From b6238272b4ebb0f31113d6c9b2f850a904b24b6a Mon Sep 17 00:00:00 2001
From: sasha <sasha_kobzev18@mail.ru>
Date: Thu, 11 Dec 2025 03:10:43 +0300
Subject: [PATCH] labwork 4

---
 labworks/LW4/1.jpg     | Bin 0 -> 22523 bytes
 labworks/LW4/LR4.ipynb |   1 +
 labworks/LW4/report.md | 367 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 368 insertions(+)
 create mode 100644 labworks/LW4/1.jpg
 create mode 100644 labworks/LW4/LR4.ipynb
 create mode 100644 labworks/LW4/report.md

diff --git a/labworks/LW4/1.jpg b/labworks/LW4/1.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4a91437a91c718a57d451546927492337abdef82
GIT binary patch
literal 22523
zcmch91zZ(P^ypr?ySuwPq`SLOkWP^fk?!u2ZWIL(Q4t9VX(?$$5D)|v5k)}Y?FCdY
zzVG}0fA77WjWefa=FFMdv$K2e(d5x9083e3NgjYeAb>fTfTKmojFOCunWnaeyppOM
zNB{sx9{_GJk^ta*#luZoL7K|Y$e0Q^vt71yzj`M7D+ucNG7f-e02pQ0@_@(umEm9V
z$ZlYPAkQXv;MpF-5I87oaRL)TVQ-JC9$;PBps?jtHz+I#!f0-~+A<)l3c^&jXJCsn
zu$8sDCCK9h@|gW>n@a%z2yFuZZ1PW>MFs#ohy(zl*`GMNA^^Y)2Y`mrpSVvN$L)m>
zJoT{l0qX()>YP%*)yr;|p)ddo9xygG0I*d70O&>lfI9>LC?+TMIOc$N2Mv7;{ogws
z%>Xh094st!hl7QKhl7JhKtV(RH*{naBos_^EG$fPObl#XB0OvyLL3ZCd@_7OVq#KK
zQY<`jN^%lPA`(&(s1gVqJUjwC0vaMB8VNQgHp%~ZJ9-LWBSE@g1YjXF01P$+78`QZ
z0gyud@Ob;tW;g_R7ziRPNF@4&0<yqDVBn6X0W??$0D}dK1@_><w;z&FfVfia2I2vF
zJ8$_pG~g?CAyI>Nw0nE&F92cZflz>B?}5K9U$a6*^4gN0FGc>}006e_UFTP?t-SYA
zYsJJOji0l}qil_-^Xwu#i;1W1yOBlw%z_k~7s_rVr_^J{w2B&|6Xp}S8wS+f$Fk5Y
zC&TqZUUm)rt~ZZF<EBahOz{ZR{dW=9;u{C@(k;`q>*Op>l9FE?yoH?qz)HlmW$R+w
zh{)%#Q{IeK2kL|a6(zWzu5h#0b_$f>O~(oDjE-9#u6HSn*IFBw^R)0gTiZ@4UL`3?
zcZkrtN$k=X!Shb)5jy4c!}pgEZV5j3lLSZ6%Txh-2)&y=X!M@9sv8ZTc6=`;JW71)
zO*~N`TMbas-_))JZLDOP9s~f$tVz{i21k!wVHPR~!n}T}Q>Ad}J%#`*@$82;JB?#$
zFC9}TV%jAEKwL$)%pBxNdBh5yaSW&p!3*6@<HSc#7@S5x*k(KXo+2`9N-ZSmz1!R7
zxd{ks=^bfkdHxwy%B^6(AJ+_^J3%Vx-luejmIq)6+P3ZP+$Q`?x4hvKX>GVPUY%_C
zT#ex6p*?=lTC!ovrRreA<kOUJrL^crW?2{HJW1!6mUX@qgH}1;riC4D&qVJ#>cM$n
z8&IJ2*)lGJw&l3N(1sl&>9xnM53KRpB*BJxYhD75K^y~m+uZa6Qr{2Q+W?I65>yJY
z$06<5eg^dB;52c9giBY^+7T=r$dTk0bs0?PdO&>dhh6T`-syIH_XcSXY6$!wu#cAR
zD}!AHc0>wjrBft~a#`j6jS-sxDkA4W*`1g9p~7!=$Gq!uhz5I$`fj}$x90c1NN>qf
zTEkMrQp7eVjCnKcd%EYbjPgAb$x)M@aueqy^^GO%RVtq*cV=Cc*0DF}R7B{9=DU@>
zZ-a=TJqV+&U?yy6w@z<v_q~h$x!+)!Z+-hZw8}%WiQuAigD)smxa7GpNgHX<chCA4
zck6i9BF-_jvK@5dwhY%~3hMbS1b_I}KRX;Gc;0I8fl2ZUp(ifA_vKTQ(N@-|Y#V1u
zW$cnk$CLEIWI&^H^B90;^f-GGZb})SB*~g|ty56SG+O;9{#K@vjmy1Oeo1RjL-##r
zp1q)xw!Lv%+qd)TxB`0oe{pHpPe;HIB4Pc>fI_gW$s3=h9Fu?b-A(?*cfOD0=oyQK
zhM@m0b|JqY(|K^*Wu9!dlsG<v(!@^x|As99v}Xg7sqs*+w&wR$yI6?*@W*KR=OG08
z`0-!>#V+doFT^~JoYnp(Vm2a-CW50YB$C$mh5ttdUf83|^!n1y-9KkD*n78q_10{%
ziNM(z`*iviZcGV31?7I9)=wyw=^E3~J|xxP%mx5Uo?XtR3uNLo1{wbL2+pO%4M{fB
zQa6^@{FB62`)3q+ov8-uLj^_xX@h&$O(oxrK&dB;sT}T&Ph1$;zsuMoxTMZKTqcnb
z7(qJ~OwQ)0(Mh@now@<EE8XTzA6fwb!2-SZ+x|9qqb19){kF6JF7R&0yCB5Py+Csb
z_5;Psfek|-yQROg!g4`X5ZIG<!(ShkieCqjKQ^>XTK8`ngZmff<vAaZuTkb~H_Uz#
z?VLXXcta^BzEVmE9XQBfia%`+Zg}k_`9tjQ045k4aDY_;LlOW61_B2L1JDf&Zy+#u
zTzpvAIQTrcR0ssrG`#Yfv;yY*V8nm~hP4oQm?PlDliOl2(qsf!t9fn1{aJ@H$TxI4
zU+T1Mnx&}>G<D$cJ?3kwaJZ6;lh!@jLZ$D$ckv5ps|%zFVe|jX1(lPIp!6`j(t}-^
zO)XGDdQ60%Xy`r$6d_aOK#r=pY8(kg7GA?Ot@{Oco>9GHg8L``dD^ORu#=i=!C8gp
z8TjMx;BKEU@eBhBQO+{$v9RWJJkAkNI{X?AgQq6u8M8J?x|XBPBO7}GwK59!@~(P=
z$MXC8AE4$#u?ZJXFe*@dW+%u#<=fStH;@#H+fePo6u!NM;tQvkQJgQOK~<5Y)6Kku
z2V&qagg_A&qA$~*K<7wwN)X}7B^;p#8LF2|6r6HsIABm-sM3nYDG(YahEHlgMnM#c
z;(ypdFy3I_7#>=oE#e7VF6419AqBQ1%|i|&EP03#fxA5H2&gHetSP0eDWR;Pp{${z
zyz?M&!X$Eip#Ag8!rrH=V&Tow_F#SBmnH8vklo|E!7!3YlKU!M=tFd_7Y0LnY)@#-
z)qHHr;H1dc-Eh^bbja8hY4Hum?XIsNRbcDGFv?L&wO0tg5}l0lhMu-UOcvQzS~5&v
z|I|8XxGcD*5yjJq<K-WjR+-=wH{2i@zVwdt{Yb7e**!L4(5M=7CiP+22=`gr=m>J}
z|1j_w6<@TgWJ1!|m#H}A{zU$qryLoYLdT3PQu)zYfWP?3wBTHs(6q3Pp<DlmQ$b1b
zqXBLjdu_%&rt{?M<ng%?^=rs3SA7^*@&YMuc!fu>$41gVqwN?LDM@|}riC`&D4hmc
zF>3!rveSgv@%}q_{))Wl-PZl_x3p>c%zeq{_atEXXzPO8Z;2^-9ucg;)34bk+i}!<
z$X3#l!e!L2LQs`eGHg<<-WJ#znAIf`j9MDA&XruB)`>64u#RLKVCWg1(jy@ltG5g2
zy<nmiZ&%|Lzhkd1kYJPn?O;YZt_||Tw|}6}$%{%wP%;O4p114(*_^T?TbVXV;BX(W
zQk~53JghN|{mAt(pK~3^=SP=beqV*z;V=R8h!l#z74fI%D`!)XM35Frw2~tO4iu1u
zE?i+r0PhzquAWTks+CnRojfIq>3&msB2986^|re7hAVNOKhwpe$o8UCR?+d1nQBzg
z>87wK;e$9iC7RM?ZACFDtrY0>H$oL1qo!`@FWe_w@JuYYW9QYJ5D+R^c>hR1!Ncc<
z7ApNoh5Jg(B%Q7spF15YuJT=KJ2D%-ZRK_2;Z7JvXg6rOwB|(>MBjOu_-;lm(XQsb
zG1M9NKu6z|zL!$rWMX=2bve6qiZk`9gR)si&adW5M379G%49O)Jhr>p!WOo*LahDW
z+xYK?o8K{afmk^=raW!pG3AP5J*;227khs(d4igDrFNHTS>HBv0Av?E-(qDs-}N~G
zQpmk%_M=J?$HnLz0Vbc*fAIi{@szyI``lYq(8>#_xO^5i(psE$a+JGP@A6pLwcf3N
z_?q#j;+O~KI*q((Bu-%&=~^ns)1(UHXX9U4-}SF-joymBWr0IV9W~yu!yHJM)ssC=
z&|rYUn7|la=snm5YY`g#`j_--SAC)5;~&yyKB7OF#_tJU*;^b`_-hKK7cIbj_FH-y
zMZW2J!Sw=XaC)OySxntz;NlI?tVN?&xkJc|oqm~5?6#|f9df8b14}Y&61W$2WSdOb
zeqphvR*7?y)UG?cW0WJN*2Y5YLsM7MSwA@*vtu{!mG;_hIs0-SuSR!CCtk{C$}b%U
z9mo>2hn+v~GCw9ki9olJ^SumZrf5m`N;^N6#FGzUbTHF-qvcd}*fe6`ufS6*Xi-%r
ziI5^s=qj?%;p3o0!^?&gOF@xP1Y!Z3)d}<)3Hf;j+#hA&DcKnRD1$C;`24%#bLyDH
z4U?e+P5}h=y_7B~L}u%dVx3fO_(wK&3*R13|KcvS%h|;(hs%F31m(AuKQI@yd_h${
z@8ZYv-eITx`O(AEo?%n4r2mW2p!cCexnEd$->NJi=HB;@3ZW0bLl1V^7V9rX6eu16
z)XcX1*;=FhWoh^5*)4r#IiYuSrkIfF@Avw%cle+!`mnU0VZd2ZurN+X%pYZn>Eocm
z#A)d8QwCD1g1mM%s`yTVhf{%ph8t&Z@8@qA;oXi3#-*M&rJ}~A`fh8ByrBKViMoxX
zPH|l~;r?Gv5giWCul$v+7=JnP^UdQ@em}9w*Ou)4u~4ugWW%?pA4BUyqhIxwoz*>^
zx}%zIJDLJT-#Pr2iljFE7JKlWtt97Aw6x;kCcNqw>%GpZQbU?@(ep@b%MN|A%6hoW
z8BZSwYm+HI)lf`dx-UPe?XQy-ZW=p6_En0}ROiC##gQ`6QZ?>d`i8zqtzlE^dMvkH
zYgh8E<Lh!A($y<7SVL7K31-X}6HEPBZ0X{{zS&MfrDn=Bv#ZM3RE#c5N9*9VmecXx
zWZKm}0!nhHQ1;cG!aLfn7&LZTQf0h^%hr{v#f*jVS(tlpV~e{FRghG}9^q4qSaWEG
zB_KHEvtZTTcGrySR57(Rwpt+?>d$v0@am;E%pJX<Es(QpbU3AK@gn6mHfkAr9<jDm
z86BQf9$7_x)_pGBr1UbWBC=9~v7}15JhIj=+i!KN9F(i)BQzqIaQii6LzhD>49Svj
z^DrL);Bz+kV8M$GKww~D&=4T-r%xc@QX?#`Cbl*XH8&5hl-6a}<l#*kTIt}THZF6E
zt9KWUpDth_5DCb^RmCfMVmWuKDs+^e#(FRN&NS<znaoqZZM}X31eM)*)?&@NL*bw}
z?OVk@-(SVHk$+P~^uf(kOk4l4sB3spCU{W>y2rb8GRms<<%`JGj=T!Xxfl$V9~|1E
zHeTCeR7yqgYf@}>vbB(@UtHEVlDgIof0LB$qbNIizGdxahjp1aMdwgvHAr!rj5t$?
