{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "59b61714", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": null, "id": "05b4de3b", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 2, "id": "e0861ca3", "metadata": {}, "outputs": [], "source": [ "texts= pd.read_csv('Final1.0.tsv', sep='\\t').dropna(axis=0).iloc[:,-2].values.reshape(-1,).astype('object')\n" ] }, { "cell_type": "code", "execution_count": null, "id": "b8b9f9dd", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "35dbfd76", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "c0215db5", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 3, "id": "f1d3aa7e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'prison,warden,inmate,solitary,parole,cell,rock,library,prisoner,hammer,guard,state,wall,poster,red,remark,diploma,book,job,infirmary,financial,record,hope,banker,shoe,stone,project,night,several,senate,fat,oak,commemorate,beam,work,cold,hole,halfway,wooden,office,salvation,scheme,letter,contractor,expertise,morning,promise,giant,order,tax,month'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "texts[0]" ] }, { "cell_type": "code", "execution_count": null, "id": "dae810d8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 4, "id": "12644df4", "metadata": {}, "outputs": [], "source": [ "corpus=[]\n", "for text in texts:\n", " text=text.replace(',',' ').split(' ')\n", " corpus.append(text)" ] }, { "cell_type": "code", "execution_count": 5, "id": "d8fdbf16", "metadata": {}, "outputs": [], "source": [ "df=pd.DataFrame(corpus)" ] }, { "cell_type": "code", "execution_count": 6, "id": "c23457ab", "metadata": {}, "outputs": [], "source": [ "df=df.iloc[:,:51]" ] }, { "cell_type": "code", "execution_count": 7, "id": "c9a463ad", "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", " \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", " \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", " \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", " \n", " \n", " \n", "
0123456789...41424344454647484950
0prisonwardeninmatesolitaryparolecellrocklibraryprisonerhammer...schemelettercontractorexpertisemorningpromisegiantordertaxmonth
1mobcoinclownferrymemberbuildingcelldetonatorpolicemayor...cleancitizenscarredcancelraiserpeopleconvoytellfightfamily
2dreamlimboteamsubconsciousprojectionkicktoplevelfathermind...guardmobsubjectiveideaarchitectspinextractoraccesscombinationtrain
3narratorsoapmemberfightclubconsumerisminsomniatesticularbuildingburn...gynecomastiaglisteneddetrimentcancerfightingdestructionperiodsubstandardliposuctionlag
4watchtyrannyapartmentstrippawnmiraclecarbriefcasewalletgang...leaverectumeviltraveloffscreentalkpowsuitpassersbydiscreet
..................................................................
7133donkeyvoicemangercamelmessiahdoganimalbabycartcliff...outcomebelongkindnesslikingwellcowaweguidancediversionsave
7134memoryasylumlapseamnesiamarriagesensingtownmarriedlovelessrevel...firstrichfamousstaffinterviewrememberquietshockcareerbegin
7135blimphelicoptergondolastadiumisraelicompoundshrapnelcommandomissioncaptain...offsethospitalunderbellyrepressionnursewoundingwordingpilotingriflebazaar
7136computermusicaltalenthumansexologyromanceprodigiouscellistneoaccessible...lessidentitycardthankpersonalrevengebeautifulsuicidecreditstate
7137hotelwincontestaffectionnecessarytalentenginenubilecashpool...mainsongneedformtablesayhoureventcityattempt
\n", "

7138 rows × 51 columns

\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 \\\n", "0 prison warden inmate solitary parole cell \n", "1 mob coin clown ferry member building \n", "2 dream limbo team subconscious projection kick \n", "3 narrator soap member fight club consumerism \n", "4 watch tyranny apartment strip pawn miracle \n", "... ... ... ... ... ... ... \n", "7133 donkey voice manger camel messiah dog \n", "7134 memory asylum lapse amnesia marriage sensing \n", "7135 blimp helicopter gondola stadium israeli compound \n", "7136 computer musical talent human sexology romance \n", "7137 hotel win contest affection necessary talent \n", "\n", " 6 7 8 9 ... 