1 2 3 4 5 6 7 8 9 10 11 12 13 14
| from yellowbrick.text import DispersionPlot, dispersion
# Create a list of words from the corpus text
text = [df_result["id"][i] for i in range(0,201)]
text = ['alec', 'albert', 'Bella', 'Brussea', 'Chawla', 'Corradi', 'Darnell', 'david', 'Dominic', 'edith', 'Egbert', 'Felix', 'Fritz', 'Gatot', 'George', 'Gray', 'Guido', 'Hohl', 'Hugo', 'Ingemar', 'JaeYi', 'Jatin', 'Jeremy', 'JiRen', 'JoonLee', 'judy', 'Karnker', 'Kazuhiko', 'Korba', 'Kurfess', 'lily', 'Luis', 'Manheim', 'Marzul', 'Medvin', 'Mitsuru', 'Mogath', 'Moriyama74', 'Naldurg', 'Noemi', 'Norma', 'Orazio', 'Paciorek', 'Patrick', 'Peller', 'Prudence', 'Queena', 'Rebecca', 'Roger', 'Sunder', 'Shah', 'Stefan', 'Sumit', 'Tiffany', 'Tardo', 'Thomas', 'TomLee', 'Theresa', 'Vitek', 'VuAnh', 'Warsaw', 'Weissman', 'Xudong', 'Yiling', 'Yuuichi', 'Zhung', 'zzHwang', 'Addison', 'Anand', 'Antorun', 'Bishop', 'Cesare', 'Gifford', 'Cremon', 'Damianos', 'Dennis', 'Donny', 'eric', 'Emmanuel', 'Franz', 'Fuenfr', 'Gavalas', 'Ghanbar', 'Green', 'Hansoth', 'Holding', 'Hylton', 'Isidore', 'JanLee', 'jean', 'JinHong', 'Jessica', 'Jorge', 'kaiKin', 'Kristin', 'Keith', 'Kelly', 'Larry', 'Leopold', 'maggie', 'Marco', 'Masse', 'Mickun', 'Mizuno', 'Mohamme', 'Moura', 'Neeran', 'Nicola', 'Okamoto', 'Oshima', 'Pagurek', 'Pedersen', 'Prasad', 'Question', 'Rahul', 'Richaard', 'Rossum', 'Saurab', 'Silva', 'Stockton', 'Susilo', 'Takashi', 'Tatsuaki', 'TinQian', 'Tomoya', 'Valente', 'Vogler', 'Walsh', 'Watanabe', 'William', 'Xaviera', 'Yvonne', 'Zhaoyu', 'ZingCG', 'Adam', 'Andrzej', 'barry', 'Boebert', 'Chaum', 'colin', 'Cybenko', 'Daniela', 'Dhaval', 'EA95611', 'Ebank', 'eyeQuR', 'freddy', 'Gabriel', 'Gennady', 'Gleeson', 'Guan', 'Hartmut', 'Holger', 'Itabashi', 'Isabel', 'jane', 'Jepsen', 'Jimyuan', 'Johan', 'Joseph', 'Kare', 'Katsuya', 'Ken', 'Kunkel', 'Lauvset', 'Louise', 'Mahony', 'Marques', 'Matasz', 'Mike', 'Mladen', 'Montan', 'Myeong', 'Neumann', 'Nydia', 'Oliver', 'OREO', 'Paolo', 'Peine', 'Pulia', 'Quintina', 'Renee', 'Robat', 'Roberta', 'Seung', 'Someya', 'Suzanne', 'Tadanori', 'Taococ', 'Theoph', 'Tomar', 'Torben', 'Valerie', 'Vouk', 'Winifred', 'WCZexe', 'WongMS', 'YangGH', 'Yutaka', 'ChZero', 'Zyang']
target_words = ['MTV','3377','dell','qAzX','slsl','popsecu']
target_words = ['MTV','3377','dell','qAzX','slsl','popsecu']
# Create the visualizer and draw the plot
dispersion(target_words, text, colors=['olive']) |