def plotting(sim_context1,sim_context2,diff,data_df,total_samples):
plt.plot(sim_context1,label="Context 1")
plt.plot(sim_context2,label="Context 2")
x_labels_word1 = data_df["word1"]
x_labels_word2 = data_df["word2"]
xlabels = [0] * total_samples
xticks_x = [0] * total_samples
for wp in range (total_samples):
xlabels[wp] = x_labels_word1[wp]+ "\n"+x_labels_word2[wp]
xticks_x[wp] = wp+1
plt.plot(diff,label="Difference")
plt.legend(loc='center right')
# Add title and x, y labels
plt.title("Elmo Embedding Model Results", fontsize=16, fontweight='bold')
plt.xlabel("Word")
plt.ylabel("Similarity")
plt.xticks(xticks_x, xlabels)
plt.show()
def plot_four(plot_data):
fig = plt.figure(figsize=(20, 10))
# gs = gridspec.GridSpec(1, 2, height_ratios=[1, 2])
ax = fig.add_subplot(223, projection='3d')
ax.scatter(plot_data['sx'], plot_data['sy'], plot_data['sz'])
ax.plot(plot_data['sx'], plot_data['sy'], plot_data['sz'], color='b')
ax.view_init(azim=0, elev=90) #xy plane
plt.xticks(fontsize=10)
ax.set_title('Displacement Projection in xy Plane',size=20)
ax2 = fig.add_subplot(224, projection='3d')
ax2.scatter(plot_data['sx'], plot_data['sy'], plot_data['sz'])
ax2.plot(plot_data['sx'], plot_data['sy'], plot_data['sz'], color='b')
ax2.view_init(azim=0, elev=45)
ax2.set_title('Displacement',size=20)
ax3 = fig.add_subplot(221)
# 50 represents number of points to make between T.min and T.max
xnew = np.linspace(0,8,50)
spl = make_interp_spline(pd.Series(range(9)), plot_data['tilt1'], k=3) # type: BSpline
x = spl(xnew)
spl = make_interp_spline(pd.Series(range(9)), plot_data['tilt2'], k=3) # type: BSpline
y = spl(xnew)
spl = make_interp_spline(pd.Series(range(9)), plot_data['compass'], k=3) # type: BSpline
z = spl(xnew)
ax3.plot(x,"b-",label='tilt1')
ax3.plot(y,"r-",label='tilt2')
ax3.plot(z,"g-",label='compass')
ax3.legend(loc="lower left",prop={'size': 20})
ax3.set_title('Orientation Plot (degree)',size=20)
ax3.tick_params(labelsize=20)
ax4 = fig.add_subplot(222)
# x = gaussian_filter1d(plot_data['ax'], sigma=1)
# y = gaussian_filter1d(plot_data['ay'], sigma=1)
# z = gaussian_filter1d(plot_data['az'], sigma=1)
# mag = gaussian_filter1d(plot_data['accelerometer'], sigma=1)
spl = make_interp_spline(pd.Series(range(9)), plot_data['ax'], k=3) # type: BSpline
x = spl(xnew)
spl = make_interp_spline(pd.Series(range(9)), plot_data['ay'], k=3) # type: BSpline
y = spl(xnew)
spl = make_interp_spline(pd.Series(range(9)), plot_data['az'], k=3) # type: BSpline
z = spl(xnew)
spl = make_interp_spline(pd.Series(range(9)), plot_data['accelerometer'], k=3) # type: BSpline
mag = spl(xnew)
ax4.plot(x/1000,"c--",label='ax')
ax4.plot(y/1000,"g--",label='ay')
ax4.plot(z/1000,"b--",label='az')
ax4.plot(mag,"r-",label='Acc')
ax4.legend(loc="lower left",prop={'size': 20})
ax4.set_title('Acceleration Plot (g)',size=20)
ax4.tick_params(labelsize=20)
plt.tight_layout()
plt.show()
fig.savefig('FourInOne.png')
def bar_graph(category, age_grp, sex, x, y, year=None, country=None):
plt.figure()
plt.ylabel('ATE = Y1 - Y0')
plt.xlabel('Years')
plt.bar(range(len(x)), x, align='center')
plt.xticks(range(len(x)), y, rotation='vertical')
if country:
plt.title("%s Suicide Rates for WC; %s ages %s" %
(country, sex, age_grp))
name = country + sex + age_grp + '.png'
# plt.show()
plt.tight_layout()
plt.savefig('./graphs/Countries' + '/' + sex + '/' +
name.replace(' ', '_'))
elif year:
plt.title("Change in Suicide Rates per Country in %s; %s ages %s" %
(year, sex, age_grp))
