scattertext
0.0.2.4.4
Uma ferramenta para encontrar termos distintivos no Corpora e exibi -los em um gráfico interativo de dispersão HTML. Os pontos correspondentes aos termos são rotulados seletivamente para que não se sobreponham com outros rótulos ou pontos.
Cite como: Jason S. Kessler. ScatterText: Uma ferramenta baseada em navegador para visualizar como os corpora diferem. Demonstrações do sistema ACL. 2017.
Abaixo está um exemplo de uso do ScatterText para criar termos visualizados usados nas convenções políticas americanas de 2012. Os 2.000 gramações uni associados a festas são exibidos como pontos no gráfico de dispersão. Seus eixos X e Y são as densas fileiras de seu uso dos falantes republicanos e democratas, respectivamente.
import scattertext as st
df = st.SampleCorpora.ConventionData2012.get_data().assign(
parse=lambda df: df.text.apply(st.whitespace_nlp_with_sentences)
)
corpus = st.CorpusFromParsedDocuments(
df, category_col='party', parsed_col='parse'
).build().get_unigram_corpus().compact(st.AssociationCompactor(2000))
html = st.produce_scattertext_explorer(
corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
metadata=corpus.get_df()['speaker'],
transform=st.Scalers.dense_rank,
include_gradient=True,
left_gradient_term='More Republican',
middle_gradient_term='Metric: Dense Rank Difference',
right_gradient_term='More Democratic',
)
open('./demo_compact.html', 'w').write(html)
O arquivo html escrito se pareceria com a imagem abaixo. Clique nele para a visualização interativa real.
Jason S. Kessler. ScatterText: Uma ferramenta baseada em navegador para visualizar como os corpora diferem. Demonstrações do sistema ACL. 2017. Link para o artigo: arxiv.org/abs/1703.00565
@article{kessler2017scattertext,
author = {Kessler, Jason S.},
title = {Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ},
booktitle = {Proceedings of ACL-2017 System Demonstrations},
year = {2017},
address = {Vancouver, Canada},
publisher = {Association for Computational Linguistics},
}
Índice
Instalação
Visão geral
Personalizando a visualização e a plotagem de dispersão
Tutorial
Entendendo a escala F-score
Métodos de pontuação de termos alternativos
O processo de seleção de posição
Usos avançados
Exemplos
Uma nota no layout do gráfico
O que há de novo
Fontes
Instale o Python 3.11 ou superior e execute:
$ pip install scattertext
Se você não puder (ou não quiser) instalar linhas Spacy, substitua nlp = spacy.load('en') com nlp = scattertext.WhitespaceNLP.whitespace_nlp . Observe que isso não é compatível com word_similarity_explorer , e os recursos de detecção de limite de tokenização e frase serão expressões regulares de baixo desempenho. Consulte demo_without_spacy.py para um exemplo.
Recomenda-se que você instale jieba , spacy , empath , astropy , flashtext , gensim e umap-learn a fim de aproveitar ao máximo o ScatterText.
O ScatterText deve funcionar principalmente com o Python 2.7, mas pode não.
As saídas HTML parecem melhores no Chrome e Safari.
O nome deste projeto é o ScatterText. "ScatterText" é escrito como uma única palavra e deve ser capitalizado. Quando usado no Python, o pacote scattertext deve ser definido como o nome st , ou seja, import scattertext as st .
Esta é uma ferramenta destinada a visualizar quais palavras e frases são mais características de uma categoria do que outras.
Considere o exemplo na parte superior da página.
Olhando para isso parece esmagador. De fato, é uma visualização relativamente simples do uso de palavras durante a Convenção Política de 2012. Cada ponto corresponde a uma palavra ou frase mencionada por republicanos ou democratas durante suas convenções. Quanto mais próximo um ponto é do topo da trama, mais frequentemente era usado pelos democratas. Quanto mais à direita um ponto, mais essa palavra ou frase era usada pelos republicanos. Palavras freqüentemente usadas por ambas as partes, como "de" e "The" e até "Mitt" tendem a ocorrer no canto superior direito. Embora as palavras de frequência muito baixa tenham sido ocultas para preservar os recursos de computação, uma palavra que nenhuma das partes usou, como "girafa", estaria no canto inferior esquerdo.
As coisas interessantes acontecem perto dos cantos superior esquerdo e inferior à direita. No canto superior esquerdo, palavras como "Auto" (como em resgate de automóveis) e "milionários" são freqüentemente usados pelos democratas, mas com pouca frequência ou nunca usados pelos republicanos. Da mesma forma, os termos freqüentemente usados pelos republicanos e raramente pelos democratas ocupam o canto inferior direito. Isso inclui "grande governo" e "Olimpíadas", referindo -se às Olimpíadas de Salt Lake City, nas quais o governador Romney estava envolvido.
Os termos são coloridos por sua associação. Aqueles que estão mais associados aos democratas são azuis e os mais associados aos republicanos vermelhos.
Os termos mais característicos dos dois conjuntos de documentos são exibidos na extrema direita da visualização.
A inspiração para essa visualização veio do Dataclysm (Rudder, 2014).
O ScatterText foi projetado para ajudá -lo a criar esses gráficos e rotular com eficiência pontos neles.
A documentação (incluindo este readme) é um trabalho em andamento. Consulte o tutorial abaixo, bem como o tutorial do Pydata 2017.
A ritmo do código e dos testes deve dar uma boa idéia de como as coisas funcionam.
A biblioteca abrange algumas fórmulas novas e eficazes de importância a termos, incluindo a escala F-Score .
Novo no ScatterText 0.1.0, pode-se usar um quadro de dados para posições de termo/metadados e outros dados específicos do termo. Também podemos usá-lo para determinar informações específicas a termos que são mostradas após o clicado de um termo.
Observe que é possível desativar o uso de categorias de documentos no ScatterText, como veremos neste exemplo.
Este exemplo abrange a plotagem de dispersão do termo contra a frequência de palavras e a identificação dos termos que são mais e menos dispersos, dadas suas frequências. Usando a medida de dispersão de Rosengren (GRIES 2021), os termos tendem a aumentar em suas pontuações de dispersão à medida que ficam mais frequentes. Veremos como podemos plotar esse efeito e considerar o efeito da frequência.
Isso, juntamente com várias outras métricas de dispersão apresentadas em Gries (2021), estão disponíveis e documentadas na classe Dispersion , que usaremos mais adiante na seção.
Vamos começar criando um corpus de convenção, mas usaremos as CorpusWithoutCategoriesFromParsedDocuments da fábrica de documentos para garantir que nenhuma categoria seja incluída no corpus. Se tentarmos encontrar categorias de documentos, veremos que todos os documentos tenham a categoria '_'.
import scattertext as st
df = st . SampleCorpora . ConventionData2012 . get_data (). assign (
parse = lambda df : df . text . apply ( st . whitespace_nlp_with_sentences ))
corpus = st . CorpusWithoutCategoriesFromParsedDocuments (
df , parsed_col = 'parse'
). build (). get_unigram_corpus (). remove_infrequent_words ( minimum_term_count = 6 )
corpus . get_categories ()
# Returns ['_']Em seguida, criaremos um quadro de dados para todos os termos que planejaremos. Começaremos criando um quadro de dados onde capturamos a frequência de cada termo e várias métricas de dispersão. Estes serão mostrados após a ativação de um termo no gráfico.
dispersion = st . Dispersion ( corpus )
dispersion_df = dispersion . get_df ()
dispersion_df . head ( 3 )Que retorna
Frequency Range SD VC Juilland's D Rosengren's S DP DP norm KL-divergence Dissemination
thank 363 134 3.108113 1.618274 0.707416 0.694898 0.391548 0.391560 0.748808 0.972954
you 1630 177 12.383708 1.435902 0.888596 0.898805 0.233627 0.233635 0.263337 0.963905
so 549 155 3.523380 1.212967 0.774299 0.822244 0.283151 0.283160 0.411750 0.986423```
These are discussed in detail in [Gries 2021](http://www.stgries.info/research/ToApp_STG_Dispersion_PHCL.pdf).
Dissementation is presented in Altmann et al. (2011).
We'll use Rosengren's S to find the dispersion of each term. It's which a metric designed for corpus parts
(convention speeches in our case) of varying length. Where n is the number of documents in the corpus, s_i is the
percentage of tokens in the corpus found in document i, v_i is term count in document i, and f is the total number
of tokens in the corpus of type term type.
Rosengren's
S: [^2}{f})](https://render.githubusercontent.com/render/math?math=frac{Sum_{i=1}^{n}sqrt{s_i%20cdot%20v_i})
^2}{f})
In order to start plotting, we'll need to add coordinates for each term to the data frame.
To use the `dataframe_scattertext` function, you need, at a minimum a dataframe with 'X' and 'Y' columns.
The `Xpos` and `Ypos` columns indicate the positions of the original `X` and `Y` values on the scatterplot, and
need to be between 0 and 1. Functions in `st.Scalers` perform this scaling. Absent `Xpos` or `Ypos`,
`st.Scalers.scale` would be used.
Here is a sample of values:
* `st.Scalers.scale(vec)` Rescales the vector to where the minimum value is 0 and the maximum is 1.
* `st.Scalers.log_scale(vec)` Rescales the lgo of the vector
* `st.Scalers.dense_ranke(vec)` Rescales the dense rank of the vector
* `st.Scalers.scale_center_zero_abs(vec)` Rescales a vector with both positive and negative values such that the 0 value
in the original vector is plotted at 0.5, negative values are projected from [-argmax(abs(vec)), 0] to [0, 0.5] and
positive values projected from [0, argmax(abs(vec))] to [0.5, 1].
```python
dispersion_df = dispersion_df.assign(
X=lambda df: df.Frequency,
Xpos=lambda df: st.Scalers.log_scale(df.X),
Y=lambda df: df["Rosengren's S"],
Ypos=lambda df: st.Scalers.scale(df.Y),
)
Observe que a coluna Ypos aqui não é necessária, pois Y seria automaticamente escalonada.
Finalmente, como não estamos distinguindo entre as categorias, podemos definir ignore_categories=True .
Agora podemos plotar este gráfico usando a função dataframe_scattertext :
html = st . dataframe_scattertext (
corpus ,
plot_df = dispersion_df ,
metadata = corpus . get_df ()[ 'speaker' ] + ' (' + corpus . get_df ()[ 'party' ]. str . upper () + ')' ,
ignore_categories = True ,
x_label = 'Log Frequency' ,
y_label = "Rosengren's S" ,
y_axis_labels = [ 'Less Dispersion' , 'Medium' , 'More Dispersion' ],
)Que produz (clique para uma versão interativa):
Observe que podemos ver várias estatísticas de dispersão sob o nome de um termo, além das estatísticas de uso padrão. Para personalizar as estatísticas exibidas, defina o parâmetro term_description_column=[...] com uma lista de nomes de colunas a serem exibidos.
Uma questão neste gráfico de dispersão, que tende a ser comum às métricas de dispersão em geral, é que a dispersão e a frequência tendem a ter uma alta correlação, mas com uma curva complexa e não linear. Dependendo da métrica, essa curva de correlação pode ser poder, linear, sigmoidal ou normalmente, outra coisa.
Para levar em consideração essa correlação, podemos prever a dispersão da frequência usando um regressor não paramétrico e ver quais termos têm os resíduos mais altos e mais baixos em relação às suas dispersões esperadas com base em suas frequências.
Nesse caso, usaremos um regressor do KNN com 10 vizinhos para prever Rosengren a partir de frequências de termo ( dispersion_df.X e .Y respectivamente) e calculamos o resíduo.
Vamos os pontos residuais para colorir, com uma cor neutra para resíduos em torno de 0 e outras cores para valores positivos e negativos. Adicionaremos uma coluna no quadro de dados para cores de ponto e chamamos de cores de cores. É preenchido com valores entre 0 e 1, com 0,5 como uma cor netural na escala de cor d3 interpolateWarm . Usamos st.Scalers.scale_center_zero_abs , discutidos acima, para fazer essa transformação.
from sklearn . neighbors import KNeighborsRegressor
dispersion_df = dispersion_df . assign (
Expected = lambda df : KNeighborsRegressor ( n_neighbors = 10 ). fit (
df . X . values . reshape ( - 1 , 1 ), df . Y
). predict ( df . X . values . reshape ( - 1 , 1 )),
Residual = lambda df : df . Y - df . Expected ,
ColorScore = lambda df : st . Scalers . scale_center_zero_abs ( df . Residual )
) Agora estamos prontos para plotar nosso gráfico de dispersão colorida. Atribuímos o nome da coluna Colorcore ao parâmetro color_score_column no dataframe_scattertext .
Além disso, gostaríamos de preencher as listas de dois termos à esquerda, com termos que possuem valores residuais altos e baixos, indicando termos que têm mais dispersão em relação ao seu nível de frequência e o mais baixo. Podemos fazer isso pelo parâmetro left_list_column . Podemos especificar os nomes da lista de termos superiores e inferiores usando o parâmetro header_names . Finalmente, podemos espalhar o enredo adicionando uma cor de fundo atraente.
html = st . dataframe_scattertext (
corpus ,
plot_df = dispersion_df ,
metadata = corpus . get_df ()[ 'speaker' ] + ' (' + corpus . get_df ()[ 'party' ]. str . upper () + ')' ,
ignore_categories = True ,
x_label = 'Log Frequency' ,
y_label = "Rosengren's S" ,
y_axis_labels = [ 'Less Dispersion' , 'Medium' , 'More Dispersion' ],
color_score_column = 'ColorScore' ,
header_names = { 'upper' : 'Lower than Expected' , 'lower' : 'More than Expected' },
left_list_column = 'Residual' ,
background_color = '#e5e5e3'
)Que produz (clique para uma versão interativa):
Embora você deva aprender Python usar totalmente o ScatterText, coloquei parte da funcionalidade básica em uma ferramenta de comando. A ferramenta é instalada quando você segue o procedimento estabelecido acima.