zCk_G68}FD1wHTm|sHm$Gy&DxiO=t>u$&}2SBY2=iUgq)yYb_G9k!q9zPk!y<J6W4+
z2Q4@0F1&Hw!&5Z6_^b?v@K$uO^k-K-6}CgpANGMoMudZ|XhXMC`%r7+fcAl!2egh9
zXr5s%nY(SEg^uk51GUfLRfup}=GWP>L_+vfOv1YN5BAwAeXft2a2@Klg?YX$KLWIR
z)I<^K`R9NNi9)<LpKYJ!;kuZnt=`au?pbN84^Q@(JVI>sYXzkN)y16G`&dZbQGH7A
z-*g3a5mp7~G&_pH$8icUHoxq1*PNewKwHp>fdxOF+lHIw%*Q<y<~>YfO7gO%D0a;G
za#33|mHa1}@Z7wvXiT|h-tVL4Or9_m*nKP}*L*GOb-TG<VO4PAlWah&Przz2uVCZ=
z4r69Gcmx%jxa<ak22q7Ri9!$&kr3e#;1G`=ML`FG!^Yv_c1uZx$D-!tZ(G2n0UgKV
z-UuEQEswP8T^a4*<RUsg9gC1*e9hvg^yZfCp<$a=r_ZSf65w-c&d@`3jdYW4r$^Gf
z9IoBi@M#C+rX})=WLEL~2Fyf4)w#1Q)QP&8Z`7|gZtLwuP+EuT>I`lnn-5lqDE8Bi
z^rClZyj-fF8{M4%XWqKdv}i5WjL@WmEhOPS*Q_stq-mZu_XV2c8HX-cvQ^q*;-lrO
z&gA&-is+0}yTvR_h;gsSdZuu=X+8?nriv({Sk5(*#_^voFxVBdxNBIg&x#+@`M(DY
z<Wi=ioH^<%OVU}G6%SIn20~jEr)qtWkvKP3l^6;p8Ec&;FTlm$KnzO0XTFIe;6wo<
z|DA_a024xM)Aow)J4=#|n+LUf>KEko-$?%=9Wh`eg4I7_X8tdH=PDvox3sE;GQ5F1
zCUdqH|DqzIv}Y(suVRw1@<(I;Lv1lgz@`z?9k%^wa9r9$A$jUCR|a|K2BqO1&KJCQ
z)C>2NGP6uj=&Cr9v0rd(Mrij9W3n?;#bXn9UlfsXsda0pON&tapz!KZ-eZ(GdHvDP
zr4DUcEiSHFcU@eE^~py!Dg2XPCbqec_r?m@)v4TK#1<j8Pm8Y4RPsW2JxD_B^aPbh
zmd`;O!^k7qzg_7%FBw0(O~GSf`6>ymRD$qkn}_Mx&!dc+d#>BCx?^=-u^^ICZt*ze
z-N1hoW$}O;O@D<tX10UdBrD>Se7j%flthre-}Ci(^*?Zcq<9viz$NbI(RAMyg~HsD
zjcqbQj2~b)KIdG%aE-w-uTJ^!^^Mf6=x=WbKKAz{OT56cC!5W;-|g(>;~Ms#H`u|K
zAv{z-s3U5*ZMoAy*n9PjH7{ohY{5qb6q!Rx+kR(*D<4U<KGrYFkHj?bEfdX3m5YlK
z1?-Z>N%+QgQ8vj@9%@xbb)vh^kJK!B5$zOoa+^#>h)-ZWYka)I@6f?rCAz}T=>P2f
z5wLEsL;3g!xNSBY@Zs=&;MM!|(P*j6?k^6YMgdz*%%C*?gxrC5pOMK;!A}Cd|J|hi
zTb_o3nyPmN&Jtr1))q9ZhclLwR-+n@3D^Ol%0<Mx*jZm5X_*ZTV;vOpu+QHJ%^k`7
zbhRr={|LZI6R^KrEL^sUH7tAZq*K20$us$Pq0du9hre=YE+uRSpk~k1-X61dme8WT
zqx?o1x3oW?4^EZwgZQ<`Z}P$uDrHD3SYNJoXFkaLj6-<mMMz1&%f%9lm#<5_+TQe#
zuYMyuQ%hp?q8_Vl7WVh08HxQkC5ys%B(YPxpVo0|hjE%eu89a#<CA{b!6zlyAt!CX
z6hHPind7S1UU~XJ(+#UqsIp+8qGW~9+BU&ulT_Sg5xD_NQOX00)qZb;-@J1E!NbbQ
z2M<^0YJIn$w&^81c1lq%{Kpfz9BNl@IFn4=`i4YeG-CUKZC&53q2M;HK1%%lwV3$W
zYYFi)hy`@sC7Y&2#}(&&aM|REEpe~`EmCOCgXW!XTvY}KmCv71rUUBZ4Os-=y=M_%
ze=j2FbmIDMk;k%wbKzG$2e!ZRd`~E5)~@KB@m5Od(`V&B%ecRY_l(D&4zH3BMo`|S
za4F?$)|VM~SA0YH`ZHR6me=d@_MG_0bbj~>=|+!37}DIb9K{j$TeP%1Jl|M|c}J)x
zrN!uV&^bxUzNj2(-MVrFK%gfe!Gb=gCUJR^-+BJk_XE9CAXIBr3g?zYH}jP;)F_`f
zLL~-knlBy%2K{<4YbN?iP`Y$G%(S%rr(-xU=!z_jQrX8%l7<ie>A+MByEY$K`xxQ&
z<8S}vfaNKo*qPrDZ~M{6<Cgx16R=b%o2v2p6~Em{W32MEm^I!hXqW9XiWy-l5t-5T
zrw%#qzZJ$EyJ!~VaLs|%o)@e1VQDs@Zs}!qnZg^+@HE;NVSjcmA&#{O31QZ}!`>0F
ze{bU7T~G9udhKrIZkBcGPSm4$3DesZ>x%z4P&VGl^le<Wa=m_Yl?CQsee|BPCsI}?
zUL?+1w$Tx=X7?BWbic5Z^g5DXIcG}Q4c~^`s*JuNt#bLTo|(+&AM?n@Fbc~6Z=e_?
z<0c<f)S(BwvxKqy9|mO}R&(m=Fsk)P0X4CzaA~nbf0(fW?wYF(sUR6$ijH6&UsMb1
z8MRa5q(#pvSeJC^|Dv!U^9VqTh>I4;^^|`bfQPLzT>6#<n`=EREQ}9_Kn_(qT6^u*
zy%#^m<vpR2oy*yDnf<GO8(G4sNgT3#J*ny<+U~YJ#p*fT7Xl)(_&AiRmem};1>Qwm
zBpb;v;V*b4jbB}uK^G%cMV8joPLm;%Q9DM<B2A_(ETcW6lY;jISv?h9v{ztbyH6Or
zA;~aMN0pNq)95<TJyc+<GaN781b3;es1*C{ZxQzi!~CV^H0u3id#}UsS2q1|M^V83
zz*tf5sO9s|yMX*6(n_Y{NeO>D`x#)DnO&;|Oa6yFlt(BYWq&T>kJb5sB%^UfaMvh3
zsgzZU^hnKgLJ7Dwzv7*{{jmIzby+9%eZ16Ex=4eqB-7Q(sO<SJ9$^U@%=Sk`oC0<d
z9ibSVEF}K4$_zHypT@1}ZVngnQlhD{&?YTilpeFnSsrrpjF>czcA(Wxv(_!QvHeU;
z`-C!V#cPB0s^|Q}P|e7U`*<G)!~QZlc=rV-(B|pZo~tML67utWS;Ka)erb%)?37Zx
zW4o3|eR%24_xNO%Mx#z+j3==%gmdJt>WXaBu;I=4J5o~KESN2kF-2XHL+|N%sKl3A
zK$oBL({~rpI_lhpk(Gw=>ksTnYIR*^W_6uRW<9P<Uf2ceAF|@(H4|g~Fq+(0x6<g_
zl*$7+>ra?>iScHYhtgQHo-+y<UDLSr({UrzoDPZC4}`S-rp}`yU&Vs{vpT(cRCY<>
z+tI=nV22SN6Dd2O^HAIM%j(aXy-HjP&-`5cm-(mvo$Lc#OcZ<R>D;|i4*wjL2a>+C
zxvyEnbetRVRc`b2ab77f_%W$rNA8d)d;h(S^z@USviCXfdb(TZF=YE;O2)**%BbGn
zE$eBh8d2g%6=ofM`y*OtXW`r(Dd?_@`O8gDTvt}Gn3Q{tLp?YDGNVV4*&;>auwXLp
zf%QPQ!1f(wE7Q@W{#!|JxhlxDsF9g<ZHJ^V+gYxu?5Hat{ODua+5KVVzc&5|s4GHs
zPjQ{M*Bv7$sEmr_%dC@e%ouB#5s>d$J@`Vt?KZGo>~t><oWe_`MN?Dyb;;J&m1p_X
zd2TI;;Y9fA(v#>3$f<A&b*XMgMG%BW>poRs$QDaE0<s)QA9X+v+Wcsng0`)9xFhw1
zOpEF7y}otbeVi-*FNc(J{k5L2q5+nMbAz=1>4?phabw3(;|z@&7j*wmho4-@%l*9Y
zY5w@x#s6{;r`zo`zq$M+-qKs>zZ{YD#&kJ>h}hL~CrzN+icvZo^JLJda~C1qrc_nW
zzTQG-|4mj`q;L?sgG9IL`BwQOKkIK|rpMvfh4<wdfl}yS57eXnHrSs&z$bYq@IqX#
zXgA0Ae&mbP#RLBK)O0h>UP_xI;M8x|KFd6MD18LXu+aSFCiy&F3~d3q?z+gAcm+<n
zgrOESA<GP<rcj%LL7mfq^nvmKKJyJ#q=t?X=g8mca~i|0r<UOaR#7v*WoG(|Z+{O0
zrvr9-_R@(>G{%!}!OQ<8uzrPldy55(-2W*CU8*|*w(<X_$Zv|3DOaV>jeRM#l0Umx
z?lYlmXj)8^7kNh1fc#AP{2MBzP7Pju7F*^I{h2pJ8>CXP!o=mH(uto(8VB@Tw_<Te
