def web_plotting_plots():
# static
start = dt.datetime(2010, 1, 1)
end = dt.datetime(2013, 1, 27)
data = DataReader("MSFT", 'google', start, end)
data = data.reset_index()
fig, ax = plt.subplots()
data.plot(x='Date', y='Close', grid=True, ax=ax)
plt.savefig(PATH + 'MSFT.png', dpi=300)
# interactive - may not work in cloud 9
warnings.simplefilter('ignore')
py.sign_in('Python-Demo-Account', 'gwt101uhh0')
# to interactive D3.js plot
py.iplot_mpl(fig)
# direct approach with Cufflinks
data.set_index('Date')['Close'].iplot(world_readable=True)
def plot_df(d, ylabel = '', xlabel = '', title = '', interactive = False, rotate = False):
fig = plt.figure(figsize=(10, 4), dpi=80)
for c in d.columns:
plt.plot(d.index, d[c], label = c)
if rotate:
plt.xticks(d.index, d.index, rotation='vertical')
plt.ylabel(ylabel)
plt.xlabel(xlabel)
plt.title(title)
if interactive:
plt.legend()
return py.iplot_mpl(fig)
else:
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))
def plot_df(d,
ylabel='',
xlabel='',
title='',
interactive=False,
rotate=False):
fig = plt.figure(figsize=(10, 4), dpi=80)
for c in d.columns:
plt.plot(d.index, d[c], label=c)
if rotate:
plt.xticks(d.index, d.index, rotation='vertical')
plt.ylabel(ylabel)
plt.xlabel(xlabel)
plt.title(title)
if interactive:
plt.legend()
return py.iplot_mpl(fig)
else:
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))
import plotly.plotly as py
import plotly.tools as tls
from plotly.graph_objs import *
import numpy as np
import matplotlib.pyplot as plt
import os
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = 'C:\Users\Cat\Documents\Research_Halos\HaloDetail'
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
parent_spin_val = oldvalues[whparent]['Spin(26)'] #Find parent spin parameter
elif file.endswith('_Lambda.txt'):
newvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whalo = np.where(newvalues['Halo_Name'] == haloname) #Locate halo
orb_ang_mom = newvalues[whalo]['orb_lambda_subhalo']
plt.loglog(parent_spin_val, orb_ang_mom, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Comparing Host Spin Parameter to Normalized(from subhalos) orbital Angular Momentum of Satellites')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Comparing Host Spin Parameter to Normalized(from subhalos) orbital Angular Momentum of Satellites')
def plot_plotly(self, plotly_filename=None, mpl_type=False, xlim=None, ylim=None, title=None, figsize=None,
xlabel=None, ylabel=None, fontsize=None, show_legend=True, grid=False):
"""
Plot data using plotly library in IPython
:param plotly_filename: name for resulting plot file on server (use unique name, else the same plot will be showen)
:type plotly_filename: None or str
:param bool mpl_type: use or not plotly converter from matplotlib (experimental parameter)
:param xlim: x-axis range
:param ylim: y-axis range
:type xlim: None or tuple(x_min, x_max)
:type ylim: None or tuple(y_min, y_max)
:param title: title
:type title: None or str
:param figsize: figure size
:type figsize: None or tuple(weight, height)
:param xlabel: x-axis name
:type xlabel: None or str
:param ylabel: y-axis name
:type ylabel: None or str
:param fontsize: font size
:type fontsize: None or int
:param bool show_legend: show or not labels for plots
:param bool grid: show grid or not
"""
import plotly.plotly as py
from plotly import graph_objs
from ipykernel import connect
plotly_filename = self.plotly_filename if plotly_filename is None else plotly_filename
try:
connection_file_path = connect.find_connection_file()
connection_file = os.path.basename(connection_file_path)
if '-' in connection_file:
kernel_id = connection_file.split('-', 1)[1].split('.')[0]
else:
kernel_id = connection_file.split('.')[0]
except Exception as e:
kernel_id = "no_kernel"
PLOTLY_API_USER, PLOTLY_API_KEY, PLOTLY_USER = self._plotly_config()
save_name = '{user}_{id}:{name}'.format(user=PLOTLY_USER, id=kernel_id, name=plotly_filename)
py.sign_in(PLOTLY_API_USER, PLOTLY_API_KEY)
if mpl_type:
self.plot(new_plot=True, xlim=xlim, ylim=ylim, title=title, figsize=figsize, xlabel=xlabel, ylabel=ylabel,