Execute $ scattertext --help da linha de comando para ver as informações completas de uso. Aqui está um exemplo rápido de como usar o Vanilla ScatterText em um arquivo CSV. O arquivo precisa ter pelo menos duas colunas, uma contendo o texto a ser analisado e outra contendo a categoria. No exemplo CSV abaixo, as colunas são texto e parte, respectivamente.
O exemplo abaixo processa o arquivo CSV e a visualização HTML resultante no cli_demo.html.
Observe que o parâmetro --minimum_term_frequency=8 termos omitis que ocorrem menos de 8 vezes e --regex_parser Indica que um analisador de expressão regular simples deve ser usado no lugar de spacy. O sinalizador --one_use_per_doc indica que a frequência do termo deve ser calculada apenas contando não mais de uma ocorrência de um termo em um documento.
Se você deseja analisar o texto não inglês, pode usar o argumento --spacy_language_model para configurar qual modelo de linguagem spacy a ferramenta usará. O padrão é 'en' e você pode ver os outros disponíveis em https://spacy.io/docs/api/language-models.
$ curl -s https://cdn.rawgit.com/JasonKessler/scattertext/master/scattertext/data/political_data.csv | head -2
party,speaker,text
democrat,BARACK OBAMA, " Thank you. Thank you. Thank you. Thank you so much.Thank you.Thank you so much. Thank you. Thank you very much, everybody. Thank you.
$
$ scattertext --datafile=https://cdn.rawgit.com/JasonKessler/scattertext/master/scattertext/data/political_data.csv
> --text_column=text --category_column=party --metadata_column=speaker --positive_category=democrat
> --category_display_name=Democratic --not_category_display_name=Republican --minimum_term_frequency=8
> --one_use_per_doc --regex_parser --outputfile=cli_demo.htmlO código a seguir cria um arquivo HTML independente que analisa palavras usadas por democratas e republicanos nas convenções do partido de 2012 e produz algumas associações notáveis de termos.
Primeiro, importe o ScatterText e Spacy.
>>> import scattertext as st
>>> import spacy
>>> from pprint import pprint
Em seguida, monte os dados que você deseja analisar em um quadro de dados de pandas. Deveria ter pelo menos duas colunas, o texto que você gostaria de analisar e a categoria que você gostaria de estudar. Aqui, a coluna text contém discursos de convenções enquanto a coluna party contém a parte do orador. Eventualmente, usaremos a coluna speaker para rotular trechos na visualização.
>>> convention_df = st.SampleCorpora.ConventionData2012.get_data()
>>> convention_df.iloc[0]
party democrat
speaker BARACK OBAMA
text Thank you. Thank you. Thank you. Thank you so ...
Name: 0, dtype: object
Transforme o quadro de dados em um corpus ScatterText para começar a analisá -lo. Para procurar diferenças nas partes, defina o parâmetro category_col como 'party' e use os discursos, presente na coluna text , como os textos a serem analisados, definindo o parâmetro text Col. Finalmente, passe um modelo de spacy no argumento nlp e chama build() para construir o corpus.
# Turn it into a Scattertext Corpus
>>> nlp = spacy.load('en')
>>> corpus = st.CorpusFromPandas(convention_df,
... category_col='party',
... text_col='text',
... nlp=nlp).build()
Vamos ver termos característicos no corpus e termos que são democratas e republicanos mais associados. Consulte os slides 52 a 59 do conteúdo não estruturado que os núcleos de idéias falam para mais detalhes sobre essas abordagens.
Aqui estão os termos que diferenciam o corpus de um corpus geral em inglês.
>>> print(list(corpus.get_scaled_f_scores_vs_background().index[:10]))
['obama',
'romney',
'barack',
'mitt',
'obamacare',
'biden',
'romneys',
'hardworking',
'bailouts',
'autoworkers']
Aqui estão os termos mais associados aos democratas:
>>> term_freq_df = corpus.get_term_freq_df()
>>> term_freq_df['Democratic Score'] = corpus.get_scaled_f_scores('democrat')
>>> pprint(list(term_freq_df.sort_values(by='Democratic Score', ascending=False).index[:10]))
['auto',
'america forward',
'auto industry',
'insurance companies',
'pell',
'last week',
'pell grants',
"women 's",
'platform',
'millionaires']
E republicanos:
>>> term_freq_df['Republican Score'] = corpus.get_scaled_f_scores('republican')
>>> pprint(list(term_freq_df.sort_values(by='Republican Score', ascending=False).index[:10]))
['big government',
"n't build",
'mitt was',
'the constitution',
'he wanted',
'hands that',
'of mitt',
'16 trillion',
'turned around',
'in florida']
Agora, vamos escrever o gráfico de dispersão um arquivo HTML independente. Vamos fazer a categoria do eixo Y "democrata" e nomearemos a categoria "democrata" com um capital "d" para fins de apresentação. Nomearemos a outra categoria "republicana" com um capital "r". Todos os documentos no corpus sem a categoria "democrata" serão considerados republicanos. Definimos a largura da visualização em pixels e rotulamos cada trecho com o alto -falante usando o parâmetro metadata . Finalmente, escrevemos a visualização em um arquivo HTML.
>>> html = st.produce_scattertext_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... width_in_pixels=1000,
... metadata=convention_df['speaker'])
>>> open("Convention-Visualization.html", 'wb').write(html.encode('utf-8'))
Abaixo está como é a página da web. Clique nele e aguarde alguns minutos para a versão interativa.
O ScatterText também pode ser usado para visualizar a associação de categoria de uma variedade de diferentes tipos de frase. A palavra "frase" indica qualquer colocação única ou de várias palavras.
O PytexTrank, criado por Paco Nathan, é uma implementação de uma versão modificada do algoritmo TexTrank (Mihalcea e Tarau 2004). Envolve o algoritmo de centralidade do gráfico para extrair uma lista pontuada das frases mais proeminentes em um documento. Aqui, nomeadas entidades reconhecidas por Spacy. A partir da versão 2.2 Spacy, eles são de um sistema NER treinado no Ontontotes 5.
Instale o PytexTrank $ pip3 install pytextrank antes de continuar com este tutorial.
Para usar, construa um corpus normalmente, mas use o Spacy para analisar cada documento em oposição a um tokenizador de whitespace_nlp -Type embutido. Observe que a adição de pytextrank ao oleoduto Spacy não é necessária, pois será executada separadamente pelo objeto PyTextRankPhrases . Reduziremos o número de frases exibidas no gráfico para 2000 usando o AssociationCompactor . As frases geradas serão tratadas como recursos não textuais, pois as pontuações de seus documentos não corresponderão à contagem de palavras.
import pytextrank, spacy
import scattertext as st
nlp = spacy.load('en')
nlp.add_pipe("textrank", last=True)
convention_df = st.SampleCorpora.ConventionData2012.get_data().assign(
parse=lambda df: df.text.apply(nlp),
party=lambda df: df.party.apply({'democrat': 'Democratic', 'republican': 'Republican'}.get)
)
corpus = st.CorpusFromParsedDocuments(
convention_df,
category_col='party',
parsed_col='parse',
feats_from_spacy_doc=st.PyTextRankPhrases()
).build(
).compact(
AssociationCompactor(2000, use_non_text_features=True)
)
Observe que os termos presentes no corpus são denominados entidades e, em oposição às contagens de frequência, suas pontuações são as pontuações da auto -centralidade atribuídas a eles pelo algoritmo Textrank. A execução corpus.get_metadata_freq_df('') retornará, para cada categoria, as somas dos termos 'TexTrank Scores. As fileiras densas dessas pontuações serão usadas para construir o gráfico de dispersão.
term_category_scores = corpus.get_metadata_freq_df('')
print(term_category_scores)
'''
Democratic Republican
term
our future 1.113434 0.699103
your country 0.314057 0.000000
their home 0.385925 0.000000
our government 0.185483 0.462122
our workers 0.199704 0.210989
her family 0.540887 0.405552
our time 0.510930 0.410058
...
'''
Antes de construirmos o enredo, vamos algumas variáveis auxiliares, pois as pontuações agregadas do TexTrank não são particularmente interpretáveis, exibiremos a classificação por categoria de cada pontuação no campo metadata_description . Estes serão exibidos após o clicado de um termo.
term_ranks = pd.DataFrame(
np.argsort(np.argsort(-term_category_scores, axis=0), axis=0) + 1,
columns=term_category_scores.columns,
index=term_category_scores.index)
metadata_descriptions = {
term: '<br/>' + '<br/>'.join(
'<b>%s</b> TextRank score rank: %s/%s' % (cat, term_ranks.loc[term, cat], corpus.get_num_metadata())
for cat in corpus.get_categories())
for term in corpus.get_metadata()
}
Podemos construir pontuações de termos de algumas maneiras. Uma é uma diferença padrão de rank densa, uma pontuação usada na maioria das parcelas contrastantes de duas categorias aqui, que nos dará as frases mais associadas à categoria. Outra é usar a pontuação máxima específica da categoria, isso nos dará as frases mais proeminentes em cada categoria, independentemente do destaque na outra categoria. Vamos adotar as duas abordagens neste tutorial, vamos calcular o segundo tipo de pontuação, o destaque específico da categoria abaixo.
category_specific_prominence = term_category_scores.apply(
lambda r: r.Democratic if r.Democratic > r.Republican else -r.Republican,
axis=1
)
Agora estamos prontos para produzir este gráfico. Observe que usamos uma transformada dense_rank , que coloca frases de forma idêntica no topo do outro. Utilizamos category_specific_prominence como pontuações e definimos sort_by_dist como False para garantir que as frases exibidas no lado direito do gráfico sejam classificadas pelas pontuações e não a distância dos cantos superior esquerdo ou inferior à direita. Como as frases correspondentes são tratadas como recursos que não são de texto, os codificamos como modelos de tópicos de frase única e definimos o topic_model_preview_size como 0 para indicar a lista de modelos de tópicos não deve ser mostrada. Por fim, definimos garantir que os documentos completos sejam exibidos. Nota Os documentos serão exibidos em ordem de pontuação específica da frase.
html = produce_scattertext_explorer(
corpus,
category='Democratic',
not_category_name='Republican',
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
transform=dense_rank,
metadata=corpus.get_df()['speaker'],
scores=category_specific_prominence,
sort_by_dist=False,
use_non_text_features=True,
topic_model_term_lists={term: [term] for term in corpus.get_metadata()},
topic_model_preview_size=0,
metadata_descriptions=metadata_descriptions,
use_full_doc=True
)
Os termos mais associados em cada categoria fazem algum sentido, pelo menos em uma análise post hoc. Ao se referir ao (então) governador Romney, os democratas usaram seu sobrenome "Romney" em suas menções mais centrais a ele, enquanto os republicanos usavam o "Mitt" mais familiar e humanizador. Em termos do presidente Obama, a frase "Obama" não apareceu como um dos principais mandatos, mas o primeiro nome "Barack" foi uma das frases mais centrais dos discursos democráticos, espelhando "Mitt".
Como alternativa, podemos densidade de diferença de classificação nas pontuações para os pontos de frases coloridas e determinar as frases superiores a serem exibidas no lado direito do gráfico. Em vez de definir scores como pontuações de destaque específicas da categoria, definimos term_scorer=RankDifference() para injetar uma maneira de determinar as pontuações do termo no processo de criação da plotagem de dispersão.
html = produce_scattertext_explorer(
corpus,
category='Democratic',
not_category_name='Republican',
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
transform=dense_rank,
use_non_text_features=True,
metadata=corpus.get_df()['speaker'],
term_scorer=RankDifference(),
sort_by_dist=False,
topic_model_term_lists={term: [term] for term in corpus.get_metadata()},
topic_model_preview_size=0,
metadata_descriptions=metadata_descriptions,
use_full_doc=True
)
Phrasemachine de Abehandler (Handler et al. 2016) usa expressões regulares sobre sequências de tags de parte da fala para identificar frases substantivas. Isso tem a vantagem de usar o NP-Chunking de Spacy, pois tende a isolar fases de substantivo significativas e grandes, livres de aprimoramentos.
Em oposição ao PytexTrank, usaremos a contagem dessas frases, tratando -as como qualquer outro termo.
import spacy
from scattertext import SampleCorpora, PhraseMachinePhrases, dense_rank, RankDifference, AssociationCompactor, produce_scattertext_explorer
from scattertext.CorpusFromPandas import CorpusFromPandas
corpus = (CorpusFromPandas(SampleCorpora.ConventionData2012.get_data(),
category_col='party',
text_col='text',
feats_from_spacy_doc=PhraseMachinePhrases(),
nlp=spacy.load('en', parser=False))
.build().compact(AssociationCompactor(4000)))
html = produce_scattertext_explorer(corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
transform=dense_rank,
metadata=corpus.get_df()['speaker'],
term_scorer=RankDifference(),
width_in_pixels=1000)
No ScatterText, várias métricas, incluindo associações de termos, geralmente são mostradas de duas maneiras. O primeiro e mais importante é a posição no gráfico. O segundo é a cor de um ponto ou texto. No ScatterText 0.2.21, é introduzida uma maneira de visualizar a semântica dessas pontuações: o gradiente como chave.
O gradiente, por padrão, segue o parâmetro d3_color_scale DE produce_scattertext_explorer , que é d3.interpolateRdYlBu por padrão.
