def get_classifier(classifier):
if classifier["name"] == 'linear-ridge':
c = RidgeClassifier()
elif classifier["name"] == 'SVC':
c = SVC()
elif classifier["name"] == "l2-SVC":
c = L2KernelClassifier()
elif classifier["name"] == "fredholm":
c = L2FredholmClassifier()
elif classifier["name"] == "TSVM":
c = SVMLight()
elif classifier["name"] == "Lap-RLSC":
c = LapRLSC()
elif classifier["name"] == "fred_kernel_appr":
c = FredholmKernelApprClassifier()
else:
raise NameError('Not existing classifier: ' + classifier["name"] + '.')
c.set_params(**classifier["params"])
return c
def get_optimal_blend_weigth(exp_, best_param_,
folder, fname, model_fname):
clf = RidgeClassifier()
X_test, y_test = exp_.get_test_data()
clf.set_params(**best_param_)
clf.fit(X_test, y_test)
# dump2csv optimal linear weight
names = np.append(np.array(['intercept'], dtype='S100'), X_test.columns.values)
coefs = np.append(clf.intercept_, clf.coef_).astype(np.float64)
optimal_linear_weight = pd.DataFrame(coefs.reshape(1,len(coefs)), columns=names)
optimal_linear_weight.to_csv(os.path.join(Config.get_string('data.path'),
folder,
fname), index=False)
# dump2cpkle for ridge model
model_fname = os.path.join(Config.get_string('data.path'), folder, model_fname)
with gzip.open(model_fname, 'wb') as gf:
cPickle.dump(clf, gf, cPickle.HIGHEST_PROTOCOL)
return True
def get_optimal_blend_weigth(exp_, best_param_,
folder, fname, model_fname):
clf = RidgeClassifier()
X_test, y_test = exp_.get_test_data()
clf.set_params(**best_param_)
clf.fit(X_test, y_test)
# dump2csv optimal linear weight
names = np.append(np.array(['intercept'], dtype='S100'), X_test.columns.values)
coefs = np.append(clf.intercept_, clf.coef_).astype(np.float64)
optimal_linear_weight = pd.DataFrame(coefs.reshape(1,len(coefs)), columns=names)
optimal_linear_weight.to_csv(os.path.join(Config.get_string('data.path'),
folder,
fname), index=False)
# dump2cpkle for ridge model
model_fname = os.path.join(Config.get_string('data.path'), folder, model_fname)
with gzip.open(model_fname, 'wb') as gf:
cPickle.dump(clf, gf, cPickle.HIGHEST_PROTOCOL)
return True
def get_ridge_plot(best_param_, experiment_,
param_keys_, param_vals_,
png_folder,
png_fname,
score_threshold=0.8):
parameters = dict(zip(param_keys_, param_vals_))
del parameters['model_type']
clf = RidgeClassifier()
X_train, y_train = experiment_.get_train_data()
clf.set_params(**best_param_)
clf.fit(X_train, y_train)
best_alpha = best_param_['alpha']
result = {'alphas':[],
'coefs':np.zeros( (len(parameters['alpha']), len(X_train.columns.values) + 1) ),
'scores':[],
'score':None}
for i, alpha in enumerate(parameters.get('alpha',None)):
result['alphas'].append(alpha)
del best_param_['alpha']
best_param_['alpha'] = alpha
clf.set_params(**best_param_)
clf.fit(X_train, y_train)
# regularization path
tmp = np.array([0 for j in xrange(len(X_train.columns.values) + 1)], dtype=np.float32)
if best_param_['fit_intercept']:
tmp = np.append(clf.intercept_, clf.coef_)
else:
tmp[1:] = clf.intercept_
result['coefs'][i,:] = tmp
result['scores'].append(experiment_.get_proba(clf, X_train))