fontsize=fontsize, grid=grid)
mpl_fig = plt.gcf()
update = dict(
layout=dict(
showlegend=show_legend
),
data=[dict(name=leg) for leg in mpl_fig.legends]
)
return py.iplot_mpl(mpl_fig, width=self.figsize[0] * 60,
update=update,
height=self.figsize[1] * 60,
filename=save_name,
fileopt='overwrite')
xlabel = self.xlabel if xlabel is None else xlabel
ylabel = self.ylabel if ylabel is None else ylabel
title = self.title if title is None else title
figsize = self.figsize if figsize is None else figsize
fontsize = self.fontsize if fontsize is None else fontsize
layout = graph_objs.Layout(yaxis={'title': ylabel, 'ticks': ''}, xaxis={'title': xlabel, 'ticks': ''},
showlegend=show_legend, title=title,
font=graph_objs.Font(family='Courier New, monospace', size=fontsize),
width=figsize[0] * self.PLOTLY_RESIZE,
height=figsize[1] * self.PLOTLY_RESIZE
)
fig = self._plot_plotly(layout)
return py.iplot(fig, width=figsize[0] * self.PLOTLY_RESIZE, height=figsize[1] * self.PLOTLY_RESIZE,
filename=save_name)
#To Plot Spin Parameters
#############################################################################
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
highmasses = []
pops = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
highmass=max(oldvalues['mvir(10)'])
highmasses = np.append(highmasses, highmass)
elif file.endswith('_from_CMF.txt'):
newvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whalo = np.where(newvalues['Halo_Name'] == haloname) #Locate halo
pop = newvalues[whalo]['interpolated_y']
pops = np.append(pops, pop)
plt.loglog(highmass, pop, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(highmasses, pops)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Interpolated Population vs. Halo Mass')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Interpolated Population vs. Halo Mass')
y_pos += 0.25
elif column == "Business":
y_pos -= 0.75
elif column == "Math and Statistics":
y_pos += 0.75
elif column == "Architecture":
y_pos -= 0.75
elif column == "Computer Science":
y_pos += 0.75
elif column == "Engineering":
y_pos -= 0.25
#again, making sure size of labels is readable
plt.text(2011.5, y_pos, column, fontsize=14, color=tableau20[rank])
#titles
plt.text(1995, 93, "Percentage of Bachelor's degree conferred to women in the U.S.A"
", by major (1970-2012)", fontsize=17, ha="center")
#and of course, citations!
plt.text(1966, -8, "Data source: nces.ed.gov/programs/digest/2013menu_tables.asp"
"\nAuthor: Randy Olson (randalolson.com / @randal_olson)"
"\nNote: Some majors are missing because the historical data "
"is not available for them", fontsize=10)
#plt.savefig("percent-bachelors-degrees-women.png", bbox_inches="tight")
#see if we can put it on plotly
dataviz1 = plt.gcf()
ply.iplot_mpl(dataviz1,resize=False,filename='dataviz1',width=960,height=1120)
py.sign_in('Cat_Phish', 'c4i0ux16og')
#############################################################################
#To Plot Angular Momentum Versus Satellite Abundance
#############################################################################
def plot_mpl_fig():
rootdir = '/Users/Cat/Documents/Research_Halos/HaloDetail'
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
values1 = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(values1['mvir(10)']))
parent_spin = values1[whparent]['Spin(26)']
elif file.endswith('_subhalos'):
values2 = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
index = np.arange(len(values2['mvir(10)']))
rindex = len(index)-index
pop = len(values2['mvir(10)'])
print pop
plt.loglog(parent_spin, pop, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Abundance vs. Host Spin Parameter')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Abundance vs. Host Spin Parameter')
y_pos += 0.75
elif column == "Engineering":
y_pos -= 0.25
#again, making sure size of labels is readable
plt.text(2011.5, y_pos, column, fontsize=14, color=tableau20[rank])
#titles
plt.text(1995,
93, "Percentage of Bachelor's degree conferred to women in the U.S.A"
", by major (1970-2012)",
fontsize=17,
ha="center")
#and of course, citations!
