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 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 PltCurve(outs):
a, c, n, alphas, Ns, x, y, x_s, y_s = GetAN(outs)
plt.figure(figsize=(16, 6))
plt.tight_layout(pad=2.0, w_pad=2.0, h_pad=2.0)
plt.subplots_adjust(left=None, bottom=None, right=None, top=None, \
wspace=None, hspace=0.4)
out_title = {'Ets500': ['(a)', 'Surface'], 'Etsra500': ['(b)', 'Radical']}
t = out_title[outs]
plt.suptitle(t[0] + ' LASSO for ' + t[1] + ' Pathway', fontsize=16)
'Learning Curve'
ax1 = plt.subplot(121)
ax1.set_title(r'Number of Nonzero Coefficient v.s. $\alpha$')
ax1.set_xlabel(r'$\alpha$')
ax1.set_ylabel('Number')
ax1.set_xlim(0, max(alphas) + 0.01)
ax1.set_ylim(0, max(Ns) + 1)
ax1.scatter(x, y, edgecolor=(0, 0, 0))
ax1.plot(x, y) ###
ax1.plot([
a,
] * 2, [0, n], linestyle='-.', color='b', marker='x')
ax1.text(
a, n + 3,
r'$\alpha$=%0.3f' % a + '\n' + r'$\theta$=%0.2f' % c + '\nn=%d' % n)
'alphas'
ax2 = plt.subplot(222)
ax2.set_title(r'Hist for $\alpha$', fontsize=10)
ax2.set_xlabel(r'$\alpha$', fontsize=10)
ax2.set_ylabel('Frequency', fontsize=10)
ax2.hist(alphas)
'Ns'
ax3 = plt.subplot(224)
ax3.set_title('Hist for Numbers', fontsize=10)
ax3.set_xlabel('Number of Nonzero Coefficient', fontsize=10)
ax3.set_ylabel('Frequency', fontsize=10)
ax3.hist(Ns)
pltsave('PerLas_' + outs + '.png')
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 Clf():
'Pre Data'
df = pd.read_csv('../Data/CH4_neo.csv', index_col=0)
df = df.loc[df.loc[:, 'E_ts'] != 'np.nan', :]
df = df.loc[df.loc[:, 'E_tsra'] != 'np.nan', :]
#n_feas = ['E_Hab3', 'E_CH3ab', 'h_O5-M2-O6-M1_hab3']
n_feas = ['E_Hab3', 'E_CH3ab', \
'h_O1-O2-O3-M1_hab3', 'a_O2-O6-M2_hab3']
indexs_cols = df.iloc[:, range(5)]
vals_cols = df.loc[:, n_feas]
DS = {}
DS['Etype'] = indexs_cols.loc[:, 'mtype'].values
En = ['E_ts', 'E_tsra']
DS['target'] = indexs_cols.loc[:, En].values.astype(np.float64)
DS['features'] = vals_cols.values.astype(np.float64)
DS['fea_names'] = vals_cols.columns.values
Etype = DS['Etype']
Ets = DS['target'].T[0]
Etsra = DS['target'].T[1]
Eh = DS['features'].T[0]
Ech3 = DS['features'].T[1]
Dihe = DS['features'].T[2]
Ange = DS['features'].T[3]
def tsclf(Ets, Etsra):
ts = {'ts': [], 'tsra': []}
tsra = {'ts': [], 'tsra': []}
for i in range(len(Etype)):
if Etype[i] == 'ts':
ts['ts'].append(Ets[i])
ts['tsra'].append(Etsra[i])
elif Etype[i] == 'tsra':
tsra['ts'].append(Ets[i])
tsra['tsra'].append(Etsra[i])
return ts, tsra
# BEP relations
#Ets_bep = 0.39*(Eh+Ech3)+2.11
Ets_bep = 0.40 * (Eh + Ech3) + 2.13
Etsra_bep = 0.90 * Eh + 3.73
# Geo relations
#Ets_geo = 0.30*Ech3+14*np.sin(Dihe)+0.63
Ets_geo = 0.37 * Ech3 + 4.69 * np.sin(Dihe) + 11.54 * np.sin(Ange) + 0.52
Etsra_geo = 0.90 * Eh + 3.73
''
fig, ax = plt.subplots(1, 3, figsize=(14, 4))
plt.suptitle('Classification for Methane Activation')
plt.tight_layout(pad=2.0, w_pad=4.0, h_pad=2.0)
plt.subplots_adjust(left=0.08, bottom=None, right=0.95, top=0.88, \
wspace=None, hspace=0.5)
# true values
ts, tsra = tsclf(Ets, Etsra)
#print(len(ts['tsra']), len(ts['ts']))
#print(len(tsra['tsra']), len(tsra['ts']))
print(tsra)
ax[0].scatter(ts['tsra'], ts['ts'], color='royalblue', marker='o')
ax[0].scatter(tsra['tsra'], tsra['ts'], color='salmon', marker='o')
ax[0].plot([Etsra.min(), Etsra.max()],
[Etsra.min(), Etsra.max()],
'k--',
lw=2)
ax[0].set_title('(a) True Values', fontsize=10)
ax[0].set_xlabel('$E_{TS-ra}\ /\ ev$')
ax[0].set_ylabel('$E_{TS-ss}\ /\ ev$')
# bep values
ts, tsra = tsclf(Ets_bep, Etsra_bep)
ax[1].scatter(ts['tsra'], ts['ts'], color='royalblue', marker='o')
ax[1].scatter(tsra['tsra'], tsra['ts'], color='salmon', marker='o')
ax[1].plot([Etsra.min(), Etsra.max()],
[Etsra.min(), Etsra.max()],
'k--',
lw=2)
ax[1].set_title('(b) BEP Relations', fontsize=10)
ax[1].set_xlabel('$E_{TS-ra}\ /\ ev$')
ax[1].set_ylabel('$E_{TS-ss}\ /\ ev$')
# geo values
ts, tsra = tsclf(Ets_geo, Etsra_geo)
ax[2].scatter(ts['tsra'], ts['ts'], color='royalblue', marker='o')
ax[2].scatter(tsra['tsra'], tsra['ts'], color='salmon', marker='o')
ax[2].plot([Etsra.min(), Etsra.max()],
[Etsra.min(), Etsra.max()],
'k--',
lw=2)
ax[2].set_title('(c) Relations including Geometrical Descriptors',
fontsize=10)
ax[2].set_xlabel('$E_{TS-ra}\ /\ ev$')
ax[2].set_ylabel('$E_{TS-ss}\ /\ ev$')
pltsave('clf.png')
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')