def clf_yx():
'Load Lasso Results'
ts_las, ts_nc = pkload('Ets_final.pk')
print('--Ets--')
print_dict(ts_nc)
tsra_las, tsra_nc = pkload('Etsra_final.pk')
print('--Etsra--')
print_dict(tsra_nc)
def cmp_etype():
feas, Ets_best, means, stds = pkload('Best_las_Ets.pk')
feas, Etsra_best, means, stds = pkload('Best_las_Etsra.pk')
def outs(bests):
for name, coef in bests.items():
print('{:<20} -> {:<10}'.format(name, round(coef, 4)))
print('Ets')
outs(Ets_best)
print('Etsra')
outs(Etsra_best)
def plt_hist(pkfile):
''
params, nc = pkload(pkfile) # nc - name_coef
'Hist'
coef_max, coef_min = max(nc.values()), min(nc.values())
up = math.ceil(coef_max * 100) / 100.0
if coef_min <= 0:
down = math.ceil(coef_min * -100) / -100.0
else:
down = math.ceil(coef_min * -100) / -100.0
print('Preparing Hist...')
fig, ax = plt.subplots()
plt.title('Coefficient Count ' + str(len(nc.keys())) + ' in total')
plt.xlabel('Coefficient')
plt.ylabel('Number')
''
ax.hist(nc.values(), bins=np.arange(down, up + 0.1 * up, (up - down) / 5))
counts, edges = np.histogram(list(nc.values()), bins=5)
ax.set_xticks(np.arange(down, up + 0.1 * up, (up - down) / 5))
ax.set_xlim(down, up)
ax.set_yticks(np.arange(0, max(counts) + 2, 2))
print('Save fig...')
pltsave(pkfile.split('.')[0] + '.png')
print('Success...')
def FeaSelection(pkfile):
'Pre Data'
print('Preparing Data...')
params, feas = pkload(pkfile)
DS = GetDS('Ets', feas.keys())
y = DS['target']
X = DS['features']
'Feature Selection'
print('Selecting Features...')
mean_MSEs = []
std_MSEs = []
feas_number = len(X[0])
for i in range(feas_number):
X_slice = []
for j in range(i + 1):
X_slice.append(X.T[j])
X_slice = np.array(X_slice).T
mean_MSE, std_MSE = reg_assemble(y, X_slice)
mean_MSEs.append(mean_MSE)
std_MSEs.append(std_MSE)
'Get Feas Name'
names = list(feas.keys())
best_index = mean_MSEs.index(min(mean_MSEs))
best_feas = {}
for i in range(best_index + 1):
best_feas[names[i]] = feas[names[i]]
'Dump Pickle'
print('Saving pk...')
bestreg_pk = (feas, best_feas, mean_MSEs, std_MSEs)
pkdump('Best' + pkfile.strip('PosCoef'), bestreg_pk)
print('Success...')
def plt_bar():
''
feas, best_feas, best_coefs, meanMSEs, stdMSEs = pkload('BestReg-test.pk')
'Plot the best feas'
x = range(len(best_feas))
fig, ax = plt.subplots()
plt.bar(x, best_coefs)
plt.xticks(x, best_feas)
plt.show()
def plt_bep():
print('Plotting...')