41 \\\n", "0 rock library prisoner hammer ... scheme \n", "1 cell detonator police mayor ... clean \n", "2 top level father mind ... guard \n", "3 insomnia testicular building burn ... gynecomastia \n", "4 car briefcase wallet gang ... leave \n", "... ... ... ... ... ... ... \n", "7133 animal baby cart cliff ... outcome \n", "7134 town married loveless revel ... first \n", "7135 shrapnel commando mission captain ... offset \n", "7136 prodigious cellist neo accessible ... less \n", "7137 engine nubile cash pool ... main \n", "\n", " 42 43 44 45 46 47 \\\n", "0 letter contractor expertise morning promise giant \n", "1 citizen scarred cancel raiser people convoy \n", "2 mob subjective idea architect spin extractor \n", "3 glistened detriment cancer fighting destruction period \n", "4 rectum evil travel offscreen talk pow \n", "... ... ... ... ... ... ... \n", "7133 belong kindness liking well cow awe \n", "7134 rich famous staff interview remember quiet \n", "7135 hospital underbelly repression nurse wounding wording \n", "7136 identity card thank personal revenge beautiful \n", "7137 song need form table say hour \n", "\n", " 48 49 50 \n", "0 order tax month \n", "1 tell fight family \n", "2 access combination train \n", "3 substandard liposuction lag \n", "4 suit passersby discreet \n", "... ... ... ... \n", "7133 guidance diversion save \n", "7134 shock career begin \n", "7135 piloting rifle bazaar \n", "7136 suicide credit state \n", "7137 event city attempt \n", "\n", "[7138 rows x 51 columns]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 8, "id": "a7d18f13", "metadata": {}, "outputs": [], "source": [ "movies= pd.read_csv('Final1.0.tsv', sep='\\t').dropna(axis=0)" ] }, { "cell_type": "code", "execution_count": 9, "id": "8f2a8d42", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "204" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(np.where(df=='detective')[0])" ] }, { "cell_type": "code", "execution_count": null, "id": "cb9c6af8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 10, "id": "b14d43f3", "metadata": {}, "outputs": [], "source": [ "def count_f(array):\n", " global movies\n", " unique, counts = np.unique(array, return_counts=True)\n", " array=dict(zip(unique, counts))\n", " array={movies.iloc[k,3]: v for k, v in sorted(array.items(), key=lambda item: item[1], reverse=True)} #set to true\n", " #print(array)\n", " return array" ] }, { "cell_type": "code", "execution_count": 11, "id": "ad4b9498", "metadata": {}, "outputs": [], "source": [ "def check(word):\n", " global df\n", " array= np.where(df== word)[0]\n", " array= count_f(array)\n", " return array" ] }, { "cell_type": "code", "execution_count": null, "id": "96ee49f5", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "a4658f04", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 19, "id": "b4ea4bbf", "metadata": {}, "outputs": [], "source": [ "scores=pd.read_csv('Final1.0.tsv', sep='\\t').dropna(axis=0).iloc[:,-1].values.reshape(-1,).astype('object')\n", "Scores=[]\n", "for score in scores:\n", " score=score.replace(',',' ').split(' ')\n", " Scores.append(score)\n", "scores= Scores\n", "del Scores" ] }, { "cell_type": "code", "execution_count": 20, "id": "4984247e", "metadata": {}, "outputs": [], "source": [ "df_scores= pd.DataFrame(scores)" ] }, { "cell_type": "code", "execution_count": 21, "id": "c959211d", "metadata": {}, "outputs": [], "source": [ "df_scores= pd.DataFrame(df_scores.values.astype('float64'))" ] }, { "cell_type": "code", "execution_count": 22, "id": "7f06cd24", "metadata": {}, "outputs": [], "source": [ "from sklearn.preprocessing import MinMaxScaler\n", "scaler=MinMaxScaler()\n", "df_scores= pd.DataFrame(scaler.fit_transform(df_scores.T).T)" ] }, { "cell_type": "code", "execution_count": 23, "id": "4550c660", "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", " \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", " \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", " \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", " \n", " \n", " \n", "
0123456789...41424344454647484950
01.00.7555480.5165690.3700190.3541130.3463810.2655160.2237060.2072250.203137...0.0194950.0194150.0129390.0119000.0031190.0019270.0012650.0010770.0008970.0
11.00.9820250.6743990.4750430.4403280.3346330.2701000.2556520.2508460.247755...0.0300260.0217760.0156220.0150450.0109210.0038170.0019340.0006690.0003440.0
21.00.4874790.3742960.3128610.2586480.2021340.1722120.1524820.1365790.133342...0.0120020.0117350.0112970.0105920.0103620.0087630.0083630.0062930.0052520.0
31.00.0727520.0533690.0474520.0465590.0459870.0342230.0224020.0223920.020933...0.0020230.0020230.0020230.0011700.0008950.0004260.0002050.0000000.0000000.0
41.00.9415210.7594170.7038500.6168940.5914220.5631990.5256770.4955570.421539...0.0222740.0174720.0167660.0104720.0081520.0080370.0039490.0033000.0000000.0
..................................................................