z>r}s-)svz=w9&i}liSX%lVx*?tm@~*7ml!~;Of_1AwDIcN*^qJLmdAHj-Mp-wAdY$
zSO20AWN)7)EHk^h7xlB0pE}M}fNL;()nHb<<Q(#k`h~PP=OlulEdv`t%ph&>LBUwH
zx#zjjecVLm@(f4&bf$8ueF<)~>BYqsTir$7rR+*@!9;tMD(As$ltj}~%3+wy@!a@4
zCH8*%0aNdvXR_1YexACI^=2gQFTQ;0JDX49ZvG3)hPV6PaQdHbGs_q!Gavcr0rX+)
zk5Sp_qtX#DdIWg>&1Fs>>OikL0)Bgte{BBgcoxsUXV36bMZJ1xv{y;h=u3c9X%3n1
zgu48UQ+?L5ac(xAy|%74iRvv{=q)^C#r=K3`;x!hhn}0zTfL6(#gM*`>S+^7r<hQ(
zmS(k4nB|k82Dhl6p!%lVBL^JPiZQ<9V-uyaRbxeZ$#yiETg2RUCM%B7T4Z0tZ*63b
zpRNIfJ=CeFx<@PgX7aaXfZv|~*;#i|KNcANTqyXB<0nbLt!9oh?(_-!AC??2?JtF2
z|MZsnPwNop)VGTml$rVO#hpX`Nk7*@FLa&bv`njP#(-_l%I6!oKc7J>|K@$+(UflF
zPIvrtXH)v9GnFU}r$1&IZK2l?dlpbd+SR2Q6{$WfG3}}+CXq<3clPP4-bI**YkZ#c
zKLP30mWA$TH;q{F@oQDbzCTfZrkwu{)=-6c&Q=gikN4`@)A5(c1>b+oac_zA63@E0
z)c*t|Nw*fNPj$i3b|-n`juYtqzipWmJ+V5w?CY*{vaUx>os_d1|MRLGR~!4v{j|kd
zV`A-ShKTyrT7f3(@upD6u8X$aM803YW+lk!jHIW!sqpm`(ND-{fD3D!B)0u_QT?eC
zr3}pX_u*;$-?z^Ar*3Rj<@YpZBR}1EEv<4jt*V!fnu%FWSv+Wg9@V}poxf|A87~$0
zQbe@#9i7zWczPZqtM$z7BAo=XF}gC|w^R|22q$%-@+Vlb87pd;-@GBlS5i+k=oZ+b
z&skKG<8($za&B^_eyQX#utI-PCf(17o`yzA*@3q*iuexss=Ww#s%svKkqW15lYIeq
zF)feArKGI#i4DByPmf`lmMCpARabNumE|(ud@jmY6FLI68nm-)=!><e#|D*HY8TZi
z(neM2gg(-hQ(tV!V_8gVf6lYPWAa6jKbx6_ceNfrmCV_>d4pxpBX=xkd8Kcn)T(8w
zz;YO?#5+xPB*SS6wPv#@<a+tohZ0%b7-?l4z5%|~CYr?;XnQ6xt_?G^PRm1=K4wZ`
z$kRuaznZ*SN)utU)kk|ro0%bVU4{^2zImNh%D+Dh^<^a1w0Vwk9=(8dxl^jnI6gjF
zJ<fG}B^8c3n_^yee)8)u_}n~hVbdzoHa*1=y!2_jU9X3gwN118bIJzuglH@=vt{H;
zXJu1JM)Z0n4C4fd-6)WCgc-(D6+~5E)8$>nV~x?lywF$M<1$4xZdF?Oym*L7UFuS5
zH}lh6)1EHdfi$Z_sjR0<Gujqn)QtQj;=~>V1&@oBab4|QtuCTBI7)Pf;j%`=s6^56
z6${{HW7cRW*!5-$73G^GyHw8@(da5RXV2jTrVujK7wh3D>!j$2CmO*mj-(n5s8$$#
zhBdjRjHQ>807gFIvCK%@1flhkDYK-${5#`HQj#gAIyq>2+Ok+#k7i4V^)hysQVg0>
zM;Q|GgY0`TntSm+mZhaC31paIiae6RM(4*W&-KoYzKv@YJz~JNrpTq@lA+Ye%j!lb
zk*A+j9B%uKJ8Lpx+8&W_SKJ|9IjM{$LkZ4_mxG0R(%a-qw6tx%o}bv1EV3ZZdW^0&
z%?{fzy<ET608i=?ZLvx0)v>Hdq-Z7Cl&v}y&0aM1+`VW-#F7u60_Bjhd^8jdip$`I
z%cq5V`TAHYD2Ld!ke23z-1#diSJtSL$2B*k1RlDltJSC~@RTs4YIG2Jrgw-UZ5z-&
zcdm0$%61Q+&alMAdfk*JQzuYbZl52|ud)}Ss!fBBQA)OaAtOf4OI6~NCofj^yPI`s
z^xVvO{5mOCB}&O(h>_#((fC?idnw`H7%0`(uk}zlU%Rn{#=wZd2$3yfEM233TBum{
z{iC{WEDZ)%YODHbb~^ORG!41y#!__|V~YIGc^UPDUQCD>$yi0)zp_;&ykaY^M9;fc
zEy3!Lv)jAqE2qYrVPusd*`YEp=tpr$O*=nYf#ofJuM%|?1~Y>74D}jWT>hZblqf7(
zj@S)^RHq6`0cXkFCEp(RGz~FrdhI@DygDr3m#WKtmozJKUj(X2Uqdz`OTl}iTZLMu
zGkgSaLEjy*Vu3Fk;o+d4FoN63%QS3iE^e(&@Ws?eDJs|CWURZx3!3JV-#=lLpawr-
zjH9`n(wBwhU)1${jDkq&$wf*DqSo-@;6of#d!a^!AV{1Z<ju-mtf?a)lsFj0m?C&n
z%NssH0h^?v*Ud3FF*q0*DI<Z-fyfl5`<ANhO;(H#UprXX>SGoEpY4VhG8mLT#z`3&
zpt39=ld8*?ho@hyyF;M&wD;jL&f1ji)-ehj2-V!eh-F#$fjQ3<_PQ1M5LEI<GBtCn
zW$V|B-?bj=kkW!YOa6FT&Uvk1(OEta$~LIhut0<{4x`rXHtF_S*$OrIBw0I+Aj#T}
zt3!0J05=$Z@A?Sw4j=LOEY!X?&KY)f8JP_#4|)h{_l?`%*^9qm*x{4Tf0BT}##TV6
zHxdlPp^9aV*UBbT_<93-KPPar8_Uof7TX*Jo<OI!*H@+u4x9+e(zfdI^`Utq4OZr5
z>kHKt=}?r`s%CK@`5y=%3Sp7|aBYKP3>k6q=>RHi1XrbCyFzrkEDJ9TD}_yXz+%e?
zZ2ZI**#)`n0Hb}@F9`v?$Pb<FYZ9tNN2aw<ept-C+1{Pro4cA<_2dY6+8&5M?|P_T
z^GQm95`J)zzGew0iNx{Q&fzV@<;(tie4`44clogRQ@?<<V(V$&SL~k(YHIeHmxP7i
zlsdeb__8>;(On=Pi#h2<{)3Q6NX!B+pS;3|+Z)b<N+(Ne52f3SaCSkku*x&^GfR(|
zt(Zk^`r(&9HB>Cz$GJykV*k8>1<pWTz#-}}Ve(-V4AANqPoO>WrN?WRqt^&Ued->>
zmy0M4pQ&inT<7|Rnn`q|=FN4a!=+w6BNdgiI+rYqjpjZewY%O$51m`qmMXN)YcMMA
zHNG^(F;73GLaj6-V9vQ7v@#lW*nx(8#W82;(7mDWS1kvI*liuNgxz+gcdir9Sm&^n
zmAy-Ow{<bC4lnPX4a{K{H>7f5iBZqJ(V?k8-D}Dwmf8NA)normYqoH)Yna1q3PC)$
zm&}vn08>F~G3+WDau*0vhrf7ja4-z^W^hm#BV`)4^`uU1N#RJ_n1>hM2J@umEaa_{
z9Wix{f=V6*YHh`3^{08^q9|lt6g2lmQI1)3eqg=u*xZH~x3TFiFrM<AVMq>P_bL1?
ze+Hif!)ccWmULDPwBVw6JSj>fqUDOq(%I_Sm`YKSXi}20g<3E9{o6~h0>iNHBU3C3
z@`M80POWCcluR(DLQB`3-qj8K(nW#&W$;;^rKCHXIfWQg{_2NKf8u!_k^L<!?hlj>
z1X_4yZmDOKFs;|SZGVm}FYRuf(b@}fz=jJ^P^&{opW@BeVWBqQYx3wOEOE0Dub|60
zv`xQg^z$O`Kn!W6@oyGOF6IIxkyLnFc)+gzI?JXqanLh3!!~Tq&gqotlCn{jR8e8x
z4R7wyOQ&K|%Y=tR%0>81k!g>b{4hH8y!U9RKbzRtv|N5%TnzNi<3iRs5W=Xa=%ih>
z$rdDEZo*Mt;3Ih&wb>%4h*StZ2Bizp((s!q3wq|DaszK0x7K^Z+frsKE=lWN4>LKq
z(*$DrYB)|V)R#NoI$!klT%O3hboP?;E*MMx2iGYxM^iKeNQTq<g*Wq(Y)G(D2+B{b
zr~EWCFaUa*IL~@_X{$Ebw|>Wn8&c*uP4@cES+a_0i-p|1ysb#Xue5RyZ{o2u8FDYu
zBI;7TqRP5aWGjgmvVt6fhRMQE5q=F(?K055iz8sw#-)l2cYG3RW)3mWVn9AUMTHC+
z{h)yi1ViQDNl>PFyq}V7Tr$}U5V-cCTG@2rHf*($28QuC3fN0Z<XNb9S}-ROS&RMQ
za?d-8pO=7yZD<lBVK*MD0>B|Ig{C+a)OeRts(9<(`C+^^={mPeibl{nC0~wjg+TM!
