def plotResults(strategiesToPlot, numTests, which=None):
plt.xkcd()
plt.figure()
if which is None:
# Which tells us to plot a subset of the results
which = range(numTests)
if len(strategiesToPlot) > 1:
colors = plt.cm.rainbow(linspace(0, 1, len(strategiesToPlot)))
else:
colors = plt.cm.rainbow(linspace(0, 1, len(which)))
colors = {a: b for (a, b) in zip(which, colors)}
for nstrat, strategy in enumerate(strategiesToPlot):
for n in xrange(numTests):
if n not in which:
continue
if n == 0 or len(strategiesToPlot) == 1:
title = '%s #%d' % (strategy, n)
else:
title = None
f = shelve.open(r'data\%s_%d.dat' % (strategy, n))
if len(strategiesToPlot) > 1:
pltAgainst(f, title, colors[nstrat])
else:
pltAgainst(f, title, colors[n])
f.close()
plt.legend(loc='upper left')
plt.title('All Strategies')
plt.show()
def plotResults(strategiesToPlot, numTests, which=None):
plt.xkcd()
plt.figure()
if which is None:
# Which tells us to plot a subset of the results
which = range(numTests)
if len(strategiesToPlot) > 1:
colors = plt.cm.rainbow(linspace(0, 1, len(strategiesToPlot)))
else:
colors = plt.cm.rainbow(linspace(0, 1, len(which)))
colors = {a: b for (a, b) in zip(which, colors)}
for nstrat, strategy in enumerate(strategiesToPlot):
for n in xrange(numTests):
if n not in which:
continue
if n == 0 or len(strategiesToPlot) == 1:
title = "%s #%d" % (strategy, n)
else:
title = None
f = shelve.open(r"data\%s_%d.dat" % (strategy, n))
if len(strategiesToPlot) > 1:
pltAgainst(f, title, colors[nstrat])
else:
pltAgainst(f, title, colors[n])
f.close()
plt.legend(loc="upper left")
plt.title("All Strategies")
plt.show()
def draw_xkcd(xx, yy, xlabel, ylabel, olabel, ext):
"""
xx is a date list
"""
pl.xkcd()
matplotlib.rc('font', family='Arial', size=32)
ax = pl.axes()
x = np.array([date2num(vv) for vv in xx])
y = np.array(yy)
#ax.plot(x, y, 'b', lw=1, label=olabel)
pl.bar(x, y)
ax.set_title(olabel, fontsize=128)
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
ax.set_xlim(datetime.date(2014, 8, 18), max(xx))
ax.set_ylim(0, max(yy))
fig = matplotlib.pyplot.gcf()
fig.set_size_inches(24,12)
fig.savefig(olabel+ext,dpi=120)
pl.clf()
import matplotlib.pylab as plt from numpy import linspace, sin, pi plt.ion() plt.xkcd( ) #should work, but doesn't: AttributeError: GraphicsContextBase instance has no attribute 'draw_path' x = linspace(-pi, pi, 101) #plt.plot(x, sin(x), '--x', linewidth =2 ,label = "sin(x)") plt.plot(x, sin(x), '-') #plt.legend() plt.pause(0.1) raw_input()
def main(
symbols,
sDate,
eDate,
maxDaysHeld,
numSim=5000,
daySpacing=10,
startDays=10,
cumulative=True,
outputFilename="simulation.dat",
silent=False,
):
###########
# Multiprocessing Stuff
# raise KeyError
# Establish communication queues
tasks = multiprocessing.Queue()
results = multiprocessing.Queue()
# Start Workers
num_workers = multiprocessing.cpu_count() * 1
if not silent:
print "Creating %d workers" % num_workers
consumers = [Worker(tasks, results) for i in xrange(num_workers)]
for w in consumers:
w.start()
# Enqueue jobs
num_jobs = 0
if type(symbols) is str:
# Pull only a single stock
df = grabSymbol(symbols, sDate, eDate)
else:
# Pull portfollio with tuples in form of ('symbol', pctAllocation)
if abs(sum([a[1] for a in symbols]) - 1) > 0.01:
raise RuntimeError("Sum of allocations must be 1.0")
df = pandas.DataFrame()
for symbol, pctAlloc in symbols:
df = df.add(grabSymbol(symbol, sDate, eDate) * pctAlloc, fill_value=0)
for daysHeld in range(startDays, maxDaysHeld, daySpacing):
tasks.put(Task(daysHeld, numSim, df, cumulative))
