infile)
<<<<<<< HEAD
counts = lines.map(lambda line:line.split('\t')[2]).map(lambda x:(x[0:7],1)).reduceByKey(add)
counts_by_month = counts.sortBy(lambda x: x[0])
length = counts_by_month.count()
x = range(0, length)
lables = counts_by_month.map(lambda x : x[0]).collect()
y = counts_by_month.map(lambda x : x[1]).collect()
plt.plot(np.array(x),np.array(y))
plt.xticks(x,lables,rotation = 'vertical')
plt.savefig("counts_by_month.pdf")
counts_by_month.collect()
=======
counts = lines.map()
>>>>>>> 65a15a888eef7c1f146383d61b9f57882504af41
## YOUR CODE GOES HERE
## PUT YOUR RESULTS IN counts
"""with open("wikipedia_by_month.txt","w") as fout:
for (date, count) in counts_by_month:
fout.write("{}\t{}\n".format(date,count))"""
##
import sys
import numpy as np
import matplotlib as plt
import math
a=sys.argv[1]
data=np.loadtxt(a)
x=data[:,3]
y=data[:,4]
figura=plt.polyfit(x,y,1)
plt.scatter(x,y)
plt.plot(x,y*figura[0]*(y**4) + figura[i]*(y**3), figura[2]*(y**2), figura[3]*y + fit[4])
plt.xlabel("Pasos (x)", frontsize=20)
plt.ylabel("Distancia (y)", frontsize =20)
plt.tittle("Numero de Pasos VS Distancia con la Regresion", frontsize =15)
plt.savefig('ajuste.png')
from mpl_toolkits.mplot3d import axes3d
import matplotlib as plt
plt.use('PS')
from pylab import *
fig = plt.figure()
ax = fig.gca(projection='3d')
X, Y, Z = axes3d.get_test_data(0.05)
print "X - data"
print X
print "Y - data"
print Y
print "Z - data"
print Z
ax.plot_surface(X, Y, Z, rstride=8, cstride=8, alpha=0.3)
cset = ax.contour(X, Y, Z, zdir='z', offset=-100)
cset = ax.contour(X, Y, Z, zdir='x', offset=-40)
cset = ax.contour(X, Y, Z, zdir='y', offset=40)
ax.set_xlabel('X')
ax.set_xlim3d(-40, 40)
ax.set_ylabel('Y')
ax.set_ylim3d(-40, 40)
ax.set_zlabel('Z')
ax.set_zlim3d(-100, 100)
plt.savefig("test.ps")
def train_dcgan_labeled(gen, dis, epoch0=0):
print('CHAINER begin training'); sys.stdout.flush()
o_gen = optimizers.Adam(alpha=0.0002, beta1=0.5)
o_dis = optimizers.Adam(alpha=0.0002, beta1=0.5)
print('CHAINER begin gen'); sys.stdout.flush()
o_gen.setup(gen)
o_dis.setup(dis)
print('CHAINER begin add'); sys.stdout.flush()
o_gen.add_hook(chainer.optimizer.WeightDecay(0.00001))
o_dis.add_hook(chainer.optimizer.WeightDecay(0.00001))
print('CHAINER begin zvis'); sys.stdout.flush()
# zvis = (xp.random.uniform(-1, 1, (100, nz), dtype=np.float32))
print('CHAINER begin for'); sys.stdout.flush()
for epoch in range(epoch0,n_epoch):
print("epoch:",epoch)
sys.stdout.flush()
perm = np.random.permutation(n_train)
sum_l_dis = np.float32(0)
sum_l_gen = np.float32(0)
for i in range(0, n_train, batchsize):
# discriminator
# 0: from dataset
# 1: from noise
#print "load image start ", i
x2 = np.zeros((batchsize, 3, 96, 96), dtype=np.float32)
for j in range(batchsize):
#try:
rnd = np.random.randint(len(dataset))
rnd2 = np.random.randint(2)
img = np.asarray(Image.open(io.BytesIO(dataset[rnd])).convert('RGB')).astype(np.float32).transpose(2, 0, 1)
x2[j,:,:,:] = (img[:,0:96,0:96]-128.0)/128.0
#except:
# print('read image error occured', fs[rnd])
#print "load image done"
# train generator
z = Variable(xp.random.uniform(-1, 1, (batchsize, nz), dtype=np.float32))
x = gen(z)
yl = dis(x)
L_gen = F.softmax_cross_entropy(yl, Variable(xp.zeros(batchsize, dtype=np.int32)))
L_dis = F.softmax_cross_entropy(yl, Variable(xp.ones(batchsize, dtype=np.int32)))
# train discriminator
x2 = Variable(cuda.to_gpu(x2))
yl2 = dis(x2)
L_dis += F.softmax_cross_entropy(yl2, Variable(xp.zeros(batchsize, dtype=np.int32)))