plt.text(1966,
-8, "Data source: nces.ed.gov/programs/digest/2013menu_tables.asp"
"\nAuthor: Randy Olson (randalolson.com / @randal_olson)"
"\nNote: Some majors are missing because the historical data "
"is not available for them",
fontsize=10)
#plt.savefig("percent-bachelors-degrees-women.png", bbox_inches="tight")
#see if we can put it on plotly
dataviz1 = plt.gcf()
ply.iplot_mpl(dataviz1,
resize=False,
filename='dataviz1',
width=960,
height=1120)
import os
import scipy
from scipy import stats
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
rmaxs = []
vmaxs = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
rmax = oldvalues[whparent]['rs(12)']*2.16
vmax = oldvalues[whparent]['vmax(16)']
rmaxs = np.append(rmaxs, rmax)
vmaxs = np.append(vmaxs, vmax)
plt.loglog(rmax, vmax, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(rmaxs, vmaxs)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Rmax-Vmax Host')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Rmax-Vmax Host')
#To Plot Spin Parameters
#############################################################################
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
parent_spin_vals = []
avg_spin_vals = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
parent_spin_val = oldvalues[whparent]['Spin(26)'] #Find parent spin parameter
parent_spin_vals = np.append(parent_spin_vals, parent_spin_val)
elif file.endswith('_subhalos'):
newvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
child_spin_vals = newvalues['Spin(26)']
avg_spin_val = (np.mean(child_spin_vals))
avg_spin_vals = np.append(avg_spin_vals, avg_spin_val)
plt.loglog(avg_spin_val, parent_spin_val, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(avg_spin_vals, parent_spin_vals)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Spin Parameter Plot')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Spin Parameter Plot')
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
orb_ang_moms = []
host_masses = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
host_mass = oldvalues[whparent]['mvir(10)']
host_masses = np.append(host_masses, host_mass)
elif file.endswith('_Lambda.txt'):
newvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whalo = np.where(newvalues['Halo_Name'] == haloname) #Locate halo
orb_ang_mom = newvalues[whalo]['orb_lambda_host']
orb_ang_moms = np.append(orb_ang_moms, orb_ang_mom)
plt.loglog(host_mass, orb_ang_mom, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(host_masses, orb_ang_moms)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Comparing Host Mass to Normalized(from host) orbital Angular Momentum of Satellites')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Comparing Host Mass to Normalized(from host) orbital Angular Momentum of Satellites')
## NUMBER OF ASSETS
n_assets = 4
## NUMBER OF OBSERVATIONS
n_obs = 1000
return_vec = np.random.randn(n_assets, n_obs)
# In[5]:
fig = plt.figure()
plt.plot(return_vec.T, alpha=.4);
plt.xlabel('time')
plt.ylabel('returns')
py.iplot_mpl(fig, filename='s6_damped_oscillation')
# These return series can be used to create a wide range of portfolios, which all
# have different returns and risks (standard deviation). We can produce a wide range
# of random weight vectors and plot those portfolios. As we want all our capital to be invested, this vector will have to some to one.
# In[6]:
def rand_weights(n):
''' Produces n random weights that sum to 1 '''
k = np.random.rand(n)
return k / sum(k)
print rand_weights(n_assets)
print rand_weights(n_assets)
## NUMBER OF ASSETS
n_assets = 4
## NUMBER OF OBSERVATIONS
n_obs = 1000
return_vec = np.random.randn(n_assets, n_obs)
# In[5]:
fig = plt.figure()
plt.plot(return_vec.T, alpha=.4)
plt.xlabel('time')
plt.ylabel('returns')
py.iplot_mpl(fig, filename='s6_damped_oscillation')
# These return series can be used to create a wide range of portfolios, which all
# have different returns and risks (standard deviation). We can produce a wide range
# of random weight vectors and plot those portfolios. As we want all our capital to be invested, this vector will have to some to one.
# In[6]:
def rand_weights(n):
''' Produces n random weights that sum to 1 '''
k = np.random.rand(n)
return k / sum(k)
print rand_weights(n_assets)
def simple_plotly(fig):
try:
return py.iplot_mpl(fig)
except Exception:
pass
highvel = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('_subhalos'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
vmax = oldvalues['vmax(16)']
mass = oldvalues['mvir(10)']
vmaxs = np.append(vmaxs, vmax)
masses = np.append(masses, mass)
whhi = np.where(mass>=1.0e8)
whmed = np.where((mass>=1.0e6)&(mass<1.0e8))
whlo = np.where(mass<1.0e6)
lowmass = np.append(lowmass, oldvalues[whlo]['mvir(10)'])
medmass = np.append(medmass, oldvalues[whmed]['mvir(10)'])