zO~9O^gb+3{N-*u$-oHHd_+6`HwX3B6_#<595KC-Y8<_PECMzcW)xQ=G=Se1KRXKti
z^HFk_VV6g~AAW4#!Cv)OHXsivA_o|`U?BB!v+#oCa&Zu}p8Go=VDx{PEkudl0)dl~
zLv+Zsao9@NHUenC>3Gk)sI5rW!(9_z*_q4jM)4T;$5l}N*>H1POWkh`?G4zHMM8*5
zG3*uzq9XYkAmOoyDtWVG2a(EUncNG5z+Vz);1vTcV(<$zSUDUrs@Gd7R~~~i%CHVc
zBh6Rb<TwJOGqVJA((%HJ;xGQotWy#XhfIn5>m;I6TMEQpqW{B06^DII4*m~#<O4hi
z=JBi}NgT-DD3SCPy_&j6SBk1!D-;ri;MySHRqzq1m)~+f{kO@$eT?Z^&{vYLGC;>n
zL&_!vj)23BDI$>q*Ysb<Yxm7(MK{n0H>|`KDLdk`3#kq9;C|^;^{LuJ@MR+NFP*49
zRmVvO!^wHxSxVpCpaqva8gV|IcQ;X+)*V<^PEn_Oa%uHX>Mk~`)MbEyK-g2K;!k5w
z!%5JjT_$O;t0FxV&}^?wl2af6ya;eqFRU-HRfNsKKfS6|Z=`|Bya3IIr)}2d6X-nc
z^*Kgyr!yr!lRJ<5!G`U~xJKAXll<-4Z*r$R(Fiz!gMZUa5GH#B<en|<hi0$>m?3JH
zzkWHEh3T+3+@dH+#0q&y^?Yeig-XSjn~S3}oW$;3K-Gg1bE_bp-we_n?8<(=JHVT-
ze{AM&I9XN-lk<j4ZE!*yqUAi#sd1QhgX8?@VRV{g%{UW=fwu~6`L;x?pqFqTmIh&q
z;pExWVRMqeAF)#NOok|%bFNO(zdWx(>>4EOqTEVVI0+vSoNdJsfC7PYe1xaZbhjw9
zjk}?ejSCW03l9?ujmwIO&?Gl7{x{)Tudf30LGf3*5z0i*zeIbQcC8BgeP_bIvw>fs
zWL)A-#_u8GF^|+o#p*zc)!(ACb72YnMk2pBS6wgViqmAYEPzFU?LGGBp3T4w0jH^Z
zYDLrx99)}l+3u$Zn+z16t8ZI*;G!B$r%t&FJxYUOB&fb-LM5Pl_GrvhG?A_1)+b7A
z269YAYSFM^Fr<RN`j40~P`LM`3EL#%kjdpPtPnE6qC%c#dh9c|N#4uAv6HePrepsq
zYYz7`0TP6@p%_K=kcHr~0h=9;BV3XrgC_(>i%6PFQgu0OR`Tv8uB66VU+E!;CzntP
zEf*F=64}MKl3rGlD?Bmg7gDsYguSTHVj#Jo=t|%onPpl?#|B?EydoSFj2McI#R;TX
z`6HqCeUX%M`iKV1Ve?TC4KW5Hnj70S+ObDP6=G}qWa+UkCS}QS3!#?~>8m`HR>irJ
z7LK(gtH|Z>3d>uBvw-Q2eX$S>{g@-2E5LLk33t_o>jt6tAa3l?oF-2fX^(<)t2`4N
zj>Ux@mr!C~x1iQ6eH3~*qg@gUs>aQLB0v|As8046GQq}{q$wR~OQ6vt$3TvfEn&<5
z%pVcW+aCn~6<IxzcZm(jzsOQ*hw7r7BIVZ*G#Q1f<|G9=SOoWxGE8eFlr!ig{R{SA
zG|r$<Md*eFqg*Crioq@|<hh*5^e~{y&YZ?CDSMYkmb+4I)D>^DYZT5PygeNtDhHU@
ziEwahv%>K)&HeBIJVxZ3%G(|_DLLf5@rJbel#@46pQ2b5k+9h}UpZ{8yy<U&MS~)R
zE#`iO3hn~7_N!taB9<^GQV4;L4ll2)WLL}QS3a(7lP!r>Iz>n}wp7?U%cRYH1S>TP
zji><}rd4PK=J%5wBZKj`^&VqT$Gn-8q_ZGe3epUr!6*`NHyjb6`&OKTU8?E9p(@RB
z0|QQ-te7x12v5o9g&%NtSM}1Dl?c@xaBf=uBsdZ#hlOnFEeXj*+|i7M!{QF^{c7<c
zE?8ex{&K<)7UF}$Q1JQq_)h_j|7QXGBJ<1!15lmGfgfvfwWIxM2LKr~C<O^h<OKmJ
zBUL*ZUuO>}k9VR2F9>*w#)W|A`s{+MJf2R^!Vl6Y(#hXdd@l>O^OQs?)CxkI-|^t}
zI|;u382JkcqDTh=pq#LuBej7zJOEPs2NGCT5FP;2`bU!F-$__7SncmO+mWG7h6S69
z0Rns=+=>oh0eFzBL4Q*SF+ZXF+Ai(yh62gwD&GlU$zlPmf0lyzyOcCojlW1it&#L+
zg@6nZlytnL0<8wjDI07D2>e|Nz=Og1i^6{(LH?=`g2Z>K?x!`N1;9eP5@?I#YDW<Q
zt?dp1a;KJm3c3*hNP-9S|4y)^0VDto1gL^QsbdnDIo>XOjAzq)`aSoLS8%0?1^lcX
z0*?d(bNXXh&^FirHMizvEpUyg=<e{QRNKNwE=lu~ueG6Hvtu0=1xi|^pw!(Z4ay5~
z=<U1|>eeR-{|#bWZL^RTb-5?Dqjs0rXAMDb*xh(VoTNt1csKl^@ZCujrq9cj*J3rj
z2?~3flLUtm_JVp9;cFR}=?WWVaJ-a<E322bVTldm%ii$RL5iePUco7CXhdMXN3t9$
z0pPHbs-M^TGPa@_q>C}Jk#=;qxd$sWFrlDyuhtV52*C?+nNs1%FV?Bkw@X@OJ}d`r
zRL22In;ix?crVS~%Uk1z*?e#U5Ti-Q2Rc8~1#EYhCPuUxL*6TXh8Yt|5tHO+jHX>K
ze`=MOQzy-!$j@Gy5I&+FJ|c;Qxpn*lfbW+2@%{hrmO3`n$#?(I@7l4x6&(TQdXOtt
zuR0`W@5CiCZ4eVBKTbw_SDjlYeo>PLi|h!9P$%gxDgJV=n}1%J|CutsRw_BbQ=?AO
z@{r&Aszd+uJ%Qbjc`74h>5TNfLOEQ+SF|~NDC<6$R<+w#4as<rsi-am$!1}^?d<1P
zKoz`&qof*+&@p)-rTwbZc=_mqXws;TqU|<Z9VK%8h=m@hShBmZOD?ENK><rj98{)C
zUP?qbfUgBS5lpt|SRBk_1I9fII>!F^8HT6VQiR7eQ-mB99W<(_Jk5tFtP=FuffXhA
zi>*pz<aA-28cKZeOYs$t7%g_GnG)X~TZt75{OlhB3oc$lmoA~+2LZ6DxurI>E^|q0
zwtYNax&-~o{KQP)kFO=Lz?I9Ywf^on-bPBh<s_Z!NVNPD%j=pV8}B3VRuqTmAFX24
zu2ElvkEL&EIRX$8yv-rDxmgx1W8rj>(zjeidZ(u@hL6H4J?Y5yb=CEh65CU~izQU|
z3Xz;5UP}*rGgd$?F6|$-i@b%q#MrIz|2~UE1Iv!Ose<EaWeMpC9K2xV`ZQVDY`*<j
zBE<!tkFTG__wN_B>U{J+&OmX~Goe?nQ|Z^VzdmK@QV~fjOS`_l@B_i>7gUyZu<#S{
zY7dAvO;7)ZNnt*|ILXQ;VWwX4iCL=fO8eW;kV4DH-RZbryVt@7Zb_kQW+ylDphwsF
z7S-HeS2w5_;$Np07vpl=<ESe89M2$&DrMG&l6#%67?RB#$o&#Q@YTvw4`$0U{cw4{
zS^U{hX{*%Ch|iE%!N9DK-Lw`xHXr5|zPBYIiZwnh;gI08EuyV+t!hXMS~a7Bvc$I?
z;H(Q|NRI#qOsWUz0sY=u9^eak9V*LyO;NL!L!zm7pJF_lZ{-<1mT0PW{1UCcuM(J{
zsc#tDGEMV2aym}uz?0siWj1i?s@WH~Qc82%`dQ4tg-eHO@Uc6^sCu@6U)zb_Yf$#{
zQ9lD;HRF@L|ENE6C?yu~UL8!Tjngc0<IEz6A75AdvJ}+kJ2}2{su3~doCzE;9i!Zt
z4ou|;d>jK$nHPIFls+Xf11r=TiEzD_Kd=OyGtTI++VkFRJclqEz>Y`^_ENLK9edxR
z5;Mn{PRw%H;+-lBw047S;tEl1P6f^VF{IYZir*?(<O@+?-;U?jXcVqb^nM=T<lu9B
z-JvHR^tS8cTI!rhnm2)Wu*E1|St^U!G`GzalO1t_`encCh$reVmzZ&TPhM2Nnzy{}
z1$%o)$q?lZ1;Z2j-t9e%C;m02BU>f%&BeaTUC%T=6uirv#((X2rYt6~EZK6kiM{)w
z1<Ve4I-cvV*Uyj{_#Bt#8sigNWn{@vau8kLH?#y&*BHA!5f7~~W1Zk@zFSmy*t@w;
z%|kf9ar;2z(>kknc~ykFx(VqG*dxFv$Q75Mwx2oQ=xX$>E3@e@MX}y@h|$RhJLpAP
zkWWT>Q4h#%e+Vb!B+_b;43fEvu_5yq<Pg1!K_Bcz`t&T~2W3NM+GA=^#Y9_2dl;%=
zF3S5v)eoS@lckUy*5gm4xhM}^<zm!Fb<m1{#hlT4TyV^nFoL1d(zVpbSg$5IZe7|L
zW!ZvQh(x0n&Ks^hs12L!=E!4KrADx0A_sh6&5+lLItuL*_qL2bSFnz*ihSOB;;zyi
zPx7^oIcGOvalx1s1L1kf#BJeA1yU0=>FYU{WbGz8r&)ar_OcIl#r#Io*S5+1b}v0D
zTSAEU_lc<-Lb$~fEXr&a7MXfR%1m)~k}LL0uw3O>c$Ov;A#85ym(7S~ce_BJ5}8du
zJLlbdOP`O2sOS2!-%93)Kn;rxY(SuuN+SODm=lxV#gDJzult$5Pm4bARX^hzd-56b
z@lMs#NerBtRH3*`Z*Q9p2!NWg91}z;($3XjS_0OQN_P<Qs9G@qHEIxvUeR>Gs5Cpv
zTd}qfaiiAS!safE%yn2KH(1H}tFU7j=wXO+hL==djNdgv@EZ*LAbbQgY4KG*9aj(h
z09jH(SU9XG*gwU;Is9}6-c)`2+FUR92zcp!1o%Ebcq6g%r;N||_QMtU-4I#wzcBn1
z6%Ee_R?GgAlAk<aSw2nr%J2d!|5z$0@cJSiy<R96Wb{q;^MhA6zcGoL^?G`Uljy47
z87&tbRVbT#a}oI#Un;Nq0!048v;e)0_r@!l&3nN^^zy_CHq<->@;9W5CL@9lLcEX&
zhlN8_#0*CF;w57~*d3JAs<(;4ZQ!0<u<8-a%=1FLkS7^`Uf^r(kxK(Vp5;4XXNY#&
z{~`KaLylGR8HFcUbebo#DCQ$xNUC`S%X-nA7+gnyYgp}clOvpY#PxY3$0g&|Kn{sZ
zI+uP<GuLUQXu9S$o^i{&;mTUOo6o`Am}n!}tx^aSoV;-7oJ&>OYH3zHvu;5NV|%-y
z<a_0#-h3O$SAzOWuUc5nPCcd0e9TWAZidHvYjD@?l?@V)fU4ZTnK(%KY5DAcS|bUU
zOO{tO&3|`KVgrra5OG!YE3KKBu>Jw-vf7z3v>op+*uezzQBJD?BUy#TX|*?P({SQ>
zn&;u}#dB=6G}Huh21`iD9q2TIrGvd6zESXJ)NQ}Bw4^Jti+~wk#on$Cr7>(vue?rc
zrb&*uhsknoER58@$u_=6OL;9OSdfEc|JFemL=+)Ej-RQY|8Uwq@EWUZvTe8<RdsfF
z=GrHOzHG|)LYO{;i!=_sCG1}!mV_T+fd63wSl`=>h&C<K7Ydq<6r>*Lc6TE?1JK*X
zAzZD!B6A~Y1uAe3_>w2!jsFgb`Ih22^bf|>%1m8CORL|NLNRU^RSHqH=FopB?}V9r
z>HdBCdS_-4tCb~@FNiVo*LLdy<|Q5ALu8!2;#p(51~l~uHr8ID3vLFydL3P6_C9fK
ztMSa_w?-P$b~Wibw*E}R!!One=GZSth~`^KKYBlXH@|K6dD-*qG{ujT_Bg*T?arfz
z&CLRs+r)Y;L41ChsGbGL*w=i|cG+um(nb~uE}kP`5pqsN9G?Ssw_F*gLdKa6y2Lfy
zazK@DavoLB?0W=Q_W7Nu>^f;UL9DEOME}Cv+H0HlE9CVZsQN{QkUO9J#8M<UE*Fc?
