Re: minimize does not stop
Andrew Nelson <[email protected]> Mon, 18 Jul 2022 09:53:29 +1000
| Newsgroups | gmane.comp.python.scientific.user |
|---|---|
| Message-ID | <CAAbtOZe+DN+rtEcptsr37YUOOv6QEoAAqS0C2qV_a7qMvpLrvw@mail.gmail.com> |
--===============5005865336534498096== Content-Type: multipart/related; boundary="000000000000f2c58a05e408f56c" --000000000000f2c58a05e408f56c Content-Type: multipart/alternative; boundary="000000000000f2c58905e408f56b" --000000000000f2c58905e408f56b Content-Type: text/plain; charset="UTF-8" Unfortunately that is not a MWE, firstly because the example is a little bit convoluted, and secondly because it's using data from a file that we don't have. On Sun, 17 Jul 2022 at 18:24, Hao Wang <[email protected]> wrote: > Here is the full list of the code (minimize function doesn't work) : > > from scipy.optimize import minimize > import numpy as np > import random > > def marx_reallocate(x_data): > > x_len = int(x_data[-2]) > y_len = int(x_data[-1]) > > p_list = x_data[x_len+y_len:-2] > > print('marx_reallocate') > > x = p_list[0:x_len] > y = p_list[x_len:x_len+y_len] > > a = x_data[0:x_len] > b = x_data[x_len:x_len+y_len] > > sum_val = 0.0 > > for x_ind_0 in range(0, x.__len__()-1): > for x_ind_1 in range(x_ind_0+1, x.__len__()): > sum_val += (x[x_ind_0] - a[x_ind_0] - x[x_ind_1] + > a[x_ind_1])**2 > > for x_ind in range(0, x.__len__()): > for y_ind in range(0, y.__len__()): > sum_val += (x[x_ind] - a[x_ind] - y[y_ind] - b[y_ind])**2 > > for y_ind_0 in range(0, y.__len__()-1): > for y_ind_1 in range(y_ind_0+1, y.__len__()): > sum_val += (y[y_ind_0] + b[y_ind_0] - y[y_ind_1] - > b[y_ind_1])**2 > > print(sum_val) > > return sum_val > > def cons_0(x_data): > > y_len = int(x_data[-1]) > x_len = int(x_data[-2]) > > p_list = x_data[x_len+y_len:-2] > > return sum(np.array(p_list[:x_len])) - > sum(np.array(p_list[x_len:x_len+y_len])) > > def cons_1(x_data): > > y_len = int(x_data[-1]) > x_len = int(x_data[-2]) > > a_list = x_data[:x_len] > x_list = x_data[x_len:x_len+y_len] > > flag = 1 > #a_list = p_list[0] > #x_list = args[0] > > for a_val, x_val in zip(a_list, x_list): > if a_val > x_val - 1e-7: > flag = 0 > return flag > > return flag > > def cons_2(x_data): > > y_len = int(x_data[-1]) > x_len = int(x_data[-2]) > > flag = 1 > > b_list = x_data[x_len:x_len+y_len] > y_list = x_data[2*x_len+y_len:2*(x_len+y_len)] > > for b_val, y_val in zip(b_list, y_list): > if b_val > y_val - 1e-7: > flag = 0 > return flag > > return flag > > def cons_3(x_data): > > y_len = int(x_data[-1]) > x_len = int(x_data[-2]) > > args = x_data[:x_len+y_len] > p_list = x_data[x_len+y_len: 2*(x_len+y_len)] > > args_0 = args[:x_len] > args_1 = args[x_len:x_len+y_len] > > p_list_0 = p_list[:x_len] > p_list_1 = p_list[x_len:x_len+y_len] > > return sum( np.array(p_list_0) - args_0 ) + sum( np.array(p_list_1) - > args_1 ) - 2.5*(x_len+y_len)*2.0 > > def compute_Marx(p_list): > > #print('Flag 0') > > x_list = [] > y_list = [] > > for p_id in range(0, p_list[0].__len__()): > x_list.append(random.random() * 5.0) > > for p_id in range(0, p_list[1].__len__()): > y_list.append(random.random() * 5.0) > > #print('Flag 1') > > x0_data = x_list[:] > x0_data.extend(y_list) > > cons = ({'type' : 'eq', 'fun' : cons_0}, > {'type' : 'ineq', 'fun' : cons_1}, > {'type' : 'ineq', 'fun' : cons_2}, > {'type' : 'eq', 'fun' : cons_3} > ) > > #print('Flag 2') > > #arg_tuple = (p_list, x_list.__len__(), y_list.__len__()) > > x0_data.extend(p_list[0]) > x0_data.extend(p_list[1]) > x0_data.extend([x_list.__len__(), y_list.__len__()]) > > #print(x0_data) > > res = minimize(fun=marx_reallocate, x0=x0_data, method='SLSQP', > tol=1e-4, constraints=cons, options={"maxiter":20, "disp":True}) > > #marx_reallocate(x0, (p_list, x_list.__len__(), y_list.__len__())) > > print(res) > > if __name__ == '__main__': > > item_rank_list_large = [] > item_rank_list_small = [] > > with open('LDOS.csv', 'r') as FILE: > for line in FILE: > data_rec = line.strip().split(',') > user_id = int(data_rec[1]) > item_id = int(data_rec[2]) > rating_val = float(data_rec[3]) > if rating_val > 2.5-1e-7: > item_rank_list_large.append(rating_val) > else: > item_rank_list_small.append(rating_val) > > p_list = [] > p_list.append(np.array(item_rank_list_large)) > p_list.append(np.array(item_rank_list_small)) > p_list = np.array(p_list, dtype='object') > > compute_Marx(p_list) > > ------------------------------ > *From:* Andrew Nelson <[email protected]> > *Sent:* Saturday, July 16, 2022 8:46 PM > *To:* SciPy Users List <[email protected]> > *Subject:* [SciPy-User] Re: minimize does not stop > > > On Sun, 17 Jul 2022 at 09:24, Hao Wang <[email protected]> wrote: > > > Would it be possible to provide a minimal working example so we could help > you further? > > > _______________________________________________ > SciPy-User mailing list -- [email protected] > To unsubscribe send an email to [email protected] > https://mail.python.org/mailman3/lists/scipy-user.python.org/ > Member address: [email protected] > -- _____________________________________ Dr. Andrew Nelson _____________________________________ --000000000000f2c58905e408f56b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr">Unfortunately that is not a MWE, firstly because the examp= le is a little bit convoluted, and secondly because it's using data fro= m a file that we don't have.</div><br><div class=3D"gmail_quote"><div d= ir=3D"ltr" class=3D"gmail_attr">On Sun, 17 Jul 2022 at 18:24, Hao Wang <= <a href=3D"mailto:[email protected]">[email protected]</a>> wrote:<br></div>= <blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-= left:1px solid rgb(204,204,204);padding-left:1ex"> <div dir=3D"ltr"> <div style=3D"font-family:Calibri,Helvetica,sans-serif;font-size:12pt;color= :rgb(0,0,0)"> Here is the full list of the code (minimize function doesn't work) : <b= r> </div> <div style=3D"font-family:Calibri,Helvetica,sans-serif;font-size:12pt;color= :rgb(0,0,0)"> <br> </div> <div style=3D"font-family:Calibri,Helvetica,sans-serif;font-size:12pt;color= :rgb(0,0,0)"> from scipy.optimize import minimize <div>import numpy as np</div> <div>import random</div> <div><br> </div> <div>def marx_reallocate(x_data):</div> <div>=C2=A0 =C2=A0 </div> <div>=C2=A0 =C2=A0 x_len =3D int(x_data[-2])</div> <div>=C2=A0 =C2=A0 y_len =3D int(x_data[-1])</div> <div><br> </div> <div>=C2=A0 =C2=A0 p_list =3D x_data[x_len+y_len:-2]</div> <div><br> </div> <div>=C2=A0 =C2=A0 print('marx_reallocate')</div> <div><br> </div> <div>=C2=A0 =C2=A0 x =3D p_list[0:x_len]</div> <div>=C2=A0 =C2=A0 y =3D p_list[x_len:x_len+y_len]</div> <div><br> </div> <div>=C2=A0 =C2=A0 a =3D x_data[0:x_len]</div> <div>=C2=A0 =C2=A0 b =3D x_data[x_len:x_len+y_len]</div> <div><br> </div> <div>=C2=A0 =C2=A0 sum_val =3D 0.0</div> <div><br> </div> <div>=C2=A0 =C2=A0 for x_ind_0 in range(0, x.__len__()-1):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 for x_ind_1 in range(x_ind_0+1, x.__len__(= )):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 sum_val +=3D (x[x_ind_0] - a= [x_ind_0] - x[x_ind_1] + a[x_ind_1])**2</div> <div><br> </div> <div>=C2=A0 =C2=A0 for x_ind in range(0, x.__len__()):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 for y_ind in range(0, y.__len__()):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 sum_val +=3D (x[x_ind] - a[x= _ind] - y[y_ind] - b[y_ind])**2</div> <div><br> </div> <div>=C2=A0 =C2=A0 for y_ind_0 in range(0, y.__len__()-1):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 for y_ind_1 in range(y_ind_0+1, y.