highmass = np.append(highmass, oldvalues[whhi]['mvir(10)'])
lowvel = np.append(lowvel, oldvalues[whlo]['vmax(16)'])
medvel = np.append(medvel, oldvalues[whmed]['vmax(16)'])
highvel = np.append(highvel, oldvalues[whhi]['vmax(16)'])
print "%s done. On to the next." %haloname
plt.loglog(highmass, highvel, 'o', medmass, medvel, 'bs', lowmass, lowvel, 'g*', alpha=0.8)
#spearman = scipy.stats.spearmanr(rmaxs, vmaxs)
#print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Vmax-Mass Subhaloes')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Vmax-Mass Subhaloes')
def plotly_date_frequency_plot(
df=None,
array=None,
series=None,
title=None,
filename="plotly_date_frequency_plot_test",
weekend_bool=True,
weekend_height=20,
xlabel=None,
ylabel=None,
vlines=None,
hlines=None,
xlim=None,
ylim=None,
**kwargs
):
"""plotly_date_frequency_plot uses plotly to interactively plot a bar chart showing a date series or df[array] frequency
Requires df, array str or series
To write a permanent, linkable plot, change filename
Optional weekend indicators with adjustable height
.. todo:
Add hue parameter for stacked bar plot (see Jason's implementation)
Add resample argument for weekly, monthly views
"""
if series is None:
series = df[array]
else:
series = pd.Series(series)
day_vcs = series.value_counts().sort_index()
day_tuples = zip(day_vcs.keys(), day_vcs.values)
if weekend_bool:
# create list of weekend tuples to indicate weekends
start, end = utils.date.extract_date(min(series)), utils.date.extract_date(max(series))
running_day = start
weekend_days = []
while running_day <= end:
if running_day.weekday() in set([5, 6]):
weekend_days.append(running_day)
running_day += dt.timedelta(days=1)
if len(weekend_days) % 2 == 1:
weekend_days = weekend_days[:-1]
weekend_tuples = []
for i in range(len(weekend_days) / 2):
weekend_tuples.append((weekend_days[i * 2], weekend_days[i * 2 + 1]))
# plotly plot
fig = plt.figure(figsize=(8, 6))
ax = fig.add_subplot(1, 1, 1)
plt.bar(utils.date.extract_date([day[0] for day in day_tuples]), [count[1] for count in day_tuples], **kwargs)
if weekend_bool:
for i in weekend_tuples:
plt.plot([i[0], i[1], i[0], i[1]], [0.1, weekend_height, weekend_height, 0.1], alpha=0.6, color="grey")
if vlines is not None:
if ylim is None:
ylim = plt.ylim()
if not isinstance(vlines, (list, pd.core.series.Series, np.ndarray)):
vlines = [vlines]
for vl in vlines:
plt.plot([vl, vl], [ylim[0], ylim[1]])
if hlines is not None:
if xlim is None:
xlim = plt.xlim()
if not isinstance(hlines, (list, pd.core.series.Series, np.ndarray)):
hlines = [hlines]
for hl in hlines:
plt.plot([xlim[0], xlim[1]], [hl, hl])
if title is not None:
plt.title(title, size=20)
if xlabel is not None:
plt.xlabel(xlabel, size=20)
if ylabel is not None:
plt.ylabel(ylabel, size=20)
if xlim is not None:
plt.xlim(xlim)
if ylim is not None:
plt.ylim(ylim)
return py.iplot_mpl(fig, filename=filename, fileopt="overwrite")
left="off",
right="off",
labelleft="on",
labelsize=16)
ax.set_ylim(-5, 60)
ax.set_xlim(-5, 100)
ax.set_ylabel('% HH in Poverty', fontsize=fontsize)
ax.set_xlabel('% Population', fontsize=fontsize)
# Matplotlib code is very long... But sometimes you have existing matplotlib code, right? The good news is, plotly can eat it!
# In[25]:
py.iplot_mpl(mpl_fig, filename='baltimore-poverty')
# So, at the moment, matplotlib legends do not fully convert to plotly legends (please refer to our [user guide](https://plot.ly/python/matplotlib-to-plotly-tutorial/#Careful,-matplotlib-is-not-perfect-%28yet%29)). Let's tweak this now.
# In[26]:
import plotly.tools as tls
# In[27]:
# Convert mpl fig object to plotly fig object, resize to plotly's default.
py_fig = tls.mpl_to_plotly(mpl_fig, resize=True)
# In[28]:
# Give each trace a name to appear in legend.
data_file = urllib2.urlopen(data_url)
df = pd.read_csv(data_file, sep=',')
df = df.drop(df.index[0]) # drop first row (US totals)
df = df[df['murder'] < 11] # drop out-of-range rows
mpl_fig_bubble = plt.figure() # (!) set new mpl figure object
ax = mpl_fig_bubble.add_subplot(111) # add axis
plt.axis([0, 11, 200, 1280])
plt.xlabel('Murders per 100,000 population')
plt.ylabel('Burglaries per 100,000 population')
scatter = ax.scatter(
df['murder'],
df['burglary'],
c=df['larceny_theft'], # using some color scale
s=np.sqrt(df['population']),
linewidths=2,
edgecolor='w',
alpha=0.6)
for i_X, X in df.iterrows():
plt.text(
X['murder'],
X['burglary'],
X['state'][0:8], # only the first 8 letters
size=8,
horizontalalignment='center')
py.iplot_mpl(mpl_fig_bubble, filename='s6_bubble-chart')
# Now, we can use picks to select magnetometer data and plot it. The matplotlib graph can be converted into an interactive one using Plotly with just one line of code:
# In[11]:
picks = mne.pick_types(raw.info, meg='mag', exclude=[])
