def timestep(self,data):
if type(data)==QtCore.QString:
data=json.loads(unicode(data))
timestamp=float(data["data"]["stat"]["time"])
#if (self.app.tab.currentIndex()==2 ):
if (2==2):
self.figure.clf()
ax=self.figure.add_subplot(111)
self.figure.set_frameon(False)
ax.patch.set_alpha(0)
ax.set_xlabel("Time [s]")
ax.set_ylabel("Image Count")
try:
ppl.hist(ax,self.histdata-np.ceil(timestamp),bins=100,range=(-100,0))
except (ValueError,AttributeError):
pass
ax.set_xlim((-100,0))
if size(self.histdata)>100:
speed = -100./(self.histdata[size(self.histdata)-101]-self.histdata[size(self.histdata)-1])
else:
speed = 0
tstr= datetime.datetime.fromtimestamp(timestamp).strftime('%Y-%m-%d %H:%M:%S')
ax.set_title(tstr +", "+ str(data["data"]["stat"]['images processed'])+" Images Processed @"+ str(speed) + "fps")
self.figure.tight_layout()
self.canvas.draw()
def timestep(self, data):
if type(data) == QtCore.QString:
data = json.loads(unicode(data))
timestamp = float(data["data"]["stat"]["time"])
#if (self.app.tab.currentIndex()==2 ):
if (2 == 2):
self.figure.clf()
ax = self.figure.add_subplot(111)
self.figure.set_frameon(False)
ax.patch.set_alpha(0)
ax.set_xlabel("Time [s]")
ax.set_ylabel("Image Count")
try:
ppl.hist(ax,
self.histdata - np.ceil(timestamp),
bins=100,
range=(-100, 0))
except (ValueError, AttributeError):
pass
ax.set_xlim((-100, 0))
if size(self.histdata) > 100:
speed = -100. / (self.histdata[size(self.histdata) - 101] -
self.histdata[size(self.histdata) - 1])
else:
speed = 0
tstr = datetime.datetime.fromtimestamp(timestamp).strftime(
'%Y-%m-%d %H:%M:%S')
ax.set_title(tstr + ", " +
str(data["data"]["stat"]['images processed']) +
" Images Processed @" + str(speed) + "fps")
self.figure.tight_layout()
self.canvas.draw()
def pairs(name, data, labels=None):
""" Generate something similar to R `pairs` """
nvariables = data.shape[1]
mpl.rcParams["figure.figsize"] = 3.5 * nvariables, 3.5 * nvariables
if labels is None:
labels = ["var {}".format(i) for i in range(nvariables)]
fig = plt.figure()
s = clock()
for i in range(nvariables):
for j in range(i, nvariables):
nsub = i * nvariables + j + 1
ax = fig.add_subplot(nvariables, nvariables, nsub)
ax.tick_params(left="off", bottom="off", right="off", top="off", labelbottom="off", labelleft="off")
ax.spines["top"].set_visible(False)
ax.spines["left"].set_linewidth(0.5)
ax.spines["bottom"].set_linewidth(0.5)
ax.spines["right"].set_visible(False)
if i == j:
ppl.hist(ax, data[:, i], grid="y")
ax.set_title(labels[i], fontsize=10)
else:
ax.set_xlim([data[:, i].min(), data[:, i].max()])
ax.set_ylim([data[:, j].min(), data[:, j].max()])
ax.scatter(data[:, i], data[:, j], marker=".", color="k", s=4)
ax.tick_params(labelbottom="off", labelleft="off")
print(clock() - s)
s = clock()
plt.savefig(name + "_corr.png", dpi=96, transparent=False, frameon=False, bbox_inches="tight", pad_inches=0.1)
print(clock() - s)
def test_scatter():
# Set the random seed for consistency
np.random.seed(12)
# Show some color range
for i in range(2):
x = np.random.randn(1000)
ppl.hist(x)
def test_scatter():
# Set the random seed for consistency
np.random.seed(12)
# Show some color range
for i in range(2):
x = np.random.randn(1000)
ppl.hist(x)
def test_scatter():
# Set the random seed for consistency
np.random.seed(12)
fig, ax = plt.subplots(1)
# Show some color range
for i in range(2):
x = np.random.randn(1000)
ppl.hist(ax, x)
def hist(data, xtext, ttext, figname):
#mpl.use('PDF')
import matplotlib.pyplot as plt, prettyplotlib as ppl
fig, ax = plt.subplots(1)
ppl.hist(ax, data[~np.isnan(data)], bins=20, grid='y')
plt.ylabel('Pixel Number', fontsize=14)
plt.ticklabel_format(style='sci', axis='y', scilimits=(0, 0))
plt.xlabel(xtext, fontsize=14)
plt.title('Histogram of ' + ttext, fontsize=16)