__len__(= )):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 sum_val +=3D (y[y_ind_0] + b= [y_ind_0] - y[y_ind_1] - b[y_ind_1])**2</div> <div><br> </div> <div>=C2=A0 =C2=A0 print(sum_val)</div> <div><br> </div> <div>=C2=A0 =C2=A0 return sum_val</div> <div><br> </div> <div>def cons_0(x_data):</div> <div><br> </div> <div>=C2=A0 =C2=A0 y_len =3D int(x_data[-1])</div> <div>=C2=A0 =C2=A0 x_len =3D int(x_data[-2])</div> <div><br> </div> <div>=C2=A0 =C2=A0 p_list =3D x_data[x_len+y_len:-2]</div> <div><br> </div> <div>=C2=A0 =C2=A0 return sum(np.array(p_list[:x_len])) - sum(np.array(p_li= st[x_len:x_len+y_len]))</div> <div><br> </div> <div>def cons_1(x_data):</div> <div><br> </div> <div>=C2=A0 =C2=A0 y_len =3D int(x_data[-1])</div> <div>=C2=A0 =C2=A0 x_len =3D int(x_data[-2])</div> <div><br> </div> <div>=C2=A0 =C2=A0 a_list =3D x_data[:x_len]</div> <div>=C2=A0 =C2=A0 x_list =3D x_data[x_len:x_len+y_len]</div> <div><br> </div> <div>=C2=A0 =C2=A0 flag =3D 1</div> <div>=C2=A0 =C2=A0 #a_list =3D p_list[0]</div> <div>=C2=A0 =C2=A0 #x_list =3D args[0]</div> <div><br> </div> <div>=C2=A0 =C2=A0 for a_val, x_val in zip(a_list, x_list):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 if a_val > x_val - 1e-7:</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 flag =3D 0</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 return flag</div> <div><br> </div> <div>=C2=A0 =C2=A0 return flag</div> <div><br> </div> <div>def cons_2(x_data):</div> <div><br> </div> <div>=C2=A0 =C2=A0 y_len =3D int(x_data[-1])</div> <div>=C2=A0 =C2=A0 x_len =3D int(x_data[-2])</div> <div><br> </div> <div>=C2=A0 =C2=A0 flag =3D 1</div> <div><br> </div> <div>=C2=A0 =C2=A0 b_list =3D x_data[x_len:x_len+y_len]</div> <div>=C2=A0 =C2=A0 y_list =3D x_data[2*x_len+y_len:2*(x_len+y_len)]</div> <div><br> </div> <div>=C2=A0 =C2=A0 for b_val, y_val in zip(b_list, y_list):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 if b_val > y_val - 1e-7:</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 flag =3D 0</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 return flag</div> <div><br> </div> <div>=C2=A0 =C2=A0 return flag</div> <div><br> </div> <div>def cons_3(x_data):</div> <div><br> </div> <div>=C2=A0 =C2=A0 y_len =3D int(x_data[-1])</div> <div>=C2=A0 =C2=A0 x_len =3D int(x_data[-2])</div> <div><br> </div> <div>=C2=A0 =C2=A0 args =3D x_data[:x_len+y_len]</div> <div>=C2=A0 =C2=A0 p_list =3D x_data[x_len+y_len: 2*(x_len+y_len)]</div> <div><br> </div> <div>=C2=A0 =C2=A0 args_0 =3D args[:x_len]</div> <div>=C2=A0 =C2=A0 args_1 =3D args[x_len:x_len+y_len]</div> <div><br> </div> <div>=C2=A0 =C2=A0 p_list_0 =3D p_list[:x_len]</div> <div>=C2=A0 =C2=A0 p_list_1 =3D p_list[x_len:x_len+y_len]</div> <div><br> </div> <div>=C2=A0 =C2=A0 return sum( np.array(p_list_0) - args_0 ) + sum( np.arra= y(p_list_1) - args_1 ) - 2.5*(x_len+y_len)*2.0</div> <div><br> </div> <div>def compute_Marx(p_list):</div> <div><br> </div> <div>=C2=A0 =C2=A0 #print('Flag 0')</div> <div><br> </div> <div>=C2=A0 =C2=A0 x_list =3D []</div> <div>=C2=A0 =C2=A0 y_list =3D []</div> <div><br> </div> <div>=C2=A0 =C2=A0 for p_id in range(0, p_list[0].__len__()):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 x_list.append(random.random() * 5.0)</div> <div><br> </div> <div>=C2=A0 =C2=A0 for p_id in range(0, p_list[1].__len__()):</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 y_list.append(random.random() * 5.0)</div> <div><br> </div> <div>=C2=A0 =C2=A0 #print('Flag 1')</div> <div><br> </div> <div>=C2=A0 =C2=A0 x0_data =3D x_list[:]</div> <div>=C2=A0 =C2=A0 x0_data.extend(y_list)</div> <div><br> </div> <div>=C2=A0 =C2=A0 cons =3D ({'type' : 'eq', 'fun' = : cons_0},</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 {'type' : 'ineq&= #39;, 'fun' : cons_1},</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 {'type' : 'ineq&= #39;, 'fun' : cons_2},</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 {'type' : 'eq= 9;, 'fun' : cons_3}</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 )</div> <div><br> </div> <div>=C2=A0 =C2=A0 #print('Flag 2')</div> <div><br> </div> <div>=C2=A0 =C2=A0 #arg_tuple =3D (p_list, x_list.__len__(), y_list.__len__= ())</div> <div><br> </div> <div>=C2=A0 =C2=A0 x0_data.extend(p_list[0])</div> <div>=C2=A0 =C2=A0 x0_data.extend(p_list[1])</div> <div>=C2=A0 =C2=A0 x0_data.extend([x_list.__len__(), y_list.__len__()])</di= v> <div><br> </div> <div>=C2=A0 =C2=A0 #print(x0_data)</div> <div><br> </div> <div>=C2=A0 =C2=A0 res =3D minimize(fun=3Dmarx_reallocate, x0=3Dx0_data, me= thod=3D'SLSQP', tol=3D1e-4, constraints=3Dcons, options=3D{"ma= xiter":20, "disp":True})</div> <div>=C2=A0 =C2=A0 </div> <div>=C2=A0 =C2=A0 #marx_reallocate(x0, (p_list, x_list.__len__(), y_list._= _len__()))</div> <div><br> </div> <div>=C2=A0 =C2=A0 print(res)</div> <div><br> </div> <div>if __name__ =3D=3D '__main__':</div> <div><br> </div> <div>=C2=A0 =C2=A0 item_rank_list_large =3D []</div> <div>=C2=A0 =C2=A0 item_rank_list_small =3D []</div> <div><br> </div> <div>=C2=A0 =C2=A0 with open('LDOS.csv', 'r') as FILE:</div= > <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 for line in FILE:</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 data_rec =3D line.strip().sp= lit(',')</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 user_id =3D int(data_rec[1])= </div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 item_id =3D int(data_rec[2])= </div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 rating_val =3D float(data_re= c[3])</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 if rating_val > 2.5-1e-7:= </div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 item_rank_list= _large.append(rating_val)</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 else:</div> <div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 item_rank_list= _small.append(rating_val)</div> <div>=C2=A0 =C2=A0 </div> <div>=C2=A0 =C2=A0 p_list =3D []</div> <div>=C2=A0 =C2=A0 p_list.append(np.array(item_rank_list_large))</div> <div>=C2=A0 =C2=A0 p_list.append(np.array(item_rank_list_small))</div> <div>=C2=A0 =C2=A0 p_list =3D np.array(p_list, dtype=3D'object')</d= iv> <div><br> </div> <div>=C2=A0 =C2=A0 compute_Marx(p_list)</div> <br> </div> <div id=3D"gmail-m_426290688831851966appendonsend"></div> <hr style=3D"display:inline-block;width:98%"> <div id=3D"gmail-m_426290688831851966divRplyFwdMsg" dir=3D"ltr"><font face= =3D"Calibri, sans-serif" style=3D"font-size:11pt" color=3D"#000000"><b>From= :</b> Andrew Nelson <<a href=3D"mailto:[email protected]" target=3D"_bl= ank">[email protected]</a>><br> <b>Sent:</b> Saturday, July 16, 2022 8:46 PM<br> <b>To:</b> SciPy Users List <<a href=3D"mailto:[email protected]" ta= rget=3D"_blank">[email protected]</a>><br> <b>Subject:</b> [SciPy-User] Re: minimize does not stop</font> <div>=C2=A0</div> </div> <div> <div dir=3D"ltr"> <div dir=3D"ltr"><br> </div> <div> <div dir=3D"ltr">On Sun, 17 Jul 2022 at 09:24, Hao Wang <<a href=3D"mail= to:[email protected]" target=3D"_blank">[email protected]</a>> wrote:</div> <blockquote style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204= ,204,204);padding-left:1ex"> <div dir=3D"ltr"> <div style=3D"font-family:Calibri,Helvetica,sans-serif;font-size:12pt;color= :rgb(0,0,0)"> <img style=3D"max-width: 100%;" src=3D"cid:1820e92884e9fb5208b1"><span styl= e=3D"color:rgb(34,34,34);font-family:Arial,Helvetica,sans-serif;font-size:s= mall"></span></div> </div> </blockquote> <div><br> </div> <div>Would it be possible to provide a minimal working example so we could = help you further?</div> <div><br> </div> <div><br> </div> </div> </div> </div> </div> _______________________________________________<br> SciPy-User mailing list -- <a href=3D"mailto:[email protected]" target= =3D"_blank">[email protected]</a><br> To unsubscribe send an email to <a href=3D"mailto:[email protected]= rg" target=3D"_blank">[email protected]</a><br> <a href=3D"https://mail.python.org/mailman3/lists/scipy-user.python.org/" r= el=3D"noreferrer" target=3D"_blank">https://mail.python.org/mailman3/lists/= scipy-user.python.org/</a><br> Member address: <a href=3D"mailto:[email protected]" target=3D"_blank">and= [email protected]</a><br> </blockquote></div><br clear=3D"all"><div><br></div>-- <br><div dir=3D"ltr"= class=3D"gmail_signature">_____________________________________<br>Dr. And= rew Nelson<br><br><br>_____________________________________</div> --000000000000f2c58905e408f56b-- --000000000000f2c58a05e408f56c Content-Type: image/png; name="Outlook-puewvwog.png" Content-Disposition: inline; filename="Outlook-puewvwog.png" Content-Transfer-Encoding: base64 Content-ID: <1820e92884e9fb5208b1> X-Attachment-Id: 1820e92884e9fb5208b1 iVBORw0KGgoAAAANSUhEUgAAAm0AAACnCAIAAADMhfwSAAAAA3NCSVQICAjb4U/gAAAgAElEQVR4 XuxdB5wUtRqftn2v0LuANBERAUEECwr6aCJVeq8n0kTFAgjSbYBUQRBRUbGCqBRFinSOJiD14Djq Ua5sn/r+mdnd273ba3Rl5r2f3E4myZd/vuTLV5LQDz5Uj8ry7N29Jcu7jBcP1aqfQ+qdliRJciaS WJaJSKSiUDRNR0zSX+oI6AjoCOgI6AhERICL+PbfJSkjNkF/qSOgI6AjoCOgI3ALEIismd2CivUq dAR0BHQEdAR0BP4DCOhy9D/QiXoTdAR0BHQEdARuGwK6HL1t0OsV6wjoCOgI6Aj8BxD4l8rRgm1n