71331.00.7047970.4708190.3757150.3113710.2625650.2122780.1693120.1474010.115342...0.0038420.0038420.0034210.0032140.0027680.0018360.0018360.0016480.0007400.0
71341.00.5988470.4983660.4315300.3188330.2343920.2036990.1867390.1856230.179766...0.0279610.0226760.0197170.0154820.0146770.0145770.0143790.0110210.0101020.0
71351.00.2151650.1932080.1640440.1590770.0989980.0989320.0899120.0759840.071009...0.0029790.0022530.0018640.0018640.0009570.0008800.0008800.0008800.0007170.0
71361.00.9780770.8567380.7728130.5400520.4960460.4181160.3984890.3571480.346789...0.0413410.0383590.0363300.0350500.0289160.0224440.0168750.0137170.0036780.0
71371.00.6442720.5565040.5414360.4970820.4714570.4635790.4511800.3848090.361875...0.0620420.0615830.0507000.0480530.0377630.0339630.0250480.0158100.0091140.0
\n", "

7138 rows × 51 columns

\n", "
" ], "text/plain": [ " 0 1 2 3 4 5 6 \\\n", "0 1.0 0.755548 0.516569 0.370019 0.354113 0.346381 0.265516 \n", "1 1.0 0.982025 0.674399 0.475043 0.440328 0.334633 0.270100 \n", "2 1.0 0.487479 0.374296 0.312861 0.258648 0.202134 0.172212 \n", "3 1.0 0.072752 0.053369 0.047452 0.046559 0.045987 0.034223 \n", "4 1.0 0.941521 0.759417 0.703850 0.616894 0.591422 0.563199 \n", "... ... ... ... ... ... ... ... \n", "7133 1.0 0.704797 0.470819 0.375715 0.311371 0.262565 0.212278 \n", "7134 1.0 0.598847 0.498366 0.431530 0.318833 0.234392 0.203699 \n", "7135 1.0 0.215165 0.193208 0.164044 0.159077 0.098998 0.098932 \n", "7136 1.0 0.978077 0.856738 0.772813 0.540052 0.496046 0.418116 \n", "7137 1.0 0.644272 0.556504 0.541436 0.497082 0.471457 0.463579 \n", "\n", " 7 8 9 ... 41 42 43 \\\n", "0 0.223706 0.207225 0.203137 ... 0.019495 0.019415 0.012939 \n", "1 0.255652 0.250846 0.247755 ... 0.030026 0.021776 0.015622 \n", "2 0.152482 0.136579 0.133342 ... 0.012002 0.011735 0.011297 \n", "3 0.022402 0.022392 0.020933 ... 0.002023 0.002023 0.002023 \n", "4 0.525677 0.495557 0.421539 ... 0.022274 0.017472 0.016766 \n", "... ... ... ... ... ... ... ... \n", "7133 0.169312 0.147401 0.115342 ... 0.003842 0.003842 0.003421 \n", "7134 0.186739 0.185623 0.179766 ... 0.027961 0.022676 0.019717 \n", "7135 0.089912 0.075984 0.071009 ... 0.002979 0.002253 0.001864 \n", "7136 0.398489 0.357148 0.346789 ... 0.041341 0.038359 0.036330 \n", "7137 0.451180 0.384809 0.361875 ... 0.062042 0.061583 0.050700 \n", "\n", " 44 45 46 47 48 49 50 \n", "0 0.011900 0.003119 0.001927 0.001265 0.001077 0.000897 0.0 \n", "1 0.015045 0.010921 0.003817 0.001934 0.000669 0.000344 0.0 \n", "2 0.010592 0.010362 0.008763 0.008363 0.006293 0.005252 0.0 \n", "3 0.001170 0.000895 0.000426 0.000205 0.000000 0.000000 0.0 \n", "4 0.010472 0.008152 0.008037 0.003949 0.003300 0.000000 0.0 \n", "... ... ... ... ... ... ... ... \n", "7133 0.003214 0.002768 0.001836 0.001836 0.001648 0.000740 0.0 \n", "7134 