From 79b6644fb24f3e0304b495f3333ac66d59f3775e Mon Sep 17 00:00:00 2001 From: lauragreemko Date: Sat, 8 Oct 2022 17:33:56 +0200 Subject: [PATCH] finished extract notebook --- data/twitter.db | Bin 65536 -> 0 bytes notebooks/extract_data.ipynb | 524 ++++++++++++++++++++++++++++++++++- 2 files changed, 520 insertions(+), 4 deletions(-) delete mode 100644 data/twitter.db diff --git a/data/twitter.db b/data/twitter.db deleted file mode 100644 index 562e4c2d48e4f5065d881d3df9d5537bcfe3d7c2..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 65536 zcmeIbYjB*|dEZF_&D+b{$g(sZjVQh#G{d1tV)}l8ED<08lHdR&2!K~Rre8D~K!c5b z!M=b5<%_yWNl_}6B1>M&v$jXHBd^D{63dfhZ8__4$W&6<^?q4bCE2R=hs>rn+463A z^1<2EI-Ae5)TR&eM1%92-e6WgBI zwtf4y0oUEOZCixjXZQ_&y11do!k_Kojd%DrvaK)a?&k$v2ma}{gCFP5*3Xs%wj{76 zfh`GaNnlF?TN2okz?KBIB(NocEeUK%;JcT=k96&N_St8*H$GJJW=e&6wNR;=KL>^; zM+T=y-08v7VvI7%U23stuTAjTmP;~!F=M) zyk9T#_~?b{k+UO{X3Uksa%pw5CrZUzh0PwnUH5C9PdLYRAam#7A4&525B|l$e}C}b z9sIuz{+oku9sHAn|MKAfa`2C~7ry&R*?MOnf#$XS&Vy5lo=@%O=dEA*d3Us2D^ve*DJaCI)BRb zLbX=mBfYB66SLe})yEX(?VZ_Tb*@scd6mZx%ld|T*|Vc9lr^;Fiq9u5dG2Z7ujRd^ zWxb|%s5rysE6msVVsDnqnf7Nrx8%9S@|^F!{n}T);4IW?%hmpuU#|7#{g+phsp-l} zDmCcGQkiHvn~BG=skHeolZiz$iF7=kNk-$*c>H8EcQTfqj%NE~iT-G=FB*;BX#VIv z=RqQoK(yO;k5p@(TP+|S^NsV!SQ2Jf1E-7rLVf1S*pNF=^=2x?vNu;)LUf+H;JH?& z-;GF@y^4o0`M`>H@A}G}v5OO1nyVGd^X{EuZGj2?TR-CtOso!jHE-OTWf7ck2S!Iu7w7fJ2^aBf zSeIP6Tk}e{T-I;B#z%bZn}hj$p;V}N=7aT4_e{yZ!%F4tV+F5L))$WZvxQRCyxw{H zwO4=Lon+;*qIs8Jc1y+bt^RhgtX!X*o4Qb|j1}7-KQ~)kIg_uR&D4#!lF4`~9g8N@ z@oYSvj_0D8bT*#IW!6b47VA&t`jc5JrH1D?%~NI(?%6%C!i-l|SrYf$0XE3;g2dLj z7tfi!Tq+gH>^toy4+z$G-+J{MfA+gyc9#p>e)Q0L{2g{$wf6WSSMJt|g{5V))xBlR zfmdN^n{{5|qRpBsRC%Mcs!R(#ge&X zB9)3qv&l>%n@J`U+15p7r(>!9RJK2wvK#F~dz|~9OdM)$H0h$Hx)cU`tX$(Bt3Fgh z74ArbbzZi1fCgJE7tuI16rSESFjXro&H6V{WXpc#cD>;8iDvY=z4n=W4XciQ!k3wy z$Cr4OidJF8E%2cjQ8qQAF`KbiUG~exnPN$ri0>(Bm1(H$vw!vMsDEcTdi6#H3B_}< zG+QQ?V!m^^Xex$mQYqF!pnu}=Y0Z6XZSFt5+i8r1bKjwHH(v{n9*)=Z3n=22Lf#-J z#DJRi7g_0kwZ|-R2A7B@(2mJuDjCbf)0yNuOkX@9J(*+%(`Nb_S9Uqg6dQT_?(N&J zqa^3+Ma>|y=avwA#a}AainD&d<4jbFODrQ7*&{bIL8!L8zf><9LG}(!Oi7j5?akO; z{cL}`PQP2ey7)>xJvUKwcpY|%g^51%-F#t|@6aT7UU8qfykt6;%%*dRG%HhEFv_Bg zbGML&{}$u3oFlqF*nR(3g72+pm4|4P=|lCUc2Yf_0O~BvR32ERl<4 z6WJI#E`gL&tooLaGt;r0mUzmV*sf+}hx6ce;;`1v?sNXCnZLPW84V+WmFoB0r6Nm6 z%f=n@7}ONw=4Fq+GsA`YeeUJ5i&~!X7JW7;d%Id(F^Wtd!iCL*4g@}Msd!HsQ6iOt zQ!27y3rq_B%7CnEzPRj7j}E!WSZcsp`*kuaA;1(PtJI2lV|tNF$7Hw*D4)l#^Hx5< ze5LdQ-!^__qR+ipWsECDw1lURVRP_JXq34^VRpvL-|A~$>y=wWi+Ag#>r=UQtuk?Y zJUY8_cQJ7d>8Ii`q>ek2$|ck3crqPLCXqRhhiWA|9gp_MlKnAjQo1A6$e#H`3~h@= zS@bLOh51ThWy6(>lnErfnL1{~&EwwPl9o^7KxLwd1T&sV<}%#YE%UXp z=*g(n650NE;7y(Gb{-tGT4MJ|iMa{&>nvOLPGLrSqFy$0S3-E0o4KO=nmjenv`#{awfNP)?l}0i@|ard+3ju3KTlbG?z>m{vNQEkiM7OKX_c_ln1A!# zofB%e*LqL0yN)B4ch5=j$QPp>$!|~>2~|X-Cgzu@7=vNHLQtC=c4gkE|!XB zjKRb)z-;DnX#}X5vm%s1i1){>o$T&zPIWmCVu27R3wgi7@dn^XB~;(|N+WC%k3Z=S@ZQnDs{#Sj<=I_$cOs zmn)CoxLaJ}{R~c)M9S#Z&mz?fYm>j2*<=cjgMHDa=q1(UbS&K;&-BL=*2UV_oZjv{ zc){4&-Mh~kr6BLa<2q**^KT*>*QoAFQR@?fi<@OuB^s5j&EGzkC64D|G`$44>{S^g zs#FfC^|q|qGVvBGsdyp~H2)N_5XiZNgTWGCb!