def writefile1():
Xtr = file1.iloc[:, 2:]
ytr = file1.iloc[:, 1:2]
ntr = file1.iloc[:, 0:1]
Xts = file2.iloc[:, 2:]
yts = file2.iloc[:, 1:2]
nts = file2.iloc[:, 0:1]
if var1.get():
a, b, c, d = trainsetfit(Xtr, ytr)
filer = open(str(c_) + "_fslda.txt", "w")
elif var2.get():
a, b, c, d = trainsetfit2(Xtr, ytr)
filer = open(str(c_) + "_sfslda.txt", "w")
#filer = open("resultsx.txt","w")
filer.write("Sub-training set results " + "\n")
filer.write("\n")
#file3.write("Selected features are:"+str(a)+"\n")
filer.write("Wilks lambda: " + str(b) + "\n")
filer.write("Fvalue: " + str(c) + "\n")
filer.write("pvalue: " + str(d) + "\n")
model.fit(Xtr[a], ytr)
filer.write("Selected features :" + str(a) + "\n")
filer.write("intercept: " + str(model.intercept_) + "\n")
filer.write("coefficients: " + str(model.coef_) + "\n")
yprtr = pd.DataFrame(model.predict(Xtr[a]))
yprtr.columns = ['Pred']
yprtr2 = pd.DataFrame(model.predict_proba(Xtr[a]))
yprtr2.columns = ['%Prob(-1)', '%Prob(+1)']
adstr = apdom(Xtr[a], Xtr[a])
yadstr = adstr.fit()
dfstr = pd.concat([ntr, Xtr[a], ytr, yprtr, yprtr2, yadstr], axis=1)
dfstr['Set'] = 'Sub_train'
yprts = pd.DataFrame(model.predict(Xts[a]))
yprts.columns = ['Pred']
yprts2 = pd.DataFrame(model.predict_proba(Xts[a]))
yprts2.columns = ['%Prob(-1)', '%Prob(+1)']
adts = apdom(Xts[a], Xtr[a])
yadts = adts.fit()
dfsts = pd.concat([nts, Xts[a], yts, yprts, yprts2, yadts], axis=1)
dfsts['Set'] = 'Test'
tb = Xtr[a].corr()
mx, mn = corr(tb)
tbn = str(c_) + '_corr.csv'
tb.to_csv(tbn)
finda = pd.concat([dfstr, dfsts], axis=0)
#finda.to_csv('find.csv',index=False)
#savename4 = filedialog.asksaveasfilename(initialdir=initialdir,title = "Save File with Predicted Activity")
savename4 = str(c_) + '_pred.csv'
finda.to_csv(savename4, index=False)
writefile2(Xtr[a], ytr, model, filer)
filer.write('Maximum correlation between descriptors: ' + str(mx) + "\n")
filer.write('Minimum correlation between descriptors: ' + str(mn))
filer.write("\n")
filer.write("Test set results: " + "\n")
filer.write("\n")
writefile2(Xts[a], yts, model, filer)
filer.close()
def writefile3():
nf = secondEntryTabFive.get()
nf = int(nf)
global file5
file5 = file4[file4['Set'] == 'Sub_train']
#global Xtr5
Xtr5 = file5.iloc[:, 1:nf + 1]
ytr5 = file5.iloc[:, nf + 1:nf + 2]
file6 = file4[file4['Set'] == 'Test']
Xts = file6.iloc[:, 1:nf + 1]
yts = file6.iloc[:, nf + 1:nf + 2]
model.fit(Xtr5, ytr5)
Xvd = file3[Xtr5.columns]
if ytr5.columns[0] in file3.columns:
yvd = file3[ytr5.columns]
nvd = file3.iloc[:, 0:1]
yprvd = pd.DataFrame(model.predict(Xvd))
yprvd.columns = ['Pred']
yprvd2 = pd.DataFrame(model.predict_proba(Xvd))
yprvd2.columns = ['%Prob(-1)', '%Prob(+1)']
advd = apdom(Xvd, Xtr5)
yadvd = advd.fit()
dfsvd = pd.concat([nvd, Xvd, yvd, yprvd, yprvd2, yadvd], axis=1)
dfsvd['Set'] = 'Validation'
#findv=pd.concat([dfstr,dfsts],axis=0)
#finda.to_csv('find.csv',index=False)
#savename4 = filedialog.asksaveasfilename(initialdir=initialdir,title = "Save File with Predicted Activity")
savename4 = str(e_) + '_pred.csv'
dfsvd.to_csv(savename4, index=False)
filer2 = open(str(e_) + "_pred.txt", "w")
filer2.write("Validation set results: " + "\n")
filer2.write("\n")
writefile2(Xvd, yvd, model, filer2)
e, f = ROCplot(Xtr5, ytr5)