Os seguintes parâmetros adicionais para produce_scattertext_explorer (e funções semelhantes) permitem os gradientes de manipulação.
include_gradient: bool ( False por padrão) é um sinalizador que aciona a aparência de um gradiente.left_gradient_term: Optional[str] indica o texto escrito no lado da extrema esquerda do gradiente. Está escrito em gradient_text_color e é category_name por padrão.right_gradient_term: Optional[str] indica o texto escrito no lado da esquerda do gradiente. Está escrito em gradient_text_color e not_category_name por padrão.middle_gradient_term: Optional[str] indica o texto escrito no meio do gradiente. É a cor oposta da cor do gradiente central e está vazia por padrão.gradient_text_color: Optional[str] indica a cor fixa do texto escrito no gradiente. Se não for, isso padrão é a cor oposta do gradiente.left_text_color: Optional[str] substitui gradient_text_color para o termo de gradiente esquerdomiddle_text_color: Optional[str] substitui gradient_text_color para o termo gradiente médioright_text_color: Optional[str] substitui gradient_text_color para o termo de gradiente certogradient_colors: Optional[List[str]] Lista de cores hexadecimal, incluindo '#', (por exemplo, ['#0000ff', '#980067', '#cc3300', '#32cd00'] ) que descreve o gradiente. Se for dado, estes substituem d3_color_scale . Um exemplo direto é o seguinte. As cores do termo são definidas como um mapeamento entre um nome de termo e uma cor #RRGGBB como parte do parâmetro term_color , e o gradiente de cores é definido em gradient_colors . O
import matplotlib . pyplot as plt
import matplotlib as mpl
df = st . SampleCorpora . ConventionData2012 . get_data (). assign (
parse = lambda df : df . text . apply ( st . whitespace_nlp_with_sentences )
)
corpus = st . CorpusFromParsedDocuments (
df , category_col = 'party' , parsed_col = 'parse'
). build (). get_unigram_corpus (). compact ( st . AssociationCompactor ( 2000 ))
html = st . produce_scattertext_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
minimum_term_frequency = 0 ,
pmi_threshold_coefficient = 0 ,
width_in_pixels = 1000 ,
metadata = corpus . get_df ()[ 'speaker' ],
transform = st . Scalers . dense_rank ,
include_gradient = True ,
left_gradient_term = "More Democratic" ,
right_gradient_term = "More Republican" ,
middle_gradient_term = 'Metric: Dense Rank Difference' ,
gradient_text_color = "white" ,
term_colors = dict ( zip (
corpus . get_terms (),
[
mpl . colors . to_hex ( x ) for x in plt . get_cmap ( 'brg' )(
st . Scalers . scale_center_zero_abs (
st . RankDifferenceScorer ( corpus ). set_categories ( 'democrat' ). get_scores ()). values
)
]
)),
gradient_colors = [ mpl . colors . to_hex ( x ) for x in plt . get_cmap ( 'brg' )( np . arange ( 1. , 0. , - 0.01 ))],
) Para visualizar tópicos e categorias Empath (Fast et al., 2016), em vez de termos, precisaremos criar um Corpus de tópicos e categorias extraídas, em vez de unigramas e bigrams. Para fazer isso, use o extrator de recurso FeatsOnlyFromEmpath . Veja o código -fonte para obter exemplos de como fazer o seu próprio.
Ao criar a visualização, passe o use_non_text_features=True em produce_scattertext_explorer . Isso o instruirá a usar os tópicos e categorias de empata rotulados, em vez de procurar termos. Como os documentos retornados quando um tópico ou rótulo de categoria for clicado estará em ordem da força da associação de categoria no nível do documento, definir use_full_doc=True faz sentido, a menos que você tenha documentos enormes. Caso contrário, os primeiros 300 caracteres serão mostrados.
(Novo em 0.0.26). Certifique -se de incluir topic_model_term_lists=feat_builder.get_top_model_term_lists() em produce_scattertext_explorer para garantir que ele ousado as passagens de trechos que correspondam ao modelo de tópico.
>>> feat_builder = st.FeatsFromOnlyEmpath()
>>> empath_corpus = st.CorpusFromParsedDocuments(convention_df,
... category_col='party',
... feats_from_spacy_doc=feat_builder,
... parsed_col='text').build()
>>> html = st.produce_scattertext_explorer(empath_corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... width_in_pixels=1000,
... metadata=convention_df['speaker'],
... use_non_text_features=True,
... use_full_doc=True,
... topic_model_term_lists=feat_builder.get_top_model_term_lists())
>>> open("Convention-Visualization-Empath.html", 'wb').write(html.encode('utf-8'))
C ScatterText também inclui um construtor de recursos para explorar o relacionamento entre as categorias de categoires de Tag Geral Inquirer e documentos. Usaremos uma abordagem ligeiramente diferente, analisando o relacionamento das categorias de tags GI com os partidos políticos usando os escores Z da Ratio Log-odds com os Priors Dirichlet não informativos (Monroe 2008). Usaremos a variação do gráfico produce_frequency_explorer para visualizar esse relacionamento, definindo o eixo x como o número de vezes uma palavra na categoria de tags e o eixo y como o z-score.
Para obter mais informações sobre o Inquérito Geral, consulte a página inicial do Geral Inquirer.
Usaremos o mesmo conjunto de dados de antes, exceto que usaremos os FeatsFromGeneralInquirer Feature Builder.
>>> general_inquirer_feature_builder = st.FeatsFromGeneralInquirer()
>>> corpus = st.CorpusFromPandas(convention_df,
... category_col='party',
... text_col='text',
... nlp=st.whitespace_nlp_with_sentences,
... feats_from_spacy_doc=general_inquirer_feature_builder).build()
Em seguida, chamaremos de produce_frequency_explorer de uma maneira semelhante que chamamos de produce_scattertext_explorer na seção anterior. Existem algumas diferenças, no entanto. Primeiro, especificamos o marcador LogOddsRatioUninformativeDirichletPrior , que obtém as relações entre as categorias. O grey_threshold indica que os pontos de pontuação entre [-1,96, 1,96] (ou seja, p> 0,05) devem ser cinza coloridos. O argumento metadata_descriptions=general_inquirer_feature_builder.get_definitions() indica que um dicionário mapeando o nome da tag para uma definição de string é passado. Quando uma tag é clicada, a definição no dicionário será mostrada abaixo do gráfico, como mostrado na imagem seguindo o snippet.
>>> html = st.produce_frequency_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... metadata=convention_df['speaker'],
... use_non_text_features=True,
... use_full_doc=True,
... term_scorer=st.LogOddsRatioUninformativeDirichletPrior(),
... grey_threshold=1.96,
... width_in_pixels=1000,
... topic_model_term_lists=general_inquirer_feature_builder.get_top_model_term_lists(),
... metadata_descriptions=general_inquirer_feature_builder.get_definitions())
Aqui está o gráfico resultante.
A teoria dos [fundamentos morais] propõe seis construções psicológicas como blocos de construção do pensamento moral, como descrito em Graham et al. (2013). Essas fundações são, conforme descrito em [Moralfoundations.org]: Cuidado/dano, justiça/trapaça, lealdade/traição, autoridade/subversão, santidade/degradação e liberdade/opressão. Consulte o site para uma discussão mais aprofundada sobre essas fundações.
Frimer et al. (2019) criaram o dicionário de fundações morais 2.0, ou um léxico de termos que invocam uma base moral como uma virtude (favorável à fundação) ou um vício (em oposição à fundação).
Este dicionário pode ser usado da mesma maneira que o Inquiridor Geral. Neste exemplo, podemos plotar as pontuações de cohen de contagens de palavras da fundação em relação às frequências que as palavras envolvendo essas fundações foram invocadas.
Primeiro, podemos carregar o corpus e usar st.FeatsFromMoralFoundationsDictionary() para extrair recursos.
import scattertext as st
convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
moral_foundations_feats = st . FeatsFromMoralFoundationsDictionary ()
corpus = st . CorpusFromPandas ( convention_df ,
category_col = 'party' ,
text_col = 'text' ,
nlp = st . whitespace_nlp_with_sentences ,
feats_from_spacy_doc = moral_foundations_feats ). build ()Em seguida, vamos usar o marcador de termo de Cohen para analisar o corpus e descrever um conjunto de pontuações da Association de Cohen.
cohens_d_scorer = st . CohensD ( corpus ). use_metadata ()
term_scorer = cohens_d_scorer . set_categories ( 'democrat' , [ 'republican' ]). term_scorer . get_score_df ()Que produz o seguinte quadro de dados:
| cohens_d | cohens_d_se | cohens_d_z | cohens_d_p | hedges_g | hedges_g_se | hedges_g_z | hedges_g_p | M1 | M2 | contagem1 | contagem2 | DOCS1 | DOCS2 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Care.Virtue | 0,662891 | 0,149425 | 4.43629 | 4.57621E-06 | 0,660257 | 0.159049 | 4.15129 | 1.65302E-05 | 0.195049 | 0,12164 | 760 | 379 | 115 | 54 |
| Care.vice | 0,24435 | 0,146025 | 1.67335 | 0,0471292 | 0,243379 | 0,152654 | 1.59432 | 0.0554325 | 0,0580005 | 0,0428358 | 244 | 121 | 80 | 41 |
| Fairness.Virtue | 0,176794 | 0.145767 | 1.21286 | 0,112592 | 0,176092 | 0,152164 | 1.15725 | 0,123586 | 0,0502469 | 0,0403369 | 225 | 107 | 71 | 39 |
| justiça.vice | 0,0707162 | 0.145528 | 0,485928 | 0,313509 | 0,0704352 | 0.151711 | 0,464273 | 0,321226 | 0,00718627 | 0,00573227 | 32 | 14 | 21 | 10 |
| Autoridade.virtue | -0.0187793 | 0,145486 | -0.12908 | 0,551353 | -0.0187047 | 0,15163 | -0.123357 | 0,549088 | 0,358192 | 0,361191 | 1281 | 788 | 122 | 66 |
| Autoridade.vice | -0.0354164 | 0,145494 | -0.243422 | 0,596161 | -0.0352757 | 0,151646 | -0.232619 | 0,591971 | 0,00353465 | 0,00390602 | 20 | 14 | 14 | 10 |
| santidade.virtue | -0.512145 | 0.147848 | -3.46399 | 0,999734 | -0.51011 | 0.156098 | -3.26788 | 0,999458 | 0,0587987 | 0.101677 | 265 | 309 | 74 | 48 |
| santidade.vice | -0.108011 | 0,145589 | -0.74189 | 0,770923 | -0.107582 | 0.151826 | -0.708585 | 0,760709 | 0,00845048 | 0.0109339 | 35 | 28 | 23 | 20 |
| lealdade | -0.413696 | 0,147031 | -2.81367 | 0,997551 | -0.412052 | 0,154558 | -2.666 | 0,996162 | 0,259296 | 0,309776 | 1056 | 717 | 119 | 66 |
| lealdade.vice | -0.0854683 | 0.145549 | -0.587213 | 0,72147 | -0.0851287 | 0,151751 | -0.560978 | 0,712594 | 0,00124518 | 0,00197022 | 5 | 5 | 5 | 4 |
Esse quadro de dados nos fornece as pontuações de D Cohen (e seus erros padrão e escores Z), Hedge's
Observe que D de Cohen é a diferença de M1 e M2 dividido por seu desvio padrão agrupado.
Agora, vamos plotar os escores D das fundações versus suas frequências.
html = st . produce_frequency_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
metadata = convention_df [ 'speaker' ],
use_non_text_features = True ,
use_full_doc = True ,
term_scorer = st . CohensD ( corpus ). use_metadata (),
grey_threshold = 0 ,
width_in_pixels = 1000 ,
topic_model_term_lists = moral_foundations_feats . get_top_model_term_lists (),
metadata_descriptions = moral_foundations_feats . get_definitions ()
)Freqüentemente, os termos de maior interesse são aqueles que são característicos do corpus como um todo. Esses são termos que ocorrem frequentemente em todos os conjuntos de documentos que estão sendo estudados, mas relativamente pouco frequentes em comparação com as frequências de termos gerais.
Podemos produzir um gráfico com uma pontuação característica nas pontuações do eixo x e da associação de classe no eixo y usando a função produce_characteristic_explorer .