0.015482 0.014677 0.014577 0.014379 0.011021 0.010102 0.0 \n", "7135 0.001864 0.000957 0.000880 0.000880 0.000880 0.000717 0.0 \n", "7136 0.035050 0.028916 0.022444 0.016875 0.013717 0.003678 0.0 \n", "7137 0.048053 0.037763 0.033963 0.025048 0.015810 0.009114 0.0 \n", "\n", "[7138 rows x 51 columns]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_scores" ] }, { "cell_type": "code", "execution_count": 155, "id": "e4057031", "metadata": {}, "outputs": [], "source": [ "def apply( row, idx,n=20):\n", " c,s,cc=0,0,0\n", " keys=df.iloc[idx,:][:n]\n", " k= set(keys)\n", " ch_k=df.iloc[row.name,:]\n", " ch_keys= set(ch_k)\n", " scores= df_scores.iloc[idx,:]\n", " ch_scores= df_scores.iloc[idx,:]\n", " k=list(k.intersection(ch_keys))\n", " #print(scores)\n", " if len(k)>0:\n", " s=0\n", " for i in k:\n", " #print(i)\n", " #print(ch_keys)\n", " c=np.where( np.array(list(ch_k))== i)[0][0]\n", " cc=np.where( keys== i)[0][0]\n", " #print(movies.title[row.name],c,cc, i)\n", " s=s+ pow(ch_scores[c]*scores[cc],0.5)\n", " \n", " #print(movies.title[row.name], ch_scores[c],scores[cc],s, i)\n", " return movies.title[row.name],s, ' '.join(k), len(k)\n", " else:\n", " return movies.title[row.name],0, 0,0" ] }, { "cell_type": "code", "execution_count": 156, "id": "9f1313c8", "metadata": {}, "outputs": [], "source": [ "t= df.T" ] }, { "cell_type": "code", "execution_count": 159, "id": "cbb4a56f", "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", " \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", " \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", " \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", " \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", "
0123
58The Sixth Sense6.322532continual failure patient second unfinished pr...20
1828Gothika1.751718boy patient ghost illness4
2024Volver1.711314funeral asleep ghost mother4
2770A Ghost Story1.597113ghost wife2
4804Rose Red1.472727ability sick ghost mother4
1466Crimson Peak1.438085ghost mother2
6717Ringu 01.3394second ability ghost mother4
6065Backtrack1.323586patient ghost wife3
1714Scary Movie 41.318869second boy ghost3
2781The Devil's Backbone1.285802boy ghost gun3
1050The Darjeeling Limited1.248182boy funeral mother wife4
2752The Awakening1.244946boy ghost2
6714Bag of Bones1.239956ghost wife2
3067Macbeth1.223319boy ghost wife3
3599The Ward1.208044patient ghost2
6753Golmaal Again1.201297boy ghost2
6533Noel1.184068patient mother wife3
5792The Canal1.180173ghost wife2
299619221.169989ghost mother wife3
2580Who's Afraid of Virginia Woolf?1.155451boy wife2
5088Lake Mungo1.129981videotape ghost mother3
2512Awake1.123247wedding patient mother wife4
6160Eternity and a Day1.123246boy unfinished wedding mother4
6855Haunt1.119474patient ghost2
7083Panic in the Streets1.119224illness sick wife3