data, times = raw[picks[:10], start:stop]
import matplotlib.pyplot as plt
import plotly.plotly as py
plt.plot(times, data.T)
plt.xlabel('time (s)')
plt.ylabel('MEG data (T)')
update = dict(layout=dict(showlegend=True), data=[dict(name=raw.info['ch_names'][p]) for p in picks[:10]])
py.iplot_mpl(plt.gcf(), update=update)
# But, we can also use MNE-Python's interactive data browser to get a better visualization:
# In[12]:
raw.plot();
# Let us do the same using Plotly. First, we import the required classes
# In[13]:
from plotly import tools
from plotly.graph_objs import Layout, YAxis, Scatter, Annotation, Annotations, Data, Figure, Marker, Font
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
orb_ang_moms = []
cs = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
c = oldvalues[whparent]['rvir(11)']/oldvalues[whparent]['rs(12)']
cs = np.append(cs, c)
elif file.endswith('_Lambda.txt'):
newvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whalo = np.where(newvalues['Halo_Name'] == haloname) #Locate halo
orb_ang_mom = newvalues[whalo]['orb_lambda_host']
orb_ang_moms = np.append(orb_ang_moms, orb_ang_mom)
plt.loglog(orb_ang_mom, c, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(orb_ang_moms, cs)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Concentration vs. Normalized(from host) Orbital Angular Momentum of Satellites')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Concentration vs. Normalized(from host) Orbital Angular Momentum of Satellites')
import os
import scipy
from scipy import stats
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
parent_spin_vals = []
masses = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
parent_spin_val = oldvalues[whparent]['Spin(26)'] #Find parent spin parameter
mass = max(oldvalues['mvir(10)'])
parent_spin_vals = np.append(parent_spin_vals, parent_spin_val)
masses = np.append(masses, mass)
plt.loglog(mass, parent_spin_val, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(masses, parent_spin_vals)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Spin parameter vs. Mass')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Spin Parameter vs. Mass')
index25 = np.arange(len(nvfrac25))
rindex25 = len(index25)-index25
nrindex25 = np.delete(rindex25, whlimit25)
rindex25s = np.append(rindex25s, nrindex25)
vfrac25s = np.append(vfrac25s, nvfrac25)
plt.loglog(vfrac25, rindex25, alpha=0.8, label=haloname)
if c < twentyfifth:
vfracx = sorted(values['vmax(16)'])
whlimitx = np.where(vfracx<=0.13)
nvfracx = np.delete(vfracx, whlimitx)
indexx = np.arange(len(vfracx))
rindexx = len(indexx)-indexx
nrindexx = np.delete(rindexx, whlimitx)
rindexxs = np.append(rindexxs, nrindexx)
vfracxs = np.append(vfracxs, nvfracx)
plt.loglog(vfracx, rindexx, alpha=0.8, label=haloname)
print "%s done. On to the next." %haloname
#plt.loglog(sorted(vfracxs,reverse=True), sorted(rindexxs), label= haloname)
#plt.loglog(sorted(vfrac25s,reverse=True), sorted(rindex25s), label=haloname)
#plt.loglog(sorted(vfrac50s,reverse=True), sorted(rindex50s), label=haloname)
#plt.loglog(sorted(vfrac75s,reverse=True), sorted(rindex75s), label=haloname)
#plt.xlim(xmin=0.12, xmax=0.4)
#print stats.ks_2samp(vfrac75s,vfracxs)
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Total Mean CMF')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Total_Mean_CVF-style2')
x = np.linspace(0,40,1000)
for i in range(4):
sigma = np.sqrt(variance[i])
y = mlab.normpdf(x,mean[i],sigma)
plt.plot(x,y, label=r'$v_{}$'.format(i+1))
plt.xlabel("X")
plt.ylabel("P(X)")
# To re-create the graph in Plotly and use Plotly's defaults, call `iplot` and add `strip_style`.
# In[6]:
py.iplot_mpl(fig1, strip_style = True)
# It's shareable at a URL, contains the data as part of the plot, and can be edited collaboratively from any API or our web app. Head over to [Plotly's API](https://plot.ly/api) to see more, and check out our [user guide](https://plot.ly/python/user-guide/) to see how it all works.
#
# Plotly also jointly preserves the data in a graph, the graph, and the graph description (in this case JSON). That's valuable. [One study](http://www.smithsonianmag.com/science-nature/the-vast-majority-of-raw-data-from-old-scientific-studies-may-now-be-missing-180948067/?no-ist) in *current biology* found that over 90 percent of data from papers published over the past 20 years was not available. So sharing data is good for science and reproducibility, useful for your projects, and great for collaboration.
### II. ggplot2 plots in Plotly
# Let's take a real-world look storing data and graphs together. Suppose you see a graph on the [World Bank website](http://blogs.worldbank.org/opendata/accessing-world-bank-data-apis-python-r-ruby-stata). The graph uses [ggplot2](http://ggplot2.org), a remarkable plotting library for R.
