def LogisticGridSearch_OLD():
# C=1 is best
cs = 10.0**np.arange(-1,2,0.25)
aucs = []
for c in cs:
clf = LogisticRegression(penalty='l1',C=c).fit(f_train, y_train)
probs = clf.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
roc_auc = auc(fpr,tpr)
cstr = '%0.2e'%c
myplt = st.plotROC(fpr,tpr,roc_auc,
figure=False,
show=False,
returnplt=True,
showlegend=False,
title='Grid Search - Logistic Regression ROC Curve')
aucs.append(roc_auc)
best = 0
for i in range(len(cs)):
if aucs[i] > aucs[best]:
best = i
c = cs[best]
clf = LogisticRegression(penalty='l1',C=c).fit(f_train, y_train)
probs = clf.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
myplt = st.plotROC(fpr,tpr,roc_auc,
legendlabel='Best C = %0.2e' % c,
figure=False,
show=False,
returnplt=True,
showlegend=True,
title='Grid Search - Logistic Regression ROC Curve')
myplt.show()
return clf
def MultinomialNaiveBayesGridSearch_OLD():
# C=1 is best
cs = 10.0**np.arange(-9,2,0.5)
aucs = []
for c in cs:
clf = MultinomialNB(alpha=c).fit(f_train, y_train)
probs = clf.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
roc_auc = auc(fpr,tpr)
cstr = '%0.2e'%c
myplt = st.plotROC(fpr,tpr,roc_auc,
figure=False,
show=False,
returnplt=True,
showlegend=False,
title='Grid Search - Multinomial Naive Bayes ROC Curve')
aucs.append(roc_auc)
best = 0
for i in range(len(cs)):
if aucs[i] > aucs[best]:
best = i
c = cs[best]
clf = MultinomialNB(alpha=c).fit(f_train, y_train)
probs = clf.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
myplt = st.plotROC(fpr,tpr,roc_auc,
legendlabel='Best alpha = %0.2e' % c,
figure=False,
show=False,
returnplt=True,
showlegend=True,
title='Grid Search - Multinomial Naive Bayes ROC Curve')
myplt.show()
return clf
def GridSearch(data,params,classifier,classifier_name,paramname,probstype=1,clf_kwargs={}):
f_train,f_test,y_train,y_test = data
# C=1 is best
def getROC(clf,probstype):
if probstype == 1:
probs = clf.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
else:
probs = clf.decision_function(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs)
return fpr,tpr
aucs = []
mykwargs = clf_kwargs.copy()
for c in params:
mykwargs[paramname] = c
clf = classifier(**mykwargs).fit(f_train, y_train)
fpr,tpr = getROC(clf,probstype)
roc_auc = auc(fpr,tpr)
#cstr = '%0.2e'%c
myplt = st.plotROC(fpr,tpr,roc_auc,
figure=False,
show=False,
returnplt=True,
showlegend=False,
title='Grid Search: '+classifier_name+' ROC Curve')
aucs.append(roc_auc)
best = 0
for i in range(len(params)):
if aucs[i] > aucs[best]:
best = i
c = params[best]
mykwargs[paramname] = c
clf = classifier(**mykwargs).fit(f_train, y_train)
fpr,tpr = getROC(clf,probstype)
myplt = st.plotROC(fpr,tpr,roc_auc,
legendlabel='Best '+paramname+' = %0.2e' % c,
figure=False,
show=False,
returnplt=True,
showlegend=True,
title='Grid Search: '+classifier_name+' ROC Curve')
myplt.show()
maxAUC = aucs[best]
cs = params
optC = params[best]
plt.figure()
maxauclabel = ("Max AUC = %0.2f, " %maxAUC)+paramname+(" =%s" %optC)
plt.semilogx(cs,np.ones(len(cs))*maxAUC,'r',label=maxauclabel,linewidth=2,zorder=10)
plt.semilogx(cs,aucs,zorder=1)
plt.title('Grid Search: '+classifier_name+'AUC Scores')
plt.xlabel(paramname)
plt.ylabel('AUC Score')
plt.legend(loc="lower right")
#plt.legend(loc='lower left', bbox_to_anchor=(1, 0),
# ncol=1, fancybox=True, shadow=False)
plt.show()
return clf
def SGDGridSearch_OLD():
# C=1 is best
cs = 10.0**np.arange(-9,9,1)
aucs = []
for c in cs:
clf = SGDClassifier(penalty='l1',alpha=c).fit(f_train, y_train)
probs = clf.decision_function(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs)
roc_auc = auc(fpr,tpr)
cstr = '%0.2e'%c
myplt = st.plotROC(fpr,tpr,roc_auc,
figure=False,
show=False,
returnplt=True,
showlegend=False,
title='Grid Search - SGD Classifier ROC Curve')
aucs.append(roc_auc)
best = 0
for i in range(len(cs)):
if aucs[i] > aucs[best]:
best = i
c = cs[best]
clf = SGDClassifier(penalty='l1',alpha=c).fit(f_train, y_train)
probs = clf.decision_function(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs)
myplt = st.plotROC(fpr,tpr,roc_auc,
legendlabel='Best C = %0.2e' % c,
figure=False,
show=False,
returnplt=True,
showlegend=True,
title='Grid Search - SGD Classifier ROC Curve')
myplt.show()
return clf, aucs
sel_bool_test = train == 0
sel_ind_train = np.where(sel_bool_train)[0]
sel_ind_test = np.where(sel_bool_test)[0]
f_train = features[sel_ind_train]
f_test = features[sel_ind_test]
# N
approved = 1-rejected
y_train = np.array(approved[sel_bool_train]).astype(int)
y_test = np.array(approved[sel_bool_test]).astype(int)
return f_train,f_test,y_train,y_test
# CLASSIFIERS
'''
clf1 = MultinomialNB().fit(f_train, y_train)
probs = clf1.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
roc_auc = auc(fpr,tpr)
st.plotROC(fpr,tpr,roc_auc,"MultinomialNB")
clf2 = LogisticRegression(penalty='l1').fit(f_train, y_train)
probs = clf2.predict_proba(f_test)
fpr,tpr,_ = roc_curve(y_true=y_test,y_score=probs[:,1])
roc_auc = auc(fpr,tpr)
st.plotROC(fpr,tpr,roc_auc,"LogReg")
clf3 = SGDClassifier(penalty='l1').fit(f_train, y_train)