fig, ((ax1, ax2, ax5), (ax3, ax4, ax6)) = plt.subplots(nrows=2,
ncols=3,
figsize=(12, 8))
plt.suptitle('BEP for Methane Activation')
plt.tight_layout(pad=2.0, w_pad=2.0, h_pad=2.0)
plt.subplots_adjust(left=None, bottom=None, right=None, top=0.9, \
wspace=None, hspace=0.2)
y, y_p, r2, mse = pkload('ts_Hab2_CH3ab.pk')
ax1.set_title('(a) $E_{H^{{sp}^2}} + E_{{{CH}_3}^v}$')
ax1.scatter(y, y_p, edgecolors=(0, 0, 0))
ax1.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax1.text(-0.5, 1, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
y, y_p, r2, mse = pkload('ts_Hab2_CH3ab2.pk')
ax2.set_title('(b) $E_{H^{{sp}^2}} + E_{{{CH}_3}^p}$')
ax2.scatter(y, y_p, edgecolors=(0, 0, 0))
ax2.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax2.text(-0.5, 1, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
y, y_p, r2, mse = pkload('ts_Hab3_CH3ab.pk')
ax3.set_title('(c) $E_{H^{{sp}^3}} + E_{{{CH}_3}^v}$')
ax3.scatter(y, y_p, edgecolors=(0, 0, 0))
ax3.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax3.text(-0.5, 1, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
y, y_p, r2, mse = pkload('ts_Hab3_CH3ab2.pk')
ax4.set_title('(d) $E_{H^{{sp}^3}} + E_{{{CH}_3}^p}$')
ax4.scatter(y, y_p, edgecolors=(0, 0, 0))
ax4.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax4.text(-0.5, 1, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
y, y_p, r2, mse = pkload('tsra_Hab2.pk')
ax5.set_title('(e) $E_{H^{{sp}^2}}$')
ax5.scatter(y, y_p, edgecolors=(0, 0, 0))
ax5.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax5.text(0.4, 1.4, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
y, y_p, r2, mse = pkload('tsra_Hab3.pk')
ax6.set_title('(f) $E_{H^{{sp}^3}}$')
ax6.scatter(y, y_p, edgecolors=(0, 0, 0))
ax6.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax6.text(0.4, 1.4, '${R^2}$=%0.2f, MSE=%0.2f' % (r2, mse))
#plt.show()
pltsave('bep.png')
print('Success...')
def FeaSelection():
'Pre Data'
print('Preparing Data...')
las, nc = pkload('Ets_final.pk')
DS = GetDS('Ets', nc.keys())
y = DS['target']; X = DS['features']
names = list(nc.keys())
for i in range(len(names)):
t = names[i].split('_')[0]
if t == 'h':
X.T[i] = np.sin((X.T[i]/2)**2)
elif t == 'a':
X.T[i] = X.T[i]**2
'Feature Selection'
print('Selecting Features...')
mean_MSEs = []; std_MSEs = []; r2s = []
feas_number = len(X[0])
for i in range(feas_number):
X_slice = []
for j in range(i+1):
X_slice.append(X.T[j])
X_slice = np.array(X_slice).T
mean_MSE, std_MSE = reg_assemble(y, X_slice)
mean_MSEs.append(mean_MSE)
std_MSEs.append(std_MSE)
'Get Feas Name'
best_index = mean_MSEs.index(min(mean_MSEs))
best_feas = {}
for i in range(best_index+1):
best_feas[names[i]] = nc[names[i]]
'Dump Pickle'
print('Saving pk...')
bestreg_pk = (nc, best_feas, mean_MSEs, std_MSEs)
pkdump('Best_Ets.pk', bestreg_pk)
print('Success...')
def PreSelection(pkfile):
print('-' * 20)
'Load DataSet'
print('Loading DataSet...')
DS = GetDS(pkfile.split('.')[0].split('_')[1])
'Load Pickle'
print('Loading ' + pkfile + '...')
gs = pkload(pkfile)
if pkfile == 'lsr.pk':
best_gs = gs
else:
best_gs = gs.best_estimator_
'Get Positive Coef'
print('Collecting Coefficients...')
# get feature name and coef
feanames = DS['fea_names']
coefs = best_gs.coef_
#
name_coef = {}
for name, coef in zip(feanames, coefs):
if abs(coef) > 0:
name_coef[name] = coef
# sort fea by abs value
nc_sorted = sorted(name_coef.items(),
key=lambda d: abs(d[1]),
reverse=True)
nc_dict = {}
for t in nc_sorted:
nc_dict[t[0]] = t[1]
'Dump Pickle'
print('Dumping Pickle...')
laspk = nc_dict
pkdump('PosCoef_' + pkfile, laspk)
print('Success...')
print('-' * 20)
def plt_curve(pkfile):
'Load pk'
feas, best_feas, mean_MSEs, std_MSEs = pkload(pkfile)
print(best_feas)
'Plt Learning Curve'
print('Plotting Learning Curve...')