&Cz6LVQD+*NRe%y4eZOP0{jv-rM? zi;I2kbfG-&yYqx7MyC@8E)k4Wq(MXb5r_}(wu0RA{56r6+2mDX3dMKqhpC0)j8`cl z&uluDh~|<+oBJ9c=I`FdPX0Q#`LoC4&+bY7>^jY#ohkn8c!58W=lIjTe?Ncs6XYLw zegD+H1ABkL`S|XCwCmsQ8r*qo$4KOG*B@@h{|M-N{n?8D*(h7_f1rQ1;{T2)X)FH6 zfN#bBTk-!IRJ#@bZ^i#x@&8u*zZL&)#s5UDVJ2lO{#T-JEB@a+{*UEi8K9|nQjkD2 zmr|x6odffW#zZU150fj`*)vAut|cicI;`&V}T^PQ_Z zrn>*MtHcw3MSq&NpR<^@^2TTCi^W>C?yf%iMhCq1=o{cT^)mZT9vN=B1=uYd`RE(H z`L=BLqi?+Z+JF0y1fDYjI9{xPg6owgnGhrkPS{kxNvSWA#REkHBjRs}+_&eAm9%>N z5R6)%)Ba^V!f=D3-yE4b;erx-W#Du3;a;BXn({TEU$(k~WLp(P%p>VYjsxHj>Hy#0 z*Vp&x8||3()Y;j~(R6I`+?{r4^lHIRjGetyzq=GmkxWh|GqH3u7mKG;(RebIC8?N- zlQRu4?PyA=GL~92!0?(s@k7podH~^d2wHePAOY7y{+v`%`EouX49&`3IAuw>7C~Wa z=>lZ(M8p^##V>wtylCF&mH{roK9`nD1#TEfxFcnisNYG%%Y%d0t~=zCzw$->3N-%W zRK1$7JpR^9!DL%)3dVCU6z){{EYLf5oOA|&Uq`CBvO0accFwD%7aT{)|FU25p;fqU zZ?RnVSIi}H$6F>rV(u_aumm>CPYw^?TCF8=w?}UvbrLyj=5&gTj&5dRiFhWJ&Bn;; zkUYx)rnZv#QSvw-(~16A#%%Rw;aTT_GL?H+^5nY09N99wAkr$xmc>T$>+!cLMZipw z&Cn-i3qt-8bgf<`Z?ZT5wr`jtByd^;5S|_Yl3lG=r+``g5_8!(y^kJpfqZJUNOHdC z?bp8kMalUW{-#nxrTRQyKI`*kK*{DyP5wAY?TYIHn@eA}Ec!}uw!q(29#ghk&q9-8 z2eC;DT+^}->115_h!Ao5VjE{7dG*HR%$=2?S2FF3J32odU0xYpdF8CcoXL?dNhf1j zl4K;!xg94rNy0V9%8w>;(PV3xqfxW{36^=(Le1hxhn~@;2I)%+NDI$5D_lu4=?Y6jSs+)(yAx($lHVF5rO$Q79=~27yTxY> z6iOo`2>c}x2@2J|cEM!E@5KDGnKSoB+aJF^z3jgd8ycNHCxK<7@pLwkNJrzCAriP7 zv;ktu^-Ced?P|R7A?LwyR^#?PB%}qwLvtV_s$8ZaL{u!9BS9@jwDhHKISRhKMlG-~AE4v3M%L!L1i z?j#!>5)|~ECo?soFg2olQh&lqcE|3n#^?_^%^sGZw)%!8Xv_gd;vFpy%VLAQX}gZP8qsy+0rx7!&|l7NP(wkP?K_W_D_j`6rJxONQ3a0Lf;VWSF)HCiuxj z7iakKw>&q|=MEahPePQO~cbO5dZ0LvT~D{UkPf+}`?KJeuM>vsW+bp8o2a z^~Jp_MVaE-0@N=N#Cof@3bp(K)*lsWh(RUuvijXp$RTT!*7Swb7yZ-MM(@62q@^tv z%|NsK1(--C?(k31uzt}orQfm({B zjAbxNK3FyA&i}GGrl`tr)bf7gsTZ^_xz%zvT6t2G>PEh4+l*RvY4YwXmn2>2FYt*_ zt}wdD>2Ja=O--B7sNb5*8}|<#bUrsKQ_iv!u^|TZr4Ud}yIV_DTbb>0ZAX5LBa38u7z6K13;^S}2eA_8KTdbX{&tSa2^t+m$ zBs4pCD>zteH?|qP0Gx_c%hiezQNaDejj$eVck|Q%@l`A-abU3QU0tA>{f=Ln`ztm< z9n&xc5uwWOf_F~=(ZnPo{QB382&FyJNl^mO@)?voMAmGZ1T&&fr!2v@+rQlb8)l1xLH`#iQdIprW81IGoLcn9cGgC!@^0?LBJ?;<_bjuZqT?68y zO7Mdi(gKJ}2S6}*_d-19#m`)rY?syD%+mF%R~D{Z8ADc>ezAU|aRf!QpNsZRK@&^ySOf1f%${}kE;@%l?W&ix+=R@E2|P(7bm3h)c;ddH3lDQqFK zgpaUp=qL=FypZV$trRq3aA^iqhk*x}r9W3GKz&o`(M&)OHrglTgifWSpZ?rQo(F7ChpX3|%47tfv>pNB9DSC{Pv zjW&@^vhe^nvq|{0qVI-+ikmPXp$OdWz^=x;>oji~0Ej@KeJ8MHV1hso33Q4qpR~c$Xsj+{hWYJ2(p-ks~m@Z@x|tq}&Lh*U7;gT2ER5h)pmW5u{;%mxK3 z{wa4t=@3up3>B~d+l%PEUa~+!p)p$YF+3;Q5=D=`!S@)2!yXk}9F`Vhr8XqM(9F~8 z%3n0h4x2Syx%SH7^3Xzcwq4e@&Xt$%ExuCoMvyhMd9V}e5mbSaNszMWOco()EHgC_ z*4%VO8j~M&nhB#t!7w-Mxpo{qFhr#3B%ALJ{?iI=zl5Q?=Wb_;%hzWv1O=R}Ob*ko ztJ38pz=%>&fKAFO(Cc%_8Fc+vs zQZdXu%8BX#6E){+pjxIb<`hx=e}*X6bvn&f2N1yv-U}4ryazA>xuz3<-pMrXNFog! zrqY$RC|1=0c)W1}Sz~g$cQ(@>aqbrlNQ}vC18V+r$m=Q6GO~IfV46n{N5ETbro@DT zJ?(@@s*XBxR$(>#A5WqEr0;%=RDJcHkHG z@7s5A@88**aNIptcOT!iedo-MKZ^WCWVE~4b&?l+pZzp{Am!XoN&D>Cvzr_xl`tyA zSn#NBr(T|*PFh+CHsjM!;z1rtK8=F);tV?)z!E@AE~*LY!#stFPF4Sp*Fy%05S3Sw ztT+D9Y++7t0DE6$E%g8w(1(WppS;<&05?qfGa7wgr=IL^_ZF{TU#Mm-ELDh38(pNVCM#a8Tcl^+YW)X4b(kfm+)=IT#jte z8A44wjZNnvIy@M5N#SmI#jVoP*#dRNx_YW(F*N-XrXPjMrkRjph4iB?BbCEXP34FJ zk~u{LBtMb_*(Uj6F9g4oYY939G+vH7jaw!W0aSjrjIy)`J82R_RRB|F?=5L#X_JJ7Xz*7E|D(|qqt51(Da}$Ijm85rVJ!zG zmYI|Bm=e&bmN(bcxDa!iCt1z1#ZMb?=X3-EJvt7=&RV@gqWGwmA~CBm=V8&h#n6`6 z9aN*T{uGz<4)eB2e->uRe7$gwPZ;oPbcLXGjRKypH|-@Eb`3lmqE7s!