name = category + sex + str(year) + age_grp + '.png'
# plt.show()
plt.tight_layout()
plt.savefig('./graphs/' + category + '/' + sex + '/' + str(year) +
'/' + name.replace(' ', ''))
else:
plt.title("Change in Suicide Rates in %s Countries; %s ages %s" %
(category, sex, age_grp))
name = category + sex + age_grp + '.png'
# plt.show()
plt.tight_layout()
plt.savefig('./graphs/' + category + '/' + sex + '/' +
name.replace(' ', ''))
def tmp(cm, acts):
import matplotlib.pyplot as plt
import numpy as np
plt.imshow(cm, interpolation='nearest')
plt.xticks(np.arange(0, len(acts)), acts)
plt.yticks(np.arange(0, len(acts)), acts)
def plot():
plt.figure(figsize=(20, 10))
width = 0.5
index = np.arange(26)
print 'SUM PLOT 1', sum(row[0] for row in data)
print 'SUM PLOT 2', sum(row[1] for row in data)
print 'SUM PLOT 3', sum(row[2] for row in data)
print data[0]
p0 = plt.bar(index, data[0], width, color='y') # people
p1 = plt.bar(index, data[1], width, color='g') # nature
p2 = plt.bar(index, data[2], width, color='r') # activity
p3 = plt.bar(index, data[3], width, color='b') # food
p4 = plt.bar(index, data[4], width, color='c') # symbols
p5 = plt.bar(index, data[5], width, color='m') # objects
p6 = plt.bar(index, data[6], width, color='k') # flags
p7 = plt.bar(index, data[7], width, color='w') # uncategorized
plt.ylabel('Usage')
plt.title('Emoji category usage per city')
plt.xticks(index + width/2.0, cities)
plt.yticks(np.arange(0, 1, 0.1))
plt.legend((p0[0], p1[0], p2[0], p3[0], p4[0], p5[0], p6[0], p7[0]), categories_names)
plt.show()
def getGraph():
for i, clf in enumerate((svm, rbf_svc, rbf_svc_tunning)):
# Se grafican las fronteras
plt.subplot(2, 2, i + 1)
plt.subplots_adjust(wspace=0.4, hspace=0.4)
Z = clf.predict(np.c_[x_matrizSetEntrenamientoVect, y_clases])
#Color en las gráficas
Z = Z.reshape(x_matrizSetEntrenamientoVect.shape)
plt.contourf(x_matrizSetEntrenamientoVect,
y_clases,
Z,
cmap=plt.cm.Paired,
alpha=0.8)
#Puntos de entrenamiento
plt.scatter(x_matrizSetEntrenamientoVect[:, 0],
x_matrizSetEntrenamientoVect[:, 1],
c=y_clases,
cmap=plt.cm.Paired)
plt.xlabel('Longitud Sepal')
plt.ylabel('Peso Sepal')
plt.xlim(x_matrizSetEntrenamientoVect.min(),
x_matrizSetEntrenamientoVect.max())
plt.ylim(y_clases.min(), y_clases.max())
plt.xticks(())
plt.yticks(())
plt.title(titles[i])
plt.show()
def plot_gallery(images, titles, h, w, n_row=3,n_col=4):
plt.figure(figsize=(1.8*n_col, 2.4*n_row))
plt.subplots_adjust(bottom=0,left=.01,right=.99,top=.90,hspace=.35)
for i in range(n_row * n_col):
plt.subplot(n_row,n_col,i+1)
plt.imshow(images[i].reshape(h,w),cmap=plt.cm.gray)
plt.title(titles[i],size=12)
plt.xticks(())
plt.yticks(())
def multiplot_gen_property_type():
#
# font = {'family': 'Liberation Serif',
# 'weight': 'normal',
# 'size': 15
# }
#
# # play around with the font size if it is too big or small
# matplotlib.rcParams['axes.titlesize'] = 12
# matplotlib.rcParams['axes.labelsize'] = 12
# matplotlib.rc('font', **font)
# # matplotlib.rcParams['text.usetex'] = True
# matplotlib.rcParams['pdf.fonttype'] = 42
# matplotlib.rcParams['pdf.use14corefonts'] = True
x = list(data.keys())
y1=[]
y2=[]
y3=[]
y4=[]
y5=[]
y6=[]
for year in data.keys():
for option_name, count in data[year].items():
if option_name == 'domain':
y1.append(count)
if option_name == 'sitekey':
y2.append(count)
if option_name == 'third-party':
y3.append(count)
if option_name == 'websocket':
y4.append(count)
if option_name == 'webrtc':
y5.append(count)
if option_name == 'csp':