zSuZ?+c`Yi@@3TysZ_nPk{4;{F@#yL$48%N%%@QfZDx`8V<I2siczt#K9)68T(=ad%
zSpJYnOhRWPsUR$f{4ONSNu=64_aR*V4H#}*nWSu@)OULL>LG>@OaqG%K6ysO#YxsC
z7@MkUuOW>>{-E_1+P<?Rh{$e^{NcgW@=17hGWW;v*$?d(=bM}vyFTsmcf$AOeVxw?
z0??wp7K!X<ZskpvOFZ{4+&hm6EZ&+sBlQY>Ad`#`_BoYqXQ#s0H|E<R5LTPI9Uf)m
ziXp+h7Pd1MH#3~AOjDtDdf<XlV@CQw5ADKcuo2s;lgQv?FrtO^4Jtd;6t~Tnh1@nD
zK2eAVFm7d;{T3d6H`4__^`(s_D_&a5miE(NIFS+{(d574D1q@k9QISx#p}#!@)rU_
z<zuEPpH>@!=T4=ol+P0GF5L_m@xz*!KGXZ{q*AiYp&goQJBRvgvW=HUA~2=`?|)Sx
zU^BdH(HTpC`I1i4x5eSLI0=|J#)Vr#xOMRtWc>;1zB+zqBe{}bCNSaiusskRDg|YH
zhWs&lae6|K*kz&mL>HUk3wR$bOuB0B>LrP|d%6>?D~Il1{kQ_BCD&R}B2uaa#)wh2
zi$A<WDEE6`RUV}~=Ob9q8dZ_>K%@|%wshd(%{W*r+6eo4y<smu^p$2*U}qJcJjl?7
zh%n|QlP%I3ibv(N-ouO{PcE)^&47wIvqwI<1-W?4AO`|L2LBhfB>dhWxN4(C*A13$
zUqybDTcy}h9nR16SX7d|z`tSpW^@gl=~xqKIHa)@c_j)z2(P8CUjuQofy_PJ>1+KX
zDsviBLb+(3Ix~JkZ=qGwPPoBmq6|q0E^QU6;;$<B@kF@t1`KLDgPLkBxe7Zeu!aCZ
z-a;QvVW+~{7G~yg#TMk-8?z+>eUDo=Fa`1GwZ1j2WN*To>ssIbO0ReLIU%p}LAMr`
zv%?^*@2FZjhijf84SYlYOj}tGEClCOBb(x_br$z;N<;kyhYVE}wZ@w=5{0IyhOT?j
z4ws1$vuh1iP-;<ojc1CA46e4VI!{W*6+6U3()XfM<;66wu<)vs7S=7lC>}y<ep1*O
z0GQ9>cs=TR#&}&&6LCdZPDHJNmN3B98X2K|N(zY<UysA^!7z!ge8=tleVC~XYsLx8
z*IzHWvW2tDJYkBrqb*Nqh^pqdMw1Y{Q+h?U)<Bo+fzSg;Oi7{TQrXRB?;OjQW0fOt
zS!kpOMO`&ouC-ch61c=xBvP=jk7dU)kyEuyWaOC!P(wY|zHuwqJ)>^C*_-0}oMi6_
zc5ACSPo!1}dS09}!eB^Sb)OEN!JvzcyRywf9OJBYS;mr)cX?NyRjlz$@4<LSE?y%-
zt|W}#M`s^FS={QbTv-A_*jN+PS8=g^f;J+Lu^3k@aHMRUO2*N{_$^=|K`imknjw|U
z{PH(1p<=_*JT+c7-c|^p462Ig<xaml&^}6H!Ze8COxPr8%rbWSDr{yGzET4Y`!p;7
L{(WHJ(bWF|@-mw%

literal 0
HcmV?d00001

diff --git a/labworks/LW4/LR4.ipynb b/labworks/LW4/LR4.ipynb
new file mode 100644
index 0000000..0c2ab86
--- /dev/null
+++ b/labworks/LW4/LR4.ipynb
@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","mount_file_id":"1QIiOMAmZBjzdMF2Bi5JM-jXjf4HLANTm","authorship_tag":"ABX9TyP9+9H2XR/BwZPK6jFtI0kW"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"markdown","source":["1) В среде Google Colab создали новый блокнот (notebook). Импортировали необходимые для работы библиотеки и модули. Настроили блокнот для работы с аппаратным ускорителем GPU."],"metadata":{"id":"YqtYef25bm5U"}},{"cell_type":"code","source":["from tensorflow import keras\n","from tensorflow.keras import layers\n","from tensorflow.keras.models import Sequential\n","import matplotlib.pyplot as plt\n","import numpy as np"],"metadata":{"id":"Y1y4sLVsW546","executionInfo":{"status":"ok","timestamp":1765387055442,"user_tz":-180,"elapsed":13450,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}}},"execution_count":2,"outputs":[]},{"cell_type":"code","source":["import tensorflow as tf\n","device_name = tf.test.gpu_device_name()\n","if device_name != '/device:GPU:0':\n","  raise SystemError('GPU device not found')\n","print('Found GPU at: {}'.format(device_name))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0AqVK0T-bWzu","executionInfo":{"status":"ok","timestamp":1765387056464,"user_tz":-180,"elapsed":8,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"45a1df4b-1766-425c-85c0-c0ec3410336d"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["Found GPU at: /device:GPU:0\n"]}]},{"cell_type":"markdown","source":["2) Загрузили набор данных IMDb, содержащий оцифрованные отзывы на фильмы, размеченные на два класса: позитивные и негативные. При загрузке набора данных параметр seed выбрали равным значению (4k – 1)=39, где k=10 – номер бригады. Вывели размеры полученных обучающих и тестовых массивов данных."],"metadata":{"id":"6ADb8hakbfjl"}},{"cell_type":"code","source":["# загрузка датасета\n","from keras.datasets import imdb\n","\n","vocabulary_size = 5000\n","index_from = 3\n","\n","(X_train, y_train), (X_test, y_test) = imdb.load_data(\n","    path=\"imdb.npz\",\n","    num_words=vocabulary_size,\n","    skip_top=0,\n","    maxlen=None,\n","    seed=39,\n","    start_char=1,\n","    oov_char=2,\n","    index_from=index_from\n","    )\n","\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of y train:', y_train.shape)\n","print('Shape of X test:', X_test.shape)\n","print('Shape of y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"JE5QF7cLbhKL","executionInfo":{"status":"ok","timestamp":1765387060440,"user_tz":-180,"elapsed":3967,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"4668f394-934d-4f2a-8a08-dd9961f12d12"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz\n","\u001b[1m17464789/17464789\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n","Shape of X train: (25000,)\n","Shape of y train: (25000,)\n","Shape of X test: (25000,)\n","Shape of y test: (25000,)\n"]}]},{"cell_type":"markdown","source":["3) Вывели один отзыв из обучающего множества в виде списка индексов слов. Преобразовали список индексов в текст и вывели отзыв в виде текста. Вывели длину отзыва. Вывели метку класса данного отзыва и название класса (1 – Positive, 0 – Negative)."],"metadata":{"id":"dm8qlFzecBEi"}},{"cell_type":"code","source":["# создание словаря для перевода индексов в слова\n","# загрузка словаря \"слово:индекс\"\n","word_to_id = imdb.get_word_index()\n","\n","# уточнение словаря\n","word_to_id = {key:(value + index_from) for key,value in word_to_id.items()}\n","word_to_id[\"<PAD>\"] = 0\n","word_to_id[\"<START>\"] = 1\n","word_to_id[\"<UNK>\"] = 2\n","word_to_id[\"<UNUSED>\"] = 3\n","\n","# создание обратного словаря \"индекс:слово\"\n","id_to_word = {value:key for key,value in word_to_id.items()}"],"metadata":{"id":"6Uf4JIlDcCGm","executionInfo":{"status":"ok","timestamp":1765387060803,"user_tz":-180,"elapsed":361,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"8dcff087-874f-4a5b-d579-cd42b1294037"},"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb_word_index.json\n","\u001b[1m1641221/1641221\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"]}]},{"cell_type":"code","source":["print(X_train[39])\n","print('len:',len(X_train[39]))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Z0sjggGrcH-1","executionInfo":{"status":"ok","timestamp":1765387060812,"user_tz":-180,"elapsed":7,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"bf26b133-276c-420d-f55d-92e29e1b49b9"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["[1, 3206, 2, 3413, 3852, 2, 2, 73, 256, 19, 4396, 3033, 34, 488, 2, 47, 2993, 4058, 11, 63, 29, 4653, 1496, 27, 4122, 54, 4, 1334, 1914, 380, 1587, 56, 351, 18, 147, 2, 2, 15, 29, 238, 30, 4, 455, 564, 167, 1024, 2, 2, 2, 4, 2, 65, 33, 6, 2, 1062, 3861, 6, 3793, 1166, 7, 1074, 1545, 6, 171, 2, 1134, 388, 7, 3569, 2, 567, 31, 255, 37, 47, 6, 3161, 1244, 3119, 19, 6, 2, 11, 12, 2611, 120, 41, 419, 2, 17, 4, 3777, 2, 4952, 2468, 1457, 6, 2434, 4268, 23, 4, 1780, 1309, 5, 1728, 283, 8, 113, 105, 1037, 2, 285, 11, 6, 4800, 2905, 182, 5, 2, 183, 125, 19, 6, 327, 2, 7, 2, 668, 1006, 4, 478, 116, 39, 35, 321, 177, 1525, 2294, 6, 226, 176, 2, 2, 17, 2, 1220, 119, 602, 2, 2, 592, 2, 17, 2, 2, 1405, 2, 597, 503, 1468, 2, 2, 17, 2, 1947, 3702, 884, 1265, 3378, 1561, 2, 17, 2, 2, 992, 3217, 2393, 4923, 2, 17, 2, 2, 1255, 2, 2, 2, 117, 17, 6, 254, 2, 568, 2297, 5, 2, 2, 17, 1047, 2, 2186, 2, 1479, 488, 2, 4906, 627, 166, 1159, 2552, 361, 7, 2877, 2, 2, 665, 718, 2, 2, 2, 603, 4716, 127, 4, 2873, 2, 56, 11, 646, 227, 531, 26, 670, 2, 17, 6, 2, 2, 3510, 2, 17, 6, 2, 2, 2, 3014, 17, 6, 2, 668, 2, 503, 1468, 2, 19, 11, 4, 1746, 5, 2, 4778, 11, 31, 7, 41, 1273, 154, 255, 555, 6, 1156, 5, 737, 431]\n","len: 274\n"]}]},{"cell_type":"code","source":["review_as_text = ' '.join(id_to_word[id] for id in X_train[39])\n","print(review_as_text)\n","print('len:',len(review_as_text))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"KLVb0gQ7cMKH","executionInfo":{"status":"ok","timestamp":1765387060830,"user_tz":-180,"elapsed":16,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"d95be73d-324b-40de-d096-3a99a9cdfa2b"},"execution_count":7,"outputs":[{"output_type":"stream","name":"stdout","text":["<START> troubled <UNK> magazine photographer <UNK> <UNK> well played with considerable intensity by michael <UNK> has horrific nightmares in which he brutally murders his models when the lovely ladies start turning up dead for real <UNK> <UNK> that he might be the killer writer director william <UNK> <UNK> <UNK> the <UNK> story at a <UNK> pace builds a reasonable amount of tension delivers a few <UNK> effective moments of savage <UNK> violence one woman who has a plastic garbage bag with a <UNK> in it placed over her head <UNK> as the definite <UNK> inducing highlight puts a refreshing emphasis on the nicely drawn and engaging true to life characters further <UNK> everything in a plausible everyday world and <UNK> things off with a nice <UNK> of <UNK> female nudity the fine acting from an excellent cast helps matters a whole lot <UNK> <UNK> as <UNK> charming love interest <UNK> <UNK> james <UNK> as <UNK> <UNK> double <UNK> brother b j <UNK> <UNK> as <UNK> concerned psychiatrist dr frank curtis don <UNK> as <UNK> <UNK> gay assistant louis pamela <UNK> as <UNK> <UNK> detective <UNK> <UNK> <UNK> little as a hard <UNK> police chief and <UNK> <UNK> as sweet <UNK> model <UNK> r michael <UNK> polished cinematography makes impressive occasional use of breathtaking <UNK> <UNK> shots jack <UNK> <UNK> <UNK> score likewise does the trick <UNK> up in cool bit parts are robert <UNK> as a <UNK> <UNK> sally <UNK> as a <UNK> <UNK> <UNK> shower as a <UNK> female <UNK> b j <UNK> with in the ring and <UNK> bay in one of her standard old woman roles a solid and enjoyable picture\n","len: 1584\n"]}]},{"cell_type":"markdown","source":["4) Вывели максимальную и минимальную длину отзыва в обучающем множестве."],"metadata":{"id":"G4MDeQlFcVU0"}},{"cell_type":"code","source":["print('MAX Len: ',len(max(X_train, key=len)))\n","print('MIN Len: ',len(min(X_train, key=len)))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"tGV9ptPGcWXJ","executionInfo":{"status":"ok","timestamp":1765387060843,"user_tz":-180,"elapsed":6,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"285002ae-1451-468f-89bb-2b96b426446b"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["MAX