_N5eDPpj~- ztE=(BsMGkQE=WbAPnm)zT+q5FnvTPwJ1q&Ck z0e`PK_06MwLd%RxzkNhmCR4TO2VE1~cvc2C-~klK>vRZC2yN@Cq_T*_3@kx@or$LW zkqju|DD(R0H%F)|Hp(j8lS_WTSuSe*p=foTCVce!s=>6j#zIj<6PSgXsXU~8fFXPc z9#SZ5%12D`vSKmXvViimNBT?W&W`)}%lk=CP9&EmMB;`wK0D)|O%oMd=BVG_6$H(K5tkxK=9RwjfaB%n7U1)ox*2 zVHz&J{CQR9vYs~UgtIn5u5(eZ3g)q8NC}TNv!%uWT7xR3zP7XkJGRy)lO9i?3{%wJ zl2eOk)5(pK&Q)akQ>l;~x+BuveCD`w|G2it_U(H>BeA3R%tBqiuraHh+d{TA-0Nm+ zGHN`S*PexX$UdkTecn3}804CFs^?UXJECL)=E2-q^z@&(jvyLdBEu&?h&~S!W zhdtTx<#-E0Dx~qTV@_jSx>Wh-weP-+%UQVgZpW}rHV~GOzYjrD)yi5uVv^A;#_fN} zj4-aWtO$ltx&?`j1OYCyrX`RL{0Fo|fPFUlUviqejIzfB5!2QSr8%-61|=uw{2ry% zKGNyO-*G88Uo>F0RIOZ}qjtnz`KSw6yo^`gBVyrwJNk4Y7Nzr1mVQUXN1dj?jy}$c zH*qK zEp4ohrH1nWVJ2Uw8-c)q(dJ_78^s{(lPT41vmDA*wVzTOG1Hj}e8*{l%Ol2DG(kxx z61N_G>kSwM(}u0u?hMC9)AXggb$dkVt7J5nL+Uw|`U9Hd5@Tr+bfbWWq~=Q57Kk1- zR+-Fxz!i=}nzJuD4~D|YchDftHH892?(k#CX2Fp8l9A}jL4;6TA$FoL(M;e zE)>18-L?9%vZ9IsDgj)lEf#(jFq}Rv-be1J^?`J237j>0gy53%J_0~B8!!sI;6DCN zsRloZ5J+5Vm=yYO+kC-{rq!)QKr$b{$*he*2_}%d<&SwYa{IpWWyg7GMTDq@?%g5S{`PKOH+){aLX&4|GpC_BaAVF7#aR#+_m4+}abj(U4n;5P< zg4_BcG4lp+lmIRcYfbwOI1=5G=nf6b1~&{h)!H^|`;doas>S8v-_F%fHs`k;XN(uv>`d#TTc5c` zhKFBNsnnOG+vWcty&%O9e8p^Cdi1fg>;H%X@=_2N0@#osw`>^;4oG z0?Au`rGfHM%&)d@wd?+Lp>}Rz^p(33tCFVBziCjY=;Dc6&B#}&GEsbuafvi;3^>hL z2vMFZcq^;pQp}~BXs=H3OaNcZc`JT}7BBm40BT*iF z10se*NP4$d$Lb;Yvl}S(HStOM|mv>D#1qiV|la8$7+G$Db*kuYK+Bk)LL1v)g5{?IQ175XP3XltXjg+9o_^)-kI=jq#{5k^NwfStlib zm8CPIA_-wxcsY7vaC&m&%IKhV54_d7np?@GH%rTAN^!ZpW%&%@ChRB)$Sz)=7#?0J z7l|d69tLBEv&zyDaZe0Z5!hSEi!f&dAnt|P3SC{z_@|uvVMj6fLhg}aKsL2%5*&)T zN*UFurb9}JF_NU+M{cjKtAIVVnjlPR2ALU~ZbYdXdD%RWY&#(ZI;^a1LCYM^#N55> za*+zQz!~Snr?5$C>Mz)DXyaBU`Urc`G&ZID$H!+lLziIa3A4aAcy9={GilNxw2K%0 z-0A6CW3NyzfzVhsP%zLW1m9U$zMBZm0Bm9PR9ExZ4~Ki~`z`(^B*QYP6<3DRCnBc} zdkh+s*<-N)sm^`UdC)Cu4pz}SHF#xY`rOE{Izf}=d;KRi=vxs~wW7#$)BlR)u{Q0L z)yZ+xz6{dWCgUpqk~!D50ZoQt1Brp#3QLTZHCY;%Kg#D?lhmr&=_h+#@~I8%C7@oe zn;xexf^>dT`R|pB%hk8O-cS)Cam-ggAM2$mZv;8c6B_~HO42@0 z4!>;zio@lLH&XXf^U%z}|8p6-{;Ay`m}HuflViyyfGEQmh#6lj0c2_wWOFvF*oWFE zW?(%%19vG5(NJP6zhMeKdt8;`=$4Qrn2nF$2=v>smUQo0XsHH%z(e5bg|e&!uq1c1 zWckJ0mAi%>#NSjEDZZ=T-cbd_T>inT?V5OxFT%%YDM-D%b74Gsc!rNhr3N%M%p5%f z6@msTn(oKyMQRE=t!mfD$fYrDk|`C02G=IsLUC#O@@%?tIWOVDR07c=k|doKr9JAC zs5GQ3NXEyMH4aLjyPB&R=fN!_=CG(m@f*UCr>UfT_3?KYE~P9AsoDNEremA?SPHY> zJFZu}pO79HRHKFTKpQRlZV)^Zcw4d*P4x72p<$;p>RBIBe6U)n3N_J?CsPmH6~t@O{jskRMlVF6x1;4R@b>eD)bciA}c&lF|mXJ-4VT2G2OfG??^kJ z+kx!GhHf#uzVy{G4PdSEblt@$_a+8c;LGb4t0bt$R(nD*ERB*55D=3X^H+&7_{@MC zEopU383{}kYYUUL;G`v68zVr_$0uGHLZW&VtAi(b1iFp-n36A36GYQi5&l_)ZA1nQ zj2@>z!>f983L)7oG-50mnsbf@oaLQIqo5IlP3O2&y#=ID&ZF}I1H&iK3 zk6%1XU6*Q;AaW*Xn43<6Bc@O=SrjCgHFVf0xIW(ex`{}tEpR}tj@bPFA8$MGoBRLC zzI%KB)!rrN@9p`*?ti&EvTJDP7k4}x8SMU2*B@>FK(uy@WIfF6h*N7>>SGt|rD zu2+dftcEANAfsFIijerQsH&q^?KV~Qbk3|S6@)-e)Y*NoA;9TaC6xB-c(K4dljj4;G>2X2;ioE5_se`g*%Yb4_mM3Vx-1ILv4~k;D zbMC=akz8i^7FsZKNUGd!cNKf9OcT&u%~gr+0`~nDXd$kpsXb*u0|lBokR|BP@-+Df zsvyKQrUwEhTh1CjDcB<2*Uc-3MlRDpyTYSH!RNGFQ2Z>o-YbIIam>^*!Er9uiOfg+ zX-VH|mre1RS* zPp!3#5V#luVd|x8cOx_IH1cxB_!*J=r&0g|h5~VzVq#)$_8XQp8Fx>fbjOPG3pKUh zK;$lsQ4vW6SSf62myg0(|+I+l~IkV}GPke#D;4l2R= zaTAq;i$vDj(l8r_ zx{mnl_AYvWlqk#PTB75Wk9zu*T;=K=|MrZ%2=ZJY3go$HGahFT!vIVOl2HXiG8$4K z>}uyCIOxN!_Qs`Gw1tDLVyB|HJmZySeHNpz(t&rj4o_1%W?tth+rl>BHZif7BKD4n zWemC{xKiw7?l95VoLfa$9n1lfkmDc|I-JDGbASfn`ZH6;ud$azS!gt*HFh^noOc>i zniOS9u}FBfOS20q&wc+c=Q@c}Q7{b)(~Oa_5OuRAwOWXZi2P#E?i3p-Qu%m=@Cv`DN2%Gr{j2ML?c5R=gM!7$4nm=R!rT(oTdXEp1@WYC0`9O8bNuXPKfy5k~&jubM9fI{-Q4AOU2igEBxA$p5X| z2_iSO7>11xpK%(;jCR^%IyYG2hGKur2KLe!m@CdNc@C3ydGy+5F?