def run(history, tweek, pref, selections):
logstr = ''
#
w, x, y = history.grab(nsample, ntracks, tweek + 1, pref, 180, 90, 80000)
x = xfilter(x)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
#svmutil.svm_save_model('benchmark.svm', lsvm)
#lsvm = svmutil.svm_load_model('benchmark.svm')
print 'svm trained successfully in %s sec with %d samples.' % (str(
float('{0:.3f}'.format(timer.lag()))), len(w))
#
timer = timer_c()
w, x, y = history.grab(1, ntracks, tweek, pref, 180, 90, 80000)
x = xfilter(x)
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec with %d samples.' % (str(
float('{0:.3f}'.format(timer.lag()))), len(w))
foo = []
for i in xrange(len(y)):
foo.append((p_labels[i], y[i], w[i]))
foo.sort(key=lambda tup: (-tup[0]))
selections['code'].append(foo[0][2])
selections['tweek'].append(tweek)
return [row[1] for row in foo]
def run(tday, history, logfile):
logstr = ''
#
w, x, y = history.grab(nsample, ntracks, tday + 1)
x = xfilter(x)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
#svmutil.svm_save_model('benchmark.svm', lsvm)
#lsvm = svmutil.svm_load_model('benchmark.svm')
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer = timer_c()
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
plotdraw(p_labels, y)
#
timer = timer_c()
w, x, y = history.grab(1, ntracks, tday)
x = xfilter(x)
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
plotdraw(p_labels, y)
def run(tday, history):
logstr = ''
#
w, x, y = history.grab(nsample, ntracks, tday + 1)
lsvmL = []
for options in optionL:
timer = timer_c()
lsvmL.append(svmutil.svm_train(y, x, options))
print 'options = %s' % (options)
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
plt.axvline(x=0.0, color='k', alpha=0.2)
plt.axhline(y=0.0, color='k', alpha=0.2)
for i in xrange(len(lsvmL)):
timer = timer_c()
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvmL[i], '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
plt.plot(p_labels, y, colorsL[i], alpha=0.5)
plt.show()
#
w, x, y = history.grab(1, ntracks, tday)
plt.axvline(x=0.0, color='k', alpha=0.2)
plt.axhline(y=0.0, color='k', alpha=0.2)
for i in xrange(len(lsvmL)):
timer = timer_c()
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvmL[i], '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
plt.plot(p_labels, y, colorsL[i], alpha=0.5)
plt.show()
def run(history):
#
w, x, y = history.grab(nsample, ntracks, 0)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
svmutil.svm_save_model('temp.svm', lsvm)
print 'svm trained successfully in %s sec.' % (str(float('{0:.3f}'.format(timer.lag()))))
#
timer = timer_c()
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(float('{0:.3f}'.format(timer.lag()))))
plotdraw(p_labels, y)
def run(tday, history):
logstr = ''
#
w, x, y = history.grab(nsample, ntracks, tday + 1)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer = timer_c()
w, x, y = history.grab(1, ntracks, tday)
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
pos = np.argmax(np.array(p_labels))
return p_labels[pos], y[pos]
def run(tday, history):
logstr = ''
#
w, x, y = history.grab(nsample, ntracks, tday+1)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
#svmutil.svm_save_model('benchmark.svm', lsvm)
#lsvm = svmutil.svm_load_model('benchmark.svm')
print 'svm trained successfully in %s sec.' % (str(float('{0:.3f}'.format(timer.lag()))))
#
timer = timer_c()
w, x, y = history.grab(1, ntracks, tday)
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(float('{0:.3f}'.format(timer.lag()))))
