rchurch4

import random as r

class Wand:
    def __init__(self, length, wood, core):
        self.length = length,
        self.wood = wood
        self.core = core
        self.person = 'Nobody'

    def set_owner(self, person):

rchurch4

from gdtm.helpers.common import load_dated_dataset, load_split_dataset, split_dataset_by_date, save_split_dataset, month

path_to_data = 'path/to/data/dated_tweets.csv'
dataset = load_dated_dataset(path=path_to_data, date_delimiter='\t', doc_delimiter=',')

# Split the data by month (there are epoch functions for day and week as well)
split_dataset = split_dataset_by_date(dataset, epoch_function=month)

# Save the split data set to make it easier to load in the future 
# This is useful if we are running multiple experiments on the same data

rchurch4

from gdtm.models import dNLDA

# Set these paths to the path where you saved the Mallet implementation of each model, plus bin/mallet
tnd_path = 'path/to/mallet-dtnd/bin/mallet'
lda_path = 'path/to/mallet-dlda/bin/mallet'

# We pass in the paths to the java code along with the data set and whatever parameters we want to set
model = dNLDA(dataset=split_dataset, mallet_tnd_path=tnd_path, mallet_lda_path=lda_path, num_time_periods=num_time_periods,
             tnd_k=30, lda_k=30, phi=10, top_words=20, save_path='results/dnlda/', run=True)

rchurch4

covid,coronavirus,pandemic,tombx7m,mask,kag2020,ccot,foxandfriends,died,wearing,deaths,positive,tcot,governor,morningjoe
americans,plan,economy,jobs,dead,leadership,republicans,ready,trumps,failed,safe,economic,future,record,yogagenie
black,police,person,racism,george,protest,play,based,realcandaceo,game,community,prison,conservatives,shot,mind
taxes,care,money,health,security,kids,social,public,healthcare,high,school,wall,government,federal,leaders
bidens,hunter,corruption,evidence,russia,rudygiuliani,report,threat,jsolomonreports,dems,trumpwarroom,russian,iran,concerned,epochtimes
lives,change,democracy,theyre,feel,court,justice,rights,matter,order,supreme,climate,care,maryltrump,human
president,states,united,harris,kamala,vice,nomination,elect,accept,normal,congratulations,peace,pence,honor,democratic
speech,rally,campaign,news,fake,antifa,massive,tomorrow,corrupt,disinformation,watching,realdonaldtrumps,likes,crying,attacking
donaldtrump,debate,lies,stop,things,racist,debates2020,remember,bettemidler,ques

rchurch4

rchurch4

rchurch4

from gdtm.helpers.common import save_topics

# Pass in the topics as they are returned from `get_topics()`, a file path, and optionally, a delimiter (the default is a comma)
save_topics(topics, 'results/topics.csv', delimiter=',')

rchurch4

rchurch4

from gdtm.models import GTM

# Set these paths to the path where you saved the Mallet implementation of each model, plus bin/mallet
tnd_path = 'path/to/mallet-tnd/bin/mallet'
gtm_path = 'path/to/mallet-gtm/bin/mallet'

seed_topics_file = 'data/seed_topics.csv'

# We pass in the paths to the java code along with the data set and whatever parameters we want to set
model = GTM(dataset=dataset, mallet_tnd_path=tnd_path, mallet_gtm_path=gtm_path, 

rchurch4

from gdtm.models import TND

# Set these paths to the path where you saved the Mallet implementation of each model, plus bin/mallet
tnd_path = 'path/to/mallet-tnd/bin/mallet'

# We pass in the paths to the java code along with the data set and whatever parameters we want to set
model = TND(dataset=dataset, mallet_path=tnd_path, k=30, beta1=16, top_words=20)

topics = model.get_topics()
noise = model.get_noise_distribution()