b9gxvWnUNfQAXbDtnGvP227OetRr9TodIY/T6XR5vIKkXAM5+cqiSLzX7XKqlTtdLo9PkBWm7FPd BrStEZtdgJTsdTlcfOZYq3xVm83HMu92uHw3o+RsKszhtfGpsVt3b9nzx1tPWvxf2RuN2xi/Ze+m MU/QbqfTK2mv6YJaD0bnUFZ2Sbcrb3b0UIZST/aaunjZxq0btm/8+efP3xvTu17xsAGdG29kW/Lt TqDtDUZ998fURgXDuZou8PTUtd+NaWDPjtlvN916/XcpAv9SOSqlXTh58oLTPznmr++ktPOnrivv RQepl2ZNFu0xm4wGRhEg4bziTZQqiuh1u30S6jVbrBaLycCSOj1i6YZd+rV5qGB2PUmzLMcyd8PE o7hdhnpPP2xW2cFar3Fd1uXO0h9q72s9mD+2wde3K29EQukCT4385P2u96Wsm/3O26Pf/2zlIbrW c/XvYUM/ZsvmzBsRC74DXnIV2w9u5v5+0Yar4UtTJWXjou9dzQa1rxw5PvIOIF0n4a5E4F/Kj2m/ j+/5+7V1mIK8Pa4579rxPddiQiVVMyzHBWctg9EgQI56eYPdHDaVXRuRFOaPTKJPFnlBYU02i1FL YCnOwDFul4DXOVVCG8wWQ04f/GfSpDObNjP1G9WybNrisddpXOf8pi2mZxqEN09J03rwWhqd17xZ +46i8po3z3QxRZt0blx4/5xWI5ad1RYLK777xGIxCHku4c790Fq/S+tyB5e8fEzMQqN4bMXPh7r3 6FL/mzEb3VlS9Rc6ArcHgTtLjrJlOi9e1urq6tMVGtUyHf36vW/NXV9uXVk+8MlrIz/Zrw4bw5OT 109qaiGihN84vtGw3xwZuDGlu877KS75/bdO1R3Y8tHy0b7T2z6bOGlhfKpfzhifmLJ+MvKyLOvb 8E5oXq3eK6tOV3ymlvnoN+8uM3cb0aqSdHDhyJEL9qn1BvLiT9+G8Q0Hfhs6iNkHXvxxcdeylM/l FhiL3QJQxX8+atdrzmGPAA2Vpm1Vmg99uWfzuuUKss7Tu36bNXnmL8fdMqY/mmY4o8lkZFXZKHod Xspi5USvT6BNKAdvmcJ1urw8qOVjVYqwjuRzZxP3fj9ryspEIsgN9cetndLCIsmM0cAN+HHXAEoR +fTNbzcZvOwypRZrLl63y/C4JjXLFLRzzlNbfnx/woJtaUZa9IkSXWngZ990S16yRGrY7fHyxtTE A5uXzpi3MsFH6JCEUt0WLOubumSh5/GuT1aOFS7+vfbjKbNXJngk3ucTJFlWrJWbDRnepdEDpYtE Kxd3r5r3wfw1CS6fjxdh3KYZY9UBP3zf7cSouD/u7dnzuXr3FZCvnFjxzoA5W5282+WjVYhkUf1c /R7Ums2GCBq1IgnqVzLZ2suwBpPZREABicBaNlpYwctLikLTZg/+lU6u+6v8iIa1zX/tePCRasd+ nXzo6Qa1Aub28B5sPOzXKx4nIcWM3mLKdJv7Q9/EcSMSn3y1w+PlonynNy8YPXb+rhRSL8sZop79 cNMUjeu860Y/Frc8RSUb9Fgrdl+y7Pmrq0+VrnefMfHnaV9T7Ye0esB8csnrr83bcRVAy9wTUzZM bRFrQfv4DeMbD/stndDvf9iqvT+f06G8zW41BJZN4Jz2/Rae8ivS1grPDHipc5OHNc4hOK9NVEUl XbBYUVY4dPFqiMYteTx+Cw3hjXdbxWiIqryBh981scXQZZe00cAUqdNl+EstH6tc1MQnH/1rxcxp X+64rJXFVh64aGmnswvmZ+p9lTeonFPJF9nSrOWv2Gvp0o7HRw3e/GBc3yYPlrYKft4IjCg6+tGW T0cdnL3pQhZjAgqQL2xae2jQoOfqf7Dp97QcF5BqbfqjI3ArEIgwd92KanOogytRlvpz4tifku/v Pnlg9A+jxnx5/v5eXR+1aVmE7VPbtm3Wos9He7KuVdUvTPX7dGB/fL1H01bDl6bUfGlcjxpBZYxH 3jbNWvT+aHekRTtXshypd/nFqt0nx0X/8NaYLy+Qeu1avfz2KVrePRHySseWxrXr1Lpd17ZtOrZ8 fuCMHenS5WMHz7iJ/mix2O/rPH3+6/+z7p4/ekTcqx9v4hqOeX9wg0IW1TjLUaLP4wtpi+Tz8pTB ZDGpopUp0mzMB31rXFkxfsjgga9MmbPyOBdrl3FgBB5h14cd27ds3X3iepd4/MsBzz3/9FNNGz3/ zhqP2WI20pJPLNtp+ox+tdJ/nTxs6LDJv6XW7PfRjB6VFK9IccQijQqsj7RtcHZ2vzaNWr/6RWq9 0R8NbRBFKpVEUYZki32i2zOX5vZr1fC5l790Pj72o6H1jF6PT6I4o71qt1mfjmpm37tgDGnRZmvT STPiHjLwEmM0W1A5Kwsel4958MWx3W0b343r1rb7G3M2X1EYCHpBoqFG05CDHo+gMCaAYDYRA7Va siUmJiY2Nvj/aLvZaLbHFCpSKAafGWmZhxc6Y3IFVAJjtFitVj+MknRy4/qU2k9WNddsWDt5y45k g5FVAK/quM6xBwme5vq9O3I/juzRpPXwz87d129Mz4ftgAliVvKlbZjQRuWcXU43igs0UxE8bq+o qJwzYexP5yu+MG5AwV8mTPrmwv092tdgeKxwzBZu/7QObf7XuNN7OyNxzvFvBnfo1q5tp9atO7Vu M4hwzpWTCSl++cCVa/fhwrdbFzq4KIjzzGH1o1WJK587dsJrebz78Ob3FTEFZDBJUB/CG22bNe/w 9u9Owhst2zRr3qZZ67ErA3ZSY9UeH4E30n6bPHxYkDeqGoP5KToqc+9rvKF9kUNqTjQHi6eNNV4c 3cm0/r3BvV4I8EYw0Vyzfl3Lmfg9fqmeQZP2l3x5d/wZS536NTX7feZk/beOwG1A4M7SRwkA0uUt K1Zv3Vu+ZlK7ovtWr9wRX+aBxK7PlC3JUMfIFOpNvXAhleLTvNmsRZULP89cuOkUJFPKkqVbur5b q04ZZm+CNvn6Us5fTKGFVF+kvNKlLStWbd1fodaZtsX2qvVWR733lGCpY2SR70s9fzGVFiLX60s9 eyoVc5vP5S3Z8fUeD15dOvDd39NYs83MMfbGLw58ktv40uDJv3usVgOzY7+zxI9vDWz5XdyyZJnl TLLoIeqW34yryDQsw0HlhC1f9X7LhZWLl679W6KgnO3Y9DNCi1Q9luV8whlPKmeu4JYV3nnhdGKi izIRxYZjOcpCG2u1f/7e9FUj31j0W7JosB097C78zcR2nep9N2UPxVIsNECb8dLSD+f9ecpgZq/+ 8P6SFqte6dxo4ZafkqFDMwYDK59bPmPh5jOY/f9Z9v7SZ3/o2+7x6et+9VjNMY1f7P8Yu3nE8PdX XKaNtiMHjkqllsZ1b/b5/pWaBEDZHCUo9sRv+7y3MsElGW0Xk47vAT4Q0DQHoYemSGio1WwgNnCW LBnQYcb6r6yc3lQTE+pQgDj2SZzZ5Fs9tNE7G3hGFl1q6/2PwhitZiNZCbKMAQquLMniyXV/XJ7S op+9gWPbi+eZZ7EgsQTAzLEHUYhyYeXMTzYlgqRLiz7f0mFG/Qb3LjqUIIM6mhfR+06Gv5TGK6wZ lar8BLez4hV8ggDOWb11c7EHznQpd/TP1fHxZf461fGx0iVNxnNkySC6UtJEXnJEjMgSXFeSXWp7 uHIvDAXnfD1kxnpNz6LtDfv3riusHTnkg7XEpLI7/rBc7qdXejb5bBs4R0lbPe29Oh++1n78wvaj 0xIP7d78x6/LftiS6NHA4dMuXEyjDBpvJJ+7cDYslMBUr0O7Ks5Vw95ctNGJ7/fsdxb7aXq7To98 NWaTV8tPZ+79gSpvXNHQzzY1Z5q1osl/jQWSlvWe/HMywfH0KcIbwYe95/7KNiHxeFJ2wQ/S6WOJ gq1ytbLs+sPZfRNSnv6njsDNR+DOk6OKy+lSKMXjdMtuhxvj1uP2UFarOcuaOzI44qnDCX71TkhJ cVAPxsbkLafidqI2rV6nCwPc40K9NtWEnNfHUr335GHVT85/6cOtaRQLR6misJXr1rKnb123LV2R GZkyMIzr2IEzhv4PVGS/OS9IkiDCLBlSPpyuIT+lM8dOCC1bDBl88ZsN8QePJpyHKVGW8IiiiNhd gacR4EQmI0WCRZX1Gz1JccaKdesWpw/t3K3N0hTl2rNzP//k/TXKG/ec1KYfRU7855hPkuBp5ZjL /+w/x7Srdi/3/VlRZuF5Vfjj+4/4VSg5+fCh8/Rj1Spa1h6iuCqP1I5ybPl9iwvyT607ZffWo3S/ h6pwP2/ltaYgtInmd6/deIlBcwSITyPknaaNmojoxDKAJkooTNLEy8xClEOJ2v/5sIGrgmuIICiK eOkwyBSJjRxLgODDZBzwiPMctRMdpWNr/kz9rO/TF778JFFWa0JbaMpPVkbeCH8Jpw6fgE4M8wUj p6Wk+OBXJmdKssRErn1OrNAMWqZoBgGyAmBpdIdL4xyPl/b6OcfL2uxm6Ms+Cg1kYLc2QUuHFh6h Wu2VpXqvSYRzXpyx0+FfKfhxXrsp4JdQUvbtPMH0f6AStywZDRKT1oztuG3JI080rPdQrYfrth/x VNvnlg7uNydYQLaVsWWqVY3iD+zcTYQoecAbf/NNq1Yrw25SF43o00y9n2xoAt746YrGENmm5kaz vz5K2Ldu0yVtcRt4FfiXLlqsMJ26219T5lTyW7hyOYV+uFgRhtLlaCR89He3HoE7T45C9qiTM+Yq 7S944zCZ5TV4RxbEkNlKoTCJ5RHVjNoU4rqkiPmUyXO9mLELPPrqhC7Ftk2LW3LUA+IlrxPzlInh aDfz5Ojft4yiOb9jkBd432mKx14ZUBcupwPywE+zfG7FqKHmuJ5Ne45tO9JKu5O2LZkw4eOdqfDZ wQinEOsocaYSqFQ/Y0ZhtDXKRvPpLs2pRYrjXQ4vXTnalvGN4IUxVRUKEGa80ylYo6zAj2ItRE8U PDAB+x/F6/Iq9igbKlCY6NgoJrr55L+e9brcIme1mWhIRIlPYVCENjOzTpg7+atXsSCCGKM8oqgY jZQgwFys2athWrZaKB/P+zwKNCC/59N58fiRlNATjtFArxdi2OdyeeUsHRnxMGTxxO9fr6pe7+gf pySqgko9DYUy0I6c/kXL/TM7jMWwuNNQh90uKeDCxm/CmBK2EQWaidLYAgRAP8fSdJBzGKvdDnu1 x+smIpxmjfYcdkXRBRq8NrFL0a1Tuy85ltFfAZw3NclQwQGUlGJH1/sXBlJ6wpaV+P8i7IFp8tYn E9oNbP5d/NcXI0uoYONpqz0Lb6T7aJs9ZNEY3vtuH2WPsoZwThhvZKTmhWZCBpa44I2ID+z+Bgor loiJ2kssXUiQXQ5f6Ek6ArcUAZ0ZbxDcbMlWo0c2kX5+eeKac5h7aYo2qDEsBkWirem/jx765Sl1 4oDt18XTRpOcxtrtcPrid85zxqWdX7+z82tMxTH3PjFw/Kj+43rvev7DXapegC0wJs5HEa2J1Kgg 4iZgH6YUV3q6yEXZ/aoUvjbaosyKIz1k/jJFRZlp2k2mR8ZQoKBNTk1z8CLMpapKbIqOhhGAV6mm 7ZCdULtI3I2cnuqUzm4YM/Tzww6XZLDZTIzgdnoV2ctGRWk7etmo6Ci7TY2TQpiOJkjhCYZRNxjM jAAr+A6xFsCkKCKYyOOhYhuOCbPryiQCWjGYzcLvwxuP38CT37kqlrSc+P3oEb+RqOnA0gurDNKG 3J7QjxjOYIYkRCN8IhY9kPa0DQZi9CrWQtH+VpIC2eiojBChsBqgxlqsUMIVWJsFH++DJzVUmc74 Fpzz9pvN5RVDx606Fyo9gjj7OcefQ3ZfihSoKpz949ctrzRqQBwguclRmF5cijGa8Ibf4GC0RZtg CMLyL/CE936Mnc5Tah5pVtQlSeRHSXc4KLs1RGhn/o622WwU9lDnqVczZ9Z/6wjcBAR0OXpDQDXd 3/vtYQ+cnNtn3i43VFgGGzaJpRUuNPHojt2ulpVLeo78msBazazocSImV4vFRdVQYEI8fjnQovgu 7ls599vW7UYWL44Ii4DBFbGziJ9lTGYrLrHxwUhs8NtFhYRdu5N7NK5T2/7zr6pp1167bg2jc8P+ kxBFmoShmYq1a9p/3kbmI7bSI3WL+g7FH/JCjKqRs7Shar3atpV/OpHMVqhdq6hy4uAxjyBZWa1F ZYSEX0544B+FHMWJDC6escAd7FdZJJ/b5fGHBJG4Ig9251ASRKdWM3R1t1cxWologqPXyCK2ySP7 9oXbdSXY9hUjPL7SZdXADP9nmF03IlrE7srDBKzASaw+EtTgbLMFDLSaYdxfIMKZXC5o6sAA0t5g omXRLWqRu4wik4jkwINmOhEuFfwdmuBy8xIYgUZ4uIE1gQT0dASjCjhn7GsPn1nQb9bW9PCC/Jxz j3JmQ8BTEVqRsWipqNSzV4ILC6ZImbI2JeVyIEiJfKvwgN1kylhLaQVIZw4edhjr16kdtWaDGu8O 3njQ6Nx6KMMnmbn3CwtHD54ImieyTc2F5qxAZX0jJ508I9tKloY75nIEZNEpsaVK2uUzCUnZiuKs hepvdARuKgL/MjlqjClayIq5KTYGihQbU6JEiShKEVxXL6XnqqhQppgihWwkb6wJeWORN1rNm5yn vEULwagZrLdkcU5gGMl5Rc1rrNF/dOfiR754eytXoUpFVZTIjqR/Eq64KZNR/GPu/Ofm9Z42w7Zs 9f7TTsYWXbRK/YYFN4+auDqd7OrA5MTI0CS5SNZH4+PDP2kj//Hn3mNnU+UC9z3XoULa9nm70mCB hPoJPYcXJPZsYpLcqVG3tlu8m8+5KdGRfNUlySh467crE9v2e3NKEvPJTlfpx3oMbhJ1bN7X2xwe 0WAymkQeVtnYhiMmDf5s+T5fmaYDu9x39af3115WWE0bhSJlfWr42IGmb3eT1E4VLq2dtilV5mU3 Jf8+d0Gr+X0++IBb/P3OJCW2ROly1R6uRa0cMeFP3sjB9Atzsw8mXM5vUVc1Up6nIO39b1T3qBdf UcSjq4Ba6GomJu1U/I5TGeyu8G6njzLgmAsGMlTgoSqr0kjJ8VgJ1mjCbhgvoLcQRdcNOUeQNcUU LRrSg8VLlsChVGmpV1N8opFlBF+IoZIQJ6MIHj5oScS+XSaqWJnC0RZDbOEYA5VuiilYCKq26Ew+ k8wTdTuC1RgLKRn+ay9rshcoWtAs87ytgB2e0pjiJYsTjnWC68jSwFyj15iupY5+M2mjULpiRbXp ivfy6XOpSFQc6+d/uu/TuFkzYj77cUeCw1CwZLkH6jWw/vHa+DVOiol5aswXPZiNv67bfeSCiyta 9ZkOL9Tid09dczpEp5VPHTsptWrUpeWOz/emCCg56WI6SfZu/+bHY892f3NyctRXe1IL1Ow0CLyx 5Ovt/iAjQkWm3k9e89EfGYciZJuaM80ZXZvDX/KVPXtP0m2r3Weg/oo4qA1VH6hIJ/6QXTxvDkXr SToCNwmBf5ccNdQatHBuu0KBiWvIsl+GYGZNWhLXajriWXN+uJovLUJezOSIDqGoId/+SvKeXjKw 9bS/I657Q4pDXlJvwNM65NtfersFKWnJwFbTDogUbSpRuoQpqlLc7BUvBUjDLsC2PWcfhqwQfAc/ f6n35cHDuvcZ3aWoGZGfJ3Zv/H1Z/FW3V4KyY7Ni1x+PiBubNWTbQaBuKenQIaX183FNShaCKev8 wY2fDX9v2XE3YpOIJReqnNlmSvl11rvVR/QZPvPHUYzo3DJW2z/KGg2nvhw6jHk5rsnIDzvbWdep bQuHTlh0mLKYGWJFJfsuPds+WeJpMmhC3yJy8t+/jps4c3M6wlH9ckFxbpg5L63xoAm91NS335y1 xWe2mLCd05t+4LOBPS4OHt619+h2xQuZPJdPH9q+8btTEk1Cn9T9owbsZwkGDNGcGmyEmNqgq5oc DqGQouA+RDvgNrUQaRn+kI9kr8/rcanWYaPVqkCN9Xp4xpZZwwrNyKByCruHfDjsCcc/mcjWFd6A Hpwf1oPoffHE/J7N39vnUhivAFN7UCCSkFwDaYzb7ZYY1vzYK18t6oSwFvLI4ojv6mEdIyV9Pqjd rCPGjNjqUBpgwLYioAqbj6r0njXvhaIGsp0XzQfnaBzr5xxL2XuK4dtu7y7rHcI5gf2jQsKyob2u 9Ivr2GNUW8I5ycB50w+HVWknp21b+kWFVo8/0+OxrgVttOfSid0rxr+18KcwLU1G8Pq794/oM2xa