foo = []
for i in xrange(len(y)):
foo.append((p_labels[i], y[i]))
foo.sort(key = lambda tup: (-tup[0]))
return [row[1] for row in foo]
def run(history):
#
timer = timer_c()
lsvm = svmutil.svm_load_model('temp.svm')
print 'svm loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer = timer_c()
w, x, y = history.grab(1, ntracks, -1)
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
plotdraw(p_labels, y)
#
foo = []
for i in xrange(len(w)):
foo.append((w[i], p_labels[i], y[i]))
foo.sort(key=lambda tup: (tup[1]))
for row in foo:
print '%s y\' = %.6f, y = %.6f' % row
def main():
timer = timer_c()
res = numpy.array([], dtype='i')
mat = numpy.empty((0, len(key) * ntracks), dtype='f')
with open('../data/dbf/2017.dbf', 'r') as dbf:
history = json.load(dbf)
seven = history['layout'].index('PCHG')
print 'seven at %d.' % (seven)
first = None
for code, table in history['record'].iteritems():
if len(table) < 180:
continue
if first is None or first < table[89][0]:
first = table[89][0]
for code, table in history['record'].iteritems():
# skip the stock has less than 180 rows of record
if len(table) < 180:
continue
# skip the stock has suspended in 90 trading days
if table[89][0] != first:
continue
# form mat & res
for i in xrange(nsample):
# mat++
row = []
for r in xrange(i + 1, i + ntracks + 1):
for offset in key:
row.append(table[r][offset])
mat = numpy.append(mat, numpy.array([row], dtype='f'), axis=0)
# res++
hg = table[i][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
res = numpy.append(res, int(hg / (20.0 / nlabels)))
print 'mat & res loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer.reset()
lsvm = svmutil.svm_train(res.tolist(), mat.tolist(),
'-s 0 -t 0 -g 1.00 -c 1000000.00 -b 0 -q')
svmutil.svm_save_model('temp.svm', lsvm)
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
p_labels, p_acc, p_vals = svmutil.svm_predict(res.tolist(), mat.tolist(),
lsvm, '')
def run(history, tweek, pref):
#
w, x, y = history.grab(nsample, ntracks, tweek, pref)
x = xfilter(x)
timer = timer_c()
lsvm = svmutil.svm_train(y, x, options)
#print 'svm trained successfully in %s sec with %d samples.' % (str(float('{0:.3f}'.format(timer.lag()))), len(w))
#
w, x, y = history.grab(1, ntracks, tweek - 1, pref)
x = xfilter(x)
timer.reset()
p_labels, p_acc, p_vals = svmutil.svm_predict(y, x, lsvm, '')
#print 'svm predicted successfully in %s sec with %d samples.' % (str(float('{0:.3f}'.format(timer.lag()))), len(w))
#
foo = []
for i in xrange(len(w)):
foo.append((w[i], p_labels[i], y[i]))
foo.sort(key=lambda tup: (-tup[1]))
for i in xrange(3):
print '%s y\' = %.6f, y = %.6f' % foo[i]
def run(tday=0):
timer = timer_c()
matT = numpy.empty((0, len(key) * ntracks), dtype='f')
resT = numpy.array([], dtype='i')
boundary = None
if enscale:
numpy.zeros((len(key), 2), dtype='f')
for i in xrange(len(boundary)):
boundary[i][0] = numpy.inf
boundary[i][1] = -numpy.inf
with open('../data/dbf/2017.dbf', 'r') as dbf:
history = json.load(dbf)
print 'run tday = %s' % (history['record'].values()[0][tday][0])
seven = history['layout'].index('PCHG')
print 'seven at %d.' % (seven)
first = None
for code, table in history['record'].iteritems():
if len(table) < 180:
continue
if first is None or first < table[89][0]:
first = table[89][0]
for code, table in history['record'].iteritems():
# skip the stock has less than 180 rows of record
if len(table) < tday + 181:
continue
# skip the stock has suspended in 90 trading days
if table[89][0] != first:
continue