fig.savefig('afr_' + figname + '_his.pdf', dpi=300)
plt.close()
def Plot_Histogram(self):
c = Counter()
for i in range(len(self.df)):
u = self.df['user'][i]
c[u] += self.df['plays'][i]
res = []
for u in c.keys():
res.append(c[u])
ppl.hist(np.log10(res), bins=100)
plt.xlabel('Log10(Number of play)')
plt.ylabel('N')
plt.show()
def hist(data, xtext, ttext, figname):
#mpl.use('PDF')
import matplotlib.pyplot as plt, prettyplotlib as ppl
fig, ax = plt.subplots(1)
ppl.hist(ax, data[~np.isnan(data)], bins=20, grid='y')
plt.ylabel('Pixel Number', fontsize=14)
plt.ticklabel_format(style='sci', axis='y', scilimits=(0,0))
plt.xlabel(xtext, fontsize=14)
plt.title('Histogram of '+ttext, fontsize=16)
fig.savefig('afr_'+figname+'_his.pdf', dpi = 300)
plt.close()
def plot_patchset_histogram(changes, outputfile=None):
number_of_patchsets = []
for change in changes:
number_of_patchsets.append(len(change['patchSets']))
fig = plt.figure()
ax = fig.add_subplot(111)
hist(ax, number_of_patchsets, bins=np.max(number_of_patchsets))
ax.set_xlabel('Number of Patch Sets')
ax.set_ylabel('Change Count')
ax.set_xlim(0, 20)
if outputfile:
fig.savefig(outputfile)
else:
plt.show()
def makehist(series,rejected,mincount=0,bins=[],title="",filename="_"):
rej = rejected == 1
app = rejected == 0
#nrej = sum(rej)*1.0
#napp = sum(app)*1.0
#series_rej = pd.Series({count: sum(series[rej]==count) for count in pd.unique(series[rej])})
#series_app = pd.Series({count: sum(series[app]==count) for count in pd.unique(series[app])})
#rej_plot = series_rej[series_rej.index>=mincount]/nrej
#app_plot = series_app[series_app.index>=mincount]/napp
fig, ax = plt.subplots(1)
if len(bins) > 0:
ppl.hist(ax,np.array(series[app]),bins=bins,label='approved',color=color_approved,alpha=0.8)
ppl.hist(ax,np.array(series[rej]),bins=bins,label='rejected',color=color_rejected,alpha=0.4)
#n1,bin1,_ = ppl.hist(ax,np.array(rej_plot.index),bins=bins,weights=np.array(rej_plot),label='rejected')
#n2,bin2,_ = ppl.hist(ax,np.array(app_plot.index),bins=bins,weights=np.array(app_plot),label='approved')
else:
ppl.hist(ax,np.array(series[app]),label='approved',color=color_approved,alpha=0.8)
ppl.hist(ax,np.array(series[rej]),label='rejected',color=color_rejected,alpha=0.4)
#n1,bin1,_ = ppl.hist(ax,np.array(rej_plot.index),weights=np.array(rej_plot),label='rejected')
#n2,bin2,_ = ppl.hist(ax,np.array(app_plot.index),weights=np.array(app_plot),label='approved')
plt.legend()
if mincount > 0:
title = title + "(count >= " + str(mincount) + ")"
plt.title(title)
filepath = dl.getDataFilePath('plots/fig_'+filename+'.png')
plt.savefig(filepath)
plt.show()
def plot_histogram(self, ax, x, bins, title='', xlabel='', title_font={},
axis_font={}, tick_font={}, **kwargs):
if not title_font:
title_font = title_font_default
if not axis_font:
axis_font = axis_font_default
x = x[~np.isnan(x)]
ppl.hist(ax, x, bins, grid='y', **kwargs)
if xlabel:
ax.set_xlabel(xlabel.replace("_", " "), labelpad=10, **axis_font)
if tick_font:
ax.tick_params(**tick_font)
ax.set_ylabel('No. of Occurrences', **axis_font)
ax.set_title(title.replace("_", " "), **title_font)
def _print_and_plot(mean_alpha, mean_beta, alphas, betas, n_iter, data):
print
print mean_alpha, mean_beta, ' estimated modality:', \
_assign_modality_from_estimate(mean_alpha, mean_beta)
import numpy as np
from scipy.stats import beta
import matplotlib.pyplot as plt
import prettyplotlib as ppl
fig, axes = plt.subplots(ncols=2, figsize=(12, 4))
ax = axes[0]
ppl.plot(alphas, label='alpha', ax=ax)
ppl.plot(betas, label='beta', ax=ax)
ppl.legend(ax=ax)
ax.hlines(mean_alpha, 0, n_iter)
ax.hlines(mean_beta, 0, n_iter)
ax.annotate('mean_alpha = {:.5f}'.format(mean_alpha), (0, mean_alpha),
fontsize=12,
xytext=(0, 1),
textcoords='offset points')