del X_train, y_train
# 2.
tmp_len = len(experiment_.get_data_col_name())
index2feature = dict(zip(np.arange(1, tmp_len + 1),
experiment_.get_data_col_name()))
if best_param_['fit_intercept']:
index2feature[0] = 'intercept'
# 3. plot
gs = GridSpec(2,2)
ax1 = plt.subplot(gs[:,0])
ax2 = plt.subplot(gs[0,1])
ax3 = plt.subplot(gs[1,1])
# 3.1 feature importance
labels = np.append(np.array(['intercept'], dtype='S100'), experiment_.get_data_col_name())
nrows, ncols = result['coefs'].shape
for ncol in xrange(ncols):
ax1.plot(np.array(result['alphas']), result['coefs'][:,ncol], label = labels[ncol])
ax1.legend(loc='best')
ax1.set_xscale('log')
ax1.set_title("Regularization Path:%1.3e" % (best_alpha))
ax1.set_xlabel("alpha", fontsize=10)
# 3.2 PDF
X_test, y_test = experiment_.get_test_data()
result['score'] = clf.decision_function(X_test)
sns.distplot(result['score'], kde=False, rug=False, ax=ax2)
ax2.set_title("PDF : Decision_Function")
# 3.3 CDF
num_bins = 100
try:
counts, bin_edges = np.histogram(result['score'], bins=num_bins, normed=True)
except:
counts, bin_edges = np.histogram(result['score'], normed=True)
cdf = np.cumsum(counts)
ax3.plot(bin_edges[1:], cdf / cdf.max())
ax3.set_title("CDF")
ax3.set_xlabel("Decision_Function:Confidence_Score", fontsize=10)
png_fname = os.path.join(Config.get_string('data.path'), png_folder, png_fname)
plt.tight_layout()
plt.savefig(png_fname)
plt.close()
return True
def get_ridge_plot(best_param_, experiment_,
param_keys_, param_vals_,
png_folder,
png_fname,
score_threshold=0.8):
parameters = dict(zip(param_keys_, param_vals_))
del parameters['model_type']
clf = RidgeClassifier()
X_train, y_train = experiment_.get_train_data()
clf.set_params(**best_param_)
clf.fit(X_train, y_train)
best_alpha = best_param_['alpha']
result = {'alphas':[],
'coefs':np.zeros( (len(parameters['alpha']), len(X_train.columns.values) + 1) ),
'scores':[],
'score':None}
for i, alpha in enumerate(parameters.get('alpha',None)):
result['alphas'].append(alpha)
del best_param_['alpha']
best_param_['alpha'] = alpha
clf.set_params(**best_param_)
clf.fit(X_train, y_train)
# regularization path
tmp = np.array([0 for j in xrange(len(X_train.columns.values) + 1)], dtype=np.float32)
if best_param_['fit_intercept']:
tmp = np.append(clf.intercept_, clf.coef_)
else:
tmp[1:] = clf.intercept_
result['coefs'][i,:] = tmp
result['scores'].append(experiment_.get_proba(clf, X_train))
del X_train, y_train
# 2.
tmp_len = len(experiment_.get_data_col_name())
index2feature = dict(zip(np.arange(1, tmp_len + 1),
experiment_.get_data_col_name()))
if best_param_['fit_intercept']:
index2feature[0] = 'intercept'
# 3. plot
gs = GridSpec(2,2)
ax1 = plt.subplot(gs[:,0])
ax2 = plt.subplot(gs[0,1])
ax3 = plt.subplot(gs[1,1])
# 3.1 feature importance
labels = np.append(np.array(['intercept'], dtype='S100'), experiment_.get_data_col_name())
nrows, ncols = result['coefs'].shape
for ncol in xrange(ncols):
ax1.plot(np.array(result['alphas']), result['coefs'][:,ncol], label = labels[ncol])
ax1.legend(loc='best')
ax1.set_xscale('log')
ax1.set_title("Regularization Path:%1.3e" % (best_alpha))
ax1.set_xlabel("alpha", fontsize=10)
# 3.2 PDF
X_test, y_test = experiment_.get_test_data()
result['score'] = clf.decision_function(X_test)
sns.distplot(result['score'], kde=False, rug=False, ax=ax2)
ax2.set_title("PDF : Decision_Function")
# 3.3 CDF
num_bins = 100
try:
counts, bin_edges = np.histogram(result['score'], bins=num_bins, normed=True)
except:
counts, bin_edges = np.histogram(result['score'], normed=True)
cdf = np.cumsum(counts)
ax3.plot(bin_edges[1:], cdf / cdf.max())
ax3.set_title("CDF")
ax3.set_xlabel("Decision_Function:Confidence_Score", fontsize=10)
png_fname = os.path.join(Config.get_string('data.path'), png_folder, png_fname)
plt.tight_layout()
plt.savefig(png_fname)
plt.close()
return True