plt.title('Feature Selection from LASSO '+\
pkfile.split('.')[0].split('_')[2],fontsize=16)
plt.xlabel('Number of Feature Used')
plt.ylabel('Mean MSE')
''
ax = plt.gca()
x = range(1, len(feas.keys()) + 1)
ax.set_xlim(0, len(x) + 1)
ax.set_xticks(np.arange(0, len(x) + 1, 2))
ax.set_ylim(0, max(mean_MSEs) * 1.1)
ax.set_yticks(np.arange(0, max(mean_MSEs) * 1.1, 0.5))
ax.plot(x, mean_MSEs)
'Plot best_index'
best_score = min(mean_MSEs)
best_index = mean_MSEs.index(best_score)
# Plot a dotted vertical line at the best score for that scorer marked by x
ax.plot([x[best_index], ] * 2, [0, best_score], \
linestyle='-.', color='b', marker='x', markeredgewidth=3, ms=8)
# Annotate the best score for that scorer
ax.annotate("%0.2f" % best_score, (x[best_index], best_score + 0.005))
print('Saving fig...')
pltsave(pkfile.split('.')[0] + '.png')
print('Success...')
def plt_cv():
'Load Pickle'
print('Loading Pickle...')
gslas = pkload('las_Ea.pk')
'Get Results'
results = gslas.cv_results_
scoring = gslas.scorer_
#def additional():
'Plt Learning Curve'
print('Plotting Learning Curve...')
plt.figure(figsize=(12, 8)) # figsize in inch, 1inch=2.54cm
plt.title("GridSearchCV for LASSO", fontsize=16)
plt.xlabel("Alpha")
# Get the regular numpy array from the MaskedArray
X_axis = np.array(results['param_alpha'].data, dtype=float)
ax = plt.gca()
'R2'
scorer = 'R2'
color = 'g'
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
ax.set_ylabel('R2')
for sample, style in (('train', '--'), ('test', '-')): # sample
sample_score_mean = results['mean_%s_%s' %
(sample, scorer)] # score mean
sample_score_std = results['std_%s_%s' % (sample, scorer)] # score std
ax.fill_between(X_axis, sample_score_mean - sample_score_std, \
sample_score_mean + sample_score_std, \
alpha=0.1 if sample == 'test' else 0, color=color)
ax.plot(X_axis, sample_score_mean, style, color=color, \
alpha=1 if sample == 'test' else 0.7, \
label="%s (%s)" % (scorer, sample))
best_index = np.nonzero(results['rank_test_%s' % scorer] == 1)[0][0]
best_score = results['mean_test_%s' % scorer][best_index]
# Plot a dotted vertical line at the best score for that scorer marked by x
ax.plot([
X_axis[best_index],
] * 2, [0, best_score],
linestyle='-.',
color=color,
marker='x',
markeredgewidth=3,
ms=8)
# Annotate the best score for that scorer
ax.annotate("%0.2f" % best_score, \
(X_axis[best_index], best_score + 0.005))
ax.legend(loc=2)
'MSE'
scorer = 'MSE'
color = 'k'
ax2 = ax.twinx()
ax2.set_xlim(0, 1)
ax2.set_ylim(-1, 2)
ax2.set_ylabel('MSE')
for sample, style in (('train', '--'), ('test', '-')): # sample
sample_score_mean = results['mean_%s_%s' %
(sample, scorer)] # score mean
sample_score_std = results['std_%s_%s' % (sample, scorer)] # score std
ax2.fill_between(X_axis, sample_score_mean - sample_score_std, \
sample_score_mean + sample_score_std, \
alpha=0.1 if sample == 'test' else 0, color=color)
ax2.plot(X_axis, sample_score_mean, style, color=color, \
alpha=1 if sample == 'test' else 0.7, \
label="%s (%s)" % (scorer, sample))
best_index = np.nonzero(results['rank_test_%s' % scorer] == 1)[0][0]
best_score = results['mean_test_%s' % scorer][best_index]
# Plot a dotted vertical line at the best score for that scorer marked by x
ax2.plot([
X_axis[best_index],
] * 2, [0, best_score],
linestyle='-.',
color=color,
marker='x',
markeredgewidth=3,
ms=8)
# Annotate the best score for that scorer
ax2.annotate("%0.2f" % best_score, \
(X_axis[best_index], best_score + 0.005))
ax2.legend(loc=1)
''
plt.grid("off")
pltsave('LearnCurve.png')