Len:  2494\n","MIN Len:  11\n"]}]},{"cell_type":"markdown","source":["5) Провели предобработку данных. Выбрали единую длину, к которой будут приведены все отзывы. Короткие отзывы дополнили спецсимволами, а длинные обрезали до выбранной длины."],"metadata":{"id":"t6dS8DRnccz6"}},{"cell_type":"code","source":["#предобработка данных\n","from tensorflow.keras.utils import pad_sequences\n","\n","max_words = 500\n","X_train = pad_sequences(X_train, maxlen=max_words, value=0, padding='pre', truncating='post')\n","X_test = pad_sequences(X_test, maxlen=max_words, value=0, padding='pre', truncating='post')"],"metadata":{"id":"eRN7vYrScd_T","executionInfo":{"status":"ok","timestamp":1765387062120,"user_tz":-180,"elapsed":1275,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}}},"execution_count":9,"outputs":[]},{"cell_type":"markdown","source":["6. Повторили пункт 4."],"metadata":{"id":"KduPqn6gcmJe"}},{"cell_type":"code","source":["print('MAX Len: ',len(max(X_train, key=len)))\n","print('MIN Len: ',len(min(X_train, key=len)))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"cG5lyZ1icon9","executionInfo":{"status":"ok","timestamp":1765387062147,"user_tz":-180,"elapsed":26,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"fcc705bd-894c-4c01-8b03-0e943c05cd15"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["MAX Len:  500\n","MIN Len:  500\n"]}]},{"cell_type":"markdown","source":["7) Повторили пункт 3. Сделали вывод о том, как отзыв преобразовался после предобработки."],"metadata":{"id":"8iQi-RT8cvrI"}},{"cell_type":"code","source":["print(X_train[39])\n","print('len:',len(X_train[39]))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"4LedIjtMcwo_","executionInfo":{"status":"ok","timestamp":1765387062160,"user_tz":-180,"elapsed":6,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"fd4978d5-fb69-4946-dfbb-a426a2261e5c"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["[   0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    0    0    0    0    0    0    0    0    0    0    0    0\n","    0    0    1 3206    2 3413 3852    2    2   73  256   19 4396 3033\n","   34  488    2   47 2993 4058   11   63   29 4653 1496   27 4122   54\n","    4 1334 1914  380 1587   56  351   18  147    2    2   15   29  238\n","   30    4  455  564  167 1024    2    2    2    4    2   65   33    6\n","    2 1062 3861    6 3793 1166    7 1074 1545    6  171    2 1134  388\n","    7 3569    2  567   31  255   37   47    6 3161 1244 3119   19    6\n","    2   11   12 2611  120   41  419    2   17    4 3777    2 4952 2468\n"," 1457    6 2434 4268   23    4 1780 1309    5 1728  283    8  113  105\n"," 1037    2  285   11    6 4800 2905  182    5    2  183  125   19    6\n","  327    2    7    2  668 1006    4  478  116   39   35  321  177 1525\n"," 2294    6  226  176    2    2   17    2 1220  119  602    2    2  592\n","    2   17    2    2 1405    2  597  503 1468    2    2   17    2 1947\n"," 3702  884 1265 3378 1561    2   17    2    2  992 3217 2393 4923    2\n","   17    2    2 1255    2    2    2  117   17    6  254    2  568 2297\n","    5    2    2   17 1047    2 2186    2 1479  488    2 4906  627  166\n"," 1159 2552  361    7 2877    2    2  665  718    2    2    2  603 4716\n","  127    4 2873    2   56   11  646  227  531   26  670    2   17    6\n","    2    2 3510    2   17    6    2    2    2 3014   17    6    2  668\n","    2  503 1468    2   19   11    4 1746    5    2 4778   11   31    7\n","   41 1273  154  255  555    6 1156    5  737  431]\n","len: 500\n"]}]},{"cell_type":"code","source":["review_as_text = ' '.join(id_to_word[id] for id in X_train[39])\n","print(review_as_text)\n","print('len:',len(review_as_text))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"CSssMrdVc16R","executionInfo":{"status":"ok","timestamp":1765387062206,"user_tz":-180,"elapsed":44,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"59e36760-8cd9-4d62-b956-4d18e352836d"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["<PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <START> troubled <UNK> magazine photographer <UNK> <UNK> well played with considerable intensity by michael <UNK> has horrific nightmares in which he brutally murders his models when the lovely ladies start turning up dead for real <UNK> <UNK> that he might be the killer writer director william <UNK> <UNK> <UNK> the <UNK> story at a <UNK> pace builds a reasonable amount of tension delivers a few <UNK> effective moments of savage <UNK> violence one woman who has a plastic garbage bag with a <UNK> in it placed over her head <UNK> as the definite <UNK> inducing highlight puts a refreshing emphasis on the nicely drawn and engaging true to life characters further <UNK> everything in a plausible everyday world and <UNK> things off with a nice <UNK> of <UNK> female nudity the fine acting from an excellent cast helps matters a whole lot <UNK> <UNK> as <UNK> charming love interest <UNK> <UNK> james <UNK> as <UNK> <UNK> double <UNK> brother b j <UNK> <UNK> as <UNK> concerned psychiatrist dr frank curtis don <UNK> as <UNK> <UNK> gay assistant louis pamela <UNK> as <UNK> <UNK> detective <UNK> <UNK> <UNK> little as a hard <UNK> police chief and <UNK> <UNK> as sweet <UNK> model <UNK> r michael <UNK> polished cinematography makes impressive occasional use of breathtaking <UNK> <UNK> shots jack <UNK> <UNK> <UNK> score likewise does the trick <UNK> up in cool bit parts are robert <UNK> as a <UNK> <UNK> sally <UNK> as a <UNK> <UNK> <UNK> shower as a <UNK> female <UNK> b j <UNK> with in the ring and <UNK> bay in one of her standard old woman roles a solid and enjoyable picture\n","len: 2940\n"]}]},{"cell_type":"markdown","source":["8) Вывели предобработанные массивы обучающих и тестовых данных и их размерности."],"metadata":{"id":"q0vqP9aFc58N"}},{"cell_type":"code","source":["# вывод данных\n","print('X train: \\n',X_train)\n","print('X train: \\n',X_test)\n","\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of X test:', X_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"g64JxLfVc607","executionInfo":{"status":"ok","timestamp":1765387062215,"user_tz":-180,"elapsed":6,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"18b90fd0-1838-4396-d59d-b248fda1d34b"},"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["X train: \n"," [[   0    0    0 ...    7    4 2407]\n"," [   0    0    0 ...   34  705    2]\n"," [   0    0    0 ... 2222    8  369]\n"," ...\n"," [   0    0    0 ...   11    4 4596]\n"," [   0    0    0 ...  574   42   24]\n"," [   0    0    0 ...    7   13 3891]]\n","X train: \n"," [[   0    0    0 ...    6   52   20]\n"," [   0    0    0 ...   62   30  821]\n"," [   0    0    0 ...   24 3081   25]\n"," ...\n"," [   0    0    0 ...   19  666 3159]\n"," [   0    0    0 ...    7   15 1716]\n"," [   0    0    0 ... 1194   61  113]]\n","Shape of X train: (25000, 500)\n","Shape of X test: (25000, 500)\n"]}]},{"cell_type":"markdown","source":["9) Реализовали модель рекуррентной нейронной сети, состоящей из слоев Embedding, LSTM, Dropout, Dense, и обучили ее на обучающих данных с выделением части обучающих данных в качестве валидационных. Вывели информацию об архитектуре нейронной сети. Добились качества обучения по метрике accuracy не менее 0.8."],"metadata":{"id":"tt0ie0K0dAbR"}},{"cell_type":"code","source":["embed_dim = 32\n","lstm_units = 64\n","\n","model = Sequential()\n","model.add(layers.Embedding(input_dim=vocabulary_size, output_dim=embed_dim, input_length=max_words, input_shape=(max_words,)))\n","model.add(layers.LSTM(lstm_units))\n","model.add(layers.Dropout(0.5))\n","model.add(layers.Dense(1, activation='sigmoid'))\n","\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":363},"id":"jD3pkS_qdBmo","executionInfo":{"status":"ok","timestamp":1765387064134,"user_tz":-180,"elapsed":1912,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"9e9c0371-8141-4d53-afb6-ebe331e090e3"},"execution_count":14,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/embedding.py:97: UserWarning: Argument `input_length` is deprecated. Just remove it.\n","  warnings.warn(\n","/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/embedding.py:100: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(**kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ embedding (\u001b[38;5;33mEmbedding\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m500\u001b[0m, \u001b[38;5;34m32\u001b[0m)        │       \u001b[38;5;34m160,000\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ lstm (\u001b[38;5;33mLSTM\u001b[0m)                     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │        \u001b[38;5;34m24,832\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m65\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ embedding (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">500</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)        │       <span style=\"color: #00af00; text-decoration-color: #00af00\">160,000</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ lstm (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">LSTM</span>)                     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │        <span style=\"color: #00af00; text-decoration-color: #00af00\">24,832</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">65</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m184,897\u001b[0m (722.25 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">184,897</span> (722.25 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m184,897\u001b[0m (722.25 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">184,897</span> (722.25 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["# компилируем и обучаем модель\n","batch_size = 64\n","epochs = 