>5BGq*Z({r0ux z%VVS-VN1Xa)KVuo5L3|cWUZ5k3I$f^5fqe-jyMl`3^=pLqzv4%>&~YN3+BQ)1w&=& zkWr{w4XK7Ju}L#tsm5C950m@BWDCt`;pK)nf}JLH0+&-Av7Xc^i;p9A<8y`YS$Zon z0s^iQjs=9$CC=LjvP{I7)Y=BQ=%9*4Utl&5MxR^8q>)af!%hb;cmBe}!r*YZbnBKC zDnT9E4N?jy*M>d?>62EL9MKT~Mva+ar+GD8S{L}*OZCE8yw%EtKTE5inyL)slL^K& zktvsjIo0V`id(hFOr|Kbw_)%8&6b1N+<-&EjmXFYhJcw=Jmsd$EZIoG;7l|C5VB;S zTAIOG#$lo@M&6{G@H9D%h>(>MC{pk3g}~+_QRt%H1g$P6hjgxjVe0Jx8vPa3Pv933 zZySKa_6yM%M1L@dNN@}S)O*#R^$XewPDs!dTS_;Quy3)WZ(n04@LZW!u7Rzn3l^xr zrI9@=Dx(nA=PgkeqblEEVQAKEk&dYlH3G&)!i8C%WhEZhzM=?!2?(4rs`kPQE=fn3l7?MCYFg(JVKhFyI4@9QnYW2C~X>(jZ(1kqPJ9$v@36kwH&cp0u+{3}uQ~VU zr4K~O??kFL2;h5KV~-vVE~w1FGk*hM9fPJao<-(G&X)wSE-axs#3KqGkx*4#f&JuJ zv$#$eGY>gU^~Kgy(7;N^y~sZ{9*TLL33?#%FgFx8*s5bKWFt2q7&xJnTtluG9h>R} zJma8t%fdwfFCtvpJo?T?`bV9HQ9k0Lu3P)>_kP6x53fyUDSiEm!Fb7GWk_q~vLGr? z*%QS2zDnvHnWFr%67;`9p*tOp`1!S_2xO7P`*M5+Vhcru8&2 zk21Kcc0%pLtp7YnD3uUB+DiuCXM*KUnIaSx$*EHv1mnp&qto@l*((<>TOkn=%1hUo zi`o$Hs9_P3&fhfC+ufMB;WS^?Zjg}va(BZ71y(Rc{3Y=pSoFq{Soz@U8Sz>9sK?=8 zv8>}H(Tbu^3n+yDK?~STSF99a=<`RKJFh$UcZJq+{WQP7oBQ%Ik$I0hMyf^{p8}+H z-^E1A^_OmAzFY2rq0!(r-c^WT9r;kV)ywl*0RqU>B7_Y9zt~(pq$yPesGylie#f~* z5JFwd-0oSmb}Xb8A6*`4K|TNGEgVLU4(k zh(}zGJ42ZIq)TMm1zNSSbj4|2HW4%1?!8^X27z=qHo${88}LSp_T)4LA0ABtVQH~W z?L}}UCbS~5G4=(!8yx!821QJsJ)h5yW=m7o?NwrB38qBsAey2Gj(QaxR;OZga)V(_ zy0s!S@PNG+OlfofW#|4;rc`vaF}B5%7@1)NV-wOOa)d||P1=A)H0aLMs)B2deUw*9 zDS%#X&oX;LDnQ$fc&kRYW}Q8_DXr8pQs0SuF-Rro^x{k=r&yYf=+rquLMJy(%Rd9p zLE;owPX|g{aU_k_wcLyD9Zh%Ix!+piBSqE8eSxM5XqiDd44Q2@O`2Ovx+^UD&f z7v!x16|lwd5r9l#Y9bbGIr#_1$%0jZPX%w&s96IrbchZ2%zCIMEDy@jY`5+Wo}y9I zrW^*>7{aSUYlEy|z4jfg%_JMp^&~>YLsPCBhY>k1qnN>mq&^u%u`X+~FHKws%i3%dF&Cr9rX#N`q2h(TXM& zp<@H6;Mn|M?O~Ix5PU6Ez@{$HN2L|@q*3;T)h(8Q**(14G+QJShi7SOzT|nT`7? zu`EnTxaj*Fjfgy`7}F(5L(|mRU~{5wsB}Z5ZKlCiZV(4`>Q8(8`H>OIyA23BQCKd( z!_@i~5+k~v(UI5q6h6^gHoB%`R@EmFS!)0RpWeKhERq=%L1np`CpI+t%sjP8@=0F_ zVnp=Fr;u;L%V)uHmgL9|LrR2>e}0=l$~bX zC~R|{u-Ta#hWYNLJX)?UW5X<}ZnTqaYE!F?7M$ii)TsD$6 z{kGV86mQ@hXm663Aou{blCm&elh)p7SPBHig5yXz=s;d_MVsyp1yDgz!jCOE4_=Wv zQgr-2uCWO%pVX<1L1t$y zK)c-i>Yemp>GtJ$@hCy)LCZLD0`8ND7(=7IvoU|mX^w^w%4whE z5+?yG=dl4L2%OfIL3+mvXp53N6>FHC)6%xNVB5kL2SdvCXGtSs@xyJw{)U^YHD|bf z?6wv~Ujtn)1p18Fonu(Zpn0JqX zUL|H_nmc!O8#2ANtllL?eMtma=zwb1fsQ|qldbflQGIiMjcy(zJVATM(0r8D(?%!9 z|H5C_QquW1rYk;Z8fvQJ;BXtx(ccP;G!cYzU5#T4A{N=c%dJ)6UP3d>*S%FtlFpHV zt00msi$e#8AYR#ftQ8!pK6eWCu=1wXTO#*6Z!CW2{JR5Xs6Y6QxD^G}D==I*b>L!@ zKch{7h^U7qz0%s)oQZ-rPJ6h3AkfIpJI!v>k_I#VekTZY$)YV|h;cyBnl&`BC>@|- zMYDrv3pKKumJ^6`LG>{8+Uh_|nuzORa zQeL@z?#h{5-AJ1*1#&=9pgB-2TE@}R3chIDpiTGl7L(+1!D*U9<%O`m>!Ge)-Md`& zgV^&5ECj13&4MFY?8AL+yPSeQKN3ycn7T7*F9-S=O?ILQb-;s1`cCK~7%N?~Qz5!| za@J{FH83mdsKXGqUFY|8vaz#1P(w)uwF7pAsE3{hdw`#T z`V;GwIL;_^9B86=h%i$BsC=4t4Vg zf6?sxZy2byRe-%ZQeOlC!{de-qrTd~VOv(+;})op2M7>lPiIqb)3AOAkdzC{_Va(- zF8v*iWFumCEUy3d4NgMGg>7_;TAOlUuq02%Q!pfW#eMl@cZ`Wx1WU2eW!sLum#!~Q zr)E<(%9@#YTIFBV9zk$bT6q)4nO@ZdEP-B(bTwXVbcj7|fo)>?b5E^^;0mkAk}_>rAkx%;LC@lPOGr6EPmYuGm`1TRierucxQaJy*vEeDo$Y zDV$cr3-PecY|>Ie?{FvUV8y36^rqxe2wWxn)Lg3%mAMM4Qz#~Y<-n{$%zTOrLD8`v zRy#C~{It_(<-pek3LU%Wy!