# In[7]:
from IPython.display import Image
Image(url = 'http://i.imgur.com/PkRRmHq.png')
hostvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header')
highmass=max(hostvalues['mvir(10)'])
hi = np.where(highmass>=1.0e+12) #Index of host with highmass
low = np.where(highmass<1.0e+12)
hi_id = hostvalues[hi]['id(1)'] #Id of the highmass host
low_id = hostvalues[low]['id(1)']
whhi = np.where(hostvalues['pid(5)']==hi_id) #Indices of subhalos corresponding to the highmass host
whlow = np.where(hostvalues['pid(5)']==low_id)
hmass = hostvalues[whhi]['mvir(10)']
print len(hmass)
lmass = hostvalues[whlow]['mvir(10)']
print len(lmass)
hvel = hostvalues[whhi]['vmax(16)']
lvel = hostvalues[whlow]['vmax(16)']
hmasses = np.append(hmasses, hmass)
lmasses = np.append(lmasses, lmass)
hvels = np.append(hvels, hvel)
lvels = np.append(lvels, lvel)
print "%s done. On to the next." %haloname
plt.hist(hmasses)
plt.hist(lmasses)
#spearman = scipy.stats.spearmanr(rmaxs, vmaxs)
#print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Mass Distribution of Subhaloes')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Mass Distriburion of Subhaloes')
def get_image(request):
#get the name and date of the stock below
stock = request.GET.get("name")
stockNames = stock.split(",")
stockNames.sort()
numStocksToCompare = len(stock.split(','))
d = request.GET.get('date')
begDate = dt.strptime(d, '%Y-%m-%d')
d = d.replace('-', "")
stock_price_url = 'https://www.quandl.com/api/v3/datatables/WIKI/PRICES.json?ticker=+stock+&date.gte=dt&qopts.columns=date,close&api_key=-2H8WyYB8b7FaCshLLTN'
date = []
price = []
stock_price_url = stock_price_url.replace("+stock+", stock)
stock_price_url = stock_price_url.replace("dt", d)
source_code = urllib.request.urlopen(stock_price_url).read().decode()
json_root = json.loads(source_code)
json_datatable = json_root["datatable"]
json_data = json_datatable["data"]
datesFinal = []
pricesFinal = []
#if there are more than one stocks to compare
if numStocksToCompare > 1:
for day in json_data:
#populate lists with all the data
date.append(dt.strptime(day[0], '%Y-%m-%d'))
price.append(day[1])
dataLength = len(date)
#day will be the current day in the stock information that we received
day = date[0]
dayPrice = price[0]
i = 1
#get the stock information for each stock
for x in range(0, numStocksToCompare):
datesFinal.append(day) #store the first date and price
pricesFinal.append(dayPrice)
day = date[i]
while (
(abs((day - datesFinal[-1]).days) < 6)
): #if the range between the last date and newest date is larger than 5, we are at a new stock
datesFinal.append(day)
dayPrice = price[i]
pricesFinal.append(dayPrice)
i += 1
#if we've reached the end of the data
if (i == dataLength):
break
day = date[i]
d = datesFinal
p = pricesFinal
plt.plot_date(d, p, '-',
label=stockNames[x].upper()) #plot the graph
#if we've plotted all the stocks, break out of the loop
if (stockNames[x] == stockNames[len(stockNames) - 1]):
break
del datesFinal[:]
del pricesFinal[:]
dayPrice = price[i] #store the first price of the next stock
else:
#store the price and date information for each day
for day in json_data:
date.append(day[0])
price.append(day[1])
plt.plot_date(date, price, '-', label=stock.upper())
#make sure the legend appears when the plotly graph is made
update = dict(layout=dict(showlegend=True))
plt.xlabel('Date')
plt.ylabel('Price')
plt.title(stock.upper() + " Stock")
#finally, we create plotly figure
mpl_fig = plt.gcf()
py_fig = tls.mpl_to_plotly(mpl_fig, verbose=True)
py.iplot_mpl(mpl_fig, update=update, filename='graph')
return render(request, 'home/graph.html')
import os
import scipy
from scipy import stats
from astropy.io import ascii
py.sign_in('Cat_Phish', 'c4i0ux16og')
def plot_mpl_fig():
rootdir = '/Users/catherinefielder/Documents/Research_Halos/HaloDetail'
cs = []
masses = []
for subdir, dirs, files in os.walk(rootdir):
head,tail = os.path.split(subdir)
haloname = tail
for file in files:
if file.endswith('.list'):
oldvalues = ascii.read(os.path.join(subdir, file), format = 'commented_header') #Get full path and access file
whparent = np.where(max(oldvalues['mvir(10)']))
mass = max(oldvalues['mvir(10)']) #Find parent spin parameter
c = oldvalues[whparent]['rvir(11)']/oldvalues[whparent]['rs(12)']
masses = np.append(masses, mass)
cs = np.append(cs, c)
plt.loglog(mass, c, alpha=0.8,label=haloname)
print "%s done. On to the next." %haloname
spearman = scipy.stats.spearmanr(masses, cs)
print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
#print(py_fig1.to_string())