sygjK8QH94/6Di0aPEzAvuSRH3Qz+S4d3bJw6LTPD2b4Zqmsvb8pRF3OITUnmsO7N7tf0on1fyR0 a/XYA8a/dkcQpKbqj9e1nly+4XhuAz678vX3OgI3HAE64j3eN7ya21igfo93AHxydgH8mVYisNTd 9B2PDH9m0ia/iRjhtLDFUma7laMjpN7GHrzpVaurkptey7+mgpx7P+fUG9JIpkS7D7/rn/xG60kb A9HmwXJtT7y1fFLRBS8M/+acbte9IWjrhdwABDLrADegSL2Im4eAEL5Az9/PgMAk5CkUDK2hDw8F jpyxoB7/kCU1+GX+arwOam8ehllL1oVoVkxu5xv5/C+f/uRu2KV5sczTE1OsRecnPcsXr9CF6O3s IL3uzAhkZtTM6frvOwcBhLQi2gX/1Z58/6S4oP0aeaGEBYpC/CaO+2NlGrZHIkbDUzMAyHeN10rt nYO5TsltQcCzf/7YmTvFour5WhkPHVVU2DlrzPy9gTFwW4jTK9URyIyAbtfNQERzOmZG6Ob9Zqu8 8Hq76lkPdRMPL5vy3d+ZXEMeN4UtmAhClUS/Kpn/nzgIAZs4ydSUKa/BQLZJwrqpqZvB1EDMK8Hg RhCQO/GhNd485PWSdQR0BHQEbhwCuhzNwPJWy9F89SI2mZLwKPXRNpzegp+hFN4aAvKFif6xjoCO gI7AHYDAvyte9w4A7HaREJSaICD075v6M7Sxt4aA2wWvXq+OgI6AjsC1IqD7R68VOT2fjoCOgI6A joCOAI4A0EHQEdAR0BHQEdAR0BG4ZgR0OXrN0OkZdQR0BHQEdAR0BHR9VOcBHQEdAR0BHQEdgetA QNdHrwM8PauOgI6AjoCOwF2PgC5H73oW0AHQEdAR0BHQEbgOBHQ5eh3g6Vl1BHQEdAR0BO56BHQ5 etezgA6AjoCOgI6AjsB1IKDL0esAT8+qI6AjoCOgI3DXI6DL0bueBXQAdAR0BHQEdASuAwFdjl4H eHpWHQEdAR0BHYG7HgFdjt71LKADoCOgI6AjoCNwHQjocvQ6wNOz6gjoCOgI6Ajc9QjocvSuZwEd AB0BHQEdAR2B60BAl6PXAZ6eVUdAR0BHQEfgrkdAl6N3PQvoAOgI6AjoCOgIXAcCuhy9DvD0rDoC OgI6AjoCdz0Cuhy961lAB0BHQEdAR0BH4DoQ0OXodYCnZ9UR0BHQEdARuOsR0OXoXc8COgA6AjoC OgI6AteBgC5HrwU8RXA7HG5ByU9eumC7Oet3TG8anY9MsiRKpJJryRuo5nry5koqbW8w6rs/pjYq SGf9lC3VaMjHy3/bvmvz3t1/vtfYkPWLW/tG9Dodnvz12Y0jUPa6HC5evnEFqt26b88W8v9tk5pY wkvOlGoUJdlft8K7nC6vlA9CFNHjcHrFfOSgmLJPdRvQtkZsBK7IvZi8UXgNvXkNWXKnVvI6nB4h 9+8yfaFIkiRHnD8UOaSzBLfTma/OikCIInrdLofT5buB3KdVE0ZqvvkqAqnZvpJ5t+MmNCDb+vKR oIHA5SOH/ul1ISClnT91UnTkYwqTRZ9HYG02E5v/vBmkXk/eXBrMVWw/uJn7+14brmadEqz1XxzV /p6dM4aPOZAmKGlJ+ZqIc6n3mpJpluOU27VupFmWo5hrkiuRG6uk/jq6w1YTU6jF2EW9s3wSnirx Ho/PbLeojWc4ls0fIQQ4Kl+ks2UbdulXkVn7077UfLB7oBV5ovAaevMasmQB9ga9UDCyfYzFbmaz FCijs5RAZ2VJzf8LWeQFmTFZTNwN5/0wUvPUa/kn/47PoYGgy9Fb1VFK2trxPddmrg3yJw8zVOS8 mcuK/Pt68lI5k2et36V1uYNLXj4WQUYyhUqVsfH7V6/Yss+XpzZGpv4GvmUN5kxa2w0sPLeiaFR+ YzVy2X3loptixLSIylC2qTRnsuRv0NOs0ZJ1us+twdeenjcKr6E3ryHLtbfijsmpQO1lOI5lbrgY DWti3nrtjkHlRhOSvyF1o2uPXB5bsdfSpR2PjRq8pXpcnyYPlrEJV06seKf/nK0e8r2lwjMDB3Vu 8nD5gpwjcdeqee8v+P00HyiIKVyny/AXn3/svmI22Xnp9OG/vpg+ccXJa1gTR6Ys0lv2ns6Lv3n+ 6uqkCo0fYvcsHP9d7MBR7StLBxe+MnTa1jTKYLFHPz1l/eSmBq/TI8u7Pmw6+PsLAmcxUYKPFxlr 1X7zfxxwftIrR2r2a/FIuWjx7K6v3v/wi/0OWGNgL1KMT0xcM7l5LNFJfRvGPRn342VBUhSKZg2W Sr2+/K6VWm9N89Fv3l1m7jaiVSXU+9orc3ak8DAOGZ6cumFKi2iz2cTxG8Y3HvZbegb9kliu53dL +5ZXfCiPohmWNZi4E7Nf6LfwlCx6HV7KUqjKUz37vtC0wQOlzM7E7WoMussAACAASURBVD9PnzRr VYKPommGM5pMRpam6OhHWz4dtX/G2gSnE+ZnDCQzJ2GVXSlu8c8vV6c9Dq9kqD551RO8SBsMm956 9pVVTi8vleg858e4C280mrCJMRkYmntoyPcfPbxmYNfpuz0+gSrd7eMVg1NnjT9Tp9ezNUvbvEnb v5j64df/uLMAT9Ahq3bOvwpRijw375uO/MbzQMP0zxfjP2c6DX8eaCx6Y9SSoxK+Yks92q1z0yfr 16xSIopOPblz/a9LPv5yY5JPaz1ot93XB1x3fNTgv6r16fbUfSXM/OWTv04d/PGm1MJtP/767VI/ D+w5d49KiK3mS0vmNjszoVvcskRezQ9MzGaDf6JSRN6LrpWDWBkr9Vr6Ret9L8ftqPfKi82qFVHS LiWtGd9r2ianotC0vUrzoSN6Nq9TLla8+M+2tUvmLVmXqIlGUYiu3Wdw92b1qtxTxM64Lv6zZeXH M7/ccs7t86F31V4zWALGOsnncssGMy0ijRTLkm4yU5QMF4RbpMBODodgtls50eXiWYvNWrxOxxd7 PvNo9XusztN/b1w+e/pX8elGs0HhPV7CElzBmh0HDe385ENlCyiXTuzbtfnbBYvXJxIrI1vqsf79 2z5ZqxKooj0pSfvWLpi5dOt5j4/w86Pjfn+/bWGLiWg/A37cNYDgxe+a2GLosksKTKAeylSgQsMe /Ts2qXNvETOf/PfaOZM+WnncC4IZrDRMpDsVQaOQ6GpqFrOZ4r0CsYKiwUYzYRuKUhnAZLcYaDhZ XDyYSeF9AJ0MDRTEiF4vfqJc0jWEXUOySOrQCuMpzhKlLi8USUA7BGIFZwiEZkNelhDIheajOlI7 cDeQ+hTB4/TR0Dn9c6wiul1eooPSPjQQFUhuh2CwRAXSUTs6S7O5BzpLpVGRBdIYdApIMpnNAcVS kXiCucbBBhOGeZYluTaJUJTPhapsNo4PHzUEXsVsA4iUyj9YMAkYoyr/sGi8hhshTPR5MVMQkexv IEFdtThn4itNw8b3QJEAQjIQ0tTBAfOsC3OfQSJgkfGhpWUhm3xKGoca0YWo0agC4X+yKZykZtd9 ML6qUGUdrSHlZs9spGRSQsa409DO6C9O9b/dYY9CSZTpwYGjy+z6fupL08+LBas3qiyiqzG6y7V/ f8Gw+5N+mj16ZgJf8vFeAyfMtDm6vrclnTSDKdzsrff6Vdy5YNzgfZfp2DJV6zQoBs/dydybx1lj bOgr8E9Ynyro+PQ8eD+4kuWoJRPHnn5xVM9JBdd++NaYsi+O69Gp7vyta51wg/Dbp7RtM503PvH2 J8O1uVbGYFXHO4tRKvvkml3bJUx9e+C7fNk2b43tM/KF+O4LD1Emm5X2uHd+2L37p1zBphPm9fa4 QApRJ2hFFHxet5tn/PW+NL775LhVE94aU/rFsV3bPTR/y58yPmP2T+/UbqYQ3ey9L4ZngUA6trT/ c7+YOaORDProBsPfiSt/5HiKnxu4Ms9NmjuixoVf5o379BRf+OEXeo2fZfb1wsIANfs8smK1mmw1 69cxHPtkywWFNVmMlCRgBgbXG87/+GbLPwxywUYTZ3W8OKX3tHiK5RjfFafbw2NVYbFarWYTowhe D8XY/HOIgjWFYrBYDZgAZbZWpxYJE0b2fUe5t/2osXGjOuzp9ukRTDucBX0U6B/Ryxk1Oar1EVlJ cSXLUksnvp3Q940Xxsete2/C5HsGjunTufaXI/9SrEa6eMWK8qEfZ/9+KSVNshSv06HvlA+McX0+ OyxSEuSex8MT3dtYY+DIwhuWThky7Qpd5MGG5b1k6JxfPv79J5aOHjtkV7epOx1RdYeNbRf9x1tv fHNKZDFj02SEeb0emsFah0zWbo9IesnEYNoAVh6KzKMoOW50hUO/vTf4/ZOplvuerixgSrRwhrKt Pvx4UJUzqz4ZM/Okt2DtF/q+M6Ogt/v7hJ9FQSpRpSr7z09zlicmp8nR5Z/qMWDaNKVzu7kHWQxj FE+6wuMRgyMYdICrNAYhVcuMTDEGK1YbFFY5NrMB6GkfG6v2+GhGd+uGORPi9jqKPtrr5aEfVzJ2 6rrwsIssCSxmaw1U1bnQ0RWLR7+fmELZqz7T/tFK7IazZpuN4irUqGE5tWbxL0cTL0kFqzUf8OL0 GXTnNrP/ZrCQOjSn+wsLBPrhV5dOqfrLSy9/n0SmWj4lYPdnSz035ZORNS+unD1x7iFH0cd7x42d aXL3/nDzFY8XvcBFMnRCIjJolJkBi/l8AJq1ofHhD6AQ8I2VoYAB73UJEMv4SasSyMsjR6g4ZE02 m9GPGtgHEMIoSQrEcPf4FBYIsDSZNzHGKJs1sEDKMob8L4iRVia4G/2ZZMpuhWjK7mFMVhtGNk+b wf9hnzEGi432urwY+8HOIiNFhiiyYAIkjOpltcIlECdQSDCCE0Se97gUS+byKA5CkgZDclarEauP XBQKyeeVOaMFWAFPVOVj1EUAFtYogiZ94J951AZmJTWAB0jzCPheZVKR93lcssWG+UhNl3n0h9Fi ZVGW14s5g81YDQcQUyR1QDJGo5l8hhLUdQ1Jxmos28Kz7T5SHAjKOlqzdFE2zIY1kdsrgaeC486t WKxmLgjCnaiPqo0zxJ5Z1mvSz8mE3RNPHd9D3tH2hv161RXWjBzy/tpUJOzedUQu9+OrPf+3eNu3 yUCavff++63nVy5euvYA4Zg9OzauyAJUxBfG+q+snN40Kqscda4a2uidDUF1N2JmvJQubVmxeuu+ 8rX6No/e/utP2w5XrH6q42NlShnZozzWQL7U8+cFjylNgGuKFKEoYBGrunwEl2DVlbz6k6Xbz8A6 emDZj3u6jqlRo7h86CyjCnVf6oVkDyumurzQ64wWC6UurSGZRBpsc36zVu+ZtsX2rl65I75M9VMd Hi9f1rb1NA2uFZ1XUjEzpLilCMZjPvXsaZfVhvUjV+6FEXGPOL7p+96aKzKhirY/2bfvY9ymUS9P X5sqS17X+t1ilbWj+rX4On5ZMscqWE77REvV+ysYHP+cuADhR7iIxVTkJrEAkvPKOSdW4+k+GSEq qZcuEe1KERWGMxnNRkCgKhUcDaEblABEGUF+ousa6YsrZn228wLLUPu/+j6+45iaD5f69EgSpfVR tH/eET1O6DZRsJUqah+tD/bC7hKVu7Qofmz96vj4MtvO93i6clnj5lPAIv7TVzYENZitG84Wf/KL Fk3v//rYQYk1G0WnTw3EMUad+GLYlFUuIgUvnD25X/KR+uTLf04e//CXH7w+Yvurm556vRX969CJ ay8qBqumrbCkSzTTtiJAEWVVNQn5KAstu9yCoJZc4MyyAZPXpaoL/2PHDwB5g8HeeNCLDdn1gwZN +tOHUSlv2eMrt/Ltnk0+27bsIi+K4p4vXj9iDMy0++KvFK89/cmnqi5JSNAcnEDMg3kqQ5BiHrZq CgGHbnR6eDVNW3uAmwIlUeZ6HdpVca6Ke2PRHx7McMfeEkr9NK1z10e+HL2dgRLClG41omflsx/3 HrQ4iWLQic6/Nm2MsTFE86Ypec+SV/eQlbiPMlqtCYddZerOeLzhfYtPnCQztetqmiKKV9M9vNeZ fO7C2dCpG+N3wIAnuA1vDpu2NlXiXTt2HjXcv/bNPs2W7lx2ThRgrpEpdHv4oyhYrUCq4C3SRNEj kTk10zcUY8Q35C1r4gS3AH+gKqJYxigI4MPwzwkUGhiYlWEF4bTyMRR5eBJtFkgmlZ8ZyuX28ZIh ghczvEDUDjlF3nGY9zFUfciUuSEhWbTaQ3skkEhj1GvreX9ngXQIME3VVBmVR/sNLFk4ABgibrVq GcUFg46R08jIqEttZ0aDw+nO9IvMSkQsE9xMkuCGMoi8WFAICheQ0SxW8dDmRdkAs0A4qf7SsCgm pGFw+GEEIiBN5vyrHxqLaaM6D7Jmg+iGaQWohVECycnLNJhLW/2Al1FlYIBlW3j23cdAmaEjjNas YGTDbBLPS1iT+NmQkOtyQb01cYZAf92xclTc98emS5n4n63yyMPRjq1rNxEhSh7l6v6dJ5j+1Stx 3yZD2ElJx07wLVsMGXxx2Yb4A8cSLjgjOO6ygkdRwv7Phw38DViEzDVq+eLlIxHdT5kKUdxOt0Ip HqeX9bqcsEZ4XE7JZLObDJzghSA1cAi8pVgwFplS8WD96x8nJCJXOnMi0U+pkOrwcJVibEqmyYIE 8dEclnQ+v/CBy4NWJEe6Vq9bdjtdyOJx+QwFC8camNOiomBakgRRMUVqMXkH2x/411K916Rh1U8u GDA7Ph3rVhPeAee6sW4/zqhZoRyHdicw/R+oxC1L5hkDxwiiSBUtWkBOuZKqBFmINCosKBAvApMJ DS5UPyRkiaJATIdMRvcyGR/S4qmjif54ICE11UlVio1GKbLaR6sCy/wMu25GHyku0gs0lo5i6qUr XlHEbyoqNhYDGuiyhWp36dK77dO1yhewUbxTYKPM0iF/RGlQwvh2r914heGsfshIZAotQBQoaZtn jfm6+tyJC/7HnP8qbtaWdAb2RK+HgTYP3xNMC/7FMsDCTO7vWzJT2KIUtW0C4WfMgCogGvIUV+WR 2lGObeu3pssSR2YT1vH39sPScOD8zTmXSDHWYg936denRd2qpQvYYDbAyslzuUgRI53g5xYYzFkS +ZlBbsaExKGbwHt+hvN/of3Dlq5WNYo/sDPeBXWViGTXnp1/C8/cX62MYdd5fGKvUbsqd2r2mqM+ Cv4H7ZElKdCXbMGarTt3+t8jD1UuGWtiadgW3JcKF+aohIBti/CVHCEcVeUr1xb/+CWgpx+Ix/gl fEXqjfyQPvCnYImHvsj6GfE2BDkNYxhuCn8W/E14LmsW8ob0IFQ6iFw1M+F0BjBjmat9TxhaNWYG SotcDAZ2RgwPDdyxuiHsnc3X+X3NZbQ/YzlM5hMGYiZIK5anlGrtz18MWRgxgC2IYnAqVCSYYLkQ nubMdjtYONtmEJ7DGAg2n+GAqYeYVLVXhFL/AykUqRjwGhZGGRZ1gilNbPaY4rMvPIfuY9CpWUdr pKojMhuGmNqkILEYd4zPp07s/nd3rBzlU1IwKYY/TExsFB3dfMqmJqEzMCen2mGThRyVzy8fNcz0 Ys+mPd9uN9JKu5O2LZk4/uPtEYJJMxWsOC8eP5KirQNDk4jNMDMRkdAn0gHvyXIaBiFZJPtVJChX YBmGIgtIGpyB2QWLeZIdgzswc0P64gW+DimWRjxl5qFPxgvmK6fTGfiQLYCcZAVP/otE7S98h/Ug wtwBB6rJMbgAqXSBBq9N7FJ069TuS47Dcu4flUx0bDQb23yyijOcSW7JaIPqJ6VoOBPuRwLGtyLK csjMlmkVQia0YLOI58LLC5QT9l2o1rCgh7Q47E9ZwBwRnIUw+rRGaH0UyBYiRzP6SO0FmqgmHAUr s8eRjj0JkKd4a6rW/8M5baiNS2a/suvUVYfLXazt7HmtgquZAAG+q1dcsMFm0BPsKMr99y/rTnbp W+n4ul8OuDGxWC2Uj4fFSfFm+IAIfqrOFvpovwSVn/2hRv4mAecoJrr51C1POHyMldg0Ja/HRzO7 7QYJCw1Lrbhpc3pa/low55WtJ1M8Mn1Pi3fGPh0cuqQOlZGCvBLe3TTYLTjNhoNts9toPt2VYWfh Xek+uqzdqgoqxh4TzclpVwNG/vC8hvt7T/qgvXHL54ve+PCUStVz48c2pEXwZnDJaYCcj1C1v70a