#print "forward done"
o_gen.zero_grads()
L_gen.backward()
o_gen.update()
o_dis.zero_grads()
L_dis.backward()
o_dis.update()
sum_l_gen += L_gen.data.get()
sum_l_dis += L_dis.data.get()
#print "backward done"
if i%image_save_interval==0:
pylab.rcParams['figure.figsize'] = (16.0,16.0)
pylab.clf()
vissize = 100
z = zvis
z[50:,:] = (xp.random.uniform(-1, 1, (50, nz), dtype=np.float32))
z = Variable(z)
x = gen(z, test=True)
x = x.data.get()
for i_ in range(100):
tmp = ((np.vectorize(clip_img)(x[i_,:,:,:])+1)/2).transpose(1,2,0)
pylab.subplot(10,10,i_+1)
pylab.imshow(tmp)
pylab.axis('off')
pylab.savefig('%s/vis_%d_%d.png'%(out_image_dir, epoch,i))
serializers.save_hdf5("%s/dcgan_model_dis_%d.h5"%(out_model_dir, epoch),dis)
serializers.save_hdf5("%s/dcgan_model_gen_%d.h5"%(out_model_dir, epoch),gen)
serializers.save_hdf5("%s/dcgan_state_dis_%d.h5"%(out_model_dir, epoch),o_dis)
serializers.save_hdf5("%s/dcgan_state_gen_%d.h5"%(out_model_dir, epoch),o_gen)
print('epoch end', epoch, sum_l_gen/n_train, sum_l_dis/n_train)
def main(args):
files=args.cgfiles
#Uncomment the following line to display the files in a random order.
#random.shuffle(files)
#Prepare the pyplot figure
totalFigures=len(files)
figuresPerLine=int(math.ceil(math.sqrt(totalFigures)))
fig, ax=plt.subplots(int(math.ceil(totalFigures/figuresPerLine)),figuresPerLine, squeeze=False, figsize=(8,8))
#Background color of figure (not plot)
if args.style=="WOB":
fig.patch.set_facecolor('black')
#Plot one projection per file.
for i, file_ in enumerate(files):
#get the subplot axes (Note: axes != axis in matplotlib)
current_axes=ax[i//figuresPerLine, i%figuresPerLine]
#Parse the file
cg=ftmc.CoarseGrainRNA(file_)
# Random projection direction, if no direction present in the file
if args.proj_direction:
direction=list(map(float, args.proj_direction.split(",")))
elif cg.project_from is not None:
direction=cg.project_from
else:
direction=ftuv.get_random_vector()
#Generate the projection object
proj=ftmp.Projection2D(cg, direction, rotation=180, project_virtual_atoms=args.virtual_atoms)
#Simulate a reduced resolution of the image.
if args.condense:
proj.condense(args.condense)
target_elems=[]
if args.show_distances:
try:
num_elems=int(args.show_distances)
except:
target_elems=args.show_distances.split(",")
else:
if num_elems>len(proj._coords.keys()):
raise ValueError("--show-distances must not be greater {} for the current projection ({}:'{}')".format(len(proj._coords.keys()), i, file_))
elems=list(proj._coords.keys())
random.shuffle(elems)
while len(target_elems)<num_elems:
r=random.random()
if r<0.4:
hairpins=[ x for x in elems if x[0]=="h" and x not in target_elems ]
if hairpins:
target_elems.append(hairpins[0])
continue
if r<0.6:
multiloops=[ x for x in elems if x[0]=="m" and x not in target_elems ]
if multiloops:
target_elems.append(multiloops[0])
continue
others=[ x for x in elems if x not in target_elems]
target_elems.append(others[0])
comb=list(it.combinations(target_elems, 2))
#print(comb, target_elems)
line2dproperties={}
if args.style=="BOW":
line2dproperties["color"]="black"
elif args.style=="WOB":
line2dproperties["color"]="white"
#Plot the projection #
proj.plot(current_axes, margin=15, linewidth=3, add_labels=set(target_elems), line2dproperties=line2dproperties,
show_distances=comb, print_distances=args.print_distances)
#Uncomment to set a substring of the filename as a title
#current_axes.set_title(file[-15:])
#Hide the x- and y axis.