`z^P$tS_U=2ul33rkUx@6~C1LAR_vU%cJ-D~meOaMlK zBnN-tIMc)l*XSvdW}_o%>ydUfKJ-)4vnVk26nu)Ljs77^r|JdP-;q#r9T8M!nrF8A zJF&s|#On3&LBFKkoS=deWDD{%`$XYzn+9SDfF7cOf+cY3C!MC+wQL%sbV%^go8$QP z^wBnKsTsd!dW8hLB;+hJShaIq=el+Ta~)~^p{d2%(6vkHS+r90j#$;Pr- zrwq{g#A-5@puuvxJ8y<3hs-MY#*3fP;6$Hi+QY$hi1o>$a#;zcxcG!SuCg)38f>kC z)j}jaOlsn`v!bvu2fbuhFjU4l3jknPG6EPro_gcv2tPaa}8BqH_)ov$;Zp+c2R zHI`6$ji-P?c05U&b!;5E6E+h4u7pJ3OTX3E%?zvZ8HP{Cmafh%r)n`+e}?jhxQN~v zDMnZtX>)O562rDG2Unbiq3cLhc1q|;Q#V92>7JmWZ;%?OP=^hWE0aa*H}rf+5QCy2 zH&nT7C}P-aI^0sywjL-%V(j8TV$D5u=e~{sRiVTs%!0C16iRV4im)i!>^>~#7Yg@m z<^%f&GNV#`ykuS&c*5K=i4B|MSldFIpwaqx%Q7b_gm(!cT&*ufeD7Qe1|i2rfY$-E z0A=m*>*reD)Oru&zQ=A5Z8fJ3Yt)`qJ(AZs#QdLA`JJ}&r zy3rXESjwqjMf@NsEya~pb5wbInS{E`;v-paLi5T*K`^!}!z+Prg$F}-PMYnlMW+pM zb(I!dTQY4|d&jR253Sa!8H3&EjJh0^G^XJ+DDfsJr6Q16=zw-Lhbzv5=gj5OR(R5% zFI0wUPg+K(EM&g+-DTt0X|QZO*Z8%uVD-})OzY9&+2rLPy*VbIu|A{2x^-EIZHADW z1kI6=wM4M-yEz}GdgK(DJdA{x2L@aQ4p)$40~(eYlbG0KQ}m&&fkKgXr%+jYbc{!l zGbJ6Mk)OG6eRwo8InTM(>A^{iB_KzTNWwUN_Cy}74Pq9 ze8~CS2Mhz7wbH4HJ2my7MeHfi-GH1e`cMS`PuUvoz%qU9poUgJig~FwOGti8RkNZ7 z%=+vzLoy7nSNkpiU%@JD03uptwSb0HUkiAtQq4B_FzZi;%MdMTpS}bLPVht~3qRku z`$T$#o6<9h1wDZ?!dheLl17g0Huri&5PK%;p^|t&K{#v94m^Xn-C?#2{bfW zlZS1U(z58nx?@bx*S@LzA@~H`U*k%`HUloB@Qqp%^px7dLUbh~P3uXH0T1+)CIh|# z%tss8HqJH7+0;Sx-upEf6YQ|sd3yDeXnE39&`@5YD*}Flh?v4Bjy}}JG;SLgg$v60 zKMIjl227i5;QCxE2-c;*fuf!-h|!y$Y-`%1@=?K8#Fj_$6 z*&vbGBi@*nRLcY0u%{H$q8f+MmU*ALZ>i_tOjzZtO&upHw2$IszotV4%ufdyVR*Kj zNfa-ikFJ`9kWRrhRBvFimg*AtM3h?MBVPdbC_u-W`x=}oeat9|O<>>ec3-}CabA#1 zuj^MD9dH%%%ziQ90QVk0>~mXci~R}rzho#RcsDR=gY09Gv-pYtAi!?n9-(6eog%3k z0ZrrRIA8)0wzV>B$%A-M2_Va@Z5A3Ia2}|nM#1)@hht(+$rID0&J_4I4xuj=?vy!G zEdY5;zbEuV&`_+ci|rhE|96QfKbOT}%JwiVPaJ*o2(27zYw>flXY&`25`^o-C0 zTe~!9+73$3O4dx?-#|SqLsK(8DgLlpo+IM1iJ`mWoc1h14UDU$t7>f2`e74O?l@-c$IKT3G>qNjYw0ZkMoUQ&zVX0-OM8Y$3jBzCkO2ZAq zJGQc6-M0E|XlBuoG8^Hb#OWlup)5*G(k$SPeA|jYXLu3PGcg0J+??&jcgQ@OrmgJ6 zwGLgnoNqeLqlc3PdUvYBRINZyw_p63c2SQm6pOWMV~gje+aI5r%TGto%}n~Vf=cM@ zXHvCF-QorU=0BkoG>|?$=g5*1?OSaeX_OlKL*6@HQm6JEyEr*|aazZUQvgjCWud~! z<#Pq*Nd(of0r_cyIWeA1$#iMi<5*pTpJ1-wm6J_3KrDM6slaco@Q>9fXD?nnJ2v7D z4o|Vn)Jzjj6{R&gSy4Ud(aTg<6Lg5Lr>AdRyvV7q@Ve=r4+kz|jxho`0?vl-4rek4 zvVmbDln4VRT8vu~vsD7kL}Q<7>^$6KgHR>p*7$!!n{K~-cq>b z1Umtl9EBeisL;!Ie6jH<AC3bxxn+`hTyZhP0OGplz?!b`C?(rU<0dkc&6&Y3{?muNbRqwn1LfuCwP zdp;A`_NT=lZKh)S%y1%>&lYLOY{md=Mz$-aB3+pK?=W>~HQf^{Ai&S|H1;@+7Yxey zbgYzphbyygV&vzP+3Ut_XyuW5dZ>Rh<5GhqofV;$b7G;PHHj;1GY7G z@A+woLjd#B^0)8|Xtxd@AHpTM1yl-AO_0Q*!5w>@+yPjSdRM*kq^O%f*dDaGt+C6w z|A7#8eTw@|k21^bmzzDt`l-@6Svp?m$fB+B)KdgjtV>#|05#UAr&Ea5I(opCUzvpq z{zQ?fQcfz`W$W@emeU1-BBckuzy}G?b+2=zI8B4}@e{U;gx62sDc0~k*Z{~wv8I^@ zq3E1`1xbq5MWACFr-2N0>(D5}|BvkZPumU_5B&N5$K2TZ*^}Jq{wyW9Kc+R=6UZ<+19V2w4Z%aXE z)2W$_`qrByH(@CB(4gkL6W&u~8E}Qy<&Q$(D#V!Lne~7`|FGla^X|aA&6lp1=DSOC zwZR~RtMkhxgi^gEd4Z8rS;L8fG#?_z{SHyT(k!%VgLY|)Bf26xZ#RAj_G*xU?3~z6 z7$77xDIX)!$h;4k$_xNbC5??$XF|d-O8=vE&B=prCDsnUwei8mvrZ#tzV$uOgC0G+ zPA}#jQ?6u7kZqSs;(z*dn1jHCp(;}&KB~s0K0~JMhx%`k#Eera)t19l^STiB-NC-z ze(*1}yPrAu7Y9Fm@FNHQ)q%fz;Hw9!2hJXN@xZqI|Lgu=-+zDq@cxhP`_p}I?ECz_ z^ZQ=d`xkrvc<*oQy|Z_G??;{g+xbK1p;LFps2ce9d;Zy;pW8FDC%R|v?ti=cf7<=k z-M4mUc7Jf!f7tcMyS}ljx$DZV-kopn{Kq?A-Fau{>75_h@$Yv0;~ih#F~8%}J3bKk zKO%2Nz7hFMWFm5?`_H=nsQb6Oo83R!o#^`Wu7B3`)vh1!