XxEHG0JWo21+vgqvJeNXJqbK5rNMkGfLXCHZZcEDUx1hFv/XBEcwExk6IQ+jKmXZVKu+Dtcr1V8R Gp9TCTmkhRce+FAtH5YNJ2L4Qh6WvM6R1hxqUhuSNV3j6Uz4Zv0s+AbfYxCElUSmgaD/MHRSyKYY tRVhJah2EHydU+E5dF/k0RqhsRERUHszY8omRKsLgOC4w4s7VY4iyizrSlpOS3XIZzeMGbr0JJAO PrLrciAQRb608+txO7+G561k9af7vTG8/7je8c+9vzM3nfJ67bohxEA7wQpOgiwlq1kEBsAuJok0 Flghy8qM79WJK9zulJUPSceBrWByiooKZmWjo6IC/sUQLCA+eGJVsXOqCMBkEUJc+J8yXaLV2282 l1cMHbfqnETi+vxsJKenOuUz68YN+/KUAvetC7EBVruJld2XNJxV8GUIKbhJAqobeRXKWOFVEYeH V2TMcI7abZjFrTDsEJ8HMZ/l4EkKLSRHu+649SGfqp5nmz3KZiNWKuL/4q3VGv/vXsdvL41adIBW I1O8dgpCI/ODBuB/oc0I/jBX6TW6S6mje46W6TK695a+Hx/2ahq2gsWz6jP2UFabiUyhqrk6UDaS ZRq/w/lZXf7AOAGcpbMbRg2cf4jnYL0g042XGIIRFSIiQqBJU9D82qhF27Q+5ArR1gxlSaU9vDJ/ sf5WhXRo5nZiC6lijCarIiwCyGO0RZs0dR4/ZGdamsgUKlSAprIyD1PusSfLOH5/e8Lnu7S8XGFQ BdNoVFRUhhzFjwhuRZWvzvr5SiESiw3jq8xk3sTfhCF9sMD7TYfBmliEYuWRIYN51Mk9o8fJMIg4 H4cx1nW2jYxtzpLVs5ivYvNEEOHk8A9VnoaKl3X8kNpVwR+GiDovZPN1RHrViSsU0yABuRWeXffB XqHaw8JGa67m+gBx/haFDetMTbpT5WhEfKWjO3Y7n69SRklan5Czy1x2ndv3y4LlTZ8bWqIYghZz k6PXa9cNoRaBbgwC6XhJUwZhKqF8Ak/BKJvF86PmgsoKDwSxHWoPQoigrGXYOf2v8QLTf4hrSBY9 cN4EV3mB7MScxhiMBkSYqA9+B5Iy/2uq2n3Uy7XPLOg/ayuiWiTixvPTqOLcpfI9ypkNCSJcSFBI DaonVSsSRlmKNdJJieeZJiWK2yTKqaUQ2zMalLke8hvaMgJ6SUiTC0shFnqYQqXhPVO4YoVIZzhE KCOrXVc2kTlPtesSM5f2IHjBhVMDiKhHGC08sSQMQ1aMiOd0pxM7v6oSGqvWr1M4guGNGARhdpZN WmdBiUZJWOtYaw8a07f07sld39zxyJQvR46K29J14g7BAjcoWSphUSCJ8O6hicjnQx6Dfy6WfTAy G7N0AVlpAWwROLtaVijOn/7ttAEhHZg+gLbLLdEsLBvEHaN40h0B5jVUbfBIcQ4dpfo81dbCHevy 8AxXIMZOU5eRWS1WA4J0KEJY4WiyRyM1VCJKZw8edhjr13nY/tM6VaGx1677oNGx7tAZZMdP5974 Q+KAxk2rfL7wNAGSPMQaB/OW4IXwIUG9AY+JoWp9lSpi/Q/IEsmbmpKOuJ/MHgXwVXyQr1QPKwlf zTIF2Wp1e71ldWr/59NXH/fXfoP/gSvNi9Um+i+UB4jxyIfOh9FOq4/ErYhcwPWZPQ3oEtnod0zC tweDvBqwS56MNRlsVNmNjuxLzi4FswxLkVDd4OJc8rm9ssHqd8xnl0+lKNhR6qiJOF5D8hOeBipi sCrR5/bIRiyFI8tRcIo6BoIwqjMao4b+BpgpB/JIEpk0BcwyRn90WGAYIimHwrPtPoPidXsVI8Em bLTmZq4PUknmdBCUgbZCJkuY1TMQyMLEuTTxtiYrjvULPt276MXZH8Us/mHHSaehYIly1eo1sK17 7Z01xN5pfGz4J23kP/7cd+xcqlK0ZqeuD4j7Z+3PumkiSyOU1JPxO05mt47M8nmOL6B3MqqBX5vQ GNYaGxtj5YzWEjFmhJPHlChZgvFSBtp9JZ3MkAhrg9AjOhMGH2ZCBJZBSBnRLyKmJWNM4SKFosyG grE2s0mMKhgbw5s4xX31whW4+onDNTMvE3krC7wgMYwpulA0J4rRMTFGuM9jipcsjkAqwXk1Wa3X 9FD/SX3vOfz5+D88xcuVRUicAL3JffkySQTO8xfv+3rwrBkxn/24IyFNMceUuL9Bw4J/vTVhdSrC 7UggHadc2fP3GVOzahWk73fKGCUk8iGLwAgghUUFnM0Ie6HT9uzY5+nZ9IWH1y44yNzfakSnKhR1 LkdA/YlK6qn4HacCX6oR5wpnJjtwIE28Uow/hZhVSZQmCdMhiqIXgoTllGPbdqQ+/0z75qtn/3Ge K9eoxxvPF4l0tBHCWo2sDGMwjV4h8aEkQosu8Piw8R2iNox+b/k5UV4+deqjC98ZP2xj+4mbnBRx mmBfgg+dQYYV6U3eA92bMsJBpAWDGLWgirA2wkzgpkxG8ffZc5vP6ztrZsFla/YmOgwFS5Z74OFa ysqXx631WqjjoLnDM+2e/faf5adN9zV/adTzJSiDAxHBIA8rJTV8VWIPHTiuvNg+rvmxpQdTBNe5 42edNAnoRoeCJOHQ7sNy//YvNj/y41nFwJ8/dvoK6XzP9m9+PPZslzenJFq/O8IXq91pUJOoY4u+ 3o4QamLwkM/9MvvrZ9/rPnVW7Lc/bjmZItsqN+l076Zh76xO9fHH4/e6+jRu13R5wspE5t5n4kY9 X1wxOinBQ6iCEQTmRq+YcCKJ7tKoS8ttn26/4IYbP/mKk3iZMX4X7/Xz1fYjF3320vc/0vAJ6x+v jV9DVlXaQ5tKP9q82VNe6ZcZq8NAu1E/4CrzInLGBMmn+WPUgqF0kM5zA12FLPjULRQSbVLjhSB4 SbANApIjLL6INRjmCOx2UUOoEa2txdGAExUeO3Zoss5SE4JKK6kQa0tJJr6VzGOYUIUNHzk6ZbBW 5lApag1gzstspujfrHiR5bkAzgBF6qjBEMhSeZZcZLADMTetbmZCzDCJIgosNSKQmgFjKCJhK5Ys dYS/wIrbyHh4dYiQjiDQ+enMofBsu49WUAgJP848WnMhIyMZEzI2BIHDTYFxh7il4J470l//KjkK xTJh2dDeV/sN7NhzVLsiFiH1YtKhHRt/+MfvJZDOHDqktH7+xSalCtkpx/lDm+cP+ei70zlrrnnG Ms8fktUUWVNpMo42Pzx40fS2xWxk9wGeId/+0hdejcs/DGs37YC6qEcYPELN1WMxFMpIGWD89K9t aXPdoYumty7IGbF/FIP+9eWrsdATEj+La/PRYYT1m7KIUayEsZGRhpvNY3jo5fkLupQ0kcWYJBlf +vaXIRjwSUsGtiL10tZy5e+xF7D1mvJFV9VKE7J/FDSJCd8M6ZXWP65jj1Fti5rFlPMn9mz8fdnu q8SjRPZ0ENEgnVj/Z1K3lo0fmrxlO/HqkX16OH8pIk40LGhmClsQ3PyRr8ZOrTB16LRfO6Se3L32 i4W/VXm1RsQ8Ob4k7USsJdQ9srrGPspgnCI8XvgBQeXxYBODugXFgqXHpg/f+GBQ3KDPf5tocCRu /+mjSd8NnNk5QhUk9NKEvWZet7oj1kTzMY3HjG5Cr3pr8hrECQHCS6umvFf/8wmT3tnTfujKszwm YCi+BBMyxSKeymbBngECBFn9wv2WZZMGVtXYIyGTb3z/fDW0X8pLQ7v3HtUJOKcmnz60/c8vD3vV yAqV5pHD4hateIX2XTmy/tPJ3/ac1BpxkIiK9QJntXhT8vJxkyuMixs++xm44Y980KL/Z0keGDQ0 kpTE78dOLvt2v9fmtmBp8cD0Tq99qy4rfYcWDR7mHdSzycgPBxaQLx/dsnDotEUHMYy0kyoUd/zM If2OdR/Us8e4jrHKpeP7dv31zVFBjR1yrps4ZNzIl3vO+XY4lX56zx+fTPq23+TWZLEvudWJmeww TF87773aI/oMm9aIga3gwPQXXv1ODRoEXw3181WbAnLqxcuXT+/b8sNhv3VZ6w6meKkSrJyyJ/74 TRq5WOXCeg+1SszwLiJSFXtj4A+xIoCE93pALAwNZitZTpFHjdiD4zzSfIntEEYKm4axr4s0nmye VWd99LJZQewudqQQHsVrPuB6Rf+yDGSTK3z/KMkFIwrj5d1uslUkB10RjGa1YEejJgxRLaE1N6GY edSYsZMzdx2RRIFj7KIhgrqxlITiqjVlQyqNLyy0F1txSNgfQcSWz8OUAJbFQqsdwZMNqGYrK/i9 +TkUTpIidh/Z8aKoYzrTaCWNyNMDqWmlsCb3BcddcLeuBgJdrUa9PJX07/0ocLJosAUZUWnhjbox +ui/Ayiy+0IywDgTcX2dxzbQRZ9/99u4q6PbTt7oQhZiAfbIZmy4y20857H8vHxGzFQRvVF5yZz1 G9WElBF/SfbOe2iztkc/69fX8iY35FW/IZN1K2AudeVWbC7Z75xkplTXOctf4uZ2HrAwF+fNraUZ C12BJXsrr+FRefQa8t20LDd41Nw0Ov81BV/PNPqvaaRO6M1BQD63fN5XVx7t0LQYsZBppsSgZ+jm VJmlVDXy4AY+ZAe6h4RYE8MbrHkShb0l2ZUPx3focwN+wogF1zpnlMP1+htQcoDQO7wo2l6zdoWU lfO/DT2F7PbTDH0UlphrnS1vLItmx435eH+jR00+qv5vfsoWLV76v9myYKsyXP3+V5k3JoS0/wZP yncustC74OZQzzK69gdbBy8fPJhsMTsP7j/jwAEEsGIGjxK79mJvZ04SwIEwMRhmeR4Hm6m2uaxe aJVCOKfgtRGwAVENXcrrTxbIG+D9wtyaOS9CRUhckBU7eCOk5lIRTnMjHcrDRpq15Fzy5rMJ+Wpv fj/2Hf1p/ufrk3Cs3J1EFTmjFqbY28maet13MAK6XTejc26shfAO7nRCGomwyGYbdP4p/++ZibSo xuz1CMRA4NBPY7X2r7auTqvxYviphrQitIQSD3/7wfK/EXwgiZTmEyOp/p9kXWc04lCNrKlw4qAk Gu62wMekL0Ly5vBT8cH5o5ERoeSsZORQlP5xGDjoC/3REcgRAV2OZsBzV8nRHLlCT8wNAXKuRsDc qx2iof/UMPvvoZEbL+jpOgK6HNXlqD4KdAR0BHQEdASuHQHd4n/t2Ok5dQR0BHQEdAR0BHQ5ett4 ADdCBm4xyIkGc7nGr8z6ct2WP7f9/uWcEY3L43imSA+CS7F3k3202wAAIABJREFUW03BBR0OHOkT 6auwd3ksOddyDA3e3LBjcf+KhJdk3uVwOJxucgtZ9g9T9qluA9rW8J8Sn/13gRScpuvIfGOkPw17 bRzu7A+AyL3sW/QF9qXcAjrJwc45Ih+ptdjRgQOZHeoRReSYXE9+9m2G1ph9G2Wvy6HeuZmPR8bR fW4nCHM4XeS2o3y3Kx916Z/qCFwXAnmTo7KMo2jUW1vJgy12bl/w/1KQwbG/GeyOve+4CjbTcXTB JGwp8A90BSGjuPaZlINLesOPmL2uJv2XMtNR9V6dOaZdiaOLx45+e8nR4m3HzHrl0ZhIMbbkHAds 0lAfck1J1iMawnHJe8n5wZMcRgfqtIO8ss/Ilm3YpV+bhwrmjfu0BunBktnjGUjBRh1cApA/cUVu g8blktgrT/y9OAUuy+H9OdWbxxoRBo3j5SLxbXaF40RFD24xw1WgFnIvHxqGn9l9rL/XEbi9COQW iobbQ3AgiXorSXDSU+NxtAMTSYy99h53y/jIwbB4T87hxKWa5CJDdeTgAg9cp4UDfsgGAty1rrYY khUvcao7h8PqRHxP4STU/Ay024vbramdKdm8W4sSpz/vPnHJIWgL207bK37RvWvzRduXnsthTqGx /yTbLY9+wq+t5NxaTY6mxT19Jhm3Ogqy4boOeQitixw8n1vdevo1IkCGM7nhTh3HeWCda6mGnCjj v+smb9nJkbW4gRJzCCEKoh2HNYK5AqfY5q0Q/SsdgVuEQG5ylMg9Bqe9apcRq0Sp+zHJ+VChUg9i lHyp7bWD6iDzMoxtZIkLXRY7LDgucBKIPxexQeLSerJRjjYosle9b+S6djPeIsQ0DMh5mTgnWr0j BQdX4QA57SwwcqyMDDEmQCcHIEDJiBvr/e3Cua/YZa9eEojXHHBkS7Se8dnrJX4e2HPuHvXANlvN l5bMbXZmQre4bxJ5JaryA2XFE8vXHVGNtLJ7z89rj3fr/NB91PwjDvXELa1e9bBZoot6HQ7BbMeZ XLgItUK3uYtJyd1nbk8lx0Zbag7+Yn7Ly9MGvbrivETba9WtwP/z1ZqDbg8MAjIVv3LNkS496j0c 9dWKNNzxgiMtfcROTG4t43DrduZ9pqYKLV56o/8z1Ysyl/b/Ou8P/xQpE23UYC37VN9u/6tX64Gq ZQtyrov/bFn58czPN5x0EFioWm+tmvp8LIv2M+YBP+7sjStbKebwh62HLVPPjaOL1OrSs12TJx68 t4id8eddui3Zh4OSFP/t2DjwAQd04aY5giJORA3rdpJGGkt6BXeCk+M5tXQZWhdJIFwXnqRd6CaS +yWgx+NwdSz/wsrUfpBjJtQC1GoJJOqqj9z+xePuawqnloIi9AkOE8zmFFYydMhx4v4PQxgjYuHa /QDqiZBkLUq6mDHbbephUThB3cXTOIIw5OgocpUcOTNYcjlE9ZQ7cqJxJJpDWkfKUa0YHgcO64my crDremncI8JIXrdbZMntBGozcSsCOZzcFrY0ylyjWnDENpJLg0SDlj1PgPtle5BUsgNJt1mF9Jz+ 5x2FQG5yFEIUMxVO4g6hWl3AZm5FuPdCZXtVMOIuJ8xqWc8YJecz4wZrqC84iJjMezdsM2Nmym78 b9wpgjNrIQotOOGE2MVgTWMwp/lBwUHdMoeTT9Vjq8n5yAy51ELB0eReclQNDlzFVILTzIlKeX75 +Pcf+WL02CG7uk3d6YiqO2xsu6i1b7z+zSmRhYyscF8Fo5Bw9KhbZGKjTV7ec+ZUglu5p0J5m+WI SLMWiDeTOmPGxGJO81JmcpGaIqTjb5w1REp+6/V+f3aYupsq8uQbU7oU+POt/l+d8FqsBkPJcmUM 8rFTJ9w8G10oBqfjX0xK9PDlSpVgqDRydScPtZKcDEsO3vbi+HL/fKpiScc8/vKssY0dP89+7Zck 00PtBg+uE0WfVu39OJOWM5SofB97+KeZK+a5BS6m/FM9BkyfZejWasYeAsvfc3t3/5yiqsfNG1Vp 7cg3f0qAJxdXbzs09pGlwuUrMcd+nrPqdHKaHK3lNffrOndnoBPJsag4uhYy0qIejY9DxYOWEnLV i0fEaacWQjh6BYeUatfUkEt8yS1ZZmTCdc1YJKBJ6k0jWNq4fegtc0DsoLdsGSdQB6qF+AMkao+T awB8XlyajvMPtQ4nyyOiMZtwRjtOcPB4WL+0y8x5sL37UBXuxg5lDBzsHrFwchu2QBwkRFPU7u0h VxWT+0fVu7sZTcQFK+FMNivtcQuMFZeBIUs2xYaNXJwmbKO9Lp/KOaHrYpxwajaIHq9PQs+TU9pF nECb2b6QpUbQkk0bg1TmEXDcGBkyNeFMdXKJyjWfJ5S5I/TfOgI3FoHc5Gg2tcEq61avwsD9muqa X5WCsixINKyz5LaCQEaivZK5S+LVG+UYhtwrDjFLzLxQEgRRPVoNu9j/RUZdKJqYN6GCqnMSy8ii C3dUBaHCdSjk4ks1ySQJbtX5i+35OLg1oEHAnk1BowBK8uU/J49/+MsPXh+x/dVNT73eil754ri1 lxjMawbaEF2woNV0zO2JbTzj1wl14t9uNvSqi7IUKRJrhH7/xKg1U5/kBOgoRCtBbJGHwkGwBsX5 24v1X1sjqCW/XW3ehDff3Dd2R+NR7Qxrh8/Ymoq7tXjRYLLiLi0oLr6SbecuH/3Qnont33DgJB2L FbdbqLe/wzirXhiNs4hpOjxoiCn0bOdni55cOnziD4ehJ+86xJf9ZloTVYzidjgzJ8Z/+uouHBKL 6xVwfu+++CulGixo9HSlmbv/MVjNivPSJSdluFeACSLtwrkLF3FWt5dGE0hlsujd8dnIA0GZ7c/7 VKX5O7dr6Moij2OYcLC/NqXD3ufXxJFMblfBVRuBe5mh/IIGn2CEuCMrOnKMvioqoDHi0jliFSCM SQSSkVyaQVJgHYnkhIMcEeCqs+FiALXD8bHTA3OEQb3zC6tKIkS1ss1G0ekDfhHPEgRjgIhMjAHX