num_jobs += 1
# Add a poison pill for each worker
for i in xrange(num_workers):
tasks.put(None)
# Start printing results
jobsTime = pandas.Series(pandas.datetime.now())
means = np.zeros(num_jobs)
medians = np.zeros(num_jobs)
low_25 = np.zeros(num_jobs)
high_25 = np.zeros(num_jobs)
wastedTime = np.zeros(num_jobs)
while num_jobs:
ans = results.get()
if isinstance(ans, ErrorHolder):
# We got an error, print it
print ans
else:
(mn, mds, Xn, Yn, Cn, dH, l_25, h_25, w) = ans
ix = (dH - startDays) / daySpacing
means[ix] = mn
medians[ix] = mds
low_25[ix] = l_25
high_25[ix] = h_25
wastedTime[ix] = w
if "X" not in vars().keys():
# Initalize results matrixes
X = np.zeros([num_jobs, int(Xn.shape[0])])
Y = np.zeros([num_jobs, int(Yn.shape[0])])
C = np.zeros([num_jobs, int(Cn.shape[0])])
X[ix, :] = Xn
Y[ix, :] = Yn
C[ix, :] = Cn
num_jobs -= 1
jobsTime = jobsTime.append(pandas.Series(pandas.datetime.now()))
if not silent:
print "Jobs left: %s (ETA %0.2f min)" % (
num_jobs,
np.average([(jobsTime.iloc[n] - jobsTime.iloc[n - 1]).seconds for n in range(1, len(jobsTime))])
* num_jobs
/ 60.0,
)
# Plot Results
# Convert time (X) to years
X = X.astype("f") / 365.25
if not silent:
plt.xkcd()
plt.pcolor(X, Y, C, cmap=plt.cm.YlOrRd)
# means = pandas.rolling_mean(pandas.Series(means), 10)
plt.plot(X[:, 1], means, color="k", label="Mean")
plt.plot(X[:, 1], medians, color="b", label="Median")
plt.plot(X[:, 1], low_25, color="g", label="Low25")
plt.plot(X[:, 1], high_25, color="g", label="High25")
plt.colorbar().set_label("Probability Higher/Lower than Median")
plt.legend(loc="upper left")
plt.xlabel("Years")
plt.ylabel("Return")
plt.grid(axis="y")
plt.gca().yaxis.set_major_formatter(plt.FuncFormatter(lambda x, pos: "%0.2f%%" % (x * 100)))
plt.show()
plt.figure()
plt.plot(X[:, 1], wastedTime)
plt.title("Average number of days I lost waiting to invest")
plt.show()
# Save data to dat file for reading my plotMultipleGainsOverTime
if not silent:
print "Exporing data to file %s..." % outputFilename
import shelve
sh = shelve.open(outputFilename)
sh["X"] = X
sh["Y"] = Y
sh["C"] = C
sh["means"] = means
sh["medians"] = medians
sh["low_25"] = low_25
sh["high_25"] = high_25
sh["wastedTime"] = wastedTime
sh["portfolio"] = symbols
sh.close()
return high_25, means, medians, low_25
import matplotlib.pylab as plt
if __name__ == '__main__':
A = np.array([[-1, 1], [0, -1]])
B = np.array([[-1, 5], [0, -2]])
print("Condition Number of A: {}".format(cond(A)))
npts = 100
xmin, xmax = -3.0, 1.0
ymin, ymax = -2.0, 2.0
# x = np.arange(xmin, xmax, (xmax-xmin) / (npts-1))
# y = np.arange(ymin, ymax, (ymax-ymin) / (npts-1))
# X, Y = np.meshgrid(x, y)
X, Y = np.meshgrid(np.linspace(xmin, xmax, npts),
np.linspace(ymin, ymax, npts))
spectra_a, s_max = psa(A, X, Y, method='svd')
spectra_b, s_max = psa(B, X, Y, method='svd')
plt.xkcd()
fig = plt.figure(figsize=(9, 4))
ax = fig.add_subplot(121)
circles = np.logspace(np.log10(0.05), np.log10(2.1), 10)[:-3]
CS = ax.contour(X, Y, spectra_a + 1e-20, levels=circles)
plt.clabel(CS, inline=1, fontsize=10)
ax = fig.add_subplot(122)
CS = ax.contour(X, Y, spectra_b + 1e-20, levels=circles)
plt.clabel(CS, inline=1, fontsize=10)
plt.savefig('psuedo.pdf', axis='tight')
plt.show()
plt.plot([1, 2])
plt.title(1)
plt.subplot(222)
plt.plot([1, 2])
plt.title(2)
plt.subplot(223)
plt.plot([1, 2])
plt.title(3)
plt.subplot(224)
plt.plot([1, 2])
plt.title(4)
plt.tight_layout() #약간 margin을 주는 느낌
plt.show()
#xkcd 스타일
with plt.xkcd():
plt.title('XKCD style plot!!!')