A característica do corpus é a diferença no termo denso entre as palavras em todos os documentos do estudo e uma lista geral de frequência em inglês. Veja esta palestra sobre as pontuações da Associação de Classe de Termo para uma explicação mais completa.
import scattertext as st
corpus = ( st . CorpusFromPandas ( st . SampleCorpora . ConventionData2012 . get_data (),
category_col = 'party' ,
text_col = 'text' ,
nlp = st . whitespace_nlp_with_sentences )
. build ()
. get_unigram_corpus ()
. compact ( st . ClassPercentageCompactor ( term_count = 2 ,
term_ranker = st . OncePerDocFrequencyRanker )))
html = st . produce_characteristic_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
metadata = corpus . get_df ()[ 'speaker' ]
)
open ( 'demo_characteristic_chart.html' , 'wb' ). write ( html . encode ( 'utf-8' )) Além das palavras, fases e tópicos, podemos fazer com que cada ponto corresponda a um documento. Vamos primeiro criar um objeto corpus para o conjunto de dados de convenções de 2012. Esta explicação segue demo_pca_documents.py
import pandas as pd
from sklearn . feature_extraction . text import TfidfTransformer
import scattertext as st
from scipy . sparse . linalg import svds
convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
convention_df [ 'parse' ] = convention_df [ 'text' ]. apply ( st . whitespace_nlp_with_sentences )
corpus = ( st . CorpusFromParsedDocuments ( convention_df ,
category_col = 'party' ,
parsed_col = 'parse' )
. build ()
. get_stoplisted_unigram_corpus ()) Em seguida, vamos adicionar os nomes de documentos como metadados no objeto Corpus. A função add_doc_names_as_metadata pega uma matriz de nomes de documentos e preenche os meta -dados de um novo corpus com esses nomes. Se dois documentos tiverem o mesmo nome, ele anexará um número (começando com 1) ao nome.
corpus = corpus . add_doc_names_as_metadata ( corpus . get_df ()[ 'speaker' ])Em seguida, encontramos as pontuações do TF.IDF para a matriz de documentos de termos do Corpus, executamos SVD escassos e os adicionamos a um quadro de dados de projeção, tornando os eixos X e Y os dois primeiros valores singulares e indexando-o nos meta-dados do corpus, que corresponde aos nomes dos documentos.
embeddings = TfidfTransformer (). fit_transform ( corpus . get_term_doc_mat ())
u , s , vt = svds ( embeddings , k = 3 , maxiter = 20000 , which = 'LM' )
projection = pd . DataFrame ({ 'term' : corpus . get_metadata (), 'x' : u . T [ 0 ], 'y' : u . T [ 1 ]}). set_index ( 'term' ) Finalmente, defina pontuações como 1 para os democratas e 0 para os republicanos, tornando os documentos republicanos como pontos vermelhos e documentos democratas como azul. Para saber mais sobre a função produce_pca_explorer , consulte Usando o SVD para visualizar qualquer tipo de incorporação de palavras.
category = 'democrat'
scores = ( corpus . get_category_ids () == corpus . get_categories (). index ( category )). astype ( int )
html = st . produce_pca_explorer ( corpus ,
category = category ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
metadata = convention_df [ 'speaker' ],
width_in_pixels = 1000 ,
show_axes = False ,
use_non_text_features = True ,
use_full_doc = True ,
projection = projection ,
scores = scores ,
show_top_terms = False )Clique para uma versão interativa
O D de Cohen é uma métrica popular usada para medir o tamanho do efeito. As definições de Cohen's D e Hedge's
> >> convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
> >> corpus = ( st . CorpusFromPandas ( convention_df ,
... category_col = 'party' ,
... text_col = 'text' ,
... nlp = st . whitespace_nlp_with_sentences )
.... build ()
.... get_unigram_corpus ())Podemos criar um objeto de marcador de termo para examinar os tamanhos de efeito e outras métricas.
>> > term_scorer = st . CohensD ( corpus ). set_categories ( 'democrat' , [ 'republican' ])
>> > term_scorer . get_score_df (). sort_values ( by = 'cohens_d' , ascending = False ). head ()
cohens_d
cohens_d_se
cohens_d_z
cohens_d_p
hedges_g
hedges_g_se
hedges_g_z
hedges_g_p
m1
m2
obama
1.187378
0.024588
48.290444
0.000000e+00
1.187322
0.018419
64.461363
0.0
0.007778
0.002795
class 0.855859 0.020848 41.052045 0.000000e+00 0.855818 0.017227 49.677688 0.0 0.002222 0.000375
middle
0.826895
0.020553
40.232746
0.000000e+00
0.826857
0.017138
48.245626
0.0
0.002316
0.000400
president
0.820825
0.020492
40.056541
0.000000e+00
0.820786
0.017120
47.942661
0.0
0.010231
0.005369
barack
0.730624
0.019616
37.245725
6.213052e-304
0.730589
0.016862
43.327800
0.0
0.002547
0.000725 Nosso cálculo de D de Cohen não é diretamente baseado nas contagens de termos. Em vez disso, dividimos a contagem de termos de cada documento pelo número total de termos no documento antes de calcular as estatísticas. m1 e m2 são, respectivamente, as partes médias das palavras em discursos feitos por democratas e republicanos que eram o termo em questão. O tamanho do efeito ( cohens_d ) é a diferença entre esses meios divididos pelo desvio padrão agrupado. cohens_d_se é o erro padrão da estatística, enquanto cohens_d_z e cohens_d_p são os escores z e valores p que indicavam a significância estatística do efeito. Colunas correspondentes estão presentes para a hedge
> >> st . produce_frequency_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
term_scorer = st . CohensD ( corpus ),
metadata = convention_df [ 'speaker' ],
grey_threshold = 0
)Clique para uma versão interativa.
O Delta de Cliff (Cliff 1993) usa uma abordagem não paramétrica para o tamanho do efeito de computação. Em nossa configuração, a porcentagem de frequência do termo de cada documento no conjunto de foco é comparada com a do conjunto de segundo plano. Para cada par de documentos, uma pontuação de 1 é fornecida se a porcentagem de frequência do documento de foco for maior que o plano de fundo, 0 se idêntico e -1 se diferente. Observe que isso pressupõe que os comprimentos dos documentos sejam distribuídos de maneira semelhante nos corpora de foco e plano de fundo.
Consulte [https://real-statistics.com/non-parametric-tests/mann-whitney-test/cliffs-delta/] para as fórmulas usadas em CliffsDelta .
Abaixo está um exemplo de como usar CliffsDelta para encontrar e plotar pontuações:
nlp = spacy . blank ( 'en' )
nlp . add_pipe ( 'sentencizer' )
convention_df = st . SampleCorpora . ConventionData2012 . get_data (). assign (
party = lambda df : df . party . apply (
lambda x : { 'democrat' : 'Dem' , 'republican' : 'Rep' }[ x ]),
SpacyParse = lambda df : df . text . progress_apply ( nlp )
)
corpus = st . CorpusFromParsedDocuments ( convention_df , category_col = 'party' , parsed_col = 'SpacyParse' ). build (
). remove_terms_used_in_less_than_num_docs ( 10 )
st . CliffsDelta ( corpus ). set_categories ( 'Dem' ). get_score_df (). sort_values ( by = 'Dem' , ascending = False ). iloc [: 10 ]| prazo | Métrica | Stddev | IC de baixa 5,0% | IC de 5,0% | TermCount1 | TermCount2 | DocCount1 | DocCount2 |
|---|---|---|---|---|---|---|---|---|
| Obama | 0,597191 | 0,0266606 | -1.35507 | -1.03477 | 537 | 165 | 113 | 40 |
| Presidente Obama | 0,565903 | 0,0314348 | -2.37978 | -1.74131 | 351 | 78 | 100 | 30 |
| presidente | 0,426337 | 0,0293418 | 1.22784 | 0,909226 | 740 | 301 | 113 | 53 |
| meio | 0,417591 | 0,0267365 | 1.10791 | 0,840932 | 164 | 27 | 68 | 12 |
| aula | 0,415373 | 0,0280622 | 1.09032 | 0,815649 | 161 | 25 | 69 | 14 |
| Barack | 0.406997 | 0,0281692 | 1.00765 | 0,750963 | 202 | 46 | 76 | 16 |
| Barack Obama | 0,402562 | 0,027512 | 0,965359 | 0,723403 | 164 | 45 | 76 | 16 |
| isso é | 0,384085 | 0,0227344 | 0,809747 | 0,634705 | 236 | 91 | 89 | 31 |
| Obama. | 0,356245 | 0,0237453 | 0,664688 | 0,509631 | 70 | 5 | 49 | 4 |
| para | 0,35526 | 0,0364138 | 0,70142 | 0,46487 | 1020 | 542 | 119 | 62 |
Podemos exibir elegantemente as pontuações do Delta do Cliff usando dataframe_scattertext e descrever o esquema de colorir de pontos usando o parâmetro include_gradient=True . Definimos os parâmetros de left_gradient_term , middle_gradient_term e right_gradient_term para strings que aparecerão em seus valores corresondores.
plot_df = st . CliffsDelta (
corpus
). set_categories (
category_name = 'Dem'
). get_score_df (). rename ( columns = { 'Metric' : 'CliffsDelta' }). assign (
Frequency = lambda df : df . TermCount1 + df . TermCount1 ,
X = lambda df : df . Frequency ,
Y = lambda df : df . CliffsDelta ,
Xpos = lambda df : st . Scalers . dense_rank ( df . X ),
Ypos = lambda df : st . Scalers . scale_center_zero_abs ( df . Y ),
ColorScore = lambda df : df . Ypos ,
)
html = st . dataframe_scattertext (
corpus ,
plot_df = plot_df ,
category = 'Dem' ,
category_name = 'Dem' ,
not_category_name = 'Rep' ,
width_in_pixels = 1000 ,
ignore_categories = False ,
metadata = lambda corpus : corpus . get_df ()[ 'speaker' ],
color_score_column = 'ColorScore' ,
left_list_column = 'ColorScore' ,
show_characteristic = False ,
y_label = "Cliff's Delta" ,
x_label = 'Frequency Ranks' ,
y_axis_labels = [ f'More Rep: delta= { plot_df . CliffsDelta . max ():.3f } ' ,
'' ,
f'More Dem: delta= { - plot_df . CliffsDelta . max ():.3f } ' ],
tooltip_columns = [ 'Frequency' , 'CliffsDelta' ],
term_description_columns = [ 'CliffsDelta' , 'Stddev' , 'Low-95.0% CI' , 'High-95.0% CI' ],
header_names = { 'upper' : 'Top Dem' , 'lower' : 'Top Reps' },
horizontal_line_y_position = 0 ,
include_gradient = True ,
left_gradient_term = 'More Republican' ,
right_gradient_term = 'More Democratic' ,
middle_gradient_term = "Metric: Cliff's Delta" ,
) A separação bipomal (BNS) (Forman, 2008) foi adicionada na versão 0.1.8. Uma variação de (BNS) é usada onde
corpus = ( st . CorpusFromPandas ( convention_df ,
category_col = 'party' ,
text_col = 'text' ,
nlp = st . whitespace_nlp_with_sentences )
. build ()
. get_unigram_corpus ()
. remove_infrequent_words ( 3 , term_ranker = st . OncePerDocFrequencyRanker ))
term_scorer = ( st . BNSScorer ( corpus ). set_categories ( 'democrat' ))
print ( term_scorer . get_score_df (). sort_values ( by = 'democrat BNS' ))
html = st . produce_frequency_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
scores = term_scorer . get_score_df ()[ 'democrat BNS' ]. reindex ( corpus . get_terms ()). values ,
metadata = lambda c : c . get_df ()[ 'speaker' ],
minimum_term_frequency = 0 ,
grey_threshold = 0 ,
y_label = f'Bi-normal Separation (alpha= { term_scorer . prior_counts } )'
)O BNS obteve termos usando um alfa algoritmicamente encontrado. ! [BNS] (https://raw.githubusercontent.com/jasonkessler/jasonkessler.github.io/master/d emo_bi_normal_separation.png)
Podemos treinar um classificador para produzir uma pontuação de previsão para cada documento. Freqüentemente, classificadores ou regressores usam recursos que levam em consideração os recursos além dos representados por ScatterExt, seja n-gramas, tópico, extra-linguística, neural, etc.
Podemos usar o ScatterText para visualizar as correlações entre os unigramas (ou realmente qualquer representação de recursos) e as pontuações do documento produzidas por um modelo.
No exemplo a seguir, treinamos um SVM linear usando recursos de Unigram e Bi-Gram em todo o conjunto de dados da convenção e usamos o modelo para fazer uma previsão em cada documento e, finalmente, usando o Pearson's
from sklearn . svm import LinearSVC
import scattertext as st
df = st . SampleCorpora . ConventionData2012 . get_data (). assign (
parse = lambda df : df . text . apply ( st . whitespace_nlp_with_sentences )
)
corpus = st . CorpusFromParsedDocuments (
df , category_col = 'party' , parsed_col = 'parse'
). build ()
X = corpus . get_term_doc_mat ()
y = corpus . get_category_ids ()
clf = LinearSVC ()
clf . fit ( X = X , y = y == corpus . get_categories (). index ( 'democrat' ))
doc_scores = clf . decision_function ( X = X )
compactcorpus = corpus . get_unigram_corpus (). compact ( st . AssociationCompactor ( 2000 ))
plot_df = st . Correlations (). set_correlation_type (
'pearsonr'
). get_correlation_df (
corpus = compactcorpus ,
document_scores = doc_scores
). reindex ( compactcorpus . get_terms ()). assign (
X = lambda df : df . Frequency ,
Y = lambda df : df [ 'r' ],
Xpos = lambda df : st . Scalers . dense_rank ( df . X ),
Ypos = lambda df : st . Scalers . scale_center_zero_abs ( df . Y ),
SuppressDisplay = False ,
ColorScore = lambda df : df . Ypos ,
)
html = st . dataframe_scattertext (
compactcorpus ,
plot_df = plot_df ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
width_in_pixels = 1000 ,
metadata = lambda c : c . get_df ()[ 'speaker' ],
unified_context = False ,
ignore_categories = False ,
color_score_column = 'ColorScore' ,
left_list_column = 'ColorScore' ,
y_label = "Pearson r (correlation to SVM document score)" ,
x_label = 'Frequency Ranks' ,
header_names = { 'upper' : 'Top Democratic' ,
'lower' : 'Top Republican' },
) ScatterText depende de um conjunto de frequências de palavras em inglês do domínio geral ao calcular a característica do Unigram
pontuações. Ao usar a execução do ScatterText em dados não ingleses ou em um domínio específico, a qualidade das pontuações se degradará.
Verifique se você está no ScatterText 0.1.6 ou superior.
Para remediar isso, pode-se adicionar um conjunto personalizado de pontuações em segundo plano a um objeto tipo corpus, usando a função Corpus.set_background_corpus . A função leva um objeto pd.Series , indexado em termos com valores de contagem numérica.
Por padrão, [! Score F-score com escala de compreensão] (escala F-Score) é usado para classificar como os termos característicos são.
O exemplo abaixo ilustra o uso de frequências de palavras de fundo polonês.