3\n","model.compile(loss=\"binary_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n","model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.2)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UK281-h_dcQk","executionInfo":{"status":"ok","timestamp":1765387088620,"user_tz":-180,"elapsed":24484,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"b252ad63-dabc-44fb-bf64-2d9e1e431d62"},"execution_count":15,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/3\n","\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 23ms/step - accuracy: 0.6315 - loss: 0.6268 - val_accuracy: 0.8072 - val_loss: 0.4273\n","Epoch 2/3\n","\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 20ms/step - accuracy: 0.8559 - loss: 0.3469 - val_accuracy: 0.8496 - val_loss: 0.3603\n","Epoch 3/3\n","\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 21ms/step - accuracy: 0.8993 - loss: 0.2662 - val_accuracy: 0.8666 - val_loss: 0.3242\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.src.callbacks.history.History at 0x7ee57a9e6d20>"]},"metadata":{},"execution_count":15}]},{"cell_type":"code","source":["test_loss, test_acc = model.evaluate(X_test, y_test)\n","print(f\"\\nTest accuracy: {test_acc}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"2Jdh6S_8dgXE","executionInfo":{"status":"ok","timestamp":1765387095405,"user_tz":-180,"elapsed":6779,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"492ad1bc-cd39-4e7c-dca5-c523652318b4"},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 9ms/step - accuracy: 0.8714 - loss: 0.3110\n","\n","Test accuracy: 0.8674799799919128\n"]}]},{"cell_type":"markdown","source":["10) Оценили качество обучения на тестовых данных:\n","- вывели значение метрики качества классификации на тестовых данных\n","- вывели отчет о качестве классификации тестовой выборки\n","- построили ROC-кривую по результату обработки тестовой выборки и вычислили площадь под ROC-кривой (AUC ROC)"],"metadata":{"id":"sDkhhezJdpNi"}},{"cell_type":"code","source":["#значение метрики качества классификации на тестовых данных\n","print(f\"\\nTest accuracy: {test_acc}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"OeP6ss3CdotA","executionInfo":{"status":"ok","timestamp":1765387095425,"user_tz":-180,"elapsed":16,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"b8cd954e-ae86-4f53-fed5-f46a01a72288"},"execution_count":17,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","Test accuracy: 0.8674799799919128\n"]}]},{"cell_type":"code","source":["#отчет о качестве классификации тестовой выборки\n","y_score = model.predict(X_test)\n","y_pred = [1 if y_score[i,0]>=0.5 else 0 for i in range(len(y_score))]\n","\n","from sklearn.metrics import classification_report\n","print(classification_report(y_test, y_pred, labels = [0, 1], target_names=['Negative', 'Positive']))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"YyVafpMldt5g","executionInfo":{"status":"ok","timestamp":1765387105893,"user_tz":-180,"elapsed":10466,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"88178647-99c1-4628-d374-e86bf709fae9"},"execution_count":18,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 7ms/step\n","              precision    recall  f1-score   support\n","\n","    Negative       0.86      0.88      0.87     12500\n","    Positive       0.87      0.86      0.87     12500\n","\n","    accuracy                           0.87     25000\n","   macro avg       0.87      0.87      0.87     25000\n","weighted avg       0.87      0.87      0.87     25000\n","\n"]}]},{"cell_type":"code","source":["#построение ROC-кривой и AUC ROC\n","from sklearn.metrics import roc_curve, auc\n","\n","fpr, tpr, thresholds = roc_curve(y_test, y_score)\n","plt.plot(fpr, tpr)\n","plt.grid()\n","plt.xlabel('False Positive Rate')\n","plt.ylabel('True Positive Rate')\n","plt.title('ROC')\n","plt.show()\n","print('AUC ROC:', auc(fpr, tpr))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":490},"id":"N05HejFXdyp-","executionInfo":{"status":"ok","timestamp":1765387106261,"user_tz":-180,"elapsed":366,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"acc69a49-92f4-4e4c-cd2d-e2870ddda448"},"execution_count":19,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["AUC ROC: 0.9387573504\n"]}]}]}
\ No newline at end of file
diff --git a/labworks/LW4/report.md b/labworks/LW4/report.md
new file mode 100644
index 0000000..1e430f5
--- /dev/null
+++ b/labworks/LW4/report.md
@@ -0,0 +1,367 @@
+# Отчёт по лабораторной работе №4
+
+**Кирсанов Егор, Кобзев Александр — А-01-22**
+
+---
+
+## 1. В среде Google Colab создали новый блокнот (notebook). Настроили блокнот для работы с аппаратным ускорителем GPU.
+
+```python
+from google.colab import drive
+drive.mount('/content/drive')
+import os
+os.chdir('/content/drive/MyDrive/Colab Notebooks/is_lab4')
+
+from tensorflow import keras
+from tensorflow.keras import layers
+from tensorflow.keras.models import Sequential
+import matplotlib.pyplot as plt
+import numpy as np
+```
+
+```python
+import tensorflow as tf
+device_name = tf.test.gpu_device_name()
+if device_name != '/device:GPU:0':
+  raise SystemError('GPU device not found')
+print('Found GPU at: {}'.format(device_name))
+```
+
+```
+Found GPU at: /device:GPU:0
+```
+
+---
+
+## 2. Загрузили набор данных IMDb, содержащий оцифрованные отзывы на фильмы, размеченные на два класса: позитивные и негативные. При загрузке набора данных параметр seed выбрали равным (4k – 1) = 39, где k = 10 – номер бригады. Вывели размеры полученных обучающих и тестовых массивов данных.
+
+```python
+# загрузка датасета
+from keras.datasets import imdb
+
+vocabulary_size = 5000
+index_from = 3
+
+(X_train, y_train), (X_test, y_test) = imdb.load_data(
+    path="imdb.npz",
+    num_words=vocabulary_size,
+    skip_top=0,
+    maxlen=None,
+    seed=39,
+    start_char=1,
+    oov_char=2,
+    index_from=index_from
+    )
+
+# вывод размерностей
+print('Shape of X train:', X_train.shape)
+print('Shape of y train:', y_train.shape)
+print('Shape of X test:', X_test.shape)
+print('Shape of y test:', y_test.shape)
+```
+
+```
+Shape of X train: (25000,)
+Shape of y train: (25000,)
+Shape of X test: (25000,)
+Shape of y test: (25000,)
+```
+
+---
+
+## 3. Вывели один отзыв из обучающего множества в виде списка индексовслов. Преобразовали список индексов в текст и вывели отзыв в виде текста. Вывели длину отзыва. Вывели метку класса данного отзыва и название класса (1 – Positive, 0 – Negative).
+
+```python
+# создание словаря для перевода индексов в слова
+# загрузка словаря "слово:индекс"
+word_to_id = imdb.get_word_index()
+
+# уточнение словаря
+word_to_id = {key:(value + index_from) for key,value in word_to_id.items()}
+word_to_id["<PAD>"] = 0
+word_to_id["<START>"] = 1
+word_to_id["<UNK>"] = 2
+word_to_id["<UNUSED>"] = 3
+
+# создание обратного словаря "индекс:слово"
+id_to_word = {value:key for key,value in word_to_id.items()}
+```
+
+```python
+print(X_train[39])
+print('len:',len(X_train[39]))
+```
+
+```
+[1, 3206, 2, 3413, 3852, 2, 2, 73, 256, 19, 4396, 3033, 34, 488, 2, 47, 2993, 4058, 11, 63, 29, 4653, 1496, 27, 4122, 54, 4, 1334, 1914, 380, 1587, 56, 351, 18, 147, 2, 2, 15, 29, 238, 30, 4, 455, 564, 167, 1024, 2, 2, 2, 4, 2, 65, 33, 6, 2, 1062, 3861, 6, 3793, 1166, 7, 1074, 1545, 6, 171, 2, 1134, 388, 7, 3569, 2, 567, 31, 255, 37, 47, 6, 3161, 1244, 3119, 19, 6, 2, 11, 12, 2611, 120, 41, 419, 2, 17, 4, 3777, 2, 4952, 2468, 1457, 6, 2434, 4268, 23, 4, 1780, 1309, 5, 1728, 283, 8, 113, 105, 1037, 2, 285, 11, 6, 4800, 2905, 182, 5, 2, 183, 125, 19, 6, 327, 2, 7, 2, 668, 1006, 4, 478, 116, 39, 35, 321, 177, 1525, 2294, 6, 226, 176, 2, 2, 17, 2, 1220, 119, 602, 2, 2, 592, 2, 17, 2, 2, 1405, 2, 597, 503, 1468, 2, 2, 17, 2, 1947, 3702, 884, 1265, 3378, 1561, 2, 17, 2, 2, 992, 3217, 2393, 4923, 2, 17, 2, 2, 1255, 2, 2, 2, 117, 17, 6, 254, 2, 568, 2297, 5, 2, 2, 17, 1047, 2, 2186, 2, 1479, 488, 2, 4906, 627, 166, 1159, 2552, 361, 7, 2877, 2, 2, 665, 718, 2, 2, 2, 603, 4716, 127, 4, 2873, 2, 56, 11, 646, 227, 531, 26, 670, 2, 17, 6, 2, 2, 3510, 2, 17, 6, 2, 2, 2, 3014, 17, 6, 2, 668, 2, 503, 1468, 2, 19, 11, 4, 1746, 5, 2, 4778, 11, 31, 7, 41, 1273, 154, 255, 555, 6, 1156, 5, 737, 431]
+len: 274
+```
+
+```python
+review_as_text = ' '.join(id_to_word[id] for id in X_train[39])
+print(review_as_text)
+print('len:',len(review_as_text))
+```
+
+```
+<START> troubled <UNK> magazine photographer <UNK> <UNK> well played with considerable intensity by michael <UNK> has horrific nightmares in which he brutally murders his models when the lovely ladies start turning up dead for real <UNK> <UNK> that he might be the killer writer director william <UNK> <UNK> <UNK> the <UNK> story at a <UNK> pace builds a reasonable amount of tension delivers a few <UNK> effective moments of savage <UNK> violence one woman who has a plastic garbage bag with a <UNK> in it placed over her head <UNK> as the definite <UNK> inducing highlight puts a refreshing emphasis on the nicely drawn and engaging true to life characters further <UNK> everything in a plausible everyday world and <UNK> things off with a nice <UNK> of <UNK> female nudity the fine acting from an excellent cast helps matters a whole lot <UNK> <UNK> as <UNK> charming love interest <UNK> <UNK> james <UNK> as <UNK> <UNK> double <UNK> brother b j <UNK> <UNK> as <UNK> concerned psychiatrist dr frank curtis don <UNK> as <UNK> <UNK> gay assistant louis pamela <UNK> as <UNK> <UNK> detective <UNK> <UNK> <UNK> little as a hard <UNK> police chief and <UNK> <UNK> as sweet <UNK> model <UNK> r michael <UNK> polished cinematography makes impressive occasional use of breathtaking <UNK> <UNK> shots jack <UNK> <UNK> <UNK> score likewise does the trick <UNK> up in cool bit parts are robert <UNK> as a <UNK> <UNK> sally <UNK> as a <UNK> <UNK> <UNK> shower as a <UNK> female <UNK> b j <UNK> with in the ring and <UNK> bay in one of her standard old woman roles a solid and enjoyable picture
+len: 1584
+```
+
+---
+
+## 4. Вывели максимальную и минимальную длину отзыва в обучающем множестве.