g, h = ROCplot(Xts, yts)
i, j = ROCplot(Xvd, yvd)
pyplot.figure(figsize=(15, 10))
pyplot.plot(e,
f,
label='Sub-train',
color='blue',
marker='.',
linewidth=1,
markersize=10)
pyplot.plot(g,
h,
label='Test',
color='red',
marker='.',
linewidth=1,
markersize=10)
pyplot.plot(i,
j,
label='Validation',
color='green',
marker='.',
linewidth=1,
markersize=10)
pyplot.ylabel('True postive rate', fontsize=28)
pyplot.xlabel('False postive rate', fontsize=28)
pyplot.legend(fontsize=18)
pyplot.tick_params(labelsize=18)
rocn = str(e_) + '_ROC.png'
pyplot.savefig(rocn, dpi=300, facecolor='w', edgecolor='w',orientation='portrait', papertype=None, \
format=None,transparent=False, bbox_inches=None, pad_inches=0.1,frameon=None,metadata=None)
else:
#filer2 = open("resultvd.txt","w")
#vd=pd.DataFrame(np.zeros(Xvd.shape[0]))
nvd = file3.iloc[:, 0:1]
yprvd = pd.DataFrame(model.predict(Xvd))
yprvd.columns = ['Pred']
yprvd2 = pd.DataFrame(model.predict_proba(Xvd))
yprvd2.columns = ['%Prob(-1)', '%Prob(+1)']
advd = apdom(Xvd, Xtr5)
yadvd = advd.fit()
dfsvd = pd.concat([nvd, Xvd, yprvd, yprvd2, yadvd], axis=1)
dfsvd['Set'] = 'Screening'
#findv=pd.concat([dfstr,dfsts],axis=0)
#finda.to_csv('find.csv',index=False)
#savename4 = filedialog.asksaveasfilename(initialdir=initialdir,title = "Save File with Predicted Activity")
savename4 = str(e_) + '_scpred.csv'
dfsvd.to_csv(savename4, index=False)
e, f = ROCplot(Xtr5, ytr5)
g, h = ROCplot(Xts, yts)
pyplot.figure(figsize=(15, 10))
pyplot.plot(e,
f,
label='Sub-train',
color='blue',
marker='.',
linewidth=1,
markersize=10)
pyplot.plot(g,
h,
label='Test',
color='red',
marker='.',
linewidth=1,
markersize=10)
pyplot.ylabel('True postive rate', fontsize=28)
pyplot.xlabel('False postive rate', fontsize=28)
pyplot.legend(fontsize=18)
pyplot.tick_params(labelsize=18)
rocn = str(e_) + '_ROC.png'
pyplot.savefig(rocn, dpi=300, facecolor='w', edgecolor='w',orientation='portrait', papertype=None, \
format=None,transparent=False, bbox_inches=None, pad_inches=0.1,frameon=None,metadata=None)
def writefile1():
Xtr = file1.iloc[:, 2:]
ytr = file1.iloc[:, 1:2]
ntr = file1.iloc[:, 0:1]
Xts = file2.iloc[:, 2:]
yts = file2.iloc[:, 1:2]
nts = file2.iloc[:, 0:1]
pc = int(flabel2.get())
lt = [0]
ls = []
if var1.get() and Criterionx.get() == True:
ms = int(fifthBoxTabThreer6c1.get())
a1, b1, c1, d1 = trainsetfit(Xtr, ytr, ms)
for i in range(1, len(a1) + 1, 1):
filer = open(str(c_) + "_fslda.txt", "w")
filer.write("Note that it is a Increment based selection result" +
"\n")
a, b, c, d = trainsetfit(Xtr[a1], ytr, i)
model.fit(Xtr[a], ytr)
lt.append(b)
ln = len(lt)
dv = abs(lt[ln - 1] - lt[ln - 2])
val2 = dv / lt[len(lt) - 2] * 100
ls.append(val2)
if val2 < pc:
break
filer.write("Increments :" + str(ls) + "\n")
elif var1.get() and Criterionx.get() == False:
ms = int(fifthBoxTabThreer6c1.get())
filer = open(str(c_) + "_fslda.txt", "w")
filer.write("Note that it is not a Increment based selection result" +
"\n")
a, b, c, d = trainsetfit(Xtr, ytr, ms)
elif var2.get() and Criterionx.get() == True:
ms = int(fifthBoxTabThreer6c2.get())
a1, b1, c1, d1 = trainsetfit2(Xtr, ytr, ms)
for i in range(1, len(a1) + 1, 1):
a, b, c, d = trainsetfit2(Xtr, ytr, i)
filer = open(str(c_) + "_sfslda.txt", "w")