y6.append(count)
plt.plot(x, y1,'-o',label='domain')
plt.plot(x, y2,'-v',label='sitekey')
plt.plot(x, y3,'-^',label='third-party')
plt.plot(x, y4,'-<',label='websocket')
plt.plot(x, y5,'->',label='webrtc')
plt.plot(x, y6,'-1',label='csp')
plt.xticks(rotation='vertical')
plt.xlabel('Year')
plt.ylabel('Count')
plt.legend(ncol=2)
plt.tight_layout()
plt.savefig('easylist-property-type.pdf ', format='pdf', dpi=1200)
def plot_average(collected_results, versions, args, plot_std=True):
test_type = args.test_type
model_name = args.model
means, stds = [], []
for version in versions:
data = collected_results[version]
if (plot_std):
means.append(np.mean(data))
stds.append(np.std(data))
else:
means.append(data)
means = np.array(means)
stds = np.array(stds)
if (test_type == "size" or test_type == "allsize"):
x = ["0%", "20%", "40%", "60%", "80%", "100%"]
elif (test_type == "accdomain" or test_type == "moredomain"):
x = [0, 1, 2, 3, 4]
else:
x = versions
color = 'blue'
plt.plot(x, means, color=color)
if (plot_std):
plt.fill_between(x,
means - stds,
means + stds,
alpha=0.1,
edgecolor=color,
facecolor=color,
linewidth=1,
antialiased=True)
plt.xticks(np.arange(len(x)), x, fontsize=18)
plt.yticks(fontsize=18)
plt.xlabel(XLABELS[test_type], fontsize=18)
plt.ylabel('average absolute effect size', fontsize=18)
plt.title("Influence of {} on bias removal \nfor {}".format(
TITLES[test_type], MODEL_FORMAL_NAMES[model_name]),
fontsize=18)
plt.tight_layout()
plot_path = os.path.join(
args.eval_results_dir, "plots",
"{}-{}-avg{}.png".format(model_name, test_type,
"-std" if plot_std else ""))
plt.savefig(plot_path)
def plot_score_dist(spacing, std_along, prob_miss, max_distance):
from matplotlib.pylab import plt
plt.close("Score Dist")
plt.figure("Score Dist")
d = np.linspace(0, max_distance, 500)
plt.plot(d, [score_dist(di, spacing, std_along, prob_miss) for di in d])
plt.vlines(spacing, 0, 1)
plt.vlines(spacing * 2, 0, 1, ls='--')
plt.annotate("Miss-detect the next mine", (spacing * 2, 0.5), (12, 0),
textcoords='offset points')
plt.ylabel('$p(d)$')
plt.xlabel('$d$')
plt.grid()
plt.xticks(np.arange(max_distance))
plt.xlim(0, max_distance)
plt.savefig('score_dist.pdf')
def f3():
xs = [0, 1, 2, 5]
ys = [0, 0, 1, 1]
fig, ax = plt.subplots()
ax.set_yticklabels([])
ax.set_xticklabels([])
plt.plot(xs, ys, label="$f_n(x)$")
plt.xticks(xs, ['', r'$n-1$', r'$n$', ''])
plt.yticks([1], ['$1$'])
plt.legend()
ax.spines['left'].set_position('zero')
ax.spines['right'].set_color('none')
ax.spines['bottom'].set_position('zero')
ax.spines['top'].set_color('none')
ax.axis('equal')
plt.show()
def f4():
capped_xs = np.linspace(-0.94, 0.8, 1000)
xs = np.linspace(-1, 1, 1000)
ys = [1 / (1 - x) for x in capped_xs]
def getN(N):
def fN(x):
total = 0.0
for i in range(N + 1):
total += x**i
return total
return fN
yss = []
for N in range(1, 4):
fN = getN(N)
yss.append([fN(x) for x in xs])
fig, ax = plt.subplots()
ax.set_yticklabels([])
ax.set_xticklabels([])
plt.plot(capped_xs, ys, label=r"$\frac{1}{1-x}$")
for i, ys in enumerate(yss):
plt.plot(xs, ys, label="$N={}$".format(i + 1), alpha=0.3)
plt.plot([1, 1], [0, 5], "k--", alpha=0.3)
plt.plot(-1,
0.5,
'o',
markerfacecolor='None',
markeredgecolor='C0',
markersize=5)
plt.xticks([-1, 1], ['-1', '1'])
plt.legend()
ax.spines['left'].set_position('zero')
ax.spines['right'].set_color('none')
ax.spines['bottom'].set_position('zero')
ax.spines['top'].set_color('none')
ax.axis('equal')
plt.show()
def print_all_results(collected_results, versions, args):