Primeiro, produzimos uma série que mapeia as palavras polonesas em suas frequências usando uma lista do https://github.com/oprogramador/morm-common-words-by-language repo.
polish_word_frequencies = pd . read_csv (
'https://raw.githubusercontent.com/hermitdave/FrequencyWords/master/content/2016/pl/pl_50k.txt' ,
sep = ' ' ,
names = [ 'Word' , 'Frequency' ]
). set_index ( 'Word' )[ 'Frequency' ]Observe a composição da série
>> > polish_word_frequencies
Word
nie
5875385
to
4388099
się
3507076
w
2723767
na
2309765
Name : Frequency , dtype : int64 Em seguida, construímos um DataFrame, reviews_df , composto por documentos que aparecem (para um falante não-polimento) para serem avaliações positivas e negativas de hotéis da https://klejbenchmark.com/tasks/ corpus (Kocoń, et al. 2019). Observe que esses dados estão sob uma licença CC BY-NC-SA 4.0. These are labeled as "__label__meta_plus_m" and "__label__meta_minus_m". We will use Scattertext to compare those reviews and determine
nlp = spacy . blank ( 'pl' )
nlp . add_pipe ( 'sentencizer' )
with ZipFile ( io . BytesIO ( urlopen (
'https://klejbenchmark.com/static/data/klej_polemo2.0-in.zip'
). read ())) as zf :
review_df = pd . read_csv ( zf . open ( 'train.tsv' ), sep = ' t ' )[
lambda df : df . target . isin ([ '__label__meta_plus_m' , '__label__meta_minus_m' ])
]. assign (
Parse = lambda df : df . sentence . apply ( nlp )
) Next, we wish to create a ParsedCorpus object from review_df . In preparation, we first assemble a list of Polish stopwords from the stopwords repository. We also create the not_a_word regular expression to filter out terms which do not contain a letter.
polish_stopwords = {
stopword for stopword in
urlopen (
'https://raw.githubusercontent.com/bieli/stopwords/master/polish.stopwords.txt'
). read (). decode ( 'utf-8' ). split ( ' n ' )
if stopword . strip ()
}
not_a_word = re . compile ( r'^W+$' ) With these present, we can build a corpus from review_df with the category being the binary "target" column. We reduce the term space to unigrams and then run the filter_out which takes a function to determine if a term should be removed from the corpus. The function identifies terms which are in the Polish stoplist or do not contain a letter. Finally, terms occurring less than 20 times in the corpus are removed.
We set the background frequency Series we created early as the background corpus.
corpus = st . CorpusFromParsedDocuments (
review_df ,
category_col = 'target' ,
parsed_col = 'Parse'
). build (
). get_unigram_corpus (
). filter_out (
lambda term : term in polish_stopwords or not_a_word . match ( term ) is not None
). remove_infrequent_words (
minimum_term_count = 20
). set_background_corpus (
polish_word_frequencies
)Note that a minimum word count of 20 was chosen to ensure that only around 2,000 terms would be displayed
>> > corpus . get_num_terms ()
2023 Running get_term_and_background_counts shows us total term counts in the corpus compare to background frequency counts. We limit this to terms which only occur in the corpus.
>> > corpus . get_term_and_background_counts ()[
...
lambda df : df . corpus > 0
...]. sort_values ( by = 'corpus' , ascending = False )
background
corpus
m
341583838.0
4819.0
hotelu
33108.0
1812.0
hotel
297974790.0
1651.0
doktor
154840.0
1534.0
polecam
0.0
1438.0
.........
szoku
0.0
21.0
badaniem
0.0
21.0
balkonu
0.0
21.0
stopnia
0.0
21.0
wobec
0.0
21.0Interesting, the term "polecam" appears very frequently in the corpus, but does not appear at all in the background corpus, making it highly characteristic. Judging from Google Translate, it appears to mean something related to "recommend".
We are now ready to display the plot.
html = st . produce_scattertext_explorer (
corpus ,
category = '__label__meta_plus_m' ,
category_name = 'Plus-M' ,
not_category_name = 'Minus-M' ,
minimum_term_frequency = 1 ,
width_in_pixels = 1000 ,
transform = st . Scalers . dense_rank
) We can change the formula which is used to produce the Characteristic scores using the characteristic_scorer parameter to produce_scattertext_explorer .
It takes a instance of a descendant of the CharacteristicScorer class. See DenseRankCharacteristicness.py for an example of how to make your own.
Example of plotting with a modified characteristic scorer,
html = st . produce_scattertext_explorer (
corpus ,
category = '__label__meta_plus_m' ,
category_name = 'Plus-M' ,
not_category_name = 'Minus-M' ,
minimum_term_frequency = 1 ,
transform = st . Scalers . dense_rank ,
characteristic_scorer = st . DenseRankCharacteristicness (),
term_ranker = st . termranking . AbsoluteFrequencyRanker ,
term_scorer = st . ScaledFScorePresets ( beta = 1 , one_to_neg_one = True )
). encode ( 'utf-8' ))
print ( 'open ' + fn )Note that numbers show up as more characteristic using the Dense Rank Difference. It may be they occur unusually frequently in this corpus, or perhaps the background word frequencies under counted mumbers.
Word productivity is one strategy for plotting word-based charts describing an uncategorized corpus.
Productivity is defined in Schumann (2016) (Jason: check this) as the entropy of ngrams which contain a term. For the entropy computation, the probability of an n-gram wrt the term whose productivity is being calculated is the frequency of the n-gram divided by the term's frequency.
Since productivity highly correlates with frequency, the recommended metric to plot is the dense rank difference between frequency and productivity.
The snippet below plots words in the convention corpus based on their log frequency and their productivity.
The function st.whole_corpus_productivity_scores returns a DataFrame giving each word's productivity. For example, in the convention corpus,
Productivity scores should be calculated on a Corpus -like object which contains a complete set of unigrams and at least bigrams. This corpus should not be compacted before the productivity score calculation.
The terms with lower productivity have more limited usage (eg, "thank" for "thank you", "united" for "united steates") while the terms with higher productivity occurr in a wider varity of contexts ("getting", "actually", "political", etc.).
import spacy
import scattertext as st
corpus_no_cat = st . CorpusWithoutCategoriesFromParsedDocuments (
st . SampleCorpora . ConventionData2012 . get_data (). assign (
Parse = lambda df : [ x for x in spacy . load ( 'en_core_web_sm' ). pipe ( df . text )]),
parsed_col = 'Parse'
). build ()
compact_corpus_no_cat = corpus_no_cat . get_stoplisted_unigram_corpus (). remove_infrequent_words ( 9 )
plot_df = st . whole_corpus_productivity_scores ( corpus_no_cat ). assign (
RankDelta = lambda df : st . RankDifference (). get_scores (
a = df . Productivity ,
b = df . Frequency
)
). reindex (
compact_corpus_no_cat . get_terms ()
). dropna (). assign (
X = lambda df : df . Frequency ,
Xpos = lambda df : st . Scalers . log_scale ( df . Frequency ),
Y = lambda df : df . RankDelta ,
Ypos = lambda df : st . Scalers . scale ( df . RankDelta ),
)
html = st . dataframe_scattertext (
compact_corpus_no_cat . whitelist_terms ( plot_df . index ),
plot_df = plot_df ,
metadata = lambda df : df . get_df ()[ 'speaker' ],
ignore_categories = True ,
x_label = 'Rank Frequency' ,
y_label = "Productivity" ,
left_list_column = 'Ypos' ,
color_score_column = 'Ypos' ,
y_axis_labels = [ 'Least Productive' , 'Average Productivity' , 'Most Productive' ],
header_names = { 'upper' : 'Most Productive' , 'lower' : 'Least Productive' , 'right' : 'Characteristic' },
horizontal_line_y_position = 0
)Let's now turn our attention to a novel term scoring metric, Scaled F-Score. We'll examine this on a unigram version of the Rotten Tomatoes corpus (Pang et al. 2002). It contains excerpts of positive and negative movie reviews.
Please see Scaled F Score Explanation for a notebook version of this analysis.
from scipy . stats import hmean
term_freq_df = corpus . get_unigram_corpus (). get_term_freq_df ()[[ 'Positive freq' , 'Negative freq' ]]
term_freq_df = term_freq_df [ term_freq_df . sum ( axis = 1 ) > 0 ]
term_freq_df [ 'pos_precision' ] = ( term_freq_df [ 'Positive freq' ] * 1. /
( term_freq_df [ 'Positive freq' ] + term_freq_df [ 'Negative freq' ]))
term_freq_df [ 'pos_freq_pct' ] = ( term_freq_df [ 'Positive freq' ] * 1.
/ term_freq_df [ 'Positive freq' ]. sum ())
term_freq_df [ 'pos_hmean' ] = ( term_freq_df
. apply ( lambda x : ( hmean ([ x [ 'pos_precision' ], x [ 'pos_freq_pct' ]])
if x [ 'pos_precision' ] > 0 and x [ 'pos_freq_pct' ] > 0
else 0 ), axis = 1 ))
term_freq_df . sort_values ( by = 'pos_hmean' , ascending = False ). iloc [: 10 ]If we plot term frequency on the x-axis and the percentage of a term's occurrences which are in positive documents (ie, its precision) on the y-axis, we can see that low-frequency terms have a much higher variation in the precision. Given these terms have low frequencies, the harmonic means are low. Thus, the only terms which have a high harmonic mean are extremely frequent words which tend to all have near average precisions.
freq = term_freq_df . pos_freq_pct . values
prec = term_freq_df . pos_precision . values
html = st . produce_scattertext_explorer (
corpus . remove_terms ( set ( corpus . get_terms ()) - set ( term_freq_df . index )),
category = 'Positive' ,
not_category_name = 'Negative' ,
not_categories = [ 'Negative' ],
x_label = 'Portion of words used in positive reviews' ,
original_x = freq ,
x_coords = ( freq - freq . min ()) / freq . max (),
x_axis_values = [ int ( freq . min () * 1000 ) / 1000. ,
int ( freq . max () * 1000 ) / 1000. ],
y_label = 'Portion of documents containing word that are positive' ,
original_y = prec ,
y_coords = ( prec - prec . min ()) / prec . max (),
y_axis_values = [ int ( prec . min () * 1000 ) / 1000. ,
int (( prec . max () / 2. ) * 1000 ) / 1000. ,
int ( prec . max () * 1000 ) / 1000. ],
scores = term_freq_df . pos_hmean . values ,
sort_by_dist = False ,
show_characteristic = False
)
file_name = 'not_normed_freq_prec.html'
open ( file_name , 'wb' ). write ( html . encode ( 'utf-8' ))
IFrame ( src = file_name , width = 1300 , height = 700 ) from scipy . stats import norm
def normcdf ( x ):
return norm . cdf ( x , x . mean (), x . std ())
term_freq_df [ 'pos_precision_normcdf' ] = normcdf ( term_freq_df . pos_precision )
term_freq_df [ 'pos_freq_pct_normcdf' ] = normcdf ( term_freq_df . pos_freq_pct . values )
term_freq_df [ 'pos_scaled_f_score' ] = hmean (
[ term_freq_df [ 'pos_precision_normcdf' ], term_freq_df [ 'pos_freq_pct_normcdf' ]])
term_freq_df . sort_values ( by = 'pos_scaled_f_score' , ascending = False ). iloc [: 10 ] freq = term_freq_df . pos_freq_pct_normcdf . values
prec = term_freq_df . pos_precision_normcdf . values
html = st . produce_scattertext_explorer (
corpus . remove_terms ( set ( corpus . get_terms ()) - set ( term_freq_df . index )),
category = 'Positive' ,
not_category_name = 'Negative' ,
not_categories = [ 'Negative' ],
x_label = 'Portion of words used in positive reviews (norm-cdf)' ,
original_x = freq ,
x_coords = ( freq - freq . min ()) / freq . max (),
x_axis_values = [ int ( freq . min () * 1000 ) / 1000. ,
int ( freq . max () * 1000 ) / 1000. ],
y_label = 'documents containing word that are positive (norm-cdf)' ,
original_y = prec ,
y_coords = ( prec - prec . min ()) / prec . max (),
y_axis_values = [ int ( prec . min () * 1000 ) / 1000. ,
int (( prec . max () / 2. ) * 1000 ) / 1000. ,
int ( prec . max () * 1000 ) / 1000. ],
scores = term_freq_df . pos_scaled_f_score . values ,
sort_by_dist = False ,
show_characteristic = False
) term_freq_df [ 'neg_precision_normcdf' ] = normcdf (( term_freq_df [ 'Negative freq' ] * 1. /
( term_freq_df [ 'Negative freq' ] + term_freq_df [ 'Positive freq' ])))
term_freq_df [ 'neg_freq_pct_normcdf' ] = normcdf (( term_freq_df [ 'Negative freq' ] * 1.