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Concentration vs. Mass')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Concentration vs. Mass')
ranked_df_body = unstacked_total.apply(lambda x: x[1:], axis=1)
ranked_df_body = ranked_df_body.apply(lambda x: ss.rankdata(x, method='min'), axis=1)
print len(ranked_df_body)
ranked_df_body['date'] = unstacked_total['date']
ranked_unstacked_total = ranked_df_body
my_total_ranked_line = pd.melt(ranked_unstacked_total, id_vars=['date'])
print ggplot(aes(x='date', y='value', colour="name"), data=my_total_ranked_line) + \
scale_x_date(breaks=date_breaks('6 months'), labels='%b %Y') + \
geom_line(size=3) + \
ggtitle('Ranking over Time')
###
# pt.3
###
import plotly.plotly as py
import plotly.tools as tls
from plotly.graph_objs import *
from credentials import *
py.sign_in(py_u, py_p)
plot = ggplot(aes(x='date', y='value', colour="name"), data=my_total_ranked_line) + \
scale_x_date(breaks=date_breaks('6 months'), labels='%b %Y') + \
geom_line(size=3) + \
ggtitle('Ranking over Time')
fig = plot.draw()
update = {'layout':{'showlegend':True, 'legend':Legend({'x':90}), 'font':{'size':20}}}
py.iplot_mpl(fig, update=update)
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import plotly.plotly as py
get_ipython().magic("matplotlib inline")
def sigmoid(z):
return 1.0 / (1.0 + np.exp(-z))
z = np.arange(-7, 7, 0.1)
phi_z = sigmoid(z)
plt.plot(z, phi_z)
plt.axvline(0.0, color="k")
plt.axhspan(0.0, 1.0, facecolor="1.0", alpha=1.0, ls="dotted")
plt.axhline(y=0.5, ls="dotted", color="k")
plt.yticks([0.0, 0.5, 1.0])
plt.ylim(-0.1, 1.1)
plt.xlabel("z")
plt.ylabel("$\phi (z)$")
fig = plt.gcf()
# In[9]:
py.iplot_mpl(fig, strip_style=True, filename="sigmoid function")
def plotly_plot(
x=None,
y=None,
df=None,
style="scatter",
title=None,
filename="plotly_plot_test",
xlabel=None,
ylabel=None,
vlines=None,
hlines=None,
xlim=(None, None),
ylim=(None, None),
dropna=True,
dateextractX=False,
dateextractY=False,
figsize=(16, 9),
plotlyplot=True,
saveAs=None,
**kwargs
):
"""Interactively plots a series or two in plotly.
Must set unique `title` or `filename` for plot to exist semi-permanently,
else overwritten on the next use of function.
Parameters
----------
x : array, series, or list OR column name in df
numpy array, pandas series, or list of primary values to plot
y : array, series, or list OR column name in df
numpy array, pandas series, or list of secondary values to plot
df : pandas DataFrame, optional
if given, uses dataframe to create x and y arrays using x and y column names given
style : string
argument to choose style of plot. currently implemented dist, hist, line, and scatter
title, xlabel, ylabel : string, optional
labels of plot. if filename not given, filename = title
vlines, hlines : int or list, optional
list of x/y points to make vertical/horizontal lines in the plot
xlim, ylim : tuple (min, max), optional
horizontal/vertical boundries of the figure
dropna : boolean, optional (default is True)
drop nans from series
dateextractX, dateextractY : boolean, optional (default is False)
try to convert x and y to datetimes using utils.date.extract_date
plotlyplot: boolean, optional (default is True)
set to False for prototyping
filename: string, optional
file name on server for plotly plot. unique label ensures plot will not be overwritten
saveAs : string (default is None)
If given, save the figure using saveAs as the file name.
kwargs : dict
additional keyworded arguments passed to plotting functions
Returns
-------
iframe : iframe
Notes
-----
ToDo - Fix autolabeling. broked it when fixing dates..
"""
fig = plt.figure(figsize=figsize)
ax = fig.add_subplot(1, 1, 1)
yisNone = False
if y is None:
yisNone = True
# if dataframe provided, create x (and y) array(s)
if df is not None:
x = df[x]
if not yisNone:
y = df[y]
# checking if x (and y) are pandas Series, if not convert to
if not isinstance(x, pd.Series):
x = pd.Series(x)
else:
if xlabel is None:
xlabel = x.name
if not yisNone:
if not isinstance(y, pd.Series):
y = pd.Series(y)
else:
if ylabel is None:
ylabel = y.name
# if dropna, drop nan values from x (and accompanying values in y)
if dropna:
try:
nan_indices = pd.isnull(x)
if sum(nan_indices) > 0:
print "nan values in series to be dropped:", sum(nan_indices)
x = x[~nan_indices].reset_index(drop=True)
if not yisNone:
y = y[~nan_indices].reset_index(drop=True)
except:
pass
# if y not provided: set y to x.index, swap x and y as we are interested
# in plotting x on the 'y' against the index
if yisNone:
y = x.index
x, y = y, x
# try to extract_date x and y
if dateextractX:
try:
x = utils.date.extract_date(x)
print "date extracted x"
except:
pass
if dateextractY and not yisNone:
try:
y = utils.date.extract_date(y)
print "date extracted y"
except:
pass
# dist or hist: distribution of x plot
if style == "dist":
try:
sns.distplot(y, **kwargs)
except:
print "failed producing seaborn distribution plot.. trying hist"
plt.hist(y, **kwargs)
if ylabel is None:
ylabel = "frequency"
elif style == "hist":
plt.hist(y, **kwargs)
if ylabel is None:
ylabel = "frequency"
# line or scatter: x vs y plot
elif style == "line":
plt.plot(x, y, **kwargs)
elif style == "scatter":
plt.scatter(x, y, **kwargs)
else:
print "style currently not available"
return None
if ylim[0] is None:
y_min = plt.ylim()[0]
else:
y_min = ylim[0]
if ylim[1] is None:
y_max = plt.ylim()[1]
else:
y_max = ylim[1]
plt.ylim(y_min, y_max)
if xlim[0] is None:
x_min = plt.xlim()[0]
else:
x_min = xlim[0]
if xlim[1] is None:
x_max = plt.xlim()[1]
else:
x_max = xlim[1]
plt.xlim(x_min, x_max)
# vlines, hlines. should maybe export this to their own function for other
# uses
if vlines is not None:
if not isinstance(vlines, (list, pd.core.series.Series, np.ndarray)):
vlines = [vlines]
for vl in vlines:
plt.plot([vl, vl], [y_min, y_max])
if hlines is not None:
if xlim is None:
xlim = plt.xlim()
if not isinstance(hlines, (list, pd.core.series.Series, np.ndarray)):
hlines = [hlines]
for hl in hlines:
plt.plot([x_min, x_max], [hl, hl])
# title, filename handling
if (title is None) and (filename != "plotly_plot_test"):
title = filename
if title is not None:
plt.title(title, size=20)
# if title is set and filename is default, set filename to title
if filename == "plotly_plot_test":
filename = title
# x and y label handling. auto labeling hashed out for now
if xlabel is not None:
plt.xlabel(xlabel, size=18)
if ylabel is not None:
plt.ylabel(ylabel, size=18)
if saveAs is not None:
plt.savefig(saveAs, bbox_inches="tight", dpi=270)
# render in plotly or return nothing to output static chart
if plotlyplot:
iframe = py.iplot_mpl(fig, filename=filename, fileopt="overwrite")
print iframe.embed_code.split('src="')[1].split(".emb")[0]
py.iplot_mpl(fig, filename=filename, fileopt="overwrite")
return iframe
print rmax10s
print vel10s
bin_means, bin_edges, binnumber = scipy.stats.binned_statistic(rmax10s, vel10s, statistic='mean', bins=4)
#print bin_means
#print bin_edges
plt.hlines(bin_means, bin_edges[:-1], bin_edges[1:], colors='g', lw=5, label='binned statistic of data')
#digitizedrmax10s = np.digitize(rmax10s, bins)
#print digitizedrmax10s
#bin_meansrmax10s = [rmax10s[digitizedrmax10s == i].mean() for i in range(1, len(bins))]
#print bin_meansrmax10s
#digitizedvel10s = np.digitize(vel10s, bins)
#bin_meansvel10s = [vel10s[digitizedvel10s == i].mean() for i in range(1, len(bins))]
#plt.loglog(digitizedrmax10s, digitizedvel10s, '-', alpha=0.08, label='mean 10th percentile')
plt.loglog(rmax10s, vel10s, 'o', alpha=0.08, label='10th-50th host mass percentile')
plt.loglog(rmax50s, vel50s, 'o', alpha=0.08, label='50th-90th host mass percentile')
plt.loglog(rmax90s, vel90s, 'o', alpha=0.08, label='>=90th host mass percentile')
plt.loglog(rmaxxs, velxs, 'o', alpha=0.08, label='<10th host mass percentile')
plt.xlim(xmin=0.38, xmax=50)
plt.ylim(ymin=10.0, ymax=200)
plt.xlabel('Rmax (kpc)')
plt.ylabel('Vmax (km/s)')
plt.title('Rmax-Vmax by Host Mass')
#spearman = scipy.stats.spearmanr(rmaxs, vmaxs)
#print spearman
plot_mpl_fig()
mpl_fig1 = plt.gcf()
py_fig1 = tls.mpl_to_plotly(mpl_fig1, verbose=True)
py.iplot_mpl(mpl_fig1, strip_style=True, filename='Rmax-Vmax Percentile')
py_fig1_ss = tls.mpl_to_plotly(mpl_fig1, strip_style=True)
py.plot(py_fig1_ss, filename='Rmax-Vmax Percentile')
ax.tick_params(axis="both", which="both", bottom="off", top="off",
labelbottom="on", left="off", right="off", labelleft="on",
labelsize=16)
ax.set_ylim(-5, 60)
ax.set_xlim(-5, 100)
ax.set_ylabel('% HH in Poverty', fontsize=fontsize)
ax.set_xlabel('% Population', fontsize=fontsize)
# Matplotlib code is very long... But sometimes you have existing matplotlib code, right? The good news is, plotly can eat it!
# In[25]:
py.iplot_mpl(mpl_fig, filename='baltimore-poverty')
# So, at the moment, matplotlib legends do not fully convert to plotly legends (please refer to our [user guide](https://plot.ly/python/matplotlib-to-plotly-tutorial/#Careful,-matplotlib-is-not-perfect-%28yet%29)). Let's tweak this now.
# In[26]:
import plotly.tools as tls
# In[27]:
# Convert mpl fig object to plotly fig object, resize to plotly's default.
py_fig = tls.mpl_to_plotly(mpl_fig, resize=True)