`qcLSXZt_d{+rwHZ@;lU zvh81Q`~7W4uSX6g4uyiB03!9>^M*pfA=|Jt`j*Mm=;p_+MGo~oA4=jhfU7%RuPiUD z-dQsLOkdq`sL}mGNFz{Dnmh6M^$Kjjw_bfHH1$jF7-vuk{c>kGkCW8td>@bh+8^-e zXMdkRUwxH7uYOi<9p{h;pM?I=E0NgqJsT6_Hc36Pwi{l&965CCg)rGXVORz3Ahd$V zuhR}B%crub0 zJ-$hvi8Ve^@hQr#iHkDlzUV6LMOEIim|SCC@T8s_nd-R|Io#9JO7qa2QrR#aUedZ1 zn~20t_HIl=Op$frSk4x~Ah>^%cP1}J6332jg5<+)q!*p~hgKjv*n7d9n+u<~5IJ=G zc!+mdK+z2gLOSrpA0Ce+a(u%Ey8Gisc^Me*4j}$aAT~mY%$xn+?<6 zRC>0U+#i1>a_DGp$Q!&OatDC_I6W);b!5sD=Oc$-KGx#$P5LwkC-rz*$td-hHxJOX z+TQ!fXynlI&xd3%%J$~{*;4RN&$-CqW6!n7rsqj>6(|Cj^;bwoSq|@svysE8-d6R& zc#+fRgL(xDp%HAwTUSmTI}=H~aBLIZYIGz>C)9~jyS_X&5;=VIc#C#qC%~s23yZm< z0>5`S($m|sR>Dd79sANWL|m)HJ2Zq0KNJ>D4nl(=1vS{`P8L?ZN@4Yd(~;+6hXOKl zP)&MP&zeeLKm7ODV5H~x3n=QKAaH0w^)r;(x>JR6#WR0yng^@L2O^2*n2rrJ23tkf zUQ2iM6jyt+Rb_Ps5{)-nR-_$qL12 ztBFrVV#kkd?3g&r(r2O|69M%4ReM)|G3n*wKm1;X{K?4SlRd32SmUJrb?Duty4cNS z5+jV>+;%g_T2PUBAHB*Pc;@J>yPnS2_H7yrOG|o zr!Li(GKlPOtAowBx60;Wi$RF>C=sgqOYpRGr}T+5A9lQTK1fh1!CHF!?c%-Q-pz4% zF86K@#Zr;Or+Ql_ap(*`gV0ZD=>w&|{n{74!|$)HJ9{IRj3ka8-NYl~Jyc}7rwbL@ z^x8W&?VV2~B0a~Bt(`Nm{z!_UEA96_8jtimcL-A*9FbrXtzo(~7JJWIus4c5IUIIT z4>aL;9|uo)_wr#Q{O4YlF~NA6j^&1=|G(dVV9HsK^kFU$k?kuUyn{AgVvCV=g9bk1 z$4{c8C6mrG27*0Ew;oE_tM*=S=fx9jmKRz*iPg`zrT+7U0?ZkE#zp#gB!NPN;n#8a z=m@7~z(yezZ1@4id**?g;l1ZS5jl)%3=dKaj=3Df1E51e&#}ni7Y?<~zJnV#M51yG z+U*jz>8$IOdS8khdZ9NwQ*NY$7GV`=Ew4L_IeIkGlVWh;5pGutGaQvkMzLgzgY4jFqK|Fk9$}4dm7K|qvXwfHu?E=9S?r_O7xAAy-BF|@@ zk0&|tE)@$*%VTR%IiOxgY1QpNpKvjGFVKunO-|$4^L`CV+8q+V-n@5@^GtX^_otRQ zo8-`8hI)t+KazWdNn^nY^5IGH$3KQa>mk!fjWpv7zHUqn!NSuyi)yA_EmE&>@=)YZ z?09&H{kS=u-aSJJm^MG>wBbZ!4qNBdzx>h2p|j70r^cTza2i}y=3BJPvBz)VeJgFp zrOgz~pKC8YABlbF*v3=NZ*YJ#Ei-Aua*ta&&OP>#_v{uOeJ;{-^aXr*{M1Y;7ac;H zB>pA~gpxIT$KHPNhcKB(!xJ*C7A`EQCq7|A$++7Xsrax%(1BdKF z`=C1km5X$Bq}jp{N!W87tiutvaI*?atE~r&_x|z^yhkVb#Sbv59v#^fr;9-LOntFf zqwh@M3kP>^j!b>(nMmT3>?Y{1I(~&cMF}=p*u?PY+0kip-sOdhR|cm?FJ5pjj9i_v zt&(&)&&_h-PPO+Sdhu`~r_+h3!<@n%A-8ilV^s5bWqG*s-pdCfJ&9v+&UT5x5ldvo za9SRJ+gGoNNxC=q)3ayv5G8_zvU%Wz{V2Q_2u`DrGgHYy$bN&!oZ}SlbNlK7^!_`3 zY3}3uCaSc0-n@z!Ygl1rQ}`U~|L7q{Nt;>O4JM0(iKIa&o|xu6U#%<=-1#_->d z?0&L~8{LI6eF5(bb{sLSECdRVuAURChSFvaC$V?z?aWSA3zH+MWyMaWV3T#6P7N*> z>vvrOmU3`tvU#8u+%I}ZcChGsTIZ%?*vbE2R8fQ+^kR9z%O+onL}G_}I5vy1AVXp} zMn+t5o-QEJ96kMeQ#Wp&>yGpkj\n", + "Int64Index: 154 entries, 0 to 53\n", + "Data columns (total 6 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 text 154 non-null object\n", + " 1 edit_history_tweet_ids 154 non-null object\n", + " 2 created_at 154 non-null object\n", + " 3 author_id 154 non-null object\n", + " 4 public_metrics 154 non-null object\n", + " 5 id 154 non-null object\n", + "dtypes: object(6)\n", + "memory usage: 8.4+ KB\n" + ] + } + ], + "source": [ + "tweet_df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
textedit_history_tweet_idscreated_atauthor_idpublic_metricsid
0Gente muy agradable en @TheBridge_Tech , te ri...[1578613094191796224]2022-10-08T05:07:45.000Z1578095844569514011{'retweet_count': 0, 'reply_count': 0, 'like_c...1578613094191796224
1Recordaros que la semana que viene tenemos la ...[1577334577701453827]2022-10-04T16:27:23.000Z1003872445{'retweet_count': 2, 'reply_count': 0, 'like_c...1577334577701453827