/ term_freq_df [ 'Negative freq' ]. sum ()))
term_freq_df [ 'neg_scaled_f_score' ] = hmean (
[ term_freq_df [ 'neg_precision_normcdf' ], term_freq_df [ 'neg_freq_pct_normcdf' ]])
term_freq_df [ 'scaled_f_score' ] = 0
term_freq_df . loc [ term_freq_df [ 'pos_scaled_f_score' ] > term_freq_df [ 'neg_scaled_f_score' ],
'scaled_f_score' ] = term_freq_df [ 'pos_scaled_f_score' ]
term_freq_df . loc [ term_freq_df [ 'pos_scaled_f_score' ] < term_freq_df [ 'neg_scaled_f_score' ],
'scaled_f_score' ] = 1 - term_freq_df [ 'neg_scaled_f_score' ]
term_freq_df [ 'scaled_f_score' ] = 2 * ( term_freq_df [ 'scaled_f_score' ] - 0.5 )
term_freq_df . sort_values ( by = 'scaled_f_score' , ascending = True ). iloc [: 10 ] is_pos = term_freq_df . pos_scaled_f_score > term_freq_df . neg_scaled_f_score
freq = term_freq_df . pos_freq_pct_normcdf * is_pos - term_freq_df . neg_freq_pct_normcdf * ~ is_pos
prec = term_freq_df . pos_precision_normcdf * is_pos - term_freq_df . neg_precision_normcdf * ~ is_pos
def scale ( ar ):
return ( ar - ar . min ()) / ( ar . max () - ar . min ())
def close_gap ( ar ):
ar [ ar > 0 ] -= ar [ ar > 0 ]. min ()
ar [ ar < 0 ] -= ar [ ar < 0 ]. max ()
return ar
html = st . produce_scattertext_explorer (
corpus . remove_terms ( set ( corpus . get_terms ()) - set ( term_freq_df . index )),
category = 'Positive' ,
not_category_name = 'Negative' ,
not_categories = [ 'Negative' ],
x_label = 'Frequency' ,
original_x = freq ,
x_coords = scale ( close_gap ( freq )),
x_axis_labels = [ 'Frequent in Neg' ,
'Not Frequent' ,
'Frequent in Pos' ],
y_label = 'Precision' ,
original_y = prec ,
y_coords = scale ( close_gap ( prec )),
y_axis_labels = [ 'Neg Precise' ,
'Imprecise' ,
'Pos Precise' ],
scores = ( term_freq_df . scaled_f_score . values + 1 ) / 2 ,
sort_by_dist = False ,
show_characteristic = False
) We can use st.ScaledFScorePresets as a term scorer to display terms' Scaled F-Score on the y-axis and term frequencies on the x-axis.
html = st . produce_frequency_explorer (
corpus . remove_terms ( set ( corpus . get_terms ()) - set ( term_freq_df . index )),
category = 'Positive' ,
not_category_name = 'Negative' ,
not_categories = [ 'Negative' ],
term_scorer = st . ScaledFScorePresets ( beta = 1 , one_to_neg_one = True ),
metadata = rdf [ 'movie_name' ],
grey_threshold = 0
)Scaled F-Score is not the only scoring method included in Scattertext. Please click on one of the links below to view a notebook which describes how other class association scores work and can be visualized through Scattertext.
New in 0.0.2.73 is the delta JS-Divergence scorer DeltaJSDivergence scorer (Gallagher et al. 2020), and its corresponding compactor (JSDCompactor.) See demo_deltajsd.py for an example usage.
New in 0.0.2.72
Scattertext was originally set up to visualize corpora objects, which are connected sets of documents and terms to visualize. The "compaction" process allows users to eliminate terms which may not be associated with a category using a variety of feature selection methods. The issue with this is that the terms eliminated during the selection process are not taken into account when scaling term positions.
This issue can be mitigated by using the position-select-plot process, where term positions are pre-determined before the selection process is made.
Let's first use the 2012 conventions corpus, update the category names, and create a unigram corpus.
import scattertext as st
import numpy as np
df = st . SampleCorpora . ConventionData2012 . get_data (). assign (
parse = lambda df : df . text . apply ( st . whitespace_nlp_with_sentences )
). assign ( party = lambda df : df [ 'party' ]. apply ({ 'democrat' : 'Democratic' , 'republican' : 'Republican' }. get ))
corpus = st . CorpusFromParsedDocuments (
df , category_col = 'party' , parsed_col = 'parse'
). build (). get_unigram_corpus ()
category_name = 'Democratic'
not_category_name = 'Republican'Next, let's create a dataframe consisting of the original counts and their log-scale positions.
def get_log_scale_df ( corpus , y_category , x_category ):
term_coord_df = corpus . get_term_freq_df ( '' )
# Log scale term counts (with a smoothing constant) as the initial coordinates
coord_columns = []
for category in [ y_category , x_category ]:
col_name = category + '_coord'
term_coord_df [ col_name ] = np . log ( term_coord_df [ category ] + 1e-6 ) / np . log ( 2 )
coord_columns . append ( col_name )
# Scale these coordinates to between 0 and 1
min_offset = term_coord_df [ coord_columns ]. min ( axis = 0 ). min ()
for coord_column in coord_columns :
term_coord_df [ coord_column ] -= min_offset
max_offset = term_coord_df [ coord_columns ]. max ( axis = 0 ). max ()
for coord_column in coord_columns :
term_coord_df [ coord_column ] /= max_offset
return term_coord_df
# Get term coordinates from original corpus
term_coordinates = get_log_scale_df ( corpus , category_name , not_category_name )
print ( term_coordinates ) Here is a preview of the term_coordinates dataframe. The Democrat and Republican columns contain the term counts, while the _coord columns contain their logged coordinates. Visualizing 7,973 terms is difficult (but possible) for people running Scattertext on most computers.
Democratic Republican Democratic_coord Republican_coord
term
thank 158 205 0.860166 0.872032
you 836 794 0.936078 0.933729
so 337 212 0.894681 0.873562
much 84 76 0.831380 0.826820
very 62 75 0.817543 0.826216
... ... ... ... ...
precinct 0 2 0.000000 0.661076
godspeed 0 1 0.000000 0.629493
beauty 0 1 0.000000 0.629493
bumper 0 1 0.000000 0.629493
sticker 0 1 0.000000 0.629493
[7973 rows x 4 columns]
We can visualize this full data set by running the following code block. We'll create a custom Javascript function to populate the tooltip with the original term counts, and create a Scattertext Explorer where the x and y coordinates and original values are specified from the data frame. Additionally, we can use show_diagonal=True to draw a dashed diagonal line across the plot area.
You can click the chart below to see the interactive version. Note that it will take a while to load.
# The tooltip JS function. Note that d is is the term data object, and ox and oy are the original x- and y-
# axis counts.
get_tooltip_content = ('(function(d) {return d.term + "<br/>' + not_category_name + ' Count: " ' +
'+ d.ox +"<br/>' + category_name + ' Count: " + d.oy})')
html_orig = st.produce_scattertext_explorer(
corpus,
category=category_name,
not_category_name=not_category_name,
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
metadata=corpus.get_df()['speaker'],
show_diagonal=True,
original_y=term_coordinates[category_name],
original_x=term_coordinates[not_category_name],
x_coords=term_coordinates[category_name + '_coord'],
y_coords=term_coordinates[not_category_name + '_coord'],
max_overlapping=3,
use_global_scale=True,
get_tooltip_content=get_tooltip_content,
)
Next, we can visualize the compacted version of the corpus. The compaction, using ClassPercentageCompactor , selects terms which frequently in each category. The term_count parameter, set to 2, is used to determine the percentage threshold for terms to keep in a particular category. This is done using by calculating the percentile of terms (types) in each category which appear more than two times. We find the smallest percentile, and only include terms which occur above that percentile in a given category.
Note that this compaction leaves only 2,828 terms. This number is much easier for Scattertext to display in a browser.
# Select terms which appear a minimum threshold in both corpora
compact_corpus = corpus . compact ( st . ClassPercentageCompactor ( term_count = 2 ))
# Only take term coordinates of terms remaining in corpus
term_coordinates = term_coordinates . loc [ compact_corpus . get_terms ()]
html_compact = st . produce_scattertext_explorer (
compact_corpus ,
category = category_name ,
not_category_name = not_category_name ,
minimum_term_frequency = 0 ,
pmi_threshold_coefficient = 0 ,
width_in_pixels = 1000 ,
metadata = corpus . get_df ()[ 'speaker' ],
show_diagonal = True ,
original_y = term_coordinates [ category_name ],
original_x = term_coordinates [ not_category_name ],
x_coords = term_coordinates [ category_name + '_coord' ],
y_coords = term_coordinates [ not_category_name + '_coord' ],
max_overlapping = 3 ,
use_global_scale = True ,
get_tooltip_content = get_tooltip_content ,
) Occasionally, only term frequency statistics are available. This may happen in the case of very large, lost, or proprietary data sets. TermCategoryFrequencies is a corpus representation,that can accept this sort of data, along with any categorized documents that happen to be available.
Let use the Corpus of Contemporary American English as an example.
We'll construct a visualization to analyze the difference between spoken American English and English that occurs in fiction.
df = ( pd . read_excel ( 'https://www.wordfrequency.info/files/genres_sample.xls' )
. dropna ()
. set_index ( 'lemma' )[[ 'SPOKEN' , 'FICTION' ]]
. iloc [: 1000 ])
df . head ()
'''
SPOKEN FICTION
lemma
the 3859682.0 4092394.0
I 1346545.0 1382716.0
they 609735.0 352405.0
she 212920.0 798208.0
would 233766.0 229865.0
''' Transforming this into a visualization is extremely easy. Just pass a dataframe indexed on terms with columns indicating category-counts into the the TermCategoryFrequencies constructor.
term_cat_freq = st . TermCategoryFrequencies ( df ) And call produce_scattertext_explorer normally:
html = st . produce_scattertext_explorer (
term_cat_freq ,
category = 'SPOKEN' ,
category_name = 'Spoken' ,
not_category_name = 'Fiction' ,
) If you'd like to incorporate some documents into the visualization, you can add them into to the TermCategoyFrequencies object.
First, let's extract some example Fiction and Spoken documents from the sample COCA corpus.
import requests , zipfile , io
coca_sample_url = 'http://corpus.byu.edu/cocatext/samples/text.zip'
zip_file = zipfile . ZipFile ( io . BytesIO ( requests . get ( coca_sample_url ). content ))
document_df = pd . DataFrame (
[{ 'text' : zip_file . open ( fn ). read (). decode ( 'utf-8' ),
'category' : 'SPOKEN' }
for fn in zip_file . filelist if fn . filename . startswith ( 'w_spok' )][: 2 ]
+ [{ 'text' : zip_file . open ( fn ). read (). decode ( 'utf-8' ),
'category' : 'FICTION' }
for fn in zip_file . filelist if fn . filename . startswith ( 'w_fic' )][: 2 ]) And we'll pass the documents_df dataframe into TermCategoryFrequencies via the document_category_df parameter. Ensure the dataframe has two columns, 'text' and 'category'. Afterward, we can call produce_scattertext_explorer (or your visualization function of choice) normally.
doc_term_cat_freq = st . TermCategoryFrequencies ( df , document_category_df = document_df )
html = st . produce_scattertext_explorer (
doc_term_cat_freq ,
category = 'SPOKEN' ,
category_name = 'Spoken' ,
not_category_name = 'Fiction' ,
)Word representations have recently become a hot topic in NLP. While lots of work has been done visualizing how terms relate to one another given their scores (eg, http://projector.tensorflow.org/), none to my knowledge has been done visualizing how we can use these to examine how document categories differ.
In this example given a query term, "jobs", we can see how Republicans and Democrats talk about it differently.
In this configuration of Scattertext, words are colored by their similarity to a query phrase.
This is done using spaCy-provided GloVe word vectors (trained on the Common Crawl corpus). The cosine distance between vectors is used, with mean vectors used for phrases.
The calculation of the most similar terms associated with each category is a simple heuristic. First, sets of terms closely associated with a category are found. Second, these terms are ranked based on their similarity to the query, and the top rank terms are displayed to the right of the scatterplot.
A term is considered associated if its p-value is less than 0.05. P-values are determined using Monroe et al. (2008)'s difference in the weighted log-odds-ratios with an uninformative Dirichlet prior. This is the only model-based method discussed in Monroe et al. that does not rely on a large, in-domain background corpus. Since we are scoring bigrams in addition to the unigrams scored by Monroe, the size of the corpus would have to be larger to have high enough bigram counts for proper penalization. This function relies the Dirichlet distribution's parameter alpha, a vector, which is uniformly set to 0.01.
Here is the code to produce such a visualization.
>>> from scattertext import word_similarity_explorer
>>> html = word_similarity_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... target_term='jobs',
... minimum_term_frequency=5,
... pmi_threshold_coefficient=4,
... width_in_pixels=1000,
... metadata=convention_df['speaker'],
... alpha=0.01,
... max_p_val=0.05,
... save_svg_button=True)
>>> open("Convention-Visualization-Jobs.html", 'wb').write(html.encode('utf-8'))
Scattertext can interface with Gensim Word2Vec models. For example, here's a snippet from demo_gensim_similarity.py which illustrates how to train and use a word2vec model on a corpus. Note the similarities produced reflect quirks of the corpus, eg, "8" tends to refer to the 8% unemployment rate at the time of the convention.
import spacy
from gensim . models import word2vec
from scattertext import SampleCorpora , word_similarity_explorer_gensim , Word2VecFromParsedCorpus
from scattertext . CorpusFromParsedDocuments import CorpusFromParsedDocuments
nlp = spacy . en . English ()
convention_df = SampleCorpora . ConventionData2012 . get_data ()
convention_df [ 'parsed' ] = convention_df . text . apply ( nlp )
corpus = CorpusFromParsedDocuments ( convention_df , category_col = 'party' , parsed_col = 'parsed' ). build ()
model = word2vec . Word2Vec ( size = 300 ,
alpha = 0.025 ,
window = 5 ,
min_count = 5 ,
max_vocab_size = None ,
sample = 0 ,
seed = 1 ,
workers = 1 ,
min_alpha = 0.0001 ,
sg = 1 ,
hs = 1 ,
negative = 0 ,
cbow_mean = 0 ,
iter = 1 ,
null_word = 0 ,
trim_rule = None ,
sorted_vocab = 1 )
html = word_similarity_explorer_gensim ( corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
target_term = 'jobs' ,
minimum_term_frequency = 5 ,
pmi_threshold_coefficient = 4 ,
width_in_pixels = 1000 ,
metadata = convention_df [ 'speaker' ],
word2vec = Word2VecFromParsedCorpus ( corpus , model ). train (),
max_p_val = 0.05 ,
save_svg_button = True )
open ( './demo_gensim_similarity.html' , 'wb' ). write ( html . encode ( 'utf-8' ))How Democrats and Republicans talked differently about "jobs" in their 2012 convention speeches.
We can use Scattertext to visualize alternative types of word scores, and ensure that 0 scores are greyed out. Use the sparse_explroer function to acomplish this, and see its source code for more details.