test_type = args.test_type
model_name = args.model
for test_name in collected_results:
test_results = collected_results[test_name]
x, y = [], []
for version in versions:
if (version in test_results):
x.append(version)
y.append(test_results[version]['mean'])
plt.plot(x, y, label=test_name)
plt.xticks(np.arange(len(x)), x)
plt.xlabel(XLABELS[test_type])
plt.ylabel('average absolute effect size')
plt.legend(loc='best')
plt.title("SEAT effect sizes on {} with {}".format(model_name,
TITLES[test_type]))
plot_path = os.path.join(args.eval_results_dir, "plots",
"{}-{}.png".format(model_name, test_type))
plt.savefig(plot_path)
def tmp2(cm, acts):
import numpy as np
import matplotlib.pyplot as plt
conf_arr = cm
norm_conf = []
for i in conf_arr:
a = 0
tmp_arr = []
a = sum(i, 0)
for j in i:
tmp_arr.append(0 if a == 0 else float(j) / float(a))
norm_conf.append(tmp_arr)
fig = plt.figure(figsize=(8, 8))
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(np.array(norm_conf),
cmap=plt.cm.jet,
interpolation='nearest')
width, height = conf_arr.shape
# for x in range(width):
# for y in range(height):
# ax.annotate(str(conf_arr[x][y]), xy=(y, x),
# horizontalalignment='center',
# verticalalignment='center')
cb = fig.colorbar(res)
ax.set_xlim(-.5, len(acts) - .5)
ax.set_ylim(-.5, len(acts) - .5)
# alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
plt.xticks(range(width), acts, rotation=-90)
plt.yticks(range(height), acts)
def getGraph():
for i, clf in enumerate((svm, rbf_svc, rbf_svc_tunning)):
# Se grafican las fronteras
plt.subplot(2, 2, i + 1)
plt.subplots_adjust(wspace=0.4, hspace=0.4)
Z = clf.predict(np.c_[x_matrizSetEntrenamientoVect, y_clases])
#Color en las gráficas
Z = Z.reshape(x_matrizSetEntrenamientoVect.shape)
plt.contourf(x_matrizSetEntrenamientoVect, y_clases, Z, cmap=plt.cm.Paired, alpha=0.8)
#Puntos de entrenamiento
plt.scatter(x_matrizSetEntrenamientoVect[:, 0], x_matrizSetEntrenamientoVect[:, 1], c=y_clases, cmap=plt.cm.Paired)
plt.xlabel('Longitud Sepal')
plt.ylabel('Peso Sepal')
plt.xlim(x_matrizSetEntrenamientoVect.min(), x_matrizSetEntrenamientoVect.max())
plt.ylim(y_clases.min(), y_clases.max())
plt.xticks(())
plt.yticks(())
plt.title(titles[i])
plt.show()
import os
import numpy as np
from joblib import load
from matplotlib.pylab import plt
dataset = 'BANC_freesurf'
tpot_dict = 'gpr'
project_wd = os.getcwd()
saved_tpot = load(
os.path.join(project_wd, 'tpot_%s_%s.dump' % (dataset, tpot_dict)))
# Get the internal cross validation scores
cv_scores = [
saved_tpot['evaluated_individuals_'][model]['internal_cv_score']
for model in saved_tpot['evaluated_individuals_'].keys()
]
model_names = [model for model in saved_tpot['evaluated_individuals_'].keys()]
# Just a quick solution to plot something, but you should plot histograms
ind = np.arange(len(cv_scores))
plt.bar(ind, cv_scores)
plt.ylabel('MAE')
plt.xticks(ind)
plt.show()
plt.figure()
plt.scatter(cv_scores)
plt.show()
# In[100]:
get_ipython().run_cell_magic(
'latex', '',
'$\\textbf{Visualize the Correlations}: $\n$\\text{Cor}(X_i,Y_j) = \\frac{\\text{Cov}(X_i,Y_j)}{\\sigma_{X_i}\\sigma_{Y_j}}$'
)
# In[101]:
R = np.corrcoef(data.T)
plt.figure(figsize=(10, 8))
plt.pcolor(R)
plt.colorbar()
plt.xlim([0, len(headers)])
plt.ylim([0, len(headers)])
plt.xticks(np.arange(32) + 0.5, np.array(headers), rotation='vertical')
plt.yticks(np.arange(32) + 0.5, np.array(headers))
plt.show()
# In[108]:
#Lets fit both the models using PCA/FA down to two dimensions.