2El desarrollador web es uno de los perfiles má...[1576902991507922944]2022-10-03T11:52:25.000Z2529499620{'retweet_count': 3, 'reply_count': 0, 'like_c...1576902991507922944
3@jorgegrev @TheBridge_Tech Enhorabuena crack![1576856703349374976]2022-10-03T08:48:29.000Z706520411551494145{'retweet_count': 0, 'reply_count': 0, 'like_c...1576856703349374976
4Hoy por fin ve la luz mi primer Case Study púb...[1575217357105946624]2022-09-28T20:14:18.000Z604485175{'retweet_count': 3, 'reply_count': 0, 'like_c...1575217357105946624
\n", + "
" + ], + "text/plain": [ + " text edit_history_tweet_ids \\\n", + "0 Gente muy agradable en @TheBridge_Tech , te ri... [1578613094191796224] \n", + "1 Recordaros que la semana que viene tenemos la ... [1577334577701453827] \n", + "2 El desarrollador web es uno de los perfiles má... [1576902991507922944] \n", + "3 @jorgegrev @TheBridge_Tech Enhorabuena crack! [1576856703349374976] \n", + "4 Hoy por fin ve la luz mi primer Case Study púb... [1575217357105946624] \n", + "\n", + " created_at author_id \\\n", + "0 2022-10-08T05:07:45.000Z 1578095844569514011 \n", + "1 2022-10-04T16:27:23.000Z 1003872445 \n", + "2 2022-10-03T11:52:25.000Z 2529499620 \n", + "3 2022-10-03T08:48:29.000Z 706520411551494145 \n", + "4 2022-09-28T20:14:18.000Z 604485175 \n", + "\n", + " public_metrics id \n", + "0 {'retweet_count': 0, 'reply_count': 0, 'like_c... 1578613094191796224 \n", + "1 {'retweet_count': 2, 'reply_count': 0, 'like_c... 1577334577701453827 \n", + "2 {'retweet_count': 3, 'reply_count': 0, 'like_c... 1576902991507922944 \n", + "3 {'retweet_count': 0, 'reply_count': 0, 'like_c... 1576856703349374976 \n", + "4 {'retweet_count': 3, 'reply_count': 0, 'like_c... 1575217357105946624 " + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tweet_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [], + "source": [ + "tweet_df.drop(columns='public_metrics', axis=1, inplace=True)\n", + "tweet_df.drop(columns='edit_history_tweet_ids', axis=1, inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": {}, + "outputs": [], + "source": [ + "retweet_count_list = []\n", + "reply_count = []\n", + "like_count = []\n", + "quote_count = []" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": {}, + "outputs": [], + "source": [ + "for data in data_list:\n", + " for tweet in data['data']:\n", + " retweet_count_list.append(tweet['public_metrics']['retweet_count'])\n", + " reply_count.append(tweet['public_metrics']['reply_count'])\n", + " like_count.append(tweet['public_metrics']['like_count'])\n", + " quote_count.append(tweet['public_metrics']['quote_count'])" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": {}, + "outputs": [], + "source": [ + "tweet_df['retweet_count'] = retweet_count_list\n", + "tweet_df['reply_count'] = reply_count\n", + "tweet_df['like_count'] = like_count\n", + "tweet_df['quote_count'] = quote_count" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
textcreated_atauthor_ididretweet_countreply_countlike_countquote_count
0Gente muy agradable en @TheBridge_Tech , te ri...2022-10-08T05:07:45.000Z157809584456951401115786130941917962240000
1Recordaros que la semana que viene tenemos la ...2022-10-04T16:27:23.000Z1003872445157733457770145382720120