ax.annotate('mean_beta = {:.5f}'.format(mean_alpha), (0, mean_beta),
fontsize=12,
xytext=(0, 1),
textcoords='offset points')
ax.set_xlim(0, n_iter)
ax = axes[1]
ppl.hist(data,
facecolor='grey',
alpha=0.5,
bins=np.arange(0, 1, 0.05),
zorder=10,
ax=ax)
ymin, ymax = ax.get_ylim()
one_x = np.arange(0, 1.01, 0.01)
x = np.repeat(one_x, n_iter).reshape(len(one_x), n_iter)
beta_distributions = np.vstack(
(beta(a, b).pdf(one_x) for a, b in zip(alphas, betas))).T
ppl.plot(x,
beta_distributions,
color=ppl.colors.set2[0],
alpha=0.1,
linewidth=2,
ax=ax)
ax.set_ylim(0, ymax)
def plot_dist(vars,names,title=''):
k = len(names)
fig,ax = subplots(1,k, figsize=(4*k,4))
for i in range(k):
m = np.mean(vars[i])
s = np.std(vars[i])
at = get_label("$\mu$ = %2.2f\n$\sigma$ = %2.2f"%(m,s))
if not k ==1:
ppl.hist(ax[i],vars[i])
ax[i].set_xlabel(names[i])
ax[i].add_artist(at)
else:
ppl.hist(ax,vars[i])
ax.set_xlabel(names[i])
ax.add_artist(at)
suptitle(title,size=14)
def timestep(self,resultstr):
data=json.loads(unicode(resultstr))
timestamp=data["data"]["stat"]["time"]
if ( self.app.tab.currentIndex()==2 ):
self.figure.clf()
ax=self.figure.add_subplot(111)
self.figure.set_frameon(False)
ax.patch.set_alpha(0)
ax.set_xlabel("Time [s]")
ax.set_ylabel("Image Count")
ppl.hist(ax,self.histdata-np.ceil(timestamp),bins=100,range=(-100,0))
ax.set_xlim((-100,0))
tstr= datetime.datetime.fromtimestamp(timestamp).strftime('%Y-%m-%d %H:%M:%S')
ax.set_title(tstr +", "+ str(data["data"]["stat"]['images processed'])+" Images Processed")
self.canvas.draw()
def timestep(self, data):
if type(data) == QtCore.QString:
data = json.loads(unicode(data))
timestamp = float(data["data"]["stat"]["time"])
print timestamp
if self.app.tab.currentIndex() == 2:
self.figure.clf()
ax = self.figure.add_subplot(111)
self.figure.set_frameon(False)
ax.patch.set_alpha(0)
ax.set_xlabel("Time [s]")
ax.set_ylabel("Image Count")
ppl.hist(ax, self.histdata - np.ceil(timestamp), bins=100, range=(-100, 0))
ax.set_xlim((-100, 0))
tstr = datetime.datetime.fromtimestamp(timestamp).strftime("%Y-%m-%d %H:%M:%S")
ax.set_title(tstr + ", " + str(data["data"]["stat"]["images processed"]) + " Images Processed")
self.canvas.draw()
def pairs(name, data, labels=None):
""" Generate something similar to R `pairs` """
nvariables = data.shape[1]
mpl.rcParams['figure.figsize'] = 3.5 * nvariables, 3.5 * nvariables
if labels is None:
labels = ['var {}'.format(i) for i in range(nvariables)]
fig = plt.figure()
s = clock()
for i in range(nvariables):
for j in range(i, nvariables):
nsub = i * nvariables + j + 1
ax = fig.add_subplot(nvariables, nvariables, nsub)
ax.tick_params(left='off',
bottom='off',
right='off',
top='off',
labelbottom='off',
labelleft='off')
ax.spines['top'].set_visible(False)
ax.spines['left'].set_linewidth(0.5)
ax.spines['bottom'].set_linewidth(0.5)
ax.spines['right'].set_visible(False)
if i == j:
ppl.hist(ax, data[:, i], grid='y')
ax.set_title(labels[i], fontsize=10)
else:
ax.set_xlim([data[:, i].min(), data[:, i].max()])
ax.set_ylim([data[:, j].min(), data[:, j].max()])
ax.scatter(data[:, i], data[:, j], marker='.', color='k', s=4)
ax.tick_params(labelbottom='off', labelleft='off')
print(clock() - s)
s = clock()
plt.savefig(name + '_corr.png',
dpi=96,
transparent=False,
frameon=False,
bbox_inches='tight',
pad_inches=0.1)
print(clock() - s)
def _print_and_plot(mean_alpha, mean_beta, alphas, betas, n_iter, data):
print
print mean_alpha, mean_beta, ' estimated modality:', \
_assign_modality_from_estimate(mean_alpha, mean_beta)
import numpy as np
from scipy.stats import beta
import matplotlib.pyplot as plt
import prettyplotlib as ppl
fig, axes = plt.subplots(ncols=2, figsize=(12, 4))
ax = axes[0]
ppl.plot(alphas, label='alpha', ax=ax)
ppl.plot(betas, label='beta', ax=ax)
ppl.legend(ax=ax)
ax.hlines(mean_alpha, 0, n_iter)