+
+```python
+print('MAX Len: ',len(max(X_train, key=len)))
+print('MIN Len: ',len(min(X_train, key=len)))
+```
+
+```
+MAX Len:  2494
+MIN Len:  11
+```
+
+---
+
+## 5. Провели предобработку данных. Выбрали единую длину, к которой будутприведены все отзывы. Короткие отзывы дополнили спецсимволами, а длинные обрезали до выбранной длины.
+
+```python
+#предобработка данных
+from tensorflow.keras.utils import pad_sequences
+
+max_words = 500
+X_train = pad_sequences(X_train, maxlen=max_words, value=0, padding='pre', truncating='post')
+X_test = pad_sequences(X_test, maxlen=max_words, value=0, padding='pre', truncating='post')
+```
+
+---
+
+## 6. Повторили п. 4.
+
+```python
+print('MAX Len: ',len(max(X_train, key=len)))
+print('MIN Len: ',len(min(X_train, key=len)))
+```
+
+```
+MAX Len:  500
+MIN Len:  500
+```
+
+---
+
+## 7. Повторили п. 3. Сделали вывод о том, как отзыв преобразовался после предобработки.
+
+```python
+print(X_train[39])
+print('len:',len(X_train[39]))
+```
+
+```
+[   0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    0    0    0    0    0    0    0    0    0    0    0    0
+    0    0    1 3206    2 3413 3852    2    2   73  256   19 4396 3033
+   34  488    2   47 2993 4058   11   63   29 4653 1496   27 4122   54
+    4 1334 1914  380 1587   56  351   18  147    2    2   15   29  238
+   30    4  455  564  167 1024    2    2    2    4    2   65   33    6
+    2 1062 3861    6 3793 1166    7 1074 1545    6  171    2 1134  388
+    7 3569    2  567   31  255   37   47    6 3161 1244 3119   19    6
+    2   11   12 2611  120   41  419    2   17    4 3777    2 4952 2468
+ 1457    6 2434 4268   23    4 1780 1309    5 1728  283    8  113  105
+ 1037    2  285   11    6 4800 2905  182    5    2  183  125   19    6
+...
+    2    2 3510    2   17    6    2    2    2 3014   17    6    2  668
+    2  503 1468    2   19   11    4 1746    5    2 4778   11   31    7
+   41 1273  154  255  555    6 1156    5  737  431]
+len: 500
+```
+
+```python
+review_as_text = ' '.join(id_to_word[id] for id in X_train[17])
+print(review_as_text)
+print('len:',len(review_as_text))
+```
+
+```
+<PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <START> when many people say it's the worst movie i've ever seen they tend to say that about virtually any movie they didn't like however of the nearly <UNK> movies i can remember ever seeing this one is one of two that i walked away from feeling personally <UNK> and angry this is my first movie review by the way and i <UNK> with imdb just to <UNK> at this movie's <UNK> i went to see it when it was in the theaters myself and my two buddies were 3 of 5 people there and after 15 years i can't remember very many <UNK> but my attitude upon leaving the theater is still <UNK> clear br br spoiler alert br br oh my where to begin fat loser left at <UNK> goes on <UNK> weekend meets blonde <UNK> who takes an interest in him takes him home to meet the family they're all <UNK> and he's the main course pathetic attempt at a dramatic escape kicks all their <UNK> and runs off with the <UNK> girlfriend they live happily ever after <UNK> firstly the gags are so bad that it took me a while to understand that they were trying to be funny and that this was a comedy the special effects what few there are look like they were done 15 years earlier the big dramatic ending was so <UNK> and poorly acted that it was nearly unbearable to watch he <UNK> out the entire <UNK> family with <UNK> <UNK> in the <UNK> that stand up tom and jerry style when they step on them i'm sure that there's much much more but i have no intention on seeing it again for a <UNK>
+len: 2741
+```
+
+### После предобработки отзыв был приведён к фиксированной длине: в начале последовательности появились токены <PAD>, которые заполнили недостающие позиции. Содержательная часть отзыва сохранилась, но была сдвинута вправо, что обеспечивает единый формат данных для подачи в нейронную сеть.
+
+---
+
+## 8. Вывели предобработанные массивы обучающих и тестовых данных и их размерности.
+
+```python
+# вывод данных
+print('X train: \n',X_train)
+print('X train: \n',X_test)
+
+# вывод размерностей
+print('Shape of X train:', X_train.shape)
+print('Shape of X test:', X_test.shape)
+```
+
+```
+X train: 
+ [[   0    0    0 ...    7    4 2407]
+ [   0    0    0 ...   34  705    2]
+ [   0    0    0 ... 2222    8  369]
+ ...
+ [   0    0    0 ...   11    4 4596]
+ [   0    0    0 ...  574   42   24]
+ [   0    0    0 ...    7   13 3891]]
+X train: 
+ [[   0    0    0 ...    6   52   20]
+ [   0    0    0 ...   62   30  821]
+ [   0    0    0 ...   24 3081   25]
+ ...
+ [   0    0    0 ...   19  666 3159]
+ [   0    0    0 ...    7   15 1716]
+ [   0    0    0 ... 1194   61  113]]
+Shape of X train: (25000, 500)
+Shape of X test: (25000, 500)
+```
+
+---
+
+## 9. Реализовали модель рекуррентной нейронной сети, состоящей из слоев Embedding, LSTM, Dropout, Dense, и обучили ее на обучающих данных с выделением части обучающих данных в качестве валидационных. Вывели информацию об архитектуре нейронной сети. Добились качества обучения по метрике accuracy не менее 0.8.
+
+```python
+embed_dim = 32
+lstm_units = 64
+
+model = Sequential()
+model.add(layers.Embedding(input_dim=vocabulary_size, output_dim=embed_dim, input_length=max_words, input_shape=(max_words,)))
+model.add(layers.LSTM(lstm_units))
+model.add(layers.Dropout(0.5))
+model.add(layers.Dense(1, activation='sigmoid'))
+
+model.summary()
+```
+
+```
+Model: "sequential_2"
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
+┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
+│ embedding_2 (Embedding)         │ (None, 500, 32)        │       160,000 │
+├─────────────────────────────────┼────────────────────────┼───────────────┤
+│ lstm_2 (LSTM)                   │ (None, 64)             │        24,832 │
+├─────────────────────────────────┼────────────────────────┼───────────────┤
+│ dropout_2 (Dropout)             │ (None, 64)             │             0 │
+├─────────────────────────────────┼────────────────────────┼───────────────┤
+│ dense_2 (Dense)                 │ (None, 1)              │            65 │
+└─────────────────────────────────┴────────────────────────┴───────────────┘
+ Total params: 184,897 (722.25 KB)
+ Trainable params: 184,897 (722.25 KB)
+ Non-trainable params: 0 (0.00 B)
+```
+
+```python
+# компилируем и обучаем модель
+batch_size = 64
+epochs = 3
+model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
+model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.2)
+```
+
+```
+Epoch 1/3
+313/313 ━━━━━━━━━━━━━━━━━━━━ 8s 20ms/step - accuracy: 0.6648 - loss: 0.5901 - val_accuracy: 0.8204 - val_loss: 0.4243
+Epoch 2/3
+313/313 ━━━━━━━━━━━━━━━━━━━━ 7s 22ms/step - accuracy: 0.8623 - loss: 0.3341 - val_accuracy: 0.8492 - val_loss: 0.3553
+Epoch 3/3
+313/313 ━━━━━━━━━━━━━━━━━━━━ 6s 19ms/step - accuracy: 0.8987 - loss: 0.2659 - val_accuracy: 0.8632 - val_loss: 0.3416
+<keras.src.callbacks.history.History at 0x7f1e723806b0>
+```
+
+```python
+test_loss, test_acc = model.evaluate(X_test, y_test)
+print(f"\nTest accuracy: {test_acc}")
+```
+
+```
+782/782 ━━━━━━━━━━━━━━━━━━━━ 7s 9ms/step - accuracy: 0.8770 - loss: 0.3202
+
+Test accuracy: 0.8710799813270569
+```
+
+---
+
+## 10. Оценили качество обучения на тестовых данных:
+- вывести значение метрики качества классификации на тестовых данных,
+- вывести отчет о качестве классификации тестовой выборки.
+- построить ROC-кривую по результату обработки тестовой выборки и вычислить площадь под ROC-кривой (AUC ROC).
+
+```python
+#значение метрики качества классификации на тестовых данных
+print(f"\nTest accuracy: {test_acc}")
+```
+
+```
+Test accuracy: 0.8710799813270569
+```
+
+```python
+#отчет о качестве классификации тестовой выборки
+y_score = model.predict(X_test)
+y_pred = [1 if y_score[i,0]>=0.5 else 0 for i in range(len(y_score))]
+
+from sklearn.metrics import classification_report
+print(classification_report(y_test, y_pred, labels = [0, 1], target_names=['Negative', 'Positive']))
+```
+
+```
+782/782 ━━━━━━━━━━━━━━━━━━━━ 5s 7ms/step
+              precision    recall  f1-score   support
+
+    Negative       0.89      0.85      0.87     12500
+    Positive       0.86      0.89      0.87     12500
+
+    accuracy                           0.87     25000
+   macro avg       0.87      0.87      0.87     25000
+weighted avg       0.87      0.87      0.87     25000
+```
+
+```python
+#построение ROC-кривой и AUC ROC
+from sklearn.metrics import roc_curve, auc
+
+fpr, tpr, thresholds = roc_curve(y_test, y_score)
+plt.plot(fpr, tpr)
+plt.grid()
+plt.xlabel('False Positive Rate')
+plt.ylabel('True Positive Rate')
+plt.title('ROC')
+plt.show()
+print('AUC ROC:', auc(fpr, tpr))
+```
+
+![image](1.jpg)
+
+```
+AUC ROC: 0.9419218976
+```
+
+---
+
+## 11. Сделали выводы по результатам применения рекуррентной нейронной сети для решения задачи определения тональности текста. 
+
+### В результате выполнения лабораторной работы была построена рекуррентная нейронная сеть на основе слоёв Embedding и LSTM, которая успешно справилась с задачей определения тональности текста. Модель достигла требуемого качества: accuracy выше 0.8 и AUC ROC выше 0.9, что подтверждает её способность эффективно различать позитивные и негативные отзывы. Полученные результаты демонстрируют, что рекуррентные сети хорошо подходят для анализа текстовой информации и работы с последовательностями.
\ No newline at end of file