# form mat & res
for i in xrange(tday + 1, tday + 1 + nsample):
# mat++
row = []
for r in xrange(i + 1, i + ntracks + 1):
for offset in key:
row.append(table[r][offset])
matT = numpy.append(matT,
numpy.array([row], dtype='f'),
axis=0)
# res++
hg = table[i][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
resT = numpy.append(resT, int(hg / (20.0 / nlabels)))
# boundray-update
if enscale:
for i in xrange(nsample + ntracks + 1):
for j in xrange(len(key)):
boundary[j][0] = min(boundary[j][0], table[i][key[j]])
boundary[j][1] = max(boundary[j][1], table[i][key[j]])
if enscale:
autoscale(matT, boundary)
print 'matT & resT loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer.reset()
matQ = numpy.empty((0, len(key) * ntracks), dtype='f')
resQ = numpy.array([], dtype='i')
with open('../data/dbf/2017.dbf', 'r') as dbf:
history = json.load(dbf)
seven = history['layout'].index('PCHG')
print 'seven at %d.' % (seven)
first = None
for code, table in history['record'].iteritems():
if len(table) < 180:
continue
if first is None or first < table[89][0]:
first = table[89][0]
for code, table in history['record'].iteritems():
# skip the stock has less than 180 rows of record
if len(table) < 180:
continue
# skip the stock has suspended in 90 trading days
if table[89][0] != first:
continue
# mat++
row = []
for r in xrange(tday + 1, tday + 1 + ntracks):
for offset in key:
row.append(table[r][offset])
matQ = numpy.append(matQ, numpy.array([row], dtype='f'), axis=0)
# res++
hg = table[tday][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
resQ = numpy.append(resQ, int(hg / (20.0 / nlabels)))
if enscale:
autoscale(matQ, boundary)
print 'matQ & resQ loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
sys.stdout.flush()
for i in xrange(-6, 6, 2):
for j in xrange(-6, 6, 2):
cost = 10.**i
gamma = 10.**j
param = '-s 0 -t 2 -c %f -g %f -b 0 -q' % (cost, gamma)
print 'param = %s' % param
#
timer.reset()
lsvm = svmutil.svm_train(resT.tolist(), matT.tolist(), param)
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
timer.reset()
p_labels, p_acc, p_vals = svmutil.svm_predict(
resT.tolist(), matT.tolist(), lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
timer.reset()
p_labels, p_acc, p_vals = svmutil.svm_predict(
resQ.tolist(), matQ.tolist(), lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
print[[int(x) for x in p_labels].count(i) for i in xrange(nlabels)]
sys.stdout.flush()
def run(tday, logfile):
logstr = ''
timer = timer_c()
res = numpy.array([], dtype='i')
rat = numpy.array([], dtype='f')
mat = numpy.empty((0, len(key) * ntracks), dtype='f')
boundary = None
if enscale:
numpy.zeros((len(key), 2), dtype='f')
for i in xrange(len(boundary)):
boundary[i][0] = numpy.inf
boundary[i][1] = -numpy.inf
with open('../data/dbf/2017.dbf', 'r') as dbf:
history = json.load(dbf)
date = '1990-01-01'
date2 = '1990-01-01'
for table in history['record'].values():
if len(table) < 180:
continue
if date < table[tday][0]:
date = table[tday][0]
if date2 < table[tday + 1][0]:
date2 = table[tday + 1][0]
print 'run tday = %s' % (date)
logstr += 'tday = %s\n' % (date)
seven = history['layout'].index('PCHG')
print 'seven at %d.' % (seven)
first = '1990-01-01'
for code, table in history['record'].iteritems():
offset2 = -1
for i in xrange(len(table)):
if table[i][0] < date2:
break
elif table[i][0] == date2:
offset2 = i
break
if offset2 < 0:
continue
if len(table) < offset2 + 180:
continue
if first < table[offset2 + 89][0]:
first = table[offset2 + 89][0]