current_axes.get_xaxis().set_visible(False)
current_axes.get_yaxis().set_visible(False)
#Print the projection direction and the filename in the plot.
if args.show_direction or args.p:
current_axes.text(0.01,0.01,"Projection direction: ({},{},{})".format(round(direction[0],3), round(direction[1],3), round(direction[2],3)), transform=current_axes.transAxes)
if args.show_filename or args.p:
current_axes.text(0.01,0.99,"File: {}".format(file_), transform=current_axes.transAxes, verticalalignment='top',)
#Change the backgroundcolor of the plot area.
if args.style=="WOB":
current_axes.set_axis_bgcolor('black')
#Hide additional subplots with no projection on them.
for i in range(len(files),int(math.ceil(totalFigures/figuresPerLine))*figuresPerLine):
ax[i//figuresPerLine, i%figuresPerLine].axis('off')
# Reduce the space outside of the plots and between the subplots.
plt.subplots_adjust(left=0.025, right=0.975, bottom=0.025, top=0.975, wspace=0.05, hspace=0.05)
if args.out:
for ofname in args.out:
if args.out_path:
ofname=os.path.join(args.out_path, ofname)
ofname=os.path.expanduser(ofname)
matplotlib.savefig(ofname,format=ofname[-3:])
if not args.out or args.show:
#Show the plot and clear it from the internal memory of matplotlib.
plt.show()
ax4 = subplot(325)
ax5 = subplot(326)
ind = 4
ax5.set_xticklabels(xlabels)
ax5.get_yaxis().set_ticks([])
plot(gfv[kmeans.labels_==ind].T,lw=0.5,color='grey')
plot(kmeans.cluster_centers_.T[:,ind],lw=2,color='#4B088A')
ax5 = subplot(326)
text(-14.5, 11, 'Total Number of Employees\n k = 5', size=16)
# save plot to pdf:
from matplotlib.backends.backend_pdf import PdfPages
pp = PdfPages('employees.pdf')
plt.savefig(pp, format='pdf')
pp.close()
# create geodataframe of different classes:
#gdf = gp.GeoDataFrame.from_file('../output/nyc-zip-code-extend.json')
gdf = gp.GeoDataFrame.from_file('../data/nyc_zipcta/nyc_zipcta.shp')
# dictionary of cluster labels for each zip code
labels = {}
for i in range(0, len(zcta)):
labels[zcta[i]] = kmeans.labels_[i]
# add "clusterLabels" to existing gdf
labelList = []
zipList = []
for i in range(0, len(gdf)):
def show_overfitting(request):
dic = {}
# 实验一：对比不同模型的cross-validation结果
# 用load_wine方法导入数据
wine_data = datasets.load_wine()
# print(wine_data.feature_names)
data_input = wine_data.data
data_output = wine_data.target
rf_class = RandomForestClassifier()
lr_class = LogisticRegression()
svm_class = svm.LinearSVC()
# print(cross_val_score(rf_class, data_input, data_output, scoring='accuracy', cv=4))
# 1.使用随机森林方法观察准确率
accuracy_rf = cross_val_score(
rf_class, data_input, data_output, scoring='accuracy',
cv=10).mean() * 100
print('Accuracy of Random Forest is:', accuracy_rf)
# 2.使用支持向量机方法观察准确率
accuracy_svm = cross_val_score(
svm_class, data_input, data_output, scoring='accuracy',
cv=10).mean() * 100
print('Accuracy of SVM is:', accuracy_svm)
# 3.使用逻辑回归方法观察准确率
accuracy_lr = cross_val_score(
lr_class, data_input, data_output, scoring='accuracy',
cv=10).mean() * 100
print('Accuracy of LogisticRegression is:', accuracy_lr)
rcParams['figure.figsize'] = 12, 10
x = np.array([1.4 * i * np.pi / 180 for i in range(0, 300, 4)])
np.random.seed(20) # 固定每次生成的随机数
y = np.sin(x) + np.random.normal(0, 0.2, len(x))
data = pd.DataFrame(np.column_stack([x, y]), columns=['x', 'y'])
plt.plot(data['x'], data['y'], '.')
