def train_test(Xtrain, Ytrain, Xtest, la, R):
if la == "logistic":
lr = LogisticRegression(Xtrain, Ytrain, Xtest, 1.0 / R)
lr.train()
return 2 * lr.test_predictions() - 1
if la == "ridge":
wvec = ridge_regression(Xtrain, Ytrain, R)
if la == "svm":
wvec = simple_SVM(Xtrain, Ytrain, R)
if la == "boosting":
wvec = adaboost_feats(Xtrain, Ytrain, R)
return dot(wvec, Xtest.T)
def train_test(Xtrain,Ytrain,Xtest,la,R):
if la=="logistic":
lr = LogisticRegression(Xtrain,Ytrain,Xtest,1.0/R)
lr.train()
return 2*lr.test_predictions()-1
if la=="ridge":
wvec = ridge_regression(Xtrain,Ytrain,R)
if la=="svm":
wvec = simple_SVM(Xtrain,Ytrain,R)
if la=="boosting":
wvec = adaboost_feats(Xtrain,Ytrain,R)
return dot(wvec,Xtest.T)
def help_learn( self, train, test ):
data = self.data
hf = self.hf.get()
mf = self.mf.get()
la = self.learning_alg.get()
#print (mf,hf),"FEATURES",self.X.shape
tmpY = [(i in data.po)*2-1. for i in train]
if (mf == hf) or self.X.shape[1]!=1256:
if data.tags!=[]:
print "Learning with tags!"
tmpX = hstack([2*data.Mtag[train]-1.,self.X[train]])
else:
tmpX = self.X[train]
self.R=self.scale.get()
print "Learning, R=",self.R, la
if la=="Logistic regression":
if data.tags!=[]:
tstX = hstack([2*data.Mtag[test]-1.,self.X[test]])
else:
tstX = self.X[test]
print "Training:",tmpX.shape[0]
lr = LogisticRegression(tmpX,tmpY,tstX,1.0/self.R)
lr.train()
print "Testing:",tstX.shape[0]
u=lr.test_predictions()
else:
if la=="Linear SVM":
wvec = simple_SVM(tmpX,tmpY,self.R)
else:
assert la=="Boosting"
wvec = adaboost_feats(tmpX,tmpY,self.R)
print sorted(abs(wvec),reverse=True)[:10]
if data.tags!=[]:
tmpX = hstack([2*data.Mtag[test]-1.,self.X[test]])
else:
tmpX = self.X[test]
u= dot(tmpX,wvec)
assert nan not in u
else:
a = 255
b = 1255
if hf==1:
print "Human Features"
assert mf==0
rang = range(0,a)
rang.append(b) # the all 1's col
else:
print "Machine Features"
assert mf==1
rang = range(a,b+1)
if data.tags!=[]:
print "Learning with tags"
tmpX = hstack([2*data.Mtag[train]-1.,self.X[train,:][:,rang]])
else:
tmpX = self.X[train,:][:,rang]
self.R=self.scale.get()
print "Learning, R=",self.R,la
if la=="Logistic regression":
if data.tags!=[]:
tstX = hstack([2*data.Mtag[test]-1.,self.X[test,:][:,rang]])
else:
tstX = self.X[test,:][:,rang]
print "Training:",tmpX.shape[0]
lr = LogisticRegression(tmpX,tmpY,tstX,1.0/self.R)
lr.train()
print "Testing:",tstX.shape[0]
u=lr.test_predictions()
else:
if la=="Linear SVM":
wvec = simple_SVM(tmpX,tmpY,self.R)
else:
assert la=="Boosting"
wvec = adaboost_feats(tmpX,tmpY,self.R)
print sorted(abs(wvec),reverse=True)[:10]
if data.tags!=[]:
tmpX = hstack([2*data.Mtag[test]-1.,self.X[test,:][:,rang]])
else:
tmpX = self.X[test][:,rang]
u= dot(tmpX,wvec)
return u
def learn(pos,neg,X,la="boosting",R=20):
assert len(pos)>1 and len(neg)>1
n = X.shape[0]
lpos = [le2n(i) for i in pos]
lneg = [le2n(i) for i in neg]
Y = zeros(len(lpos)+len(lneg))
for i in range(len(lpos)):
Y[i]=1.