plt.plot(X, C, label='cosine')
t = 2 * np.pi / 3
plt.scatter(t, np.cos(t), 50, color='b')
plt.annotate(r'0.5 Here!',
xy=(t, np.cos(t)),
xycoords='data',
xytext=(-90, -50),
textcoords='offset points',
fontsize=16,
arrowprops=dict(arrowstyle='->'))
plt.show()
#==============================================================================
# matplotlib의 여러가지 플롯
def main(symbols,
sDate,
eDate,
maxDaysHeld,
numSim=5000,
daySpacing=10,
startDays=10,
cumulative=True,
outputFilename='simulation.dat',
silent=False):
###########
# Multiprocessing Stuff
#raise KeyError
# Establish communication queues
tasks = multiprocessing.Queue()
results = multiprocessing.Queue()
# Start Workers
num_workers = multiprocessing.cpu_count() * 1
if not silent:
print 'Creating %d workers' % num_workers
consumers = [Worker(tasks, results) for i in xrange(num_workers)]
for w in consumers:
w.start()
# Enqueue jobs
num_jobs = 0
if type(symbols) is str:
# Pull only a single stock
df = grabSymbol(symbols, sDate, eDate)
else:
# Pull portfollio with tuples in form of ('symbol', pctAllocation)
if abs(sum([a[1] for a in symbols]) - 1) > 0.01:
raise RuntimeError('Sum of allocations must be 1.0')
df = pandas.DataFrame()
for symbol, pctAlloc in symbols:
df = df.add(grabSymbol(symbol, sDate, eDate) * pctAlloc,
fill_value=0)
for daysHeld in range(startDays, maxDaysHeld, daySpacing):
tasks.put(Task(daysHeld, numSim, df, cumulative))
num_jobs += 1
# Add a poison pill for each worker
for i in xrange(num_workers):
tasks.put(None)
# Start printing results
jobsTime = pandas.Series(pandas.datetime.now())
means = np.zeros(num_jobs)
medians = np.zeros(num_jobs)
low_25 = np.zeros(num_jobs)
high_25 = np.zeros(num_jobs)
wastedTime = np.zeros(num_jobs)
while num_jobs:
ans = results.get()
if isinstance(ans, ErrorHolder):
# We got an error, print it
print ans
else:
(mn, mds, Xn, Yn, Cn, dH, l_25, h_25, w) = ans
ix = (dH - startDays) / daySpacing
means[ix] = mn
medians[ix] = mds
low_25[ix] = l_25
high_25[ix] = h_25
wastedTime[ix] = w
if 'X' not in vars().keys():
# Initalize results matrixes
X = np.zeros([num_jobs, int(Xn.shape[0])])
Y = np.zeros([num_jobs, int(Yn.shape[0])])
C = np.zeros([num_jobs, int(Cn.shape[0])])
X[ix, :] = Xn
Y[ix, :] = Yn
C[ix, :] = Cn
num_jobs -= 1
jobsTime = jobsTime.append(pandas.Series(pandas.datetime.now()))
if not silent:
print "Jobs left: %s (ETA %0.2f min)"% \
(num_jobs,
np.average([(jobsTime.iloc[n] - jobsTime.iloc[n-1]).seconds
for n in range(1,len(jobsTime))])*num_jobs/60.0 )
# Plot Results
# Convert time (X) to years
X = X.astype('f') / 365.25
if not silent:
plt.xkcd()
plt.pcolor(X, Y, C, cmap=plt.cm.YlOrRd)
#means = pandas.rolling_mean(pandas.Series(means), 10)
plt.plot(X[:, 1], means, color='k', label='Mean')
plt.plot(X[:, 1], medians, color='b', label='Median')
plt.plot(X[:, 1], low_25, color='g', label='Low25')
plt.plot(X[:, 1], high_25, color='g', label='High25')
plt.colorbar().set_label('Probability Higher/Lower than Median')
plt.legend(loc='upper left')
plt.xlabel('Years')
plt.ylabel('Return')
plt.grid(axis='y')
plt.gca().yaxis.set_major_formatter(
plt.FuncFormatter(lambda x, pos: '%0.2f%%' % (x * 100)))
plt.show()
plt.figure()
plt.plot(X[:, 1], wastedTime)
plt.title("Average number of days I lost waiting to invest")
plt.show()
# Save data to dat file for reading my plotMultipleGainsOverTime
if not silent:
print "Exporing data to file %s..." % outputFilename
import shelve
sh = shelve.open(outputFilename)
sh['X'] = X
sh['Y'] = Y
sh['C'] = C
sh['means'] = means
sh['medians'] = medians
sh['low_25'] = low_25
sh['high_25'] = high_25
sh['wastedTime'] = wastedTime
sh['portfolio'] = symbols
sh.close()
return high_25, means, medians, low_25
# -*- coding: utf-8 -*-
import numpy as np
import matplotlib.pylab as plt
plt.xkcd()
# HMTK Catalogue Import/Export Libraries
from hmtk.parsers.catalogue.csv_catalogue_parser import CsvCatalogueParser, CsvCatalogueWriter
input_catalogue_file = '../data_input/hmtk_chile.csv'
#input_catalogue_file = 'data_input/hmtk_sa.csv'
parser = CsvCatalogueParser(input_catalogue_file)
catalogue = parser.read_file()
print 'Input complete: %s events in catalogue' % catalogue.get_number_events()
print 'Catalogue Covers the Period: %s to %s' % (catalogue.start_year, catalogue.end_year)
valid_magnitudes = catalogue.data['magnitude'] <> np.nan
catalogue.select_catalogue_events(valid_magnitudes)
valid_magnitudes = catalogue.data['magnitude'] >= 2.0
catalogue.select_catalogue_events(valid_magnitudes)
print catalogue.data['magnitude']
def gr(m, a, b=1):
return 10**(a) - 10**(b*m)
def F_gr(m, b=1, m_min=2.0):