#construct a function implementing the factor analysis which returns a vector of n_components largest
# variances and the corresponding components (as column vectors in a matrix). You can
# check your work by using decomposition.FactorAnalysis from sklearn
#### ~THIS FUNCTION IS WAS A STAB, NEW CODE HERE: ###########
def FactorAnalysis(data, n_components):
ni = 20
import pandas as pd
import numpy as np
from matplotlib.pylab import plt #load plot library
df = pd.read_csv("../data/well_monthly_2017.csv", header=0)
cumulative_months = []
months_label = []
for m in range(1, 13):
if m < 10:
pad = '0' + str(m)
else:
pad = str(m)
year_month = "2017-" + pad
month_data = df[df["month"] == year_month]
month_data.drop(columns=["month", "well"], inplace=True)
cumulative_month = sum(month_data.values.flatten())
cumulative_months.append(cumulative_month)
months_label.append("m-" + str(m))
month_count = 12
y_pos = np.arange(month_count)
plt.bar(y_pos, cumulative_months, align='center', alpha=0.5)
plt.xticks(y_pos, months_label)
plt.ylabel('Pumped water')
plt.title('Well water pumped in one year 2017')
plt.show()
import pandas as pd
import numpy as np
from matplotlib.pylab import plt #load plot library
df = pd.read_csv("../data/well_monthly.csv", header=0)
cum_pump = []
wells_label = []
for well_i in range(1, 18):
data_i = df[df["well"] == well_i]
data_i.drop(columns=["month", "well"], inplace=True)
data = data_i.values.flatten()
effective = data[0:len(data) - 1]
my_cumulative_pump = sum(effective)
cum_pump.append(my_cumulative_pump)
print("well:", well_i, "; pump:", my_cumulative_pump)
wells_label.append('W-' + str(well_i))
well_count = 17
y_pos = np.arange(well_count)
plt.bar(y_pos, cum_pump, align='center', alpha=0.5)
plt.xticks(y_pos, wells_label)
plt.ylabel('Pumped water')
plt.title('Well water pumped in one year 2017')
print("Total water usage:", sum(cum_pump))
plt.show()
def multiplot_gen_content_type():
font = {'family': 'Liberation Serif',
'weight': 'normal',
'size': 15
}
# play around with the font size if it is too big or small
matplotlib.rcParams['axes.titlesize'] = 12
matplotlib.rcParams['axes.labelsize'] = 12
matplotlib.rc('font', **font)
# matplotlib.rcParams['text.usetex'] = True
matplotlib.rcParams['pdf.fonttype'] = 42
matplotlib.rcParams['pdf.use14corefonts'] = True
x = list(data.keys())
y1 =[]
y2 =[]
y3 =[]
y4 =[]
y5 =[]
y6 =[]
y7 =[]
y8 =[]
y9 =[]
y10 =[]
y11 =[]
y12 =[]
y13 =[]
y14 =[]
y15 =[]
print("---",y1)
for year in data.keys():
for option_name, count in data[year].items():
if option_name == 'script':
y1.append(count)
if option_name == 'xmlhttprequest':
y2.append(count)
if option_name == 'document':
y3.append(count)
if option_name == 'elemhide':
y4.append(count)
if option_name == 'subdocument':
y5.append(count)
if option_name == 'image':
y6.append(count)
if option_name == 'popup':
y7.append(count)
if option_name == 'ping':
y8.append(count)
if option_name == 'stylesheet':
y9.append(count)
if option_name == 'object':
y10.append(count)
if option_name == 'generichide':
y11.append(count)
if option_name == 'font':
y12.append(count)
if option_name == 'media':
y13.append(count)
if option_name == 'genericblock':
y14.append(count)
if option_name == 'other':
y15.append(count)
print("x-->",x)
print("y-->",y1)
print("y-->",y2)
plt.xticks(rotation='vertical')
plt.xlabel('Year')
plt.ylabel('Count')
plt.legend(ncol=2)
plt.tight_layout()
plt.savefig('easylist-content-type.pdf ', format='pdf', dpi=1200)