file = "static/img/han01.png"
dic["pic1"] = "/" + file
plt.savefig(file)
# plt.show()
for i in range(2, 16): # power of 1 is already there
colname = 'x_%d' % i # new var will be x_power
data[colname] = data['x']**i
# print(data.head())
def linear_regression(data, power, models_to_plot):
# initialize predictors:
predictors = ['x']
if power >= 2:
predictors.extend(['x_%d' % i for i in range(2, power + 1)])
# Fit the model
linreg = LinearRegression(normalize=True)
linreg.fit(data[predictors], data['y'])
y_pred = linreg.predict(data[predictors])
# Check if a plot is to be made for the entered power
if power in models_to_plot:
plt.subplot(models_to_plot[power])
plt.tight_layout()
plt.plot(data['x'], y_pred)
plt.plot(data['x'], data['y'], '.')
plt.title('Plot for power: %d' % power)
# Return the result in pre-defined_format
rss = sum((y_pred - data['y'])**2)
ret = [rss]
ret.extend([linreg.intercept_])
ret.extend(linreg.coef_)
return ret
col = ['rss', 'intercept'] + ['coef_x_%d' % i for i in range(1, 16)]
ind = ['model_pow_%d' % i for i in range(1, 16)]
coef_matrix_simple = pd.DataFrame(index=ind, columns=col)
# 注意上行代码的columns不能携程column单数，画图就无法画出来了
# 定义作图的位置与模型的复杂度
models_to_plot = {1: 231, 3: 232, 6: 233, 8: 234, 11: 235, 14: 236}
# 画出来
for i in range(1, 16):
coef_matrix_simple.iloc[i - 1, 0:i + 2] = linear_regression(
data, power=i, models_to_plot=models_to_plot)
file = "static/img/han02.png"
dic["pic2"] = "/" + file
plt.savefig(file)
# plt.show()
# 定义作图的位置与模型的复杂度
models_to_plot = {
1e-15: 231,
1e-10: 232,
1e-4: 233,
1e-3: 234,
1e-2: 235,
5: 236
}
def ridge_regression(data, predictors, alpha, models_to_plot={}):
# Fit the model:1.初始化模型配置 2.模型拟合 3.模型预测
ridgereg = Ridge(alpha=alpha, normalize=True)
ridgereg.fit(data[predictors], data['y'])
# predictors的内容实际是data(定义的一种DataFrame数据结构)的某列名称
y_pred = ridgereg.predict(data[predictors])
# Check if a plot is to be made for the entered alpha
if alpha in models_to_plot:
plt.subplot(models_to_plot[alpha])
plt.tight_layout()
plt.plot(data['x'], y_pred) # 画出拟合曲线图
plt.plot(data['x'], data['y'], '.') # 画出样本的散点图
plt.title('Plot for alpha: %.3g' % alpha)
# Return the result in pre-defined format
rss = sum((y_pred - data['y'])**2)
ret = [rss]
ret.extend([ridgereg.intercept_])
ret.extend(ridgereg.coef_)
return ret
predictors = ['x']
predictors.extend(['x_%d' % i for i in range(2, 16)])
# Set the different values of alpha to be tested
alpha_ridge = [1e-15, 1e-10, 1e-8, 1e-4, 1e-3, 1e-2, 1, 5, 10, 20]
# Initialize the dataframe for storing coeficients
col = ['rss', 'intercept'] + ['coef_x_%d' % i for i in range(1, 16)]
ind = ['alpha_%.2g' % alpha_ridge[i] for i in range(0, 10)]
coef_matrix_ridge = pd.DataFrame(index=ind, columns=col)
models_to_plot = {
1e-15: 231,
1e-10: 232,
1e-4: 233,
1e-3: 234,
1e-2: 235,
5: 236
}
for i in range(10):
coef_matrix_ridge.iloc[i, ] = ridge_regression(data, predictors,
alpha_ridge[i],
models_to_plot)
file = "static/img/han03.png"
dic["pic3"] = "/" + file
plt.savefig(file)
# plt.show()
def lasso_regression(data, predictors, alpha, models_to_plot={}):
# Fit the model
lassoreg = Lasso(alpha=alpha, normalize=True, max_iter=1e5)
lassoreg.fit(data[predictors], data['y'])
y_pred = lassoreg.predict(data[predictors])
# Check if a plot is to be made for the entered alpha
if alpha in models_to_plot:
plt.subplot(models_to_plot[alpha])
plt.tight_layout()
plt.plot(data['x'], y_pred)
plt.plot(data['x'], data['y'], '.')