filer.write("Note that it is a Increment based selection result" +
"\n")
model.fit(Xtr[a], ytr)
lt.append(b)
ln = len(lt)
dv = abs(lt[ln - 1] - lt[ln - 2])
val2 = dv / lt[len(lt) - 2] * 100
ls.append(val2)
if val2 < pc:
break
filer.write("Increments :" + str(ls) + "\n")
elif var2.get() and Criterionx.get() == False:
ms = int(fifthBoxTabThreer6c2.get())
filer = open(str(c_) + "_sfslda.txt", "w")
filer.write("Note that it is not a Increment based selection result" +
"\n")
a, b, c, d = trainsetfit2(Xtr, ytr, ms)
#filer = open("resultsx.txt","w")
filer.write("Sub-training set results " + "\n")
filer.write("\n")
#file3.write("Selected features are:"+str(a)+"\n")
filer.write("Wilks lambda: " + str(b) + "\n")
filer.write("Fvalue: " + str(c) + "\n")
filer.write("pvalue: " + str(d) + "\n")
model.fit(Xtr[a], ytr)
filer.write("Selected features :" + str(a) + "\n")
filer.write("intercept: " + str(model.intercept_) + "\n")
filer.write("coefficients: " + str(model.coef_) + "\n")
yprtr = pd.DataFrame(model.predict(Xtr[a]))
yprtr.columns = ['Pred']
yprtr2 = pd.DataFrame(model.predict_proba(Xtr[a]))
yprtr2.columns = ['%Prob(-1)', '%Prob(+1)']
adstr = apdom(Xtr[a], Xtr[a])
yadstr = adstr.fit()
dfstr = pd.concat([ntr, Xtr[a], ytr, yprtr, yprtr2, yadstr], axis=1)
dfstr['Set'] = 'Sub_train'
yprts = pd.DataFrame(model.predict(Xts[a]))
yprts.columns = ['Pred']
yprts2 = pd.DataFrame(model.predict_proba(Xts[a]))
yprts2.columns = ['%Prob(-1)', '%Prob(+1)']
adts = apdom(Xts[a], Xtr[a])
yadts = adts.fit()
dfsts = pd.concat([nts, Xts[a], yts, yprts, yprts2, yadts], axis=1)
dfsts['Set'] = 'Test'
tb = Xtr[a].corr()
tbn = str(c_) + '_corr.csv'
tb.to_csv(tbn)
mx, mn = corr(tb)
finda = pd.concat([dfstr, dfsts], axis=0)
#finda.to_csv('find.csv',index=False)
#savename4 = filedialog.asksaveasfilename(initialdir=initialdir,title = "Save File with Predicted Activity")
savename4 = str(c_) + '_pred.csv'
finda.to_csv(savename4, index=False)
writefile2(Xtr[a], ytr, model, filer)
filer.write('Maxmimum intercorrelation between descriptors: ' + str(mx) +
"\n")
filer.write('Minimum intercorrelation between descriptors: ' + str(mn) +
"\n")
filer.write("\n")
filer.write("Test set results: " + "\n")
filer.write("\n")
writefile2(Xts[a], yts, model, filer)
filer.close()
def writefilex():
Xtr = file1.iloc[:, 2:]
ytr = file1.iloc[:, 1:2]
ntr = file1.iloc[:, 0:1]
a, b, c, m, mx, mn, l, filer = trainsetfit2(Xtr, ytr)
reg.fit(Xtr[a], ytr)
r2 = reg.score(Xtr[a], ytr)
ypr = pd.DataFrame(reg.predict(Xtr[a]))
ypr.columns = ['Pred']
rm2tr, drm2tr = rm2(ytr, l).fit()
#savefile.to_csv('savefile.csv',index=False)
d = mean_absolute_error(ytr, ypr)
e = (mean_squared_error(ytr, ypr))**0.5
adstr = apdom(Xtr[a], Xtr[a])
yadstr = adstr.fit()
df = pd.concat([ntr, Xtr[a], ytr, ypr, l, yadstr], axis=1)
df.to_csv(str(c_) + "_sfslda_trpr.csv", index=False)
#filer = open(str(c_)+"_sfslda.txt","w")
filer.write("Sub-training set results " + "\n")
filer.write("\n")
filer.write("Selected features are:" + str(a) + "\n")
filer.write("Statistics:" + str(b) + "\n")
filer.write('Training set results: ' + "\n")
filer.write('Maxmimum intercorrelation between descriptors: ' + str(mx) +
"\n")
filer.write('Minimum intercorrelation between descriptors: ' + str(mn) +