XzaFkxuDiK0A4pocrY67BEhQD3whfqoz683aYW/+FWnONGtokv9qJ3iRrKFilCRAknIuNNNgUnDc P45fz+orCKtRKzNiG0OKzhPgGeQRfMlSR8JtDhEICPtQ/6EjcLsQuAY5SuPAUXX+wAXVcIhBnHKY G7B65uBJxV1VqlDFyNEECxGeMPXQDAxhuCkIZk3c9YS1L5GsCo0lJqQwZgdYBOE+/ZfIUlybYFXt iTgUCJcfETti6DV+mPACi36sNLT5CdMHhEyIGQ6ra1Y76kZJ2zxrzNfV505c8D/m/FcDZ2xIwc2I GcoBNDxWdKamI3SRLF0QQqTNSsL+L0YM/llw84zVjqtBJa/DoxCRqoiXDvqtB8rVDTPGLFu0ZMqC lig5btZfaTiBnUJQV3CVw1G8w+VxprtxA0xgIqXJVadQuXwUjg3E5U0wVIZxJ1uxWhXuytr44/6I YNfu7YeEJkUJDLgtF5MtW6h2x97dn65WvlSxorEW2HA5Nq1gAaygMiZ+Ys1XCyUXX1DE0olmkWtY DcUadB/Ur0XdqqUL2KBtk7zOgrFBHYrIESbEbIrsuMpJLYnc7wjPMKyZquMBD1HoyEm5BliRrap/ FUnoL6I3+730ZDmHm6S85CIynAhIbMFa3rD/EjUQdpkMTQ63sfhhVFsRekW7imLGmiqsnEiMQZaY 2RTOIVqMWLApjoEYxcqNEzyqZZoiWYg0z+HJvtiMQIccspMkct8NJKkburshz0IsYhtDKsoT4Bnf q6YfEVaXLMpwLsTryToCtxCBa5CjfjFJlEjVD6r6+4jAwD11uOmSeAwp2QcdRpWK6kRDLiYkvzAp Q+xAMUX4khZ5pHpfcAC0KMiYhiPc1HgLsch7VaobTj3MnFyalXk+y7K0JwUT7SdsmRD6y/33L+tO dulb6fi6X/52Equ5X/ji5mmFjYoxp3z7VrNn4HT1mJ6JMijYQoCaFefF48eSiTUX7iwOV6UF5Ci2 nqiqlio2XH//uv5U/6qVUfIB4oAFvbDSK7Jasj3anPrnqOZ/kvfRTe0cSnajZCz9rbi0CGoAsRVA 9Q51NCLZardQjjS/KRZfeNPSfUohcr00vHgOqtrAsVN7WP5aMHv21kQXYzHf2/aD9xqT/s+s8ah4 Y2FAtC4iLASBfeClj+b1t/+1YM4rW0+meGS6HPL+LyOAVBWRTKhTQXUHqMsC4l8nN86Qi2gzHn+d 5EZSVEJ4k3SYJsPJV7gTykLhLF1yJxQBR3Wqhlk4VRgJcBmZgjCqMOfdIxHJdZFT4eQqW+KmxjoU V3vjWi+ZIKXg2D+sGLK6SkLbnVOxYQDl+EO9vk0UyGIntPU55YnUxtDv8wJ4xvdwmpBpIdwtm1P1 epqOwO1A4FrkaCY6w0aYOt0oCBqCsUuVL2TSkzIW6NqMBA9P1sZGeJX1ozvhjaL6D8k9odhdguaS GJDwiz8iUElgCShKarI206l/mqv0Gt2l1NE9R8t0Gd17fecP9/n81vBzp5IEtmzp0nBaqijTpUqX YsSkxPOQHMb6r6z8sBELB6eFePqy2nXJDG+p0mtUp5L+krf0/fiwi6xzYHknJTOl7ynDUMdU3JnS ZUozUkKiFgdMLra0GokdATpiiDdRpVaG+qqYLeZgv7O48hQx2bAuICjTUK1lmwekDa9N+mpTKhyZ Jlt0UcqS0yRMzv8m0TASI9KVm7ao5PjttVGLtuEMeDxc4fC86iSNVQDoVdPVx883hPOwfUP1emZ6 sBEROg1cgf4IckS9aKfXke8gJMycgZgWcO03cXUrdIarWy1I5WnVKxFsB+m83CRGZioi/86xcCh3 NAmpYqGFQ26SuFUPcY3C7p7LkjPHYiNTEuEtnMzEUIF/BEPQ/R/hu3y9yh3w0OJgxoB7JF8V6B/r CNxqBLJOOrlRgJgjjGoIENWuC3npj4mEcxRuQ0hIYrzFX6y2qocdh5VkrCrhACVGNXiq8BECWTE6 JVmA5Y5WENCOaSlnO1VuZN3CdDX2w+QP2ES9agxIVudRGEXE3IVoCUHh/BGWCoyYEBSYm621B43p W3r35K5v7nhkypcjxw77q+vk3aqhU3Hu3vYPX7fuE1VMR04DWa5ywwYlPft/3kV0QWH/50P6fM+L iNokF35GsOvS1rqDx/UruXNq/wn76qPk0YPj+0xY7wDQjFqyGFe/YeWlx0gwMCn5Hungl6RkGSGl Em4JRr+iFw2s5uLNkF3iiQOHxRb3VSnC/E3kOfI+UIkRLiHEyABbNTKaGR5ByxwspYJXoKvUf7hI 5nmQOIspk0mzocJwzZBbgmmZhIcqnnRHIKjNUDVzXtVlaKzedXTrSq6di6evToAA9gtVcnE6nL9Q bP1dAZOgB7Zpq5klhmzWEtiGRTg04M0mu27hYYbVkuiiBhNsy27CjOEPEWe4P102BXRAUY2oIoaI zJ/mnw1zKJyYpjlYvXkKTg+iEZKbu3APDS52AcE5V5VjsTlnDaTKCJpSOCyoJMR0+0Qua/hV3soJ /SpvgAdzkNuq8z9F5Z8sPYeOwHUhkMd70yAy1S0QZEIkcSj4SXYKwJYLX6k2S8JUK2KvC9FE4WmC bcw/0GkiIDFz4XuSxMGFRVKCklgrBzsrbtaqM0wLJGDl4IaNbHvMhDAEP9YFCjHokqgdGAwhTojj EpNx5vvIiGFKvZ8M6wVsCyGhOMQQSezCRAYxxmKNRs4aXmHn+JGz9jrTj+65WKnDsA4lDqxYd8JN FIH0hPOxDVu3e7oi5ZKL1+s2vPuD3pVT31mZxKNmx4WEk0nnLl65fPHCmbPnkhJPnky6cOHC+bMX oAdCvKolv1Jp+9vDp+1KSz+292KFNgOfL3zgly0XsB0JIvrUpYJPt3nh6XuldLH4oz1H9qnp/mnK +FUXFHQD7sCEx1IlFKFgPDazcCYSVEXiNrFLgk92lmzeo0mFy7t3nHAVqN1z1OBHC8kXdyxfdTAd ORxspRbtnyh0ftvO4+mGMk/HjRvwcKxFOvbzkj/OQCj7mUIoXLNt04cKpJw85zPFxFrE1BQn7ijj BOt9z6l5dxx3mCs8+9K43jWizErC6i/XHPNBBSPuWoBvqtH37V6NS15ag900HtBJHPSqLxXhsghc A1eStQ25u14h4VIq3gAeHUZWeWqHEW0S1OANIqexjCNthUIqEPkO026mUyzgMUaXEzc4KUuCjRje fGjkpDXoVIk2aHFKhE9QPk418IeghTBOtoyRU+FgAZJPguNZtTaDIwjrkaCpyPfTkdYQtRW2b9z/ lh3N4fysUexvAYKRQT7xBcuCxyOyJIAKwx6veZlcb55FemfUmAPzq63AtXpkS1FeAA8SSILhyX2s N2tuyDSy9Z86AteGQN7kKGQhGU1qFURJISHo5P9kIgrUq36jvSQxnqHkIEnLAmkSzAAFIGI519aO HHLdeDmqzlFQLlVpQy7d5DDPQDHisNE2072eQTkK2AAOJmHyJYkssZgRPVKs2buz+hZdP374wn+I 91Jxn4g/U6bdoJ4PnP3tt0MpPlH0nInfdblIvSadOrZ65gHu8HfT356/PRlBlFrVMKQGtitADoik bMSjwMjLS8Wbvzerb5H1E1/97KgHM6Uv9Z9tiaXbDepTO2X9uhPwwVK+xM0bT8fUbdalU6tnqptO LJ/++vu/n5OIRCAhLLARaJRCdgSjUVEukSCcfC5+2/kSz/YZ/MqQbk0rXl3xU0LF6vZDv6zal4o2 CKd373dU+F//l4cM6d28pungwoX/VHmmavLKUDmqOI4eulikTuvu3Xt2e6FTm0oXfli5N502mpmz e/x5B/dqUTfqyKef/F3+6apX1gTlKGEaU8Wne7a8z7tu8ay1iZJqUsYMTSS0hjAIJwgTSyhOwtHW bFoQE0CDSMKaAPti0A9E/uEhnUKykDWO2tZIuz+J8ZmISPUzBVtrrDBzqjx+/XJUvdkycuEYbUSC Q8dW1zFk8JE9utmKUVCEtoBEworYDJttsaHDJaIcpSFFBTjKtb01GKmKgJAHuEszSdKwGrNn/qAc hdafJ8ADBGIPGS9zWAzlMMD1JB2B242Aft9LRg8Qn1f4AuB29054/erme9ZmzznC5M6iOU/UIDxI 3eVvNWZRd7LmZ0p1nbP8JW5u5wELE/JzEGzWkvQ3OgI6AjoCNwIBfZ13I1DUy7h2BEiULwytMGXk QYhCI7PXrF0xZfWn357Uhei1g67n1BHQEbiBCOj6aAaYuj56Axkrj0UhPMotEIssjoDIJVQrjyXq n+kI6AjoCNxaBPRguFuL9/XUhq13di5j78X1FJVDXrbKC6+3q44z7jI94uFlU777O9f9PZmz5fIb ZxPhSAsSXJrLh3qyjoCOgI7AHYqAro9mdMydro/eoSykk6UjoCOgI3BXI6D7R+/q7tcbryOgI6Aj oCNwnQjocvQ6AdSz6wjoCOgI6Ajc1QjocvRu7n6m7FPdBrStEXsznJN0wXZz1u+Y3jQ63wDfTKry TYyeQUdAR0BHIBcEdDmaC0D/6WS2bMMu/do8VPCmcIGUdv7UyYuO/G9PualU/af7U2+cjoCOwO1A QI/XvR2o3w11Kmlrx/dceze0VG+jjoCOwN2NgB6vm9H/ty1el4mp3qbPgPaPP1S2AOe8eGTX74s+ WrhBu3mFYorU6TL8pZaPVS5q4pOP/rVi5rQvd1xWLwqjmDLd5v4Yd+mDt07WHfj8o+WifEnbPps4 +dM96YHD05nCdbq8PKjlY1WKWRXXpdOHN38xffLKRKIgGuqPW/tuq5hwPZTfNbHF0GWX/LnZir2W Lu14fNTgzQ/G9W3yYGmrcOXEincGzNnqpthSj/Xv3/bJWpXuKWJnXBf/2bLy45lLtyUHNE/jE1PW T26qXvLi2zC+8bDf0jMwzpHm3KnKvkV5Gca3Hue8UKV/oyOgI/AvR0DXR293B+K+l8Efze4au/+r RaPfT3RYStR6psWjlVhNjhqr9vhoRq8CuxZPHr4nNbZm5yH9PprB9er16T/BfZymR3t3SBo/ssc4 vlyHcVMGjeuxu+3MveqFKUyRZmM+6Fth5yfjh+y9TMeWub9Og+IFaCqRpAm7PuzYdj5jrDN84ehy ywe9/H0SEYJ8ytXw+0toY40XR9+z87v3Bk87LxSq3riyokpeunilivLBn+b8mJicJkeXf6rHgOmz zP26LvDvLuW3T2nbZiZToMn4jwdERDc7mnOjKqcWcZYYmzHrqY4KDlNMx/1t6r06tx7niM3XX+oI 6Aj8txDQ5eht7k+mVIuXOpZPWtx/8OzDPkLL3l0bV5Mbm8ljqtehXRXnqmFvLtpIrqfes99Z7Kfp 7To98tWYTV4/3crFn2cu3HgKt4elLFm6pevUWnXKMHsTSHa2fNX7LRdWLl669m8iJPfs2LTCnwf/ 8GkXLqZRhgpuWeGdyecunI3sxjQWSFrWe/LPyaS806eO79EKEOM/HREfLGtf/JVSDRY0eqrSor8P aqX4Us9fTKWFNG82t4plS3MuVOXQInIbK2KasgRMKc5VQxu9s4GnbhPOGYjrf+kI6Aj8VxHAXV// 1ab52xVZQNwxjbbXqF2VO7l49VFViGqP7L9lmi1TrWoUf2DnbiJEyePas/NvvmnVamXYTcf87RJO HU6AECWPkJKSTlWPJdZaIvekM8dOCC1bDBl88ZsN8QePJpx3+b/Tvs7Tf4V96zZd0mR66Pdsodod +/RpUbdq6QI29cYyjnUWzHvUb/Y050xUDi3CbazDBq7y3+0aUooiXj6iaud3Ns45t1tP1RHQEbij EdD10dvbPYw9JpqT066mRlLdaKvdRvPprgwRy7vSfbTNrvoetUcR/EJX/UkuiQ2kyedWjBpqjuvZ tOfYtiOttDtp25IJEz7eGbGm7ECAaHZlocxQrf8Hc7pb/low55WtJ1M8Ml2u7Qfv/e//7V0HXBTH /t/Z3bujg1JEFCsW7KjYNdZYo8beYklie/bkvfhPMzEmavKeXeOLBjUmz5LErrGgsWCl2xBFQelN 6hXubnfnP3sF7rgK3AHqzMdPcuyU32++M7vf+f2mVWBEZlpnU3qon5upERRnPX2cb9yvy1egluNs vt44FiOAEajVCGAerdnm4cSFhQxZ37MOSeQaWM5QKpZAoZuLCNmaajWFzm4iKBHLDLjNaC24nIhD 30QcIignv/aDPvx0+bzV70eO2RipKctoFv2HkL97vXygAgYPbVZ89pMv9tyWqeJoL0KH2Msnt+nf Jmtkya9bu3G2KUa4MIwARqCaEcA8Ws2Alxcnjo2KY5YMHtZyb8Ij7ZwnRVEsb2WyqQ/ji4W9gru4 XrhazGd06dKtg1B8K061Ksj6wErTY8/8fHz46GW+vg6lnIzyQ3QxNSESIZ6uQABCkQDKioq1dCwI 7NXV25Y7UK3QyqBGFv26NYozarmgmR+NbC6J2Lf5PL7wrQKdDSfFCLwKCGAereFW4tLP7Dg0asfM 77eL9h0KSyoW+XYcNsb7wpLvriCeKrlz+FjC2zM/W5ftejCmoE7Q1EXDXBP2H7qjJVyzugv7rvh5 HHfpcmxCWgH06TxlRlvm/vZ7Ut083POEJHbsoOmjw3+NzVfCktyUrCKLFM0k3A4vmDxk0siT359O ppoOXvDFGB8FLMsmcvfxdCYB8HB3AIBy9/XzdSWgUpyXXWSlIWxSKzM1ggXPo8Kfm8GjRnEmgNC/ 58gR3V9KT245n2RGSxyFEcAIvIIIYB6t6UaD0qhtS+elo/2js1ZP9KDEmU8iQ39+oqEledyeJcuV aA/oyg3vieQ5T26GLNv060OdJUlmtGdT4uLgu2MWDvPzdCbEGY9u7F6y5UiyHk1ymae2/dDm4w+W bxrhKqSUUbr7R02XLA3b+OmGlR8t+vXsF0RRcvSFkHV/zF47TpueDlocsnOCp9ZAXfrHmaVo3VPK /gVjNz2wbqGTSa2sqJFprWsSZ4L09atPcfkxUU8tDlNM1wDHYAQwArUTAdChU4/aqZmttGLZ8lN8 FGXcC1lj5zDYqqq4nFqKANlgxo8nFtM7p80PScREWksbCauFEag0AsYZpdLF4YwYAYxAeQSAS1CX gPzze//AU6PlocF/YwReBwSwPVrWitgefR16NK4DRgAjgBGoXgSwPVq9eGNpGAGMAEYAI/B6IYB5 9PVqT1wbjABGACOAEaheBDCPVi/eWBpGACOAEcAIvF4IYB59vdoT1wYjgBHACGAEqhcBvH+0evE2 Lo1sPGD6sLr3Dh+9W4HTb0HdCTuOftlTyBcpv7JywGfn1Mf0GRdh+NS3FdWvOWhcH9RzIlJvMluj jJwBaJhL84QGnXpSQ1oBTwHxMp0LvcbG5ptMiyMwAhgBjMDrjAC2R2tD61KN+0+fO65T3Qq1Biz4 68vJI0aOf2/nfSsPCtKvauOWZAs3Ij0Z5lt3Wq9u7tb9qGntiPRo9teLbLoLOW001RodOIgDRgAj gBF4AxHA9uir2+ic9GWWlCCZwkrRKBFxWnkHEsCVXNCSqtAJu8CNHNgaZMcwh6MhOqHocSGoPwk9 4R7Hop1DOGAEMAIYgTcMAXvxKGSVCgYIRLTGxIKcUqFk0XcWfbkFIhHNX+7FKeUKVvXlBZRAiO6x fMOwR9UV9Fod+sNY/sZQFOYfi5zP/18RqXM+H+kdPH3F4tF9WvqIFNlPrp/ctul/4bnlT2iqFHBc ZUnP0Q/4k/B6Ik+iKDC5XFwB2c8fOMZCvdN7K6UVzoQRwAhgBF4xBGzPo5BjGSWDvvQcpDRgQE4h VxACkYMOVUJWIWcpxKjovkyOkSNGdRC9eUyqjNw4ZfwuUhi8IuTLJicWfXREdZOLIj9Pw3HCwFlb t8ypE7lv3YqYAo+gaUvnbt1Cz5mz95HCUj+jHd2dhcbv4yySVc6A1YqsWwfQkMgpQuMfQkQTciXM KSQod4Dc0lKbMLyluuF4jABGACNQixCwPY+iypECkQAk5+qnAAAgAElEQVQwJdrj1JFtypHC8izJ QUBpLp0m0Ym3SmQevXk8SigKM7MKCUFzKQcV4uz0zDS941dFPSZPaCU+t/yzPdfECNeYe+J6xzdP mNr94KowC1e+WLqPsypd0AF5gTkoU4LgkfSk+tzhg6wM0bqw2i4hrYruOC9GACOAEbA1ArbnUYBY EWlZ5jSELANJITI79QKgKKBgWFpIAcgxLKQFFVpkY2scamV5lH/bQFfFg4honkT5IImJuK8YHtjW