>>> from sklearn.linear_model import Lasso
>>> from scattertext import sparse_explorer
>>> html = sparse_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... scores = corpus.get_regression_coefs('democrat', Lasso(max_iter=10000)),
... minimum_term_frequency=5,
... pmi_threshold_coefficient=4,
... width_in_pixels=1000,
... metadata=convention_df['speaker'])
>>> open('./Convention-Visualization-Sparse.html', 'wb').write(html.encode('utf-8'))
You can also use custom term positions and axis labels. For example, you can base terms' y-axis positions on a regression coefficient and their x-axis on term frequency and label the axes accordingly. The one catch is that axis positions must be scaled between 0 and 1.
First, let's define two scaling functions: scale to project positive values to [0,1], and zero_centered_scale project real values to [0,1], with negative values always <0.5, and positive values always >0.5.
>>> def scale(ar):
... return (ar - ar.min()) / (ar.max() - ar.min())
...
>>> def zero_centered_scale(ar):
... ar[ar > 0] = scale(ar[ar > 0])
... ar[ar < 0] = -scale(-ar[ar < 0])
... return (ar + 1) / 2.
Next, let's compute and scale term frequencies and L2-penalized regression coefficients. We'll hang on to the original coefficients and allow users to view them by mousing over terms.
>>> from sklearn.linear_model import LogisticRegression
>>> import numpy as np
>>>
>>> frequencies_scaled = scale(np.log(term_freq_df.sum(axis=1).values))
>>> scores = corpus.get_logreg_coefs('democrat',
... LogisticRegression(penalty='l2', C=10, max_iter=10000, n_jobs=-1))
>>> scores_scaled = zero_centered_scale(scores)
Finally, we can write the visualization. Note the use of the x_coords and y_coords parameters to store the respective coordinates, the scores and sort_by_dist arguments to register the original coefficients and use them to rank the terms in the right-hand list, and the x_label and y_label arguments to label axes.
>>> html = produce_scattertext_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... minimum_term_frequency=5,
... pmi_threshold_coefficient=4,
... width_in_pixels=1000,
... x_coords=frequencies_scaled,
... y_coords=scores_scaled,
... scores=scores,
... sort_by_dist=False,
... metadata=convention_df['speaker'],
... x_label='Log frequency',
... y_label='L2-penalized logistic regression coef')
>>> open('demo_custom_coordinates.html', 'wb').write(html.encode('utf-8'))
The Emoji analysis capability displays a chart of the category-specific distribution of Emoji. Let's look at a new corpus, a set of tweets. We'll build a visualization showing how men and women use emoji differently.
Note: the following example is implemented in demo_emoji.py .
First, we'll load the dataset and parse it using NLTK's tweet tokenizer. Note, install NLTK before running this example. It will take some time for the dataset to download.
import nltk , urllib . request , io , agefromname , zipfile
import scattertext as st
import pandas as pd
with zipfile . ZipFile ( io . BytesIO ( urllib . request . urlopen (
'http://followthehashtag.com/content/uploads/USA-Geolocated-tweets-free-dataset-Followthehashtag.zip'
). read ())) as zf :
df = pd . read_excel ( zf . open ( 'dashboard_x_usa_x_filter_nativeretweets.xlsx' ))
nlp = st . tweet_tokenzier_factory ( nltk . tokenize . TweetTokenizer ())
df [ 'parse' ] = df [ 'Tweet content' ]. apply ( nlp )
df . iloc [ 0 ]
'''
Tweet Id 721318437075685382
Date 2016-04-16
Hour 12:44
User Name Bill Schulhoff
Nickname BillSchulhoff
Bio Husband,Dad,GrandDad,Ordained Minister, Umpire...
Tweet content Wind 3.2 mph NNE. Barometer 30.20 in, Rising s...
Favs NaN
RTs NaN
Latitude 40.7603
Longitude -72.9547
Country US
Place (as appears on Bio) East Patchogue, NY
Profile picture http://pbs.twimg.com/profile_images/3788000007...
Followers 386
Following 705
Listed 24
Tweet language (ISO 639-1) en
Tweet Url http://www.twitter.com/BillSchulhoff/status/72...
parse Wind 3.2 mph NNE. Barometer 30.20 in, Rising s...
Name: 0, dtype: object
''' Next, we'll use the AgeFromName package to find the probabilities of the gender of each user given their first name. First, we'll find a dataframe indexed on first names that contains the probability that each someone with that first name is male ( male_prob ).
male_prob = agefromname . AgeFromName (). get_all_name_male_prob ()
male_prob . iloc [ 0 ]
'''
hi 1.00000
lo 0.95741
prob 1.00000
Name: aaban, dtype: float64
''' Next, we'll extract the first names of each user, and use the male_prob data frame to find users whose names indicate there is at least a 90% chance they are either male or female, label those users, and create new data frame df_mf with only those users.
df [ 'first_name' ] = df [ 'User Name' ]. apply ( lambda x : x . split ()[ 0 ]. lower () if type ( x ) == str and len ( x . split ()) > 0 else x )
df_aug = pd . merge ( df , male_prob , left_on = 'first_name' , right_index = True )
df_aug [ 'gender' ] = df_aug [ 'prob' ]. apply ( lambda x : 'm' if x > 0.9 else 'f' if x < 0.1 else '?' )
df_mf = df_aug [ df_aug [ 'gender' ]. isin ([ 'm' , 'f' ])] The key to this analysis is to construct a corpus using only the emoji extractor st.FeatsFromSpacyDocOnlyEmoji which builds a corpus only from emoji and not from anything else.
corpus = st . CorpusFromParsedDocuments (
df_mf ,
parsed_col = 'parse' ,
category_col = 'gender' ,
feats_from_spacy_doc = st . FeatsFromSpacyDocOnlyEmoji ()
). build () Next, we'll run this through a standard produce_scattertext_explorer visualization generation.
html = st . produce_scattertext_explorer (
corpus ,
category = 'f' ,
category_name = 'Female' ,
not_category_name = 'Male' ,
use_full_doc = True ,
term_ranker = st . OncePerDocFrequencyRanker ,
sort_by_dist = False ,
metadata = ( df_mf [ 'User Name' ]
+ ' (@' + df_mf [ 'Nickname' ] + ') '
+ df_mf [ 'Date' ]. astype ( str )),
width_in_pixels = 1000
)
open ( "EmojiGender.html" , 'wb' ). write ( html . encode ( 'utf-8' ))SentencePiece tokenization is a subword tokenization technique which relies on a language-model to produce optimized tokenization. It has been used in large, transformer-based contextual language models.
Ensure to run $ pip install sentencepiece before running this example.
First, let's load the political convention data set as normal.
import tempfile
import re
import scattertext as st
convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
convention_df [ 'parse' ] = convention_df . text . apply ( st . whitespace_nlp_with_sentences ) Next, let's train a SentencePiece tokenizer based on this data. The train_sentence_piece_tokenizer function trains a SentencePieceProcessor on the data set and returns it. You can of course use any SentencePieceProcessor.
def train_sentence_piece_tokenizer ( documents , vocab_size ):
'''
:param documents: list-like, a list of str documents
:vocab_size int: the size of the vocabulary to output
:return sentencepiece.SentencePieceProcessor
'''
import sentencepiece as spm
sp = None
with tempfile . NamedTemporaryFile ( delete = True ) as tempf :
with tempfile . NamedTemporaryFile ( delete = True ) as tempm :
tempf . write (( ' n ' . join ( documents )). encode ())
spm . SentencePieceTrainer . Train (
'--input=%s --model_prefix=%s --vocab_size=%s' % ( tempf . name , tempm . name , vocab_size )
)
sp = spm . SentencePieceProcessor ()
sp . load ( tempm . name + '.model' )
return sp
sp = train_sentence_piece_tokenizer ( convention_df . text . values , vocab_size = 2000 ) Next, let's add the SentencePiece tokens as metadata when creating our corpus. In order to do this, pass a FeatsFromSentencePiece instance into the feats_from_spacy_doc parameter. Pass the SentencePieceProcessor into the constructor.
corpus = st . CorpusFromParsedDocuments ( convention_df ,
parsed_col = 'parse' ,
category_col = 'party' ,
feats_from_spacy_doc = st . FeatsFromSentencePiece ( sp )). build ()Now we can create the SentencePiece token scatter plot.
html = st . produce_scattertext_explorer (
corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
sort_by_dist = False ,
metadata = convention_df [ 'party' ] + ': ' + convention_df [ 'speaker' ],
term_scorer = st . RankDifference (),
transform = st . Scalers . dense_rank ,
use_non_text_features = True ,
use_full_doc = True ,
)Suppose you'd like to audit or better understand weights or importances given to bag-of-words features by a classifier.
It's easy to use Scattertext to do, if you use a Scikit-learn-style classifier.
For example the Lighting package makes available high-performance linear classifiers which are have Scikit-compatible interfaces.
First, let's import sklearn 's text feature extraction classes, the 20 Newsgroup corpus, Lightning's Primal Coordinate Descent classifier, and Scattertext. We'll also fetch the training portion of the Newsgroup corpus.
from lightning . classification import CDClassifier
from sklearn . datasets import fetch_20newsgroups
from sklearn . feature_extraction . text import CountVectorizer , TfidfVectorizer
import scattertext as st
newsgroups_train = fetch_20newsgroups (
subset = 'train' ,
remove = ( 'headers' , 'footers' , 'quotes' )
)Next, we'll tokenize our corpus twice. Once into tfidf features which will be used to train the classifier, an another time into ngram counts that will be used by Scattertext. It's important that both vectorizers share the same vocabulary, since we'll need to apply the weight vector from the model onto our Scattertext Corpus.
vectorizer = TfidfVectorizer ()
tfidf_X = vectorizer . fit_transform ( newsgroups_train . data )
count_vectorizer = CountVectorizer ( vocabulary = vectorizer . vocabulary_ ) Next, we use the CorpusFromScikit factory to build a Scattertext Corpus object. Ensure the X parameter is a document-by-feature matrix. The argument to the y parameter is an array of class labels. Each label is an integer representing a different news group. We the feature_vocabulary is the vocabulary used by the vectorizers. The category_names are a list of the 20 newsgroup names which as a class-label list. The raw_texts is a list of the text of newsgroup texts.
corpus = st . CorpusFromScikit (
X = count_vectorizer . fit_transform ( newsgroups_train . data ),
y = newsgroups_train . target ,
feature_vocabulary = vectorizer . vocabulary_ ,
category_names = newsgroups_train . target_names ,
raw_texts = newsgroups_train . data
). build () Now, we can train the model on tfidf_X and the categoricla response variable, and capture feature weights for category 0 ("alt.atheism").
clf = CDClassifier ( penalty = "l1/l2" ,
loss = "squared_hinge" ,
multiclass = True ,
max_iter = 20 ,
alpha = 1e-4 ,
C = 1.0 / tfidf_X . shape [ 0 ],
tol = 1e-3 )
clf . fit ( tfidf_X , newsgroups_train . target )
term_scores = clf . coef_ [ 0 ]Finally, we can create a Scattertext plot. We'll use the Monroe-style visualization, and automatically select around 4000 terms that encompass the set of frequent terms, terms with high absolute scores, and terms that are characteristic of the corpus.
html = st . produce_frequency_explorer (
corpus ,
'alt.atheism' ,
scores = term_scores ,
use_term_significance = False ,
terms_to_include = st . AutoTermSelector . get_selected_terms ( corpus , term_scores , 4000 ),
metadata = [ '/' . join ( fn . split ( '/' )[ - 2 :]) for fn in newsgroups_train . filenames ]
)Let's take a look at the performance of the classifier:
newsgroups_test = fetch_20newsgroups ( subset = 'test' ,
remove = ( 'headers' , 'footers' , 'quotes' ))
X_test = vectorizer . transform ( newsgroups_test . data )
pred = clf . predict ( X_test )
f1 = f1_score ( pred , newsgroups_test . target , average = 'micro' )
print ( "Microaveraged F1 score" , f1 )Microaveraged F1 score 0.662108337759. Not bad over a ~0.05 baseline.
Please see Signo for an introduction to semiotic squares.
Some variants of the semiotic square-creator are can be seen in this notebook, which studies words and phrases in headlines that had low or high Facebook engagement and were published by either BuzzFeed or the New York Times: [http://nbviewer.jupyter.org/github/JasonKessler/PuPPyTalk/blob/master/notebooks/Explore-Headlines.ipynb]
The idea behind the semiotic square is to express the relationship between two opposing concepts and concepts things within a larger domain of a discourse. Examples of opposed concepts life or death, male or female, or, in our example, positive or negative sentiment. Semiotics squares are comprised of four "corners": the upper two corners are the opposing concepts, while the bottom corners are the negation of the concepts.
Circumscribing the negation of a concept involves finding everything in the domain of discourse that isn't associated with the concept. For example, in the life-death opposition, one can consider the universe of discourse to be all animate beings, real and hypothetical. The not-alive category will cover dead things, but also hypothetical entities like fictional characters or sentient AIs.
In building lexicalized semiotic squares, we consider concepts to be documents labeled in a corpus. Documents, in this setting, can belong to one of three categories: two labels corresponding to the opposing concepts, a neutral category, indicating a document is in the same domain as the opposition, but cannot fall into one of opposing categories.
In the example below positive and negative movie reviews are treated as the opposing categories, while plot descriptions of the same movies are treated as the neutral category.
Terms associated with one of the two opposing categories (relative only to the other) are listed as being associated with that category. Terms associated with a netural category (eg, not positive) are terms which are associated with the disjunction of the opposite category and the neutral category. For example, not-positive terms are those most associated with the set of negative reviews and plot descriptions vs. positive reviews.
Common terms among adjacent corners of the square are also listed.