for code, table in history['record'].iteritems():
offset2 = -1
for i in xrange(len(table)):
if table[i][0] < date2:
break
elif table[i][0] == date2:
offset2 = i
break
if offset2 < 0:
continue
# skip the stock has less than 180 rows of record
if len(table) < offset2 + 180:
continue
# skip the stock has suspended in 90 trading days
if table[offset2 + 89][0] != first:
continue
# form mat & res
for i in xrange(offset2, offset2 + nsample):
# mat++
row = []
for r in xrange(i + 1, i + ntracks + 1):
for pos in key:
row.append(table[r][pos])
mat = numpy.append(mat, numpy.array([row], dtype='f'), axis=0)
# res++
hg = table[i][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
res = numpy.append(res, int(hg / (20.0 / nlabels)))
rat = numpy.append(rat, table[i][seven])
# boundray-update
if enscale:
for i in xrange(nsample + ntracks + 1):
for j in xrange(len(key)):
boundary[j][0] = min(boundary[j][0], table[i][key[j]])
boundary[j][1] = max(boundary[j][1], table[i][key[j]])
if enscale:
autoscale(mat, boundary)
print 'mat & res loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer.reset()
lsvm = svmutil.svm_train(res.tolist(), mat.tolist(),
'-s 0 -t 0 -g 1.00 -c 1000000.00 -b 0 -q')
#svmutil.svm_save_model('benchmark.svm', lsvm)
#lsvm = svmutil.svm_load_model('benchmark.svm')
print 'svm trained successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
p_labels, p_acc, p_vals = svmutil.svm_predict(res.tolist(), mat.tolist(),
lsvm, '')
#
timer.reset()
tag = []
res = numpy.array([], dtype='i')
rat = numpy.array([], dtype='f')
mat = numpy.empty((0, len(key) * ntracks), dtype='f')
with open('../data/dbf/2017.dbf', 'r') as dbf:
history = json.load(dbf)
seven = history['layout'].index('PCHG')
print 'seven at %d.' % (seven)
first = '1990-01-01'
for code, table in history['record'].iteritems():
offset = -1
for i in xrange(len(table)):
if table[i][0] < date:
break
elif table[i][0] == date:
offset = i
break
if offset < 0:
continue
if len(table) < offset + 181:
continue
if first < table[offset + 90][0]:
first = table[offset + 90][0]
for code, table in history['record'].iteritems():
offset = -1
for i in xrange(len(table)):
if table[i][0] < date:
break
elif table[i][0] == date:
offset = i
break
if offset < 0:
continue
# skip the stock has less than 180 rows of record
if len(table) < offset + 181:
continue
# skip the stock has suspended in 90 trading days
if table[offset + 90][0] != first:
continue
# mat++
row = []
for r in xrange(offset + 1, offset + 1 + ntracks):
for pos in key:
row.append(table[r][pos])
mat = numpy.append(mat, numpy.array([row], dtype='f'), axis=0)
# res++
hg = table[offset][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
res = numpy.append(res, int(hg / (20.0 / nlabels)))
rat = numpy.append(rat, table[offset][seven])
# tag++
tag.append(code)
if enscale:
autoscale(mat, boundary)
print 'mat & res loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer.reset()
labels = lsvm.get_labels()
nlabel = len(labels)
p_labels, p_acc, p_vals = svmutil.svm_predict(res.tolist(), mat.tolist(),
lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
summary = numpy.zeros((nlabels, 2), dtype='i')
details = numpy.zeros((nlabels, nlabels), dtype='i')
#goals = numpy.zeros((nlabels, nlabels), dtype='i')
profit2 = [[[] for i in xrange(nlabels)] for j in xrange(nlabels)]
#for idx in xrange(len(tag)):