ax.hlines(mean_beta, 0, n_iter)
ax.annotate('mean_alpha = {:.5f}'.format(mean_alpha),
(0, mean_alpha), fontsize=12,
xytext=(0, 1), textcoords='offset points')
ax.annotate('mean_beta = {:.5f}'.format(mean_alpha),
(0, mean_beta), fontsize=12,
xytext=(0, 1), textcoords='offset points')
ax.set_xlim(0, n_iter)
ax = axes[1]
ppl.hist(data, facecolor='grey', alpha=0.5, bins=np.arange(0, 1, 0.05),
zorder=10, ax=ax)
ymin, ymax = ax.get_ylim()
one_x = np.arange(0, 1.01, 0.01)
x = np.repeat(one_x, n_iter).reshape(len(one_x), n_iter)
beta_distributions = np.vstack((beta(a, b).pdf(one_x)
for a, b in zip(alphas, betas))).T
ppl.plot(x, beta_distributions, color=ppl.colors.set2[0], alpha=0.1,
linewidth=2, ax=ax)
ax.set_ylim(0, ymax)
def plot_histogram(self,
ax,
x,
bins,
title='',
xlabel='',
title_font={},
axis_font={},
tick_font={},
**kwargs):
if not title_font:
title_font = title_font_default
if not axis_font:
axis_font = axis_font_default
x = x[~np.isnan(x)]
ppl.hist(ax, x, bins, grid='y', **kwargs)
if xlabel:
ax.set_xlabel(xlabel.replace("_", " "), labelpad=10, **axis_font)
if tick_font:
ax.tick_params(**tick_font)
ax.set_ylabel('No. of Occurrences', **axis_font)
ax.set_title(title.replace("_", " "), **title_font)
def timestep(self, resultstr):
data = json.loads(unicode(resultstr))
timestamp = data["data"]["stat"]["time"]
if (self.app.tab.currentIndex() == 2):
self.figure.clf()
ax = self.figure.add_subplot(111)
self.figure.set_frameon(False)
ax.patch.set_alpha(0)
ax.set_xlabel("Time [s]")
ax.set_ylabel("Image Count")
ppl.hist(ax,
self.histdata - np.ceil(timestamp),
bins=100,
range=(-100, 0))
ax.set_xlim((-100, 0))
tstr = datetime.datetime.fromtimestamp(timestamp).strftime(
'%Y-%m-%d %H:%M:%S')
ax.set_title(tstr + ", " +
str(data["data"]["stat"]['images processed']) +
" Images Processed")
self.canvas.draw()
if i % 1000 == 0: print 'iteration', i
samples[:, i] = xx.copy().ravel()
return samples
w_0 = np.array([0., 1., 1., 1., 1., 1., 1., 1., 1., 1.])
# actually do the sampling
n = 10
sigma = np.ones(10)
samples = slice_sample(w_0, iters=n, sigma=sigma)
v = samples[0, :]
fig, (ax0, ax1) = plt.subplots(2, 1)
# show values of sampled v by iteration
pplt.plot(ax0, np.arange(n), v)
ax0.set_xlabel('iteration number')
ax0.set_ylabel('value of sampled v')
# plot a histogram of values of v
pplt.hist(ax1, v, bins=80)
ax1.set_xlabel('values of sampled v')
ax1.set_ylabel('observations')
plt.tight_layout()
plt.show()
np.logical_or(
np.isinf(em_rate[r]),
np.isnan(em_rate[r])))]
qn_rate[r] = qn_rate[r][
np.logical_not(
np.logical_or(
np.isinf(qn_rate[r]),
np.isnan(qn_rate[r])))]
em_rate[r] = em_rate[r][em_rate[r]>=0]
qn_rate[r] = qn_rate[r][qn_rate[r]>=0]
em_rate[r] = em_rate[r][em_rate[r]<2]
qn_rate[r] = qn_rate[r][qn_rate[r]<2]
#fig, ax = plt.subplots(1)
#labels=[initnames[i]+': EM' for i in range(numinits)]+[initnames[i]+': QN2' for i in range(numinits)]
labels = ['EM','QN2']
ppl.hist(ax4,[np.concatenate(em_rate),np.concatenate(qn_rate)],label=labels)
ax4.set_title("(d) "+title+"histogram of convergence rates")
ax4.set_ylabel('frequency')
ax4.set_xlabel('convergence rate r')
ax4.legend()
#plt.show()
'''
#fig, ax = plt.subplots(1)
for i in range(numinits):
em_k[i][em_k[i]==0] = 1
qn_k[i][qn_k[i]==0] = 1
em_time_k_ratio = [np.log10(em_times[i]/em_k[i]*1e6) for i in range(numinits)]
qn_time_k_ratio = [np.log10(qn_times[i]/qn_k[i]*1e6) for i in range(numinits)]
#labels=[initnames[i]+': EM' for i in range(numinits)]+[initnames[i]+': QN2' for i in range(numinits)]
labels = ['EM','QN2']
def make_scatter(self, use_prettyplotlib=True, hists=True, num_bins=None):
'''
Plot two columns against each other. If self.subplot is enabled,
all comparisons returned in a triangle collection. Inspiration for
this form came from the package .