"\n")
filer.write('MAE: ' + str(d) + "\n")
filer.write('RMSE: ' + str(e) + "\n")
filer.write('Q2LOO: ' + str(c) + "\n")
if ytr.columns[0] in file2.columns:
Xts = file2.iloc[:, 2:]
nts = file2.iloc[:, 0:1]
yts = file2.iloc[:, 1:2]
ytspr = pd.DataFrame(reg.predict(Xts[a]))
ytspr.columns = ['Pred']
rm2ts, drm2ts = rm2(yts, ytspr).fit()
tsdf = pd.concat([yts, pd.DataFrame(ytspr)], axis=1)
tsdf.columns = ['Active', 'Predict']
tsdf['Aver'] = m
tsdf['Aver2'] = tsdf['Predict'].mean()
tsdf['diff'] = tsdf['Active'] - tsdf['Predict']
tsdf['diff2'] = tsdf['Active'] - tsdf['Aver']
tsdf['diff3'] = tsdf['Active'] - tsdf['Aver2']
r2pr = 1 - ((tsdf['diff']**2).sum() / (tsdf['diff2']**2).sum())
r2pr2 = 1 - ((tsdf['diff']**2).sum() / (tsdf['diff3']**2).sum())
RMSEP = ((tsdf['diff']**2).sum() / tsdf.shape[0])**0.5
adts = apdom(Xts[a], Xtr[a])
yadts = adts.fit()
dfts = pd.concat([nts, Xts[a], yts, ytspr, yadts], axis=1)
dfts.to_csv(str(c_) + "_sfslda_tspr.csv", index=False)
filer.write('rm2LOO: ' + str(rm2tr) + "\n")
filer.write('delta rm2LOO: ' + str(drm2tr) + "\n")
filer.write("\n")
filer.write('Test set results: ' + "\n")
filer.write('Number of observations: ' + str(yts.shape[0]) + "\n")
filer.write('Q2F1/R2Pred: ' + str(r2pr) + "\n")
filer.write('Q2F2: ' + str(r2pr2) + "\n")
filer.write('rm2test: ' + str(rm2ts) + "\n")
filer.write('delta rm2test: ' + str(drm2ts) + "\n")
filer.write('RMSEP: ' + str(RMSEP) + "\n")
filer.write("\n")
plt1 = pyplot.figure(figsize=(15, 10))
pyplot.scatter(ytr, ypr, label='Train', color='blue')
pyplot.plot([ytr.min(), ytr.max()], [ytr.min(), ytr.max()],
'k--',
lw=4)
pyplot.scatter(yts, ytspr, label='Test', color='red')
pyplot.ylabel('Predicted values', fontsize=28)
pyplot.xlabel('Observed values', fontsize=28)
pyplot.legend(fontsize=18)
pyplot.tick_params(labelsize=18)
rocn = str(c_) + '_obspred.png'
plt1.savefig(rocn, dpi=300, facecolor='w', edgecolor='w',orientation='portrait', papertype=None, \
format=None,transparent=False, bbox_inches=None, pad_inches=0.1,frameon=None,metadata=None)
plt2 = pyplot.figure(figsize=(15, 10))
pyplot.scatter(ytr, l, label='Train(LOO)', color='blue')
pyplot.plot([ytr.min(), ytr.max()], [ytr.min(), ytr.max()],
'k--',
lw=4)
pyplot.scatter(yts, ytspr, label='Test', color='red')
pyplot.ylabel('Predicted values', fontsize=28)
pyplot.xlabel('Observed values', fontsize=28)
pyplot.legend(fontsize=18)
pyplot.tick_params(labelsize=18)
rocn = str(c_) + '_loopred.png'
plt2.savefig(rocn, dpi=300, facecolor='w', edgecolor='w',orientation='portrait', papertype=None, \
format=None,transparent=False, bbox_inches=None, pad_inches=0.1,frameon=None,metadata=None)
else:
Xts = file2.iloc[:, 1:]
nts = file2.iloc[:, 0:1]
ytspr = pd.DataFrame(reg.predict(Xts[a]))
ytspr.columns = ['Pred']
adts = apdom(Xts[a], Xtr[a])
yadts = adts.fit()
dfts = pd.concat([nts, Xts[a], ytspr, yadts], axis=1)
dfts.to_csv(str(c_) + "_sfslda_scpr.csv", index=False)
if var3.get():
ls = []
nr = int(N1B1_x.get())
for i in range(0, nr):
yr = shuffling(ytr)
reg.fit(Xtr[a], yr)
ls.append(reg.score(Xtr[a], yr))
rr = np.mean(ls)
reg.score(Xtr[a], ytr)
#r2=b.rsquared
crp2 = math.sqrt(r2) * math.sqrt(r2 - rr)
filer.write('Crp2 after ' + str(nr) + ' run: ' + str(crp2) + "\n")