5908Paheli1.110892ghost wife2
2283The Frighteners1.071822funeral gun wife ghost mother5
51250/501.068239patient illness2
4613The Prodigy1.061415boy unfinished gun3
5272The Young and Prodigious T.S. Spivet1.054648boy mother gun3
7035Our House1.027646ghost wife2
504Jojo Rabbit1.017616boy mother2
2914A Tale of Two Sisters1.014947ghost mother wife3
1416The Grudge1.014368boy ghost wife3
4753Badlapur1.001836second mother wife3
433Ghostbusters1.0ghost1
915Ghostbusters1.0ghost1
1305Scary Movie 21.0ghost1
1601Casper1.0ghost1
2335Thir13en Ghosts1.0ghost1
5242Kairo1.0ghost1
5424The Ghost and Mrs. Muir1.0ghost1
5453No Retreat, No Surrender1.0ghost1
5491Hamlet1.0ghost1
6477Scrooge1.0ghost1
6747Bhoothnath1.0ghost1
6911Ghost Story1.0ghost1
2893Fanny and Alexander0.998165ability ghost mother3
4845Mars Needs Moms0.996341boy asleep mother3
3051House on Haunted Hill0.99189patient ghost wife3
\n", "
" ], "text/plain": [ " 0 1 \\\n", "58 The Sixth Sense 6.322532 \n", "1828 Gothika 1.751718 \n", "2024 Volver 1.711314 \n", "2770 A Ghost Story 1.597113 \n", "4804 Rose Red 1.472727 \n", "1466 Crimson Peak 1.438085 \n", "6717 Ringu 0 1.3394 \n", "6065 Backtrack 1.323586 \n", "1714 Scary Movie 4 1.318869 \n", "2781 The Devil's Backbone 1.285802 \n", "1050 The Darjeeling Limited 1.248182 \n", "2752 The Awakening 1.244946 \n", "6714 Bag of Bones 1.239956 \n", "3067 Macbeth 1.223319 \n", "3599 The Ward 1.208044 \n", "6753 Golmaal Again 1.201297 \n", "6533 Noel 1.184068 \n", "5792 The Canal 1.180173 \n", "2996 1922 1.169989 \n", "2580 Who's Afraid of Virginia Woolf? 1.155451 \n", "5088 Lake Mungo 1.129981 \n", "2512 Awake 1.123247 \n", "6160 Eternity and a Day 1.123246 \n", "6855 Haunt 1.119474 \n", "7083 Panic in the Streets 1.119224 \n", "5908 Paheli 1.110892 \n", "2283 The Frighteners 1.071822 \n", "512 50/50 1.068239 \n", "4613 The Prodigy 1.061415 \n", "5272 The Young and Prodigious T.S. Spivet 1.054648 \n", "7035 Our House 1.027646 \n", "504 Jojo Rabbit 1.017616 \n", "2914 A Tale of Two Sisters 1.014947 \n", "1416 The Grudge 1.014368 \n", "4753 Badlapur 1.001836 \n", "433 Ghostbusters 1.0 \n", "915 Ghostbusters 1.0 \n", "1305 Scary Movie 2 1.0 \n", "1601 Casper 1.0 \n", "2335 Thir13en Ghosts 1.0 \n", "5242 Kairo 1.0 \n", "5424 The Ghost and Mrs. Muir 1.0 \n", "5453 No Retreat, No Surrender 1.0 \n", "5491 Hamlet 1.0 \n", "6477 Scrooge 1.0 \n", "6747 Bhoothnath 1.0 \n", "6911 Ghost Story 1.0 \n", "2893 Fanny and Alexander 0.998165 \n", "4845 Mars Needs Moms 0.996341 \n", "3051 House on Haunted Hill 0.99189 \n", "\n", " 2 3 \n", "58 continual failure patient second unfinished pr... 20 \n", "1828 boy patient ghost illness 4 \n", "2024 funeral asleep ghost mother 4 \n", "2770 ghost wife 2 \n", "4804 ability sick ghost mother 4 \n", "1466 ghost mother 2 \n", "6717 second ability ghost mother 4 \n", "6065 patient ghost wife 3 \n", "1714 second boy ghost 3 \n", "2781 boy ghost gun 3 \n", "1050 boy funeral mother wife 4 \n", "2752 boy ghost 2 \n", "6714 ghost wife 2 \n", "3067 boy ghost wife 3 \n", "3599 patient ghost 2 \n", "6753 boy ghost 2 \n", "6533 patient mother wife 3 \n", "5792 ghost wife 2 \n", "2996 ghost mother wife 3 \n", "2580 boy wife 2 \n", "5088 videotape ghost mother 3 \n", "2512 wedding patient mother wife 4 \n", "6160 boy unfinished wedding mother 4 \n", "6855 patient ghost 2 \n", "7083 illness sick wife 3 \n", "5908 ghost wife 2 \n", "2283 funeral gun wife ghost mother 5 \n", "512 patient illness 2 \n", "4613 boy unfinished gun 3 \n", "5272 boy mother gun 3 \n", "7035 ghost wife 2 \n", "504 boy mother 2 \n", "2914 ghost mother wife 3 \n", "1416 boy ghost wife 3 \n", "4753 second mother wife 3 \n", "433 ghost 1 \n", "915 ghost 1 \n", "1305 ghost 1 \n", "1601 ghost 1 \n", "2335 ghost 1 \n", "5242 ghost 1 \n", "5424 ghost 1 \n", "5453 ghost 1 \n", "5491 ghost 1 \n", "6477 ghost 1 \n", "6747 ghost 1 \n", "6911 ghost 1 \n", "2893 ability ghost mother 3 \n", "4845 boy asleep mother 3 \n", "3051 patient ghost wife 3 " ] }, "execution_count": 159, "metadata": {}, "output_type": "execute_result" } ], "source": [ "t.apply(lambda x : apply(x,58)).T.sort_values(by=[1,3], ascending= [False,False]).head(50)" ] }, { "cell_type": "code", "execution_count": null, "id": "b94f792d", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "0fe94160", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 117, "id": "d06f3342", "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", "
titleIdaverageRatingnumVotestitlestartYearruntimeMinutesgenressynopsissynopsis_allowed_poskeywordsscores
1012tt11271806.5190958Drag Me to Hell200999HorrorIn Pasadena, California in 1969, a young Mexic...young mexican couple home medium son jewelry g...button,loan,envelope,clay,assistant,cake,goat,...0.36904204918723854,0.2306283305898838,0.22358...
\n", "
" ], "text/plain": [ " titleId averageRating numVotes title startYear \\\n", "1012 tt1127180 6.5 190958 Drag Me to Hell 2009 \n", "\n", " runtimeMinutes genres \\\n", "1012 99 Horror \n", "\n", " synopsis \\\n", "1012 In Pasadena, California in 1969, a young Mexic... \n", "\n", " synopsis_allowed_pos \\\n", "1012 young mexican couple home medium son jewelry g... \n", "\n", " keywords \\\n", "1012 button,loan,envelope,clay,assistant,cake,goat,... \n", "\n", " scores \n", "1012 0.36904204918723854,0.2306283305898838,0.22358... " ] }, "execution_count": 117, "metadata": {}, "output_type": "execute_result" } ], "source": [ "movies[movies.title=='Drag Me to Hell']" ] }, { "cell_type": "code", "execution_count": null, "id": "7a8900d3", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.8" } }, "nbformat": 4, "nbformat_minor": 5 }