Small snippets to set the labels and figure size came from triangle.py.
'''
if use_prettyplotlib:
try:
import prettyplotlib as plt
except ImportError:
import matplotlib.pyplot as plt
use_prettyplotlib = False
print "prettyplotlib not installed. Using matplotlib..."
else:
import matplotlib.pyplot as plt
# Setup subplots if plotting together
if self.subplot:
# Make the objects
num = len(self.columns)
factor = 2.0 # size of one side of one panel
lbdim = 0.5 * factor # size of left/bottom margin
trdim = 0.3 * factor # size of top/right margin
whspace = 0.05 # w/hspace size
plotdim = factor * num + factor * (num - 1.) * whspace
dim = lbdim + plotdim + trdim
fig, axes = plt.subplots(nrows=num, ncols=num, figsize=(dim, dim))
lb = lbdim / dim
tr = (lbdim + plotdim) / dim
fig.subplots_adjust(left=lb, bottom=lb, right=tr, top=tr,
wspace=whspace, hspace=whspace)
for i, column1 in enumerate(self.columns):
for j, column2 in enumerate(self.columns):
data1 = self.dataframe[column1]
data2 = self.dataframe[column2]
# Get rid of nans
nans = np.isnan(data1) + np.isnan(data2)
data1 = data1[~nans]
data2 = data2[~nans]
if self.subplot:
ax = axes[i, j]
if j > i: # Don't bother plotting duplicates
ax.set_visible(False)
ax.set_frame_on(False)
else:
if j == i: # Plot histograms
# Set number of bins
if num_bins is None:
num_bins = np.sqrt(len(data1))
if hists == True:
if use_prettyplotlib:
plt.hist(ax, data1, num_bins, grid="y")
else:
ax.hist(data1, num_bins)
ax.grid(True)
else:
ax.set_visible(False)
ax.set_frame_on(False)
ax.set_xticklabels([])
ax.set_yticklabels([])
if j != i:
if use_prettyplotlib:
plt.scatter(ax, data2, data1)
else:
ax.scatter(data2, data1)
ax.grid(True)
ax.xaxis.set_major_locator(MaxNLocator(5))
ax.yaxis.set_major_locator(MaxNLocator(5))
if i < num - 1:
ax.set_xticklabels([])
else:
[l.set_rotation(45) for l in ax.get_xticklabels()]
ax.set_xlabel(column2)
ax.xaxis.set_label_coords(0.5, -0.3)
if j > 0:
ax.set_yticklabels([])
else:
[l.set_rotation(45) for l in ax.get_yticklabels()]
ax.set_ylabel(column1)
ax.yaxis.set_label_coords(-0.3, 0.5)
else:
if j < i:
fig, axes = plt.subplots(1)
if use_prettyplotlib:
plt.scatter(axes, data2, data1, grid="y")
else:
axes.scatter(data2, data1)
axes.grid(True)
axes.set_xlabel(column2) # ADD UNITS!
axes.set_ylabel(column1) # ADD UNITS!
if self.verbose:
p.show()
else:
fig.savefig(self.save_name+"_"+column1+"_"+column2+"."+self.save_type)
p.close()
if self.subplot:
# p.tight_layout()
if self.verbose:
p.show()
else:
fig.savefig(self.save_name+"_"+"scatter"+"."+self.save_type)
#bff = bff[bff.columns.values.tolist()[1:]
# In[12]:
opg.head()
# In[13]:
#Histograms
import prettyplotlib as ppl
#for i in bff.columns.values.tolist():
print i
ppl.hist(bff[i],bins=20)
ppl.plt.savefig(i+'.png')
ppl.plt.close()
# In[14]:
opg_subset = [
'PBR_1+',
'PBR_2-',
'PBR_3+',
'PBR_4+',
'PBR_5+',
'PBR_7-',
'OPG_10+',
'OPG_12+',
fig.set_size_inches(14, 8)
# <markdowncell>
# ### Number of stations available by number of years
# <codecell>
fig, ax = plt.subplots(1)
year_list_map = []
for s in station_list:
if "data" in s:
years = s["data"].keys()
year_list_map.append(len(years))
ppl.hist(ax, np.array(year_list_map), grid='y')
plt.plot([num_years_required, num_years_required], [0, 8], 'r-', lw=2)
ax.set_ylabel("Number of Stations")
ax.set_xlabel("Number of Years Available")
ax.set_title('Number of available stations vs available years\n'
'(for bounding box) - red is minimum requested years')
# <markdowncell>
# ## Get model output from OPeNDAP URLS
# ### Try to open all the OPeNDAP URLS using Iris from the British Met Office. If we can open in Iris, we know it's a model result.