nwpLMH/eucX7OKtcYeSilyvQVaGEHNugVQYTF4ARwAi8wgjYnkcNwIDI8iQhIy9Bc6EQAJoW0rzh SdICSl4ikyHfI7JERQ6YRg2QA04uzkBRJCm7J00hKZIDZxdHi1PJUJz19HG+cb9uZedFtfrxjgYS OAmI8AvMPdXDYLT5RkHIqlqwAQD4AUYAI4ARqP0IVAePQjQBigxPkYifClWiqVCApkIJRq7gKAdH 1UP0W84AB+2ipNoPW/VoCKViCRS6uSA/qmZGU+jsJoISsWXGsqdfNy8fMgB4uxGEesMqCbzdCbYQ 5mHDtHr6BZaCEcAI1CoEqoFHkVFEUgJK7dglBTQlQ25ckuCdvfwiIxRI5N1l5CxHk2+oUYrco0pC JCq/+4RNfRhfLOwV3MX1wtViHiiXLt06CMW34lSrkTQBlkhlHHBxdwG6BqGN/Lp+zUh/ByL5GZeh c3e4LB2mcGRgM3A+i1+yS3uRbTyI5AdQ/xgIl6CZH41sLonYt/k8vi6srLnwL4wARuC1Q4Cq59vQ PpVCNihBqYgSsiykVL5cVWAZjqQp9BDoPISIW3X+tKFK0GBTo2Z1kzEZwNATaiyZzZ8x9XtMHtHe Oftpmlzk7uHAFkvkvJOUycx2emvi+CFt6IJC0qfjyBUfjW+afui7HeE5OkTKyL36jB/RySM3pVBQ 18uZyS+QIcOwpCAjLT3V4F9aRoF2hZKTJ2jdgPT1Aq2bApEMFgHg40aIC7SmLxIPQPdh9Ni2oCCe S9Jd1ySHxa5kn3akJ0uwrmBQP6o5wx29yuWq98GowQEu3RasnjPQN/fioVsZ2FC1eY/BBWIEMAK1 BoFq4FFETaySQaTJcyrHKBiCFqDfkFGyaLJUTbRK/rfWZrUtOK8Cj0Jx4tN8n6CRU6fPfm/S1HEB GcfOPVRtxWRzYq89YJv2HTl12riR3f0kEYe++eqXmCK9iUhY+ORujk+fd6fPnv7u+HeaZ5w490Bs zUylX2d6bj+yU1PgCggnL7JjC7KDH/HoHiw7mhCAZu3IFk5Ewn19HiWI3FSYKySDOpA9A0jBS+7E BfaBdi2UpvWopgM+GN+eu/7bzksvdGxZ27YtLg0jgBHACNQ8Ana7xxvy+16EmilP/lQGJYOOYEA2 Di3UuHPRDlL+aAYeA4A8u+ipXeBg2fLWENplY1QSvsfbKCyVekg2mPHjicX0zmnzQxLNryyuVPE4 E0YAI4ARqDUI2G1+FNAOZSeuovOKRJSgXKUBhfaU1hogsCK2RAC4BHUJyD//1R94atSWsOKyMAIY gdqIgN3s0VpTWWyP1pqmwIpgBDACGIHXEAHjHs7XsKK4ShgBjABGACOAEbADAphH7QAqLhIjgBHA CGAE3hgEMI++MU2NK4oRwAhgBDACdkAA86gdQMVFYgQwAhgBjMAbg4Dd1uu+MQjWdEXJxgOmD6t7 7/DRu2UbP3V1AnUn7Dj6ieL7wcvPopvOak8QNhn6z/+bObBtgzrS0wtH/Sdce5ebgJw1lwIXlfuS tD+eVJ/SLu3oL/vBP0LYSIM9r6QH2b8F8fwBl6h/blNVlatsfUkX0L0DGdQE+LoDIQvTk+GlW+zD Qh11aNCpJzWkFfAUEC/TudBrbGx+VZXV5LdCZ9KNHDWQ7OoHnNARoAnsF+e40lM6Kock3zQDgPp7 df+8cp9hr7BCK1P1921F9WsOGtcH9ZyI1JvM1ihYfrOcqZzoeY3irNGLApPfpxvEMpsj9DQ305/N VMhCVOVwhk3/lTFhOGd4MrjsnNePPzjYc3OcIPjj0ztGuRSk37+4Z+3GS8m658VYqKu10dgetRap 2pqOatx/+txxndDlnyYCW5jxPCmr2J4d1YRkc4+d3lrw0YTmKftWvD921q67VbsQ1ZycisVxJTAr 3/iB+2QdMKAb2bRsM1fFSrZ5amFDclQgkKRw56+wx9B3vwE5exzV3qlMTut+1LR2RHo0++tFNt2F nDaaal2Nygf2oPp6wAtnmC2HmW23ON3eVzkkJY+Z9b8w3/3BvqgAxVmLeuOWZAs3Ao1F8q05wUS/ 1JrF2XwNzfRn8xlfq1jlvd2zJnywbG9ys0n/nNur/OmrNqkqtkdtAmONF2Jw+GGpRrAwdM3s0BpX sJwCVL0mjRwVMeePRNrYvKtaRaVP2Y1Pq1ZEdeVWpnD/2Q/ztSOQ2JfEylFk3xbcg7t8XwBu5MDW IDuGORzNn4H8uBDUn4SecI9jTfcUG2oOgJc7ocyAt1/w0m0SoJLIV0IAgT3GXBGnlXfQMTGu5IKW VIW+szWMsyVka1F/Bkkb/P6zER3FAwM+zRg7kFNc9tyx1hGNr1CHrPjgxVLF9ePlRZnJRZlZZ6MX 92rSxJu6lmpzowLzaMVaxA6pSe/g6SsWj+7T0kekyH5y/eS2Tf8Lz1WPucmW8/cemJa6e1dJ3xn9 WnowWfdDf1q/43Siyuko6LU69Iex7mo7dMHxyAX8Q0Xkd6OW/Z6j6pjCfusvrxvuxHtS5FfXDFp+ VnXWfWkwJ9f/vZ3HFuZs+Dyp24IxPZu4ylNu//Ldur1lBxKSXsHTP1o0uk+rek5QkpMcf+O3zetO v6hI76SFAkIhk1ufBYD+E+meUi6nLtlcAK9d4wSdqJ5e8EUEuzcS8oAA0LYb2bspaOABHACRn82F R3BXkjVurrpt6eVvEXeOM2fSVQAIwTsT6OBidstp7qUKrHZDBbNb8gduESx3UN+v23qw4MNAVRRB jJghGKH6kXCF+em+lpMEIKgbOaAl6eNElOTDqHD27FMd/gBg8BS6/0t25wswsivZBN2NI4V3/mZO J6sKshiAa0C/t1q5FcVfCXtWXPbFYSVQ102ryIO5kHB15vVEiRz9gD8Jrydq1GByubgCsp8/cIyF qgMn7RWAO7lkBtVY3Sl9qe9b8ietKLV+XYtIks6gf2+qRxPgThOFOdzt2+yVFMJm9qcJJJGGXGW/ 5DWFM9JZUJd8pz8Z5AtIMQwP58odaWOmP6O8wBkMQDg3Bh5CokQCU19wx69w2SoQSC9yxWQqN5xV NCPbewK2GEZHsKfj0TDG6mACZ47vmPw/NdjoGjBWv21dpOOP5DWnqbsbPeS9i9p0YhwJUPCX5y/b RUwdyaRD+U1oOmpZvUsPANXn5ZLVMmGJ07GxdRPUigmY5tMLewyW+/hAWEhn3HG+tdcl+aWeyuha MSUhENqF8uxSqNWA44SEMHDW1i1z6kTuW7cipsAjaNrSuVu30HPm7H2k0IADXN96b8hvK+e+G1Pi /86na7/eSudP/fcN9EFVRm6cMn4XKQxeEfJlkxOLPjqiugVGkZ+n/SYo7qyfMG4bWWfYmp/mGyBt US4h6vn+5JQ1K2etVjSZvHr9otWzosdvi1V1WtJ7xKoNHzaP+HnN0thc4OHfJri3bx1AvODjaEd3 Z6Hhaf+QU0iLZIbvouH3i4FXL7BENjqkX/tDR/e6HsTFK2x2T2rQUDLyb+Y3d2p6VzLwHhuL0AKE X13iRRx3sxBKOeDbjBw2khIdZc5m8fnz4pgjDempA6mEP9gncqJVb6qPA3fgpIZEUYLH15jvbhHO Lakl3XTkqX4+vcF8F07QDcnlA8Htk+yNAv6hQqYlURL0HkmP9YHoo38yD9ZtQo0cSgmVzNEXesNs 2pec6gFvXGeOFxKuvqRfqRCz9eVTkfX6/uOruQFPfpp445lp77zQC9QDxNNsjVZ16wAaEjloRhwQ IpqQK2FOIUG5A+T+l1adl0zrDIu5vb9CASB6jKD7FrEbwyBvcSg1dG4BSQoMfoce7AAvXmGelYDm Hclho2j6CHMBdQZrgmmtNLmtQ9IaUaVpagpnNFR8dzTVSc6dOcvm0KB3D6qliMjRUd1Mf0YjzuCB 9NC63PnLbKKUcHYHLRsR6LooNY/yZQCiXWfy8jn2m3ToE0jNGkShO7qOlPZne+PMtVmcRzFUzlNB cR2mrreRKdXyTUSybT7LGdmPBQrqZSJN+igbjyho2I75c5HHC0n5tPb5G/OofXC1tlRRj8kTWonP Lf90zzW+xWPuiesd3zxhaveDq8I0N6wALv3E5pAbqYiDHv2x4cDQowumDQq5eRxZUYrCzKxCQtBc ykFFcVZ6Zlp5405ekJFVAJSFJYZsZVkuAbNObfv52nNUaP7+AzdnfN852J+MTeQ/wlTTwDaOmaf3 HQi9z4uMCQ87qa2vtfeeAgcnB4K/Lc4gQPj8qWbAqv1RlqYwmYtOhvX8yN4uMPoxfOrG5QSRPq4E gUaeHAw9W4oATEyDno3oDs35y914nSFx7yrbYhI9sS8MSQIT2xARZ9h7OmfrK2UwX0Yoda+10Ypl VFG0jLdapMUwT3+5lkNTcmhDIvYsc/SZijhTGeghGNeZvJjMFergTjsSYUfZOyqJ2QXss9I6ma2v ATomHgjAwO6kKJf9O0lD3g7IO8lBmRIEj6Qn1ecOH2RlaKghJCzfAG9Cgt5jMzpzRDG6RgEAKYvo k8gv0vPrmkdS0Ijs7QWjzjAXkpA0+CwTesyge3cEl0OtM4bMaGVNpSqVpqZwdg2gOrvAK2fYGzx5 wmQWfDpCb4WEmf5MkIS/D5Efz115qno10uHDR+Urnx/HXlD55JPvc5db0CM7kudfcBp/lp1xBhA+ czv4f25p/LsC3fz05tbL66n6m2pf3LcfS0hEoQu9YtIA4agY8GN2cCNJj0GuySepspdQoVAQjo52 WSSAedRoy1TXQ8q/baCr4n5ElHbYJImOuKcYHtjGnwpLUJMCVCTce6zhGy47Pi5bMKxNM/r4SyMU ZL3WWrnRpXJjIu7ryyWUSfHaI+aV+flFRHsP3ofMv3hsasIz5ehRS5dkHb4a9fBJYoakdBLMqntP gahB3xF9fRWPHiZWcPasRMHzBHodoIJAowNk7CCPrkh7crNrA3JoV7KVN3AREugeIfRP5oQ+Ghrn ESyBpy5yTcZSS1sQeXeZU8/17EXrsSuX0r8RcJRz0TrWJ6JwMhj4kUShzsCGzeTKX4ljpUj26d7J wXvNJAagXX+qvws8eYQrN5RCCMkV6HJbQl51G9SMAjaK8vIGjix8kqYtTgGfZBJdvZCjkbXNzXsW kaxsRaofZ796gJJwT7WOy5I0iJZfeVipP0dkvCR6tKbeEXMP0mBaHiwx6B5pmdoBEISp2ZBqCepT hGlviL7gquEMwfMjLioSRQEUpVs+g90zSI7urELveeuluQGqbM5oaA2gdyslSVClLyGT9PCRclz/ kX3+TLyWoTC0LdQSK/dfzKOVw81GuYCTizNQFIu1Tlw0lyQulgNnVx27QVlSUmZmySRywsVNNedZ laCVW7a7QyEuKicXXSCrwwOQKLu2lUs/+cUyh4Wzh8/+evxKJyBNub3/229/iuD33UBx1tPH+cb9 uqqeS3dZfnLnBD9amfrXuvWn1HOTFaiJqgzed6lenKD6L1ANxGkfau4YUpjEnj4LM6UEBKDXCKqr /ipmeRZ3L4982wvei1dNqdoiOIoAEIHZ83UkAYLiINrvQejgx8h4yrdHaNKDmhZAhJ1ibuaVFY8u W0LjCCcBEX6Buad6HCxEAxDjS5HtoVUlykS2HWAImQ5oaNgERIRdDIhK6GcsS03hLEKtKSfKproZ KGWs5lEIb4cygu5Ul85Un37okwPjo9lD4VDXBYputywNcpUno0LLr4xBZfUzUlxQoe8bdHTnfb/A RekfrCdE6KRHlvDlqe/Xd935+ZYz7zIZRxaM2RRZwVG8mRpgHjUDjsWoKo9poKRYAoWurkLeCaYK AhdXEXoqLVvEJnJzQ18S9fgJuLq7AIlYJ5bPo1bDlDLqGTMV9ZQGc3LLUpn+xeWgm1AjDhGUk1/7 QR9+unze6vcjx2yMVBIW/bpM3P6F0y62GDL38/cXzQ+9+dVVq+5KNa1JaYxfAPCVc3sucvFqJEkC lL9hiGjQmervBp/lgv6DyLgjXKot3iOZHHJF8LfTXJZuA0CiUN9hYKdFifWD6PeDiLvn2b9S9czr vHzIAODtRhDq3a4k8EbrmwphnoHlYQW01ZQEcRKkCd3xhwN6L+SEMV97NalkUUxN4cxjJUDspg0k EFq228pqw0ng1b+Zq8iX4wY6daXGdqPeTmeOpZYlcEJjGu0XA83AAOTSsIiF7RKY7qTqMTOgeDeT NoCSIhISLHzkHrLENd9MXpc+85cMd4rd+XHI34npNnn5S3XAPFqJ1jfFWBUvik17GF8k7Nm1i8v5 aypPhnOX4A7C4ttxpSuzIRC07t7Z+fQVnm+oZl06eykfP3imQwDIbYfoy0FkRinDKLXcXrpyu3UU Ft/i5eozrl6dDApipemxZ34+Pnz0Ml9fRPZKwrJfV5b34mneixf7u4/d1K9nC+pqjC3IDGlJ07yz t9SaoX3IFs56yosaUNOCwdMrzP40MGsSNbUn3BYGK/CNZnnzEq0yLhdSU2BJIPCG8L6tTjkoJwC4 thgwKNC98NGlKwn6N7h7BVIf9iISL7NHnpU/N0CWDlM4MrAZPz2MAKa9yDYeRPIDqH+GhEvQzI9G NpdE7Nt8vjovuDOBZG4OlFFky4ZsdKIKAiFo5UuUpHCaxetqWJT8iNIB+QC0yz7Lt4eZv00jaSZT aZRfM9LfgUh+xmXoUEpN4ZyRBdnWoIEL8Vw1W097AT8KuRsqHORFMDyS6xpI1XHRy9uoESmK5/i3 gwQBfgCt987U8RNYEFM1nI0WLiMVSD7NutXjv0G+bZRo0qY0vLwnlECla0tp1x5Of9/kHbnAkfEf JK371DU2viwd1aJncJ2s83tDLj8w8s2p2ruAedRos5l5qOaSCjkezJRWEn74eMLbMz9fn+N2MKag TtDURcPdEvYfCkc9mHdVoAUbEDoP/Gh1msMf0XL/4QumBmRf2PY32i1eqgD3POE5O3bQjDHhv8ai DXYluSlZRaouL3L38XQmAfDwcASA9qjvV98NWb3ivOwiZCkZyh3mWibXwsyhsO+Kn8dxly7HJqQV QJ/OU2a0Ze5vv6dyMsGC51Hhz81UWBPFFRcUoTl/2yx7UZWZlgIlHUDfViAzHpJ1yREDSA+dZfXA kRw7mHRKZHc9ggyEf14Fy4dQY9KY3xNVdaUJdyc0yCXQ0BtB7uwK6ooIyMFiMVH6xrH5MBOSHTuR j6OhmCUUUlig+p7KkrjQDHrkGNo5mnuSB0lHUK8eaCuEIX+rPkNVD2S9PvM/59fr3r2WoG5ZVZkO jakPB5JUKvdAAdoEaLoDW8TFZatGQkXc3/Hk+52oSSVcrJjo1I30Keb2xGvXGKu1AkL/niNHdH8p PbnlfFLVFbW2BFNIoh2xN1+Sg96iC4Qsv163A9nFAV66q7fICMrh0xxieHsyuJDLQnPkRTDL+n08 JpBEejt5guZ1AOmA9oMQAk/QPgBwDHz2XGePEABtulPDPeFfGXo8WlM4Fz9jY4LpAb3IpKscWq87 qBfpCYiM0hYw358pMHYcCZ/BxJfIlwuatycbcfBUWWa+FGEzcno34noG4dWKfMsTxtzSLjKyppFN 42xNbqNpFILkJ6BlB9hsYe7EwYR3RxbojOmZGNcbt0uG9lAGrclsk0tJCc7Vi6MJ8v7nrrE6pQEH RydYVKCzd0w3smrvAuZRo81m6qFtSZSXIo/bs2S5Eu3FXLnhPZE858nNkGWbfn2oM+KF4qvb/ls4 eNG3c7y57Pt/ffXZ9jA9q4TLPLXthzYff7B80whXIaWM0u4fpYMWh+yc4Kn1fyz948xSNBOfsn/B 2E38cMysXAujBDYlLg6+O2bhMD9PZ0Kc8ejG7iVbjiRbP17l6615DSxIMtUORp7Lk9h916l3e9Df DCSk+TAmir3emeqlTghA5wFUF8D9ck2zhrbwCftnY3rWAOppLhtVRNB+1PLRpJtWmdFT6dEIq0Ju +29lp+egHR0nroEJXah5U9BJcASyazX7R1kYdpop7kq+FUT1diHYEpiTDR88tNn5A0aqqnrk6sVv YqEakVMblSWRPYZfX9CIjg9jDyqpIV2pjjR/LuDBa2x8OWInff3qU1x+TNTTirWdKZWsfG4SSQaG nmIYtK+xHz0Q7R/N5c6f5i6X2/QC4Y1LbL1B5NjRtBAQideYnapzJ6oYvFtTMzurfYYE0Yqa2Yrg