2El desarrollador web es uno de los perfiles má...2022-10-03T11:52:25.000Z252949962015769029915079229443030
3@jorgegrev @TheBridge_Tech Enhorabuena crack!2022-10-03T08:48:29.000Z70652041155149414515768567033493749760010
4Hoy por fin ve la luz mi primer Case Study púb...2022-09-28T20:14:18.000Z60448517515752173571059466243040
\n", + "
" + ], + "text/plain": [ + " text \\\n", + "0 Gente muy agradable en @TheBridge_Tech , te ri... \n", + "1 Recordaros que la semana que viene tenemos la ... \n", + "2 El desarrollador web es uno de los perfiles má... \n", + "3 @jorgegrev @TheBridge_Tech Enhorabuena crack! \n", + "4 Hoy por fin ve la luz mi primer Case Study púb... \n", + "\n", + " created_at author_id id \\\n", + "0 2022-10-08T05:07:45.000Z 1578095844569514011 1578613094191796224 \n", + "1 2022-10-04T16:27:23.000Z 1003872445 1577334577701453827 \n", + "2 2022-10-03T11:52:25.000Z 2529499620 1576902991507922944 \n", + "3 2022-10-03T08:48:29.000Z 706520411551494145 1576856703349374976 \n", + "4 2022-09-28T20:14:18.000Z 604485175 1575217357105946624 \n", + "\n", + " retweet_count reply_count like_count quote_count \n", + "0 0 0 0 0 \n", + "1 2 0 12 0 \n", + "2 3 0 3 0 \n", + "3 0 0 1 0 \n", + "4 3 0 4 0 " + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tweet_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [], + "source": [ + "df_author_1 = pd.DataFrame()\n", + "df_author_2 = pd.DataFrame()\n", + "df_author_list = [df_author_1, df_author_2]" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": {}, + "outputs": [], + "source": [ + "for index, data in enumerate(data_list):\n", + " data = data['includes']['users']\n", + " df_author_list[index] = pd.DataFrame(data)\n", + " author_df = pd.concat(df_author_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idnameusername
01578095844569514011Rocket75_Rocket_
11003872445Pau MugarraPauMugarra
22529499620Formación Fundación Universidad Carlos IIIformacion_fuc3
3706520411551494145JoseSolaJose_Sola_
4604485175Berta Oterobertinha84
\n", + "
" + ], + "text/plain": [ + " id name \\\n", + "0 1578095844569514011 Rocket \n", + "1 1003872445 Pau Mugarra \n", + "2 2529499620 Formación Fundación Universidad Carlos III \n", + "3 706520411551494145 JoseSola \n", + "4 604485175 Berta Otero \n", + "\n", + " username \n", + "0 75_Rocket_ \n", + "1 PauMugarra \n", + "2 formacion_fuc3 \n", + "3 Jose_Sola_ \n", + "4 bertinha84 " + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "author_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 90 entries, 0 to 26\n", + "Data columns (total 3 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 90 non-null object\n", + " 1 name 90 non-null object\n", + " 2 username 90 non-null object\n", + "dtypes: object(3)\n", + "memory usage: 2.8+ KB\n" + ] + } + ], + "source": [ + "author_df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [], + "source": [ + "connection = sqlite3.connect('../data/twitter.db')" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [], + "source": [ + "tweet_df.to_sql('tweets', con=connection, index=False)\n", + "author_df.to_sql('users', con=connection, index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [], + "source": [ + "connection.close()" + ] } ], "metadata": {