for i in range(len(lneg)):
Y[i+len(lpos)]=-1.
y = {}
unl = set(alpha())-set(pos)-set(neg)
if len(unl)>0:
if la=="svm":
wvec = simple_SVM(X[lpos+lneg],Y,R)
for i in unl:
y[i]=dot(wvec,X[le2n(i)])
if la=="boosting":
wvec = adaboost_feats(X[lpos+lneg],Y,R)
for i in unl:
y[i]=dot(wvec,X[le2n(i)])
if la=="logistic":
lr = LogisticRegression(X[lpos+lneg],Y,X[[le2n(i) for i in unl]],1.0/R)
lr.train()
u=lr.test_predictions()
i=0
for a in unl:
y[a] = 2*u[i]-1
i+=1
for i in pos:
lpos2 = lpos[:]
lpos2.remove(le2n(i))
if la=="boosting":
wvec = adaboost_feats(X[lpos2+lneg],Y[1:],R)
y[i]=dot(wvec,X[le2n(i)])
if la=="svm":
wvec = simple_SVM(X[lpos2+lneg],Y[1:],R)
y[i]=dot(wvec,X[le2n(i)])
if la=="logistic":
lr = LogisticRegression(X[lpos2+lneg],Y[1:],X[[le2n(i)]],1.0/R)
lr.train()
y[i]=2*lr.test_predictions()[0]-1
for i in neg:
lneg2 = lneg[:]
lneg2.remove(le2n(i))
if la=="svm":
wvec = simple_SVM(X[lpos+lneg2],Y[:-1],R)
y[i]=dot(wvec,X[le2n(i)])
if la=="boosting":
wvec = adaboost_feats(X[lpos+lneg2],Y[:-1],R)
y[i]=dot(wvec,X[le2n(i)])
if la=="logistic":
lr = LogisticRegression(X[lpos+lneg2],Y[:-1],X[[le2n(i)]],1.0/R)
lr.train()
y[i]=2*lr.test_predictions()[0]-1
errs = 0
sqerr = 0.0
for i in pos:
sqerr+=(y[i]-1)**2
if y[i]<0:
errs+=1.
for i in neg:
sqerr+=(y[i]+1)**2
if y[i]>=0:
errs+=1.
m = len(pos)+len(neg)
print "Err: ",errs/m,"\tSq err:",sqerr/m
return (y,errs/m)
def learn(pos, neg, X, la="boosting", R=20):
assert len(pos) > 1 and len(neg) > 1
n = X.shape[0]
lpos = [le2n(i) for i in pos]
lneg = [le2n(i) for i in neg]
Y = zeros(len(lpos) + len(lneg))
for i in range(len(lpos)):
Y[i] = 1.
for i in range(len(lneg)):
Y[i + len(lpos)] = -1.
y = {}
unl = set(alpha()) - set(pos) - set(neg)
if len(unl) > 0:
if la == "svm":
wvec = simple_SVM(X[lpos + lneg], Y, R)
for i in unl:
y[i] = dot(wvec, X[le2n(i)])
if la == "boosting":
wvec = adaboost_feats(X[lpos + lneg], Y, R)
for i in unl:
y[i] = dot(wvec, X[le2n(i)])
if la == "logistic":
lr = LogisticRegression(X[lpos + lneg], Y,
X[[le2n(i) for i in unl]], 1.0 / R)
lr.train()
u = lr.test_predictions()
i = 0
for a in unl:
y[a] = 2 * u[i] - 1
i += 1
for i in pos:
lpos2 = lpos[:]
lpos2.remove(le2n(i))
if la == "boosting":
wvec = adaboost_feats(X[lpos2 + lneg], Y[1:], R)
y[i] = dot(wvec, X[le2n(i)])
if la == "svm":
wvec = simple_SVM(X[lpos2 + lneg], Y[1:], R)
y[i] = dot(wvec, X[le2n(i)])
if la == "logistic":
lr = LogisticRegression(X[lpos2 + lneg], Y[1:], X[[le2n(i)]],
1.0 / R)
lr.train()
y[i] = 2 * lr.test_predictions()[0] - 1
for i in neg:
lneg2 = lneg[:]
lneg2.remove(le2n(i))
if la == "svm":
wvec = simple_SVM(X[lpos + lneg2], Y[:-1], R)
y[i] = dot(wvec, X[le2n(i)])
if la == "boosting":
wvec = adaboost_feats(X[lpos + lneg2], Y[:-1], R)
y[i] = dot(wvec, X[le2n(i)])
if la == "logistic":
lr = LogisticRegression(X[lpos + lneg2], Y[:-1], X[[le2n(i)]],
1.0 / R)
lr.train()
y[i] = 2 * lr.test_predictions()[0] - 1
errs = 0
sqerr = 0.0
for i in pos:
sqerr += (y[i] - 1)**2
if y[i] < 0:
errs += 1.