# votes = numpy.zeros(nlabel, dtype='i')
# k = 0
# for i in xrange(nlabel):
# for j in xrange(i+1, nlabel):
# if p_vals[idx][k] > 0.0:
# votes[i] += 1
# else:
# votes[j] += 1
# k += 1
# bar = []
# for i in xrange(nlabel):
# bar.append((labels[i], votes[i]))
# bar = sorted(bar, key = lambda tup: (-tup[1], tup[0]))
# if bar[0][0] == res[idx]:
# summary[res[idx]][0] += 1
# summary[res[idx]][1] += 1
#print summary
for idx in xrange(len(tag)):
votes = numpy.zeros(nlabel, dtype='i')
k = 0
for i in xrange(nlabel):
for j in xrange(i + 1, nlabel):
if p_vals[idx][k] > 0.0:
votes[i] += 1
else:
votes[j] += 1
k += 1
bar = []
for i in xrange(nlabel):
bar.append((labels[i], votes[i]))
bar = sorted(bar, key=lambda tup: (-tup[1], tup[0]))
if p_labels[idx] == res[idx]:
summary[res[idx]][0] += 1
summary[res[idx]][1] += 1
details[int(p_labels[idx])][res[idx]] += 1
if int(p_labels[idx]) in (bar[0][0], bar[1][0]):
profit2[int(p_labels[idx])][bar[0][0] ^ bar[1][0]
^ int(p_labels[idx])].append(rat[idx])
#if tag[idx]=='sh600326':
# print '%d %d %d => %.6f' % (bar[0][0], bar[1][0], bar[2][0], rat[idx])
#details[min(bar[0][0], bar[1][0])][res[idx]] += 1
#if p_labels[idx]>=nlabels-1:
#if max(bar[0][0], bar[1][0])>=9:
#goals[min(bar[0][0], bar[1][0])][res[idx]] += 1
print summary
print details
for i in xrange(nlabels):
foo = ''
for j in xrange(nlabels):
if j > 0:
foo += ', '
logstr += ','
if len(profit2[i][j]) > 0:
foo += '%.6f (%d)' % (sum(profit2[i][j]) / len(profit2[i][j]),
len(profit2[i][j]))
logstr += '%.6f (%d)' % (sum(profit2[i][j]) / len(
profit2[i][j]), len(profit2[i][j]))
else:
foo += 'nil'
logstr += 'nil'
print foo
logstr += '\n'
#print goals
logstr += '\n'
with open(logfile, 'a') as log:
log.write(logstr)
def main():
timer = timer_c()
tag = []
res = numpy.array([], dtype='i')
mat = numpy.empty((0, len(key) * ntracks), dtype='f')
with open('../data/dbf/2016.dbf', 'r') as dbf:
history = json.load(dbf)
seven = history['layout'].index('PCHG')
first = None
for code, table in history['record'].iteritems():
# skip the stock has less than 180 rows of record
if len(table) < 180:
continue
# skip the stock has suspended in 90 trading days
if len([i for i in xrange(90) if None in table[i]]) > 0:
continue
# mat++
row = []
for r in xrange(ntracks):
for offset in key:
row.append(table[r][offset])
mat = numpy.append(mat, numpy.array([row], dtype='f'), axis=0)
# res++
hg = table[0][seven] + 10.0
hg = min(hg, 19.99)
hg = max(hg, 0.0)
res = numpy.append(res, int(hg / (20.0 / nlabels)))
# tag++
tag.append(code)
print 'mat & res loaded successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
#
timer.reset()
lsvm = svmutil.svm_load_model('temp.svm')
labels = lsvm.get_labels()
nlabel = len(labels)
p_labels, p_acc, p_vals = svmutil.svm_predict(res.tolist(), mat.tolist(),
lsvm, '')
print 'svm predicted successfully in %s sec.' % (str(
float('{0:.3f}'.format(timer.lag()))))
best = []
for idx in xrange(len(tag)):
votes = numpy.zeros(nlabel, dtype='i')
k = 0
for i in xrange(nlabel):
for j in xrange(i + 1, nlabel):
if p_vals[idx][k] > 0.0:
votes[i] += 1
else:
votes[j] += 1
k += 1
bar = []
for i in xrange(nlabel):
bar.append((labels[i], votes[i]))
bar = sorted(bar, key=lambda tup: (-tup[1], tup[0]))
#if tag[idx]=='sh600326':
# print '%d, %d, %d \n' % (bar[0][0], bar[1][0], bar[2][0])
if int(p_labels[idx]) in [bar[0][0], bar[1][0]]:
if int(p_labels[idx]) == bar[1][0]:
bar[0], bar[1] = bar[1], bar[0]
else:
continue
#print bar
if bar[0][0] >= nlabels - 2:
best.append((tag[idx], bar[0][0], bar[1][0], bar[2][0]))
best = sorted(best, key=lambda tup: (-tup[1], -tup[2], -tup[3], tup[0]))
for row in best:
print '%s => %d %d %d' % row