plt.title('Plot for alpha:%.3g' % alpha)
# Return the result in pre-defined format
rss = sum((y_pred - data['y'])**2)
ret = [rss]
ret.extend([lassoreg.intercept_])
ret.extend(lassoreg.coef_)
return ret
predictors = ['x']
predictors.extend(['x_%d' % i for i in range(2, 16)])
# Define the alpha values to test
alpha_lasso = [1e-15, 1e-10, 1e-8, 1e-5, 1e-4, 1e-3, 1e-2, 1, 5, 10]
# Initialize the dataframe to store coefficients
col = ['rss', 'intercept'] + ['coef_x_%d' % i for i in range(1, 16)]
ind = ['alpha_%.2g' % alpha_lasso[i] for i in range(0, 10)]
coef_matrix_lasso = pd.DataFrame(index=ind, columns=col)
# Define the models_to_plot
models_to_plot = {
1e-10: 231,
1e-5: 232,
1e-4: 233,
1e-3: 234,
1e-2: 235,
1: 236
}
# Iterate over the 10 alpha values:
for i in range(10):
coef_matrix_lasso.iloc[i, ] = lasso_regression(data, predictors,
alpha_lasso[i],
models_to_plot)
file = "static/img/han04.png"
dic["pic4"] = "/" + file
plt.savefig(file)
# plt.show()
return render(request, "overfitting.html", dic)
print t
print v
initialize(v, s, t, dt, n)
calculate(v, s, t, dt, n)
store(v, t, n)
#plot
plt.figure(1)
plt.subplot(211)
plt.plot(t, v,"g-", linewidth=2.0)
plt.scatter(t, v)
plt.title('The Velocity of a Free Falling Object')
plt.xlabel('Time($t$)', fontsize=14)
plt.ylabel('Velocity($m/s$)', fontsize=14)
plt.text(3,-60,r'$g = 9.8 m/s^2$', fontsize=16)
plt.grid(True)
plt.subplot(212)
plt.plot(t, s,"g-", linewidth=2.0)
plt.scatter(t, s)
plt.title('The Displacement of a Free Falling Object')
plt.xlabel('Time($t$)', fontsize=14)
plt.ylabel('Displacement($m$)', fontsize=14)
plt.text(3,-300,r'$g = 9.8 m/s^2$', fontsize=16)
plt.grid(True)
plt.show()
plt.savefig("ex1.jpg")
read()
def plot_trace(x_l, n_l, file_path):
figure()
plot(n_l,x_l)
plt.savefig(file_path)
def plot_hist(x_l, file_path):
figure()
n, bins, patches = hist(x_l, 20, histtype='bar')
plt.savefig(file_path)
counts = lines.map(lambda date: date.split('\t')[2]) \
.map(lambda month:month[0:7]) \
.map(lambda x: (x,1)) \
.reduceByKey(add)
month_sorted = counts.sortBy(lambda x: x[0]).collect()
## YOUR CODE GOES HERE
## PUT YOUR RESULTS IN counts
with open("wikipedia_by_month.txt","w") as fout:
for (date, count) in month_sorted:
fout.write("{}\t{}\n".format(date,count))
##
## Terminate the Spark job
##
#############
# plot
#############
data = pandas.read_csv("wikipedia_by_month.txt", sep='\t', header = None, names=['date', 'count'])
fig = pyplot.figure()
index = np.arange(len(data[0]))
pyplot.bar(index, data['count'], width = width)
fig.autofmt_xdate()
plt.xticks(index, data['date'], rotation = 'vertical')
plt.savefig("figure.pdf")
sc.stop()
t = pickle.load(pickle_file)
v = pickle.load(pickle_file)
initialize(v, s, t, dt, n)
calculate(v, s, t, dt, n)
store(v, t, n)
#plot
plt.figure(1)
plt.subplot(211)
plt.plot(t, v,"g-", linewidth=1.0)
plt.scatter(t, v)
plt.title('The Velocity of a Free Falling Object')
#plt.xlabel('Time($t$)', fontsize=12) (cancel because words overlap)
plt.ylabel('Velocity($m/s$)', fontsize=12)
plt.text(3,0,r'$g = 9.8 m/s^2$', fontsize=16)
plt.grid(True)
plt.subplot(212)
plt.plot(t, s,"g-", linewidth=1.0)
plt.scatter(t, s)
plt.title('The Displacement of a Free Falling Object')
plt.xlabel('Time($t$)', fontsize=12)
plt.ylabel('Displacement($m$)', fontsize=12)
plt.text(3,0,r'$g = 9.8 m/s^2$', fontsize=16)
plt.grid(True)
plt.show()
plt.savefig("ex4.jpg")
read()