for i in neg:
sqerr += (y[i] + 1)**2
if y[i] >= 0:
errs += 1.
m = len(pos) + len(neg)
print "Err: ", errs / m, "\tSq err:", sqerr / m
return (y, errs / m)
def help_learn(self, train, test):
data = self.data
hf = self.hf.get()
mf = self.mf.get()
la = self.learning_alg.get()
# print (mf,hf),"FEATURES",self.X.shape
tmpY = [(i in data.po) * 2 - 1.0 for i in train]
if (mf == hf) or self.X.shape[1] != 1256:
if data.tags != []:
print "Learning with tags!"
tmpX = hstack([2 * data.Mtag[train] - 1.0, self.X[train]])
else:
tmpX = self.X[train]
self.R = self.scale.get()
print "Learning, R=", self.R, la
if la == "Logistic regression":
if data.tags != []:
tstX = hstack([2 * data.Mtag[test] - 1.0, self.X[test]])
else:
tstX = self.X[test]
print "Training:", tmpX.shape[0]
lr = LogisticRegression(tmpX, tmpY, tstX, 1.0 / self.R)
lr.train()
print "Testing:", tstX.shape[0]
u = lr.test_predictions()
else:
if la == "Linear SVM":
wvec = simple_SVM(tmpX, tmpY, self.R)
else:
assert la == "Boosting"
wvec = adaboost_feats(tmpX, tmpY, self.R)
print sorted(abs(wvec), reverse=True)[:10]
if data.tags != []:
tmpX = hstack([2 * data.Mtag[test] - 1.0, self.X[test]])
else:
tmpX = self.X[test]
u = dot(tmpX, wvec)
assert nan not in u
else:
a = 255
b = 1255
if hf == 1:
print "Human Features"
assert mf == 0
rang = range(0, a)
rang.append(b) # the all 1's col
else:
print "Machine Features"
assert mf == 1
rang = range(a, b + 1)
if data.tags != []:
print "Learning with tags"
tmpX = hstack([2 * data.Mtag[train] - 1.0, self.X[train, :][:, rang]])
else:
tmpX = self.X[train, :][:, rang]
self.R = self.scale.get()
print "Learning, R=", self.R, la
if la == "Logistic regression":
if data.tags != []:
tstX = hstack([2 * data.Mtag[test] - 1.0, self.X[test, :][:, rang]])
else:
tstX = self.X[test, :][:, rang]
print "Training:", tmpX.shape[0]
lr = LogisticRegression(tmpX, tmpY, tstX, 1.0 / self.R)
lr.train()
print "Testing:", tstX.shape[0]
u = lr.test_predictions()
else:
if la == "Linear SVM":
wvec = simple_SVM(tmpX, tmpY, self.R)
else:
assert la == "Boosting"
wvec = adaboost_feats(tmpX, tmpY, self.R)
print sorted(abs(wvec), reverse=True)[:10]
if data.tags != []:
tmpX = hstack([2 * data.Mtag[test] - 1.0, self.X[test, :][:, rang]])
else:
tmpX = self.X[test][:, rang]
u = dot(tmpX, wvec)
return u