#
# #### Construct an Iris contraint to load only cubes that match the standard names:
# <codecell>
fig.set_size_inches(14, 8)
# <markdowncell>
# ### Number of stations available by number of years
# <codecell>
fig, ax = plt.subplots(1)
year_list_map = []
for s in station_list:
if "data" in s:
years = s["data"].keys()
year_list_map.append(len(years))
ppl.hist(ax, np.array(year_list_map), grid='y')
plt.plot([num_years_required, num_years_required], [0, 8], 'r-', lw=2)
ax.set_ylabel("Number of Stations")
ax.set_xlabel("Number of Years Available")
ax.set_title('Number of available stations vs available years\n'
'(for bounding box) - red is minimum requested years')
# <markdowncell>
# ## Get model output from OPeNDAP URLS
# ### Try to open all the OPeNDAP URLS using Iris from the British Met Office. If we can open in Iris, we know it's a model result.
#
# #### Construct an Iris contraint to load only cubes that match the standard names:
# <codecell>
opg.head()
# In[23]:
opg_col = [
'PBR_1+', 'PBR_2-', 'PBR_3+', 'PBR_4+', 'PBR_5+', 'PBR_6-', 'PBR_7-',
'PBR_8-', 'OPG_9+', 'OPG_10+', 'OPG_11-', 'OPG_12+', 'OPG_13+', 'OPG_14+',
'OPG_15+', 'OPG_16+', 'OPG_17-', 'OPG_18-', 'IE_19+', 'IE_20+', 'IE_21+',
'IE_22-', 'IE_23-', 'IE_24+', 'IE_25-', 'IE_26-'
]
# In[24]:
for col in opg_col:
print col
ppl.hist(opg[col], bins=20)
ppl.plt.savefig('OPG' + col + '.png')
ppl.plt.close()
# In[30]:
bff_cols = [
'BF-F1+', 'BF-F2+', 'BF-F3+', 'BF-F4+', 'BF-F5+', 'BF-F6-', 'BF-F7+',
'BF-F8+', 'BF-F9+', 'BF-F10+', 'BF-F11+', 'BF-F12+', 'BF-F13+', 'BF-F14+',
'BF-F15+', 'BF-F16+', 'BF-F17-', 'BF-F18+', 'BF-F19-', 'BF-F20+',
'BF-F21+', 'BF-F22+', 'BF-F23+', 'BF-F24+', 'BF-F25+', 'BF-F26+',
'BF-F27+', 'BF-F28-', 'BF-F29+', 'BF-F30+', 'BF-F31+', 'BF-F32+',
'BF-F33+', 'BF-F34-', 'BF-F35-', 'BF-F36-', 'BF-F37-', 'BF-F38-',
'BF-F39-', 'BF-F40+', 'BF-F41+', 'BF-F42+', 'BF-F43+', 'BF-F44-',
'BF-F45-', 'BF-F46-', 'BF-F47-', 'BF-F48-', 'BF-F49-', 'BF-F50+',
'BF-F51-', 'BF-F52+', 'BF-F53+', 'BF-F54+', 'BF-F55+', 'BF-F56-',
'IE_20+',
'IE_21+',
'IE_22-',
'IE_24+',
'IE_25-',
]
opg = opg[dropped_opg2]
# In[16]:
#Histograms
import prettyplotlib as ppl
#for i in bfas.columns.values.tolist()[1:]:
print i
ppl.hist(bfas[i],bins=15)
ppl.plt.savefig(i+'.png')
ppl.plt.close()
# In[17]:
#Histograms
import prettyplotlib as ppl
#for i in opg.columns.values.tolist()[1:]:
print i
ppl.hist(opg[i],bins=15)
ppl.plt.savefig(i+'.png')
ppl.plt.close()
fig, ax = plt.subplots(1) ppl.scatter(ax, sumpeak, suminterval) ax.set_title(savefilename + ' Heterogeneity distrubition') fig.savefig(pathfilename + '_Heterogeneity_distrubition' + '.png',dpi=500) plt.close() print 'Saved scatter plot:', savefilename csvsumpeak = np.sort(sumpeak) np.save(pathfilename+'_sorted_Peak', csvsumpeak) np.savetxt(pathfilename+'_sorted_Peak.csv', csvsumpeak, delimiter=',') print 'Saved sorted Peak:', savefilename csvsumpeakdiff = np.diff(csvsumpeak) bins = np.sqrt(len(csvsumpeakdiff)) fig, ax = plt.subplots(1) ppl.hist(ax, csvsumpeakdiff, bins = bins) ax.set_title(savefilename + ' difference distrubition') fig.savefig(pathfilename + '_difference_distrubition' + '.png',dpi=500) plt.close() ''' def determinse(result, precentage): attempt = np.zeros(20) count = 0
def make_hists(self, num_bins=None, use_prettyplotlib=True):
if use_prettyplotlib:
try:
import prettyplotlib as plt
except ImportError:
import matplotlib.pyplot as plt
use_prettyplotlib = False
print "prettyplotlib not installed. Using matplotlib..."
