# -*- coding: utf-8 -*-
"""
Created on Thu Aug 15 22:13:12 2013
@author: Vasya
"""
import marginal_topics_distr as marg
agg = marg.compute_and_save('unbranded220topics',
r'Z:\ermunds\results\1 all 100 topics')
agg2002 = marg.compute_and_save('2002 20topics',
r'Z:\ermunds\results\2002 20topics')
agg2005 = marg.compute_and_save('2005 20topics',
r'Z:\ermunds\results\2005 20topics')
agg2009 = marg.compute_and_save('2009 20topics',
r'Z:\ermunds\results\2009 20topics')
agg2010 = marg.compute_and_save('2010 20topics',
r'Z:\ermunds\results\2010 20topics')
agg2011 = marg.compute_and_save('2011 20topics',
r'Z:\ermunds\results\2011 20topics')
agg2012 = marg.compute_and_save('2012 20topics',
r'Z:\ermunds\results\2012 20topics')
words = 'Arrogant Authentic Charming Daring Different Distinctive Dynamic Friendly Fun Healthy Helpful Independent Innovative Intelligent Kind Leader Obliging Original Prestigious Progressive Reliable Restrained Rugged Simple Social Stylish Traditional Trendy Trustworthy Unique'.split()
import numpy as np
import os
import getLikes
import pandas as pd
import genSimLDAlib as gslib
import marginal_topics_distr as marginal
for year in range(2002,2013):
print year
modelDir = 'Z:\\ermunds\\results\\%d 20topics'%year
modelName = '%d 20topics' %year
marginal.compute_and_save(modelName=modelName, LDAdir=modelDir)
topicsPs = np.genfromtxt(os.path.join(modelDir,'topics_marginal.csv'))
(divs,_,_) = getLikes.get_divs (words,brands,indir=modelDir, modelName=modelName ,topics_marginal_probs=topicsPs)
(sims,b,w) = getLikes.get_likes(words,brands,indir=modelDir, modelName=modelName )
dirs = gslib.LDAdirs(modelName,modelDir)
(dict1,_,lda)=gslib.loadStuff(dirs)
brands_df = getLikes.pruneWordsList(brands,lda)
words_df = getLikes.pruneWordsList(words,lda)
probs = getLikes.ptopic_given_word(lda,topicsPs)
probs_df = pd.DataFrame(probs, columns=lda.id2word.values())
alls = pd.concat([ brands_df["IDs"] ,words_df["IDs"]])
x = probs_df[alls]
# -*- coding: utf-8 -*-
"""
Created on Thu Aug 15 22:13:12 2013
@author: Vasya
"""
import marginal_topics_distr as marg
agg = marg.compute_and_save('unbranded220topics', r'Z:\ermunds\results\1 all 100 topics')
agg2002 = marg.compute_and_save('2002 20topics',r'Z:\ermunds\results\2002 20topics')
agg2005 = marg.compute_and_save('2005 20topics',r'Z:\ermunds\results\2005 20topics')
agg2009 = marg.compute_and_save('2009 20topics',r'Z:\ermunds\results\2009 20topics')
agg2010 = marg.compute_and_save('2010 20topics',r'Z:\ermunds\results\2010 20topics')
agg2011 = marg.compute_and_save('2011 20topics',r'Z:\ermunds\results\2011 20topics')
agg2012 = marg.compute_and_save('2012 20topics',r'Z:\ermunds\results\2012 20topics')
words = 'Arrogant Authentic Charming Daring Different Distinctive Dynamic Friendly Fun Healthy Helpful Independent Innovative Intelligent Kind Leader Obliging Original Prestigious Progressive Reliable Restrained Rugged Simple Social Stylish Traditional Trendy Trustworthy Unique'.split(
)
import numpy as np
import os
import getLikes
import pandas as pd
import genSimLDAlib as gslib
import marginal_topics_distr as marginal
for year in range(2002, 2013):
print year
modelDir = 'Z:\\ermunds\\results\\%d 20topics' % year
modelName = '%d 20topics' % year
marginal.compute_and_save(modelName=modelName, LDAdir=modelDir)
topicsPs = np.genfromtxt(os.path.join(modelDir, 'topics_marginal.csv'))
(divs, _, _) = getLikes.get_divs(words,
brands,
indir=modelDir,
modelName=modelName,
topics_marginal_probs=topicsPs)
(sims, b, w) = getLikes.get_likes(words,
brands,
indir=modelDir,
modelName=modelName)
dirs = gslib.LDAdirs(modelName, modelDir)
(dict1, _, lda) = gslib.loadStuff(dirs)