irkf97NJpr2EpRJrBGe0aO7YSRbtH/3HHIqUwQd32Qd1KU+tThb6M0ckZxO9AskubgCNG/OyuXOn 2Ju6J0pC4sEtTtycnNkVQDGMvMjaalFepZuJo+9v9ai/sqhVU6WXq+OtA2T/WSVlriGOvve1t3hS UfBgua8f4wFIaYbweaRjfJL+50X9l/HeUsV3Ad/jXda06H0EhitkdOK1P2338bfQr6iWC/YcmPJ4 xZC1YVVanmtBjLHo0t5mn8pSzeb/b9+cpC/e+vRadU68GKvpG/uMbDDjxxOL6Z3T5odoF2a/sVjY s+KvFs7qcxhSzygPP7cnKDVQtrDPd5e+a7xnxqy9qp32eqGqbaS/nrF86fhvjIB9EOBy0zKUwjbB Xetij4h9ELZYKnAJ6hKQf37vH9U5NWpRq9cvAca5VrQp7dmlW1sHZWbaSwMS5df6VvFdwF+xCjYy stPsY6FVUA87J7d3NWHxlf2/Ra6duf3iu0z6kYVjbbkG3c7QvC7Fw6LTKwaffl1qU3vrgXGu6bbh 99r9iPbaKTLv7N1/3dh8epXbCPt1yxrZrF9X4+c0m6am+4vt5EOI9l+WFme3gQMQuHl5eaBp4dQ8 215GZjskcEkYAYzAK46AY52G3iJ5fm5uMWN8drTK9cP2aJUhxAVUGgGoLMrJqFW3ola6KjgjRgAj UEsRkOWnJttXNTw/ag2+2kGMnQYz1qhQ/WnKKvtGVbv6gcYSMQIYgVcbAcyjr3b7Ye0xAhgBjABG oGYRwDxqEf/aao2BuhN+vHI35ib/7/baYY76FTEfS5BN5/wcGbbqrbKTxczjUAEQqCbv/S/i8oa3 7XYgp6pq4ZuHo0PvKhxqKm+FFbUyA9l4wHvzx3f0sNsUtpV6vMLJzL8p5mOrXG1QZ+D3oX+u6o2u LcPhFUYA82gFGq8CZFKBUo0nhRynkJdtrWQYdFy9TCqVSKVS9AOic+BgwV9fTh4xcvx7O+8bbi5l lLlH/zUGxU7aHKWo1Eb16qyscQhMPmULM54nZVl7+4R+MTWV12RlqhZBNe4/fe64TuhEBhwqiYDZ 98j8W1ZJiTrZYP61PUckIxZNbIlXqlQdzZorAbeeeextzCaI/1iWUyoVQHN4CiRJiqZpkiz/IZQr 5EKhxlqUy0vQAlqBQEhRJOJEjr+RD41fuYKM5CJSwJQ7EV1TIU76MitN4uQt4eQ6fGy+tmZjERS1 Y9AMC0PXzA41q6vJyJrKa1IhHFHjCPBvipQgzbxHpmOrrjyTcPJU3MxZ03sdXnXN2JaMqkvAJdgf Acyj9sdYKwGRaElJCToyCbGmQMCfasWyLMMwLHTpPHnBoqkDOjWuQ4uzHkde3L3pp0vJKBlFNegz Z87o3h2btvT3piRZj26e/mnbgdvZGj7jOETDFvRHZSCJSBA65d4gKd1g4NJd/xjZ0ZvIfXTp5/Xb jj+RqQcOSO68eeP7d2nh7+1KSjKR3F28XJ1T0kj39uM+mD+xb6nOe7aGXE03PEZN2Ozd1Ts/afXg ++WfHk82f5A21WjavsNj8s6nNB8c5PDk8A+/O7z38dgW7MOQlSt331V9YoT91l9ZN1x1KK/86prB y8/qrPUl/d/beWxhzobPk7otGNOzias85fYv363bG6M9RNF03qrJJah2/zi2b0ZjXXSZR1snzg15 rkHDqfmQ+YunDevapC4lTo48998Nu0JfGHoQDBqHf0B6BU9HZ0b2aVXPCUpykuNv/LZ53ekX/EZy Qa/VoT+M5W+ERWH+scj5/P8VkdpTIfm83sHTVywe3aelj0iR/eT6yW2b/heuOfJddU7W1LTdu2R9 Z7zV0kOZdT/0p/U7Tieq/R/mY3k55mtEBcw5cGDK0y+W3Oiw8MNhHRo6KV8+O/nN/B9v2ZsmTPdJ dX9+q3OLRt4uZNl7ZGRHvgrPag1cZlho3KJF7/TaEHZR9+b3alUCC6saAphHq4ZfRXKrNmWSDg4O PHeq7vZEDOfo6Nlp8Y5t09we/bnvy/+8KHas33nIqOCmxNU0vmmAb4vGirtndh3flSfh3JoOmDV/ 83aHuTN230c3m8ikqECFQo48vegHIuSSEgYxNPohFOnNTVI0hR4a8ihw7LN4YcTe7V/skvoNXbD4 y20ORZPXXOJvEUVyAwK4h8d+PJ6cXci5quU6quXyNQZOXZZs3THD497BPaU683e3lOdRYbMJ3/z3 44CY75Z+cTqVpw7a0d1ZaHj2IuQU0iIZTzu0XxNi/3dfJy9eM3PdwnPffr6q4T9Wz5nR8+DdS/x1 OIo768eP20bWGbbmJxVvGARRz/cnp6xZOWu1osnk1esXrZ4VPX5brJqzzOetglw24cDCCWc0iIO6 /f9v3eLGSYnoKgFVoJtM2BiyvE3y8R2rtj1T+PWbs2DtNifJjP/c1L+6xaAm/APSe8SqDR82j/h5 zdLYXODh3ya4t28dQLzg45SRG6eM30UKg1eEfNnkxKKPjqjOOlPk52nkCgNnbd0yp07kvnUrYgo8 gqYtnbt1Cz1nzt5H2rEMcO333pDfVs4dG1PiP/2MJr4AAA+iSURBVPqztV9vpfOn/vuG9hBvM7FW 1QgIO/7jy0YRf/57yaYMpWf7wS2hpQGfUQQq8NBsn0TvEerPx3889gL1Z/33qAIi7JSUy42OSnWc 3CvI4eIVvI3aTiDbuVh78ShklQoGCEQ0en3430pO/X6TtEBAl955A1l06Zc6hhSIhFTt8Buah9wG 7k3kyC2VQTZ8Z8m05mm/zl2y84nKHIiNvHZeoSgRCPiFQ0zUno/DpPy9KLwf+G7Uywa9dw8a0GLP /Yeso6MTsm5pWujk5AQAb5hxHIdKRn/zGXni1ASKpHjaNgQXSC5t+mb3Ff7+3pg09zaH50wb+tPl w1mIz5iovR9HlR42HIvk9vp54IAWIfcf8mRHNhi1eErTlH3zluyIL9WZovSNUeAQMOnzncsbR3yz dNXZdLU25m8nvY6KZnNunjx/627Tzqnj68WePx0e5d/+xYwhjepTRALPE/KCjKwCoCws0bBFaR01 P2DWqW0h154jafn7D9yc8X3nYH8yNlGtmNm8VZErL0h7XqBSgG4yadmsDnmHlm65orYsgEv/ee93 U4auXLohlB+gREfFc02O/3P2sF9u/65r3Zevh/pvqmlgG8fM0/sOhN7nKx8THnayLKGiMDOrkBA0 l3JQIc5Oz0zTM65EPSZPaCU+t/yzPar7+GLuiesd3zxhaveDq8I0h9UDLv3ElpAb/PDm0e//OfD2 0QXTBoXcPK65Wd1krLU1EtZJ+f39dadUlUx+/jTGeA1t99R8n1T151Jheu+R7VSodElscsILpXPL to2pK/G1wkSudE3e2Iy251E0A8goGfT6cFDr6iJpoYPKCIGsvETJUiJ0Xwb/h0KObs4UOeheJfcG NQTy6SqVjFurtgFs/N5TD4oVhHZClGMYKES3WSCMSM8u05csnvhWG/+6zgIKoMlUSlzXxOpMBLEu Q5dCifgQGaxGeJR5HBGt8bWxKTHRmXPHtgugD6PrqJDt6tl1yocfjOreumEdFzS+0chFXM5/F507 dgmkk/adVxO/Wg6a99VtO6rxu9/+t2sQOLNyrZZEUbTl20mhVHVJuUws5aRiCRImk8gIJ2dr71dT Po9P1AwglPn5RUR7D97zqU/wRrtYFeWqynRsP2ft8vZJu/6xJUJr1tGtundxLb4ZGqay8lGA+Xcj npHz2rWgf8827+VGidnUhGfK0aOWLsk6fDXq4ZPEDImRexPV5Zb7L+XfNtBV8SAiWnWpLQqSmIj7 iuGBbf2pMNWABGmieHrvsca9zGXHx2ULhrVtRh9/qX5kMtbaGinv/h2WYwXwGv2q/D8X832S8uwy 5YMPRnULbFjH4ntUZV0qXIDyZW4+6FrPmyQwj1YYvFqRwfY8iqqFbEsBYNCV7epQdokK+h4DdK2j epUMo+QQv76hJIqQQSQqFIrqeHs60tJiCY18tGgBEZoTLb1TDE2CtZu3cftEGP7L9n9GJOfLONBk /IZ/D6VN2O3atUvWdizIiMWlhh2UFEugyMUZdQgFIWg7d+OOWU7Xd+/4162kvBJINh634T+lcoGr uyvNFeZpucGYPDqgg+eVawk9hi748Hj05hiNuwqKs54+zjfu19USjepGajTzi+7/VP1CIwAVKFYF qNSlcz6noRVuvCB+BXTl5aIeXaf3J99N97n1/cz9CWXLrEk3D1fSbeS6sGFlBjRJCdh8F7SEzCKP cuknv1jmsHD28Nlfj1/pBKQpt/d/++1PEeZw11QOOLk4A0WRpEwThaRIDpxddAYkSllJKS3DEqmc cHF1KkPLVKy1NULDGIkJp4HxBqjaU9LF3c10nxS0nbfhx5mO13f/+M9bSRbfo6ppUqnc/CiUFtjl Y1wpfXCmCiJg+6ZDXMl/9Yy9Q2gSj+8uqpkSvudQIntPmlQQjXLJjdWhaiWWy40+87JiMUfX9/ES kNmlXzX0NUP/IEEFDB7WTBa6bOWum4QD7+alvQhrLbNykgy5C8mgXVwcAKFQVRM4uzmDkiIxrwSS O7RZ8dlPvth7W+0E1JcLiwuLGLK+J5qqyzUFkTJyy/KPjjrP+O/upV8vvPPepluq6UDLfl2bwlt9 hVF+Y7/6bCR3ctnqc+m6djlXVCBm066uWva/57pIcdIc69bccDkRh76JOERQTn7tB3346fJ5q9+P HLMx0uIqJWReS6DQzQXN2mrSCp3dRFAi1qwj45ERubmVtb6LuwuwKtbKGqHRcjUao+hzIi4sVPVJ ksg1cI2W9uc9t9UDusq/R/bpUsDZGV3kW2z8hmn7iMSl2hQB2/OoMfU4ZYmC5Uf8lFCkplFkbUBA cUo5Wq2KvjDI8yvkp1LfvCCOjYpjlgwe1nJX3F3t55ESCACa7ESgiASQkcmVCDo5mjF1DuzV1QtA foUv5JD1icgRLTCSSZGh6uKGdnIXG8KHDA0ZAx093EgjsXTr7l2cTl7m50ephp2CfJnHcc94HgVC kRDKioq1+ghb9+qKfE6lQaLRudXehEfaq6EpSjUJqw1cYX4hp8z+3zf/7b1/2aqPw6d9fR2tvLHs 1zWswSvwRNTm/a8/6Zq6e+529XChTGXmSXi0ZHTLRjD1qtbfXKn6sNL02DM/Hx8+epmvL7p6uYxH 0UIzJSHSX1eGJLCpD+OLhb2Cu7heuKrqFS5dunUQim/Fld28CASBPbo4n74sRq8f1bxLZy/lk4eq 1lcFk7G2qBFwbTFgUKB74aNLVxKsWG6l1cns/0vfIyN9EvVngW5/FqD3SLc/qwrm3xT0HqHxBKEz 2NDKNB9rVjPLkcCjgZ8Ll5qYUq1DD8t64RRWI1A9PEoKHBzQPg/IMfzZAiJ+9RF6ezmGo0XIA8wv RJLLFcChdi80MmV6WY210YRc+pkdh0btmPn9dnL37zdfSB0bdBw2xv30grVXFSSTcDu8YPLbk8ef TDr2jPMfMPejIc5FMhmaWFUZrATaPIP2hubevv6IXTZx4cjEowkszaY9fq6Z4+LlQfG96AfKOVMX j845myZhJHqx0Kn/8q8XOvwZLfV7e97MwJeXPj6nWheiljtk0shT3595QTUdsvDLMT4KqEOSpTqL 9h0KSyoW+SKdvS8s+e5KeUOJfXH0m809Dnz+yWc341eez+UKnkeFPzeKA3po0XkrcvfxdEajBw93 NN1Oufv6+boSUCnOyy4qL9dQhP3yOgTNW/th8+cHV11TNgwIUEmGJbnJ6QVIKXQ93K69d/cu3L7F /Zdj4YnFgrp+Tdr16O106ZM1F7RTl4a6ap8I+674eRx36XJsQloB9Ok8ZUZb5v72e3qWLPc8IYkd O2j66PBfY/OVSG5KVhHfUCV3Dh9LeHvmZ+uyXQ/GFNQJmrpomGvC/kN3tMMepBp0GrDi6wWiP6Ll /sMXTG2efWHrJe1iXzOxVauRumZkvT7zP58b8OSnu9cSVNraIJS9R4Z9srQ/n/z+dDLVdPCCL/T7 s0o8/6bEc/PQe5R8Mqn8m2Ihtor6CwLbBYAXR2M0u5KqWBrOXgMIVA+PaioGkIVFs3JEn0J+3gqt 3VXP9AFkgJEyFpmrFj+lNQCRnUVCadS2pfPSP3h/7KzVUzyF0uwnkaG7kwBacCsQSMI2frph5UeL fzv3JVGUHH0hZMtfs9eOQ+YHADxzoHlDtGqXyDm7en3g6oX/CpngQDGx60cvOZjJL9xVrzliXxz5 co3P9ys+2THRsTRWXSUou759R86AxWvm+BA5D0PXLN12WbN/TaqWu2g/L/dFzPk9a/+cve7dMiC0 Os+fOGv1RA9KnIl0/vmJ0S8il3bi3//uG/LNypVj7q88Vn5jTIWwpYMWh+yc4Kk1jJf+cWYpGoyl 7F8wdtMDSwtwzOW1NEAyl5chgGOTpg2EjsJZ//59lrY6OvtHlYm/L5vzcu7CKbO+GO/jwBRkJ8fd CTsaX8ZnZiBgU+Li4LtjFg7z80Ruv4xHN3Yv2XIkWQ9mLvPUth/afPzB8k0jXIWUMqp0/6g8bs+S 5Uq093TlhvfQxXRPboYs2/Trw7L5UsQMV7f9t3Dwom/neHPZ9//66rPtYTq2oZnYqtTITGWrGmWu T2r7869nv1C/R+v+QO9ROYnoTfl6XePVC1fsGFv2HpWmMR9bJeVF7ft2c0o6cfWp0ReoSkXjzNWE gN3uH4X8OiOhQ3lnLWTkcihwEJDI1asEyDLVrGxAC3lZGhmktq82Oj+oXKHoVCCjYgzuFi3/gVWd r8fvATWa3eJDtIwIeeHQ/lF1SrRrpfQ3eqJQKGiaKl1So1Qiby5atWvtAbimpKNi0SwsTfPHPlgf VKtuytaH6WS0dt2O9bJwympHQHXSwpTHK4asDTNiyZuPrXZlX3eBzv0+P7HWZ/ekFYerNMp83WGq 3fWrBnsUbYQhADpUBwEBOSUDKSHPQ2gnBaFgWIo3SZG/l0GzgZWkp9oNsI526JAE9ZFG6BkiSPQn OilX7aHlsYGcUFjGdshnqzr/r6pBl5urWhbOjxHACNgWAbLeqGlvyU6sPIlJ1LbAVm9p1cCjaB5U rlQg6wbVDHlwtQuNkI9XgM4bQFYpek7StfEUBtWiWVsGdHqRk5odkY2IqBRxJ7+zUxUMN3cYPqmE LjYpRCsXG6OVaAGcBSNgEgHg6qOM2L7qz1h8kJFJjF6FCLv5dWtN5avg10V10OPRKvp1aw0klhUx 4dfFPGoZOmtTUK0m/d+E9iIDSJn439f/ic59fLOCeTTYWonVq6jzm9Wrqq+2mEfLsDaYH0VRhjxq fNqw+lqsWiSprWSDTacGH/1qUQYLwQhgBDACtRmB131OsjZjj3XDCGAEMAIYgVcfAcyjFWhDjTmm ndGsQM5XK6mqgtj2fLUaDWuLEcAI1BQC1bHOqKbqZnu5qoVHqs0vOntp1E9sL6z6SuQpU482VX9g Iq2+FsCSMAIYgVcYAcyj5htPxZw6Qfu3mmRUUcCAcWy7yNe8gpWLNcmRmghj8caeVU46zoURwAhg BF4jBDCPVrAxEWuWGaCl1KLPnK8e4+hpzP/x6lWhgu2Ik2MEMAIYARshgHnUIpCIUsrTJM8yeu7c 14R2TDPoa1JBi42NE2AEMAIYgYoigHm0oohp06vduVqGrf2uXFP1LGNIzJWmMMLPMQIYAYyAaQQw j5rGpizGwCQtjVJzD9T4QV8tNrWaQTHBWtNJcBqMAEbgDUUA86gtGl6fTcuVWBvI1SQTmoywBSy4 DIwARgAj8AYggHnUykY2bZKWFmDISZr1vFaKsH8yQw0ty6xMHsul4hQYAYwARuB1QQDzqPUtaQWV livsleegV74C1rcuTokRwAhgBCqHAD7PqEK4vVG88kZVtkLdACfGCGAEMAJlCPw/IkphiadVDZQA AAAASUVORK5CYII= --000000000000f2c58a05e408f56c-- --===============5005865336534498096== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ SciPy-User mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3/lists/scipy-user.python.org/ Member address: [email protected] --===============5005865336534498096==--