else:
import matplotlib.pyplot as plt
# Setup subplots if plotting together
if self.subplot:
num = len(self.columns)
if num <= 3:
ncols = 1
nrows = num
elif num <= 8:
ncols = 2
nrows = num / 2
else: # Max columns right now is 12
ncols = 3
nrows = num / 3
# Check if we need an extra row.
if num % ncols != 0:
nrows += 1
# Make the objects
fig, axes = plt.subplots(nrows=nrows, ncols=ncols)
# This is a bit awkward to get the indices, but my matplotlib version
# doesn't use the same object type as prettyplotlib creates.
posns = np.indices(axes.shape)
x, y = posns[0].ravel(), posns[1].ravel()
# Keep the mean, median, std.
data_stats = {}
for i, column in enumerate(self.columns):
data = self.dataframe[column]
data = data[np.isfinite(data)]
if num_bins is None:
num_bins = np.sqrt(len(data))
data_stats[column] = [
np.nanmean(data),
np.nanstd(data),
np.nanmedian(data)
]
if self.subplot:
if use_prettyplotlib:
plt.hist(axes[x[i], y[i]], data, num_bins, grid="y")
else:
axes[x[i], y[i]].hist(data, num_bins)
axes[x[i], y[i]].set_xlabel(column) # ADD UNITS!
else:
fig, axes = plt.subplots(1)
axes.hist(data, num_bins)
axes.set_xlabel(column) # ADD UNITS!
if self.verbose and not self.subplot:
print column + " Stats: %s" % (data_stats[column])
p.show()
elif not self.subplot:
fig.savefig(self.save_name + "_" + column + "." +
self.save_type)
p.close()
if self.subplot:
p.tight_layout()
if self.verbose:
for column in self.columns:
print column + " Stats: %s" % (data_stats[column])
p.show()
else:
fig.savefig(self.save_name + "_hists." + self.save_type)
def make_scatter(self, use_prettyplotlib=True, hists=True, num_bins=None):
'''
Plot two columns against each other. If self.subplot is enabled,
all comparisons returned in a triangle collection. Inspiration for
this form came from the package .
Small snippets to set the labels and figure size came from triangle.py.
'''
if use_prettyplotlib:
try:
import prettyplotlib as plt
except ImportError:
import matplotlib.pyplot as plt
use_prettyplotlib = False
print "prettyplotlib not installed. Using matplotlib..."
else:
import matplotlib.pyplot as plt
# Setup subplots if plotting together
if self.subplot:
# Make the objects
num = len(self.columns)
factor = 2.0 # size of one side of one panel
lbdim = 0.5 * factor # size of left/bottom margin
trdim = 0.3 * factor # size of top/right margin
whspace = 0.05 # w/hspace size
plotdim = factor * num + factor * (num - 1.) * whspace
dim = lbdim + plotdim + trdim
fig, axes = plt.subplots(nrows=num, ncols=num, figsize=(dim, dim))
lb = lbdim / dim
tr = (lbdim + plotdim) / dim
fig.subplots_adjust(left=lb,
bottom=lb,
right=tr,
top=tr,
wspace=whspace,
hspace=whspace)
for i, column1 in enumerate(self.columns):
for j, column2 in enumerate(self.columns):
data1 = self.dataframe[column1]
data2 = self.dataframe[column2]
# Get rid of nans
nans = np.isnan(data1) + np.isnan(data2)
data1 = data1[~nans]
data2 = data2[~nans]
if self.subplot:
ax = axes[i, j]
if j > i: # Don't bother plotting duplicates
ax.set_visible(False)
ax.set_frame_on(False)
else:
if j == i: # Plot histograms
# Set number of bins
if num_bins is None:
num_bins = np.sqrt(len(data1))
if hists == True:
if use_prettyplotlib:
plt.hist(ax, data1, num_bins, grid="y")
else:
ax.hist(data1, num_bins)
ax.grid(True)
else:
ax.set_visible(False)
ax.set_frame_on(False)
ax.set_xticklabels([])
ax.set_yticklabels([])
if j != i:
if use_prettyplotlib:
plt.scatter(ax, data2, data1)
else:
ax.scatter(data2, data1)
ax.grid(True)
ax.xaxis.set_major_locator(MaxNLocator(5))
ax.yaxis.set_major_locator(MaxNLocator(5))
if i < num - 1:
ax.set_xticklabels([])
else:
[l.set_rotation(45) for l in ax.get_xticklabels()]
ax.set_xlabel(column2)
ax.xaxis.set_label_coords(0.5, -0.3)
if j > 0:
ax.set_yticklabels([])
else:
[l.set_rotation(45) for l in ax.get_yticklabels()]
ax.set_ylabel(column1)
ax.yaxis.set_label_coords(-0.3, 0.5)
else:
if j < i:
fig, axes = plt.subplots(1)
if use_prettyplotlib:
plt.scatter(axes, data2, data1, grid="y")
else:
axes.scatter(data2, data1)
axes.grid(True)
axes.set_xlabel(column2) # ADD UNITS!
axes.set_ylabel(column1) # ADD UNITS!
if self.verbose:
p.show()
else:
fig.savefig(self.save_name + "_" + column1 + "_" +
column2 + "." + self.save_type)
p.close()
if self.subplot:
# p.tight_layout()
if self.verbose:
p.show()
else:
fig.savefig(self.save_name + "_" + "scatter" + "." +
self.save_type)
# <codecell>
print 'Ratio of Positive Tweets = %f'% (sum(res==1)/len(res))
print 'Ratio of Negative Tweets = %f'% (sum(res==0)/len(res))
print 'Ratio of Neutral Tweets = %f'% (sum(res==2)/len(res))
# <codecell>
#2eme verif
res_prob = predict(df, vectorizer, clf, proba = True)
# <codecell>
fig,ax = plt.subplots(1)
pplt.hist(ax,res_prob[:,1],bins=50)
plt.title('Distribution of Positive Probabilities')
plt.show()
# <codecell>
#3eme verif
df_res = pd.DataFrame({'date': df.date,'tweet': twits, 'positive': list(res_prob[:,1]), 'negative': list(res_prob[:,0]), 'neutral': list(res_prob[:,2])})
df_res = df_res.sort('positive',ascending=False)
# <codecell>
s = df_res.groupby('date').positive.mean()
fig, ax = plt.subplots(1)
pplt.plot(ax,x= s.index,y=s,linewidth=2)
plt.title('Sentiment of AAPL Stock - 01-Jan to 07-Nov 2013')
import sys
import csv
import prettyplotlib as ppl
from prettyplotlib import plt
import numpy as np
blast_data = sys.argv[1].strip()
ident = []
with open(blast_data, "r") as handle:
reader = csv.reader(handle)
for row in reader:
ident.append(float(row[2]))
fig, ax = plt.subplots(1)
ppl.hist(ax, ident)
plt.xlabel(u"Percentage of identity", fontdict={'fontsize':14})
plt.ylabel(u"Frecuency", fontdict={'fontsize':14})
ax.set_title("Plotted Blast results: % of identity")
fig.savefig('fig_blast_identity.png')
print "Made a plot of the percentags of identity from the blast data."
print "It is in the file `fig_blast_identity.png`"
#AS WRITTEN
#Stable
#Open
#Extro
#Conci
#Agree
# In[24]:
#Histograms
import prettyplotlib as ppl
#for i in bfas.columns.values.tolist()[1:]:
print i
ppl.hist(bfas[i],bins=20)
ppl.plt.savefig(i+'.png')
ppl.plt.close()
# In[25]:
bfas.head()
# In[ ]:
def make_hists(self, num_bins=None, use_prettyplotlib=True):
if use_prettyplotlib:
try:
import prettyplotlib as plt
except ImportError:
import matplotlib.pyplot as plt
use_prettyplotlib = False
print "prettyplotlib not installed. Using matplotlib..."
else:
import matplotlib.pyplot as plt
# Setup subplots if plotting together
if self.subplot:
num = len(self.columns)
if num <= 3:
ncols = 1
nrows = num
elif num <= 8:
ncols = 2
nrows = num / 2
else: # Max columns right now is 12
ncols = 3
nrows = num / 3
# Check if we need an extra row.
if num % ncols != 0:
nrows += 1
# Make the objects
fig, axes = plt.subplots(nrows=nrows, ncols=ncols)
# This is a bit awkward to get the indices, but my matplotlib version
# doesn't use the same object type as prettyplotlib creates.
posns = np.indices(axes.shape)
x, y = posns[0].ravel(), posns[1].ravel()
# Keep the mean, median, std.
data_stats = {}
for i, column in enumerate(self.columns):
data = self.dataframe[column]
data = data[np.isfinite(data)]
if num_bins is None:
num_bins = np.sqrt(len(data))
data_stats[column] = [nanmean(data), nanstd(data), nanmedian(data)]
if self.subplot:
if use_prettyplotlib:
plt.hist(axes[x[i], y[i]],data, num_bins, grid="y")
else:
axes[x[i], y[i]].hist(data, num_bins)
axes[x[i], y[i]].set_xlabel(column) # ADD UNITS!
else:
fig, axes = plt.subplots(1)
axes.hist(data, num_bins)
axes.set_xlabel(column) # ADD UNITS!
if self.verbose and not self.subplot:
print column+" Stats: %s" % (data_stats[column])
p.show()
elif not self.subplot:
fig.savefig(self.save_name+"_"+column+"."+self.save_type)
p.close()
if self.subplot:
p.tight_layout()
if self.verbose:
for column in self.columns:
print column+" Stats: %s" % (data_stats[column])
p.show()
else:
fig.savefig(self.save_name+"_hists."+self.save_type)
def plot_qual_hist(quals, in_file):
quals = [x for x in quals if x < 500.0]
out_file = "%s-hist.png" % os.path.splitext(in_file)[0]
fig, ax = plt.subplots(1)
ppl.hist(ax, [quals], bins=100)
fig.savefig(out_file)