An HTML-rendered square is accompanied by a scatter plot. Points on the plot are terms. The x-axis is the Z-score of the association to one of the opposed concepts. The y-axis is the Z-score how associated a term is with the neutral set of documents relative to the opposed set. A point's red-blue color indicate the term's opposed-association, while the more desaturated a term is, the more it is associated with the neutral set of documents.
Update to version 2.2: terms are colored by their nearest semiotic categories across the eight corresponding radial sectors.
import scattertext as st
movie_df = st . SampleCorpora . RottenTomatoes . get_data ()
movie_df . category = movie_df . category . apply
( lambda x : { 'rotten' : 'Negative' , 'fresh' : 'Positive' , 'plot' : 'Plot' }[ x ])
corpus = st . CorpusFromPandas (
movie_df ,
category_col = 'category' ,
text_col = 'text' ,
nlp = st . whitespace_nlp_with_sentences
). build (). get_unigram_corpus ()
semiotic_square = st . SemioticSquare (
corpus ,
category_a = 'Positive' ,
category_b = 'Negative' ,
neutral_categories = [ 'Plot' ],
scorer = st . RankDifference (),
labels = { 'not_a_and_not_b' : 'Plot Descriptions' , 'a_and_b' : 'Reviews' }
)
html = st . produce_semiotic_square_explorer ( semiotic_square ,
category_name = 'Positive' ,
not_category_name = 'Negative' ,
x_label = 'Fresh-Rotten' ,
y_label = 'Plot-Review' ,
neutral_category_name = 'Plot Description' ,
metadata = movie_df [ 'movie_name' ])There are a number of other types of semiotic square construction functions. Again, please see https://nbviewer.org/github/JasonKessler/PuPPyTalk/blob/master/notebooks/Explore-Headlines.ipynb for an overview of these.
A frequently requested feature of Scattertext has been the ability to visualize topic models. While this capability has existed in some forms (eg, the Empath visualization), I've finally gotten around to implementing a concise API for such a visualization. There are three main ways to visualize topic models using Scattertext. The first is the simplest: manually entering topic models and visualizing them. The second uses a Scikit-Learn pipeline to produce the topic models for visualization. The third is a novel topic modeling technique, based on finding terms similar to a custom set of seed terms.
If you have already created a topic model, simply structure it as a dictionary. This dictionary is keyed on string which serve as topic titles and are displayed in the main scatterplot. The values are lists of words that belong to that topic. The words that are in each topic list are bolded when they appear in a snippet.
Note that currently, there is no support for keyword scores.
For example, one might manually the following topic models to explore in the Convention corpus:
topic_model = {
'money' : [ 'money' , 'bank' , 'banks' , 'finances' , 'financial' , 'loan' , 'dollars' , 'income' ],
'jobs' : [ 'jobs' , 'workers' , 'labor' , 'employment' , 'worker' , 'employee' , 'job' ],
'patriotic' : [ 'america' , 'country' , 'flag' , 'americans' , 'patriotism' , 'patriotic' ],
'family' : [ 'mother' , 'father' , 'mom' , 'dad' , 'sister' , 'brother' , 'grandfather' , 'grandmother' , 'son' , 'daughter' ]
} We can use the FeatsFromTopicModel class to transform this topic model into one which can be visualized using Scattertext. This is used just like any other feature builder, and we pass the topic model object into produce_scattertext_explorer .
import scattertext as st
topic_feature_builder = st.FeatsFromTopicModel(topic_model)
topic_corpus = st.CorpusFromParsedDocuments(
convention_df,
category_col='party',
parsed_col='parse',
feats_from_spacy_doc=topic_feature_builder
).build()
html = st.produce_scattertext_explorer(
topic_corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
width_in_pixels=1000,
metadata=convention_df['speaker'],
use_non_text_features=True,
use_full_doc=True,
pmi_threshold_coefficient=0,
topic_model_term_lists=topic_feature_builder.get_top_model_term_lists()
)
Since topic modeling using document-level coocurence generally produces poor results, I've added a SentencesForTopicModeling class which allows clusterting by coocurence at the sentence-level. It requires a ParsedCorpus object to be passed to its constructor, and creates a term-sentence matrix internally.
Next, you can create a topic model dictionary like the one above by passing in a Scikit-Learn clustering or dimensionality reduction pipeline. The only constraint is the last transformer in the pipeline must populate a components_ attribute.
The num_topics_per_term attribute specifies how many terms should be added to a list.
In the following example, we'll use NMF to cluster a stoplisted, unigram corpus of documents, and use the topic model dictionary to create a FeatsFromTopicModel , just like before.
Note that in produce_scattertext_explorer , we make the topic_model_preview_size 20 in order to show a preview of the first 20 terms in the topic in the snippet view as opposed to the default 10.
from sklearn . decomposition import NMF
from sklearn . feature_extraction . text import TfidfTransformer
from sklearn . pipeline import Pipeline
convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
convention_df [ 'parse' ] = convention_df [ 'text' ]. apply ( st . whitespace_nlp_with_sentences )
unigram_corpus = ( st . CorpusFromParsedDocuments ( convention_df ,
category_col = 'party' ,
parsed_col = 'parse' )
. build (). get_stoplisted_unigram_corpus ())
topic_model = st . SentencesForTopicModeling ( unigram_corpus ). get_topics_from_model (
Pipeline ([
( 'tfidf' , TfidfTransformer ( sublinear_tf = True )),
( 'nmf' , ( NMF ( n_components = 100 , alpha = .1 , l1_ratio = .5 , random_state = 0 )))
]),
num_terms_per_topic = 20
)
topic_feature_builder = st . FeatsFromTopicModel ( topic_model )
topic_corpus = st . CorpusFromParsedDocuments (
convention_df ,
category_col = 'party' ,
parsed_col = 'parse' ,
feats_from_spacy_doc = topic_feature_builder
). build ()
html = st . produce_scattertext_explorer (
topic_corpus ,
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
width_in_pixels = 1000 ,
metadata = convention_df [ 'speaker' ],
use_non_text_features = True ,
use_full_doc = True ,
pmi_threshold_coefficient = 0 ,
topic_model_term_lists = topic_feature_builder . get_top_model_term_lists (),
topic_model_preview_size = 20
)A surprisingly easy way to generate good topic models is to use a term scoring formula to find words that are associated with sentences where a seed word occurs vs. where one doesn't occur.
Given a custom term list, the SentencesForTopicModeling.get_topics_from_terms will generate a series of topics. Note that the dense rank difference ( RankDifference ) works particularly well for this task, and is the default parameter.
term_list = [ 'obama' , 'romney' , 'democrats' , 'republicans' , 'health' , 'military' , 'taxes' ,
'education' , 'olympics' , 'auto' , 'iraq' , 'iran' , 'israel' ]
unigram_corpus = ( st . CorpusFromParsedDocuments ( convention_df ,
category_col = 'party' ,
parsed_col = 'parse' )
. build (). get_stoplisted_unigram_corpus ())
topic_model = ( st . SentencesForTopicModeling ( unigram_corpus )
. get_topics_from_terms ( term_list ,
scorer = st . RankDifference (),
num_terms_per_topic = 20 ))
topic_feature_builder = st . FeatsFromTopicModel ( topic_model )
# The remaining code is identical to two examples above. See demo_word_list_topic_model.py
# for the complete example. Scattertext makes it easy to create word-similarity plots using projections of word embeddings as the x and y-axes. In the example below, we create a stop-listed Corpus with only unigram terms. The produce_projection_explorer function by uses Gensim to create word embeddings and then projects them to two dimentions using Uniform Manifold Approximation and Projection (UMAP).
UMAP is chosen over T-SNE because it can employ the cosine similarity between two word vectors instead of just the euclidean distance.
convention_df = st . SampleCorpora . ConventionData2012 . get_data ()
convention_df [ 'parse' ] = convention_df [ 'text' ]. apply ( st . whitespace_nlp_with_sentences )
corpus = ( st . CorpusFromParsedDocuments ( convention_df , category_col = 'party' , parsed_col = 'parse' )
. build (). get_stoplisted_unigram_corpus ())
html = st . produce_projection_explorer ( corpus , category = 'democrat' , category_name = 'Democratic' ,
not_category_name = 'Republican' , metadata = convention_df . speaker ) In order to use custom word embedding functions or projection functions, pass models into the word2vec_model and projection_model parameters. In order to use T-SNE, for example, use projection_model=sklearn.manifold.TSNE() .
import umap
from gensim . models . word2vec import Word2Vec
html = st . produce_projection_explorer ( corpus ,
word2vec_model = Word2Vec ( size = 100 , window = 5 , min_count = 10 , workers = 4 ),
projection_model = umap . UMAP ( min_dist = 0.5 , metric = 'cosine' ),
category = 'democrat' ,
category_name = 'Democratic' ,
not_category_name = 'Republican' ,
metadata = convention_df . speaker ) Term positions can also be determined by the positions of terms according to the output of principal component analysis, and produce_projection_explorer also supports this functionality. We'll look at how axes transformations ("scalers" in Scattertext terminology) can make it easier to inspect the output of PCA.
We'll use the 2012 Conventions corpus for these visualizations. Only unigrams occurring in at least three documents will be considered.
>>> convention_df = st.SampleCorpora.ConventionData2012.get_data()
>>> convention_df['parse'] = convention_df['text'].apply(st.whitespace_nlp_with_sentences)
>>> corpus = (st.CorpusFromParsedDocuments(convention_df,
... category_col='party',
... parsed_col='parse')
... .build()
... .get_stoplisted_unigram_corpus()
... .remove_infrequent_words(minimum_term_count=3, term_ranker=st.OncePerDocFrequencyRanker))
Next, we use scikit-learn's tf-idf transformer to find very simple, sparse embeddings for all of these words. Since, we input a #docs x #terms matrix to the transformer, we can transpose it to get a proper term-embeddings matrix, where each row corresponds to a term, and the columns correspond to document-specific tf-idf scores.
>>> from sklearn.feature_extraction.text import TfidfTransformer
>>> embeddings = TfidfTransformer().fit_transform(corpus.get_term_doc_mat())
>>> embeddings.shape
(189, 2159)
>>> corpus.get_num_docs(), corpus.get_num_terms()
(189, 2159)
>>> embeddings = embeddings.T
>>> embeddings.shape
(2159, 189)
Given these spare embeddings, we can apply sparse singular value decomposition to extract three factors. SVD outputs factorizes the term embeddings matrix into three matrices, U, Σ, and VT. Importantly, the matrix U provides the singular values for each term, and VT provides them for each document, and Σ is a vector of the singular values.
>>> from scipy.sparse.linalg import svds
>>> U, S, VT = svds(embeddings, k = 3, maxiter=20000, which='LM')
>>> U.shape
(2159, 3)
>>> S.shape
(3,)
>>> VT.shape
(3, 189)
We'll look at the first two singular values, plotting each term such that the x-axis position is the first singular value, and the y-axis term is the second. To do this, we make a "projection" data frame, where the x and y columns store the first two singular values, and key the data frame on each term. This controls the term positions on the chart.
>>> x_dim = 0; y_dim = 1;
>>> projection = pd.DataFrame({'term':corpus.get_terms(),
... 'x':U.T[x_dim],
... 'y':U.T[y_dim]}).set_index('term')
We'll use the produce_pca_explorer function to visualize these. Note we include the projection object, and specify which singular values were used for x and y ( x_dim and y_dim ) so we they can be labeled in the interactive visualization.
html = st.produce_pca_explorer(corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
projection=projection,
metadata=convention_df['speaker'],
width_in_pixels=1000,
x_dim=x_dim,
y_dim=y_dim)
Click for an interactive visualization.
We can easily re-scale the plot in order to make more efficient use of space. For example, passing in scaler=scale_neg_1_to_1_with_zero_mean will make all four quadrants take equal area.
html = st.produce_pca_explorer(corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
projection=projection,
metadata=convention_df['speaker'],
width_in_pixels=1000,
scaler=st.scale_neg_1_to_1_with_zero_mean,
x_dim=x_dim,
y_dim=y_dim)
Click for an interactive visualization.
To export the content of a scattertext explorer object (ScattertextStructure) to matplotlib you can use produce_scattertext_pyplot . The function returns a matplotlib.figure.Figure object which can be visualized using plt.show or plt.savefig as in the example below.
Note that installation of textalloc==0.0.3 and matplotlib>=3.6.0 is required before running this.
convention_df = st.SampleCorpora.ConventionData2012.get_data().assign(
parse = lambda df: df.text.apply(st.whitespace_nlp_with_sentences)
)
corpus = st.CorpusFromParsedDocuments(convention_df, category_col='party', parsed_col='parse').build()
scattertext_structure = st.produce_scattertext_explorer(
corpus,
category='democrat',
category_name='Democratic',
not_category_name='Republican',
minimum_term_frequency=5,
pmi_threshold_coefficient=8,
width_in_pixels=1000,
return_scatterplot_structure=True,
)
fig = st.produce_scattertext_pyplot(scattertext_structure)
fig.savefig('pyplot_export.png', format='png')
[]
Please see the examples in the PyData 2017 Tutorial on Scattertext.
Cozy: The Collection Synthesizer (Loncaric 2016) was used to help determine which terms could be labeled without overlapping a circle or another label. It automatically built a data structure to efficiently store and query the locations of each circle and labeled term.
The script to build rectangle-holder.js was
fields ax1 : long, ay1 : long, ax2 : long, ay2 : long
assume ax1 < ax2 and ay1 < ay2
query findMatchingRectangles(bx1 : long, by1 : long, bx2 : long, by2 : long)
assume bx1 < bx2 and by1 < by2
ax1 < bx2 and ax2 > bx1 and ay1 < by2 and ay2 > by1
And it was called using
$ python2.7 src/main.py <script file name> --enable-volume-trees
--js-class RectangleHolder --enable-hamt --enable-arrays --js rectangle_holder.js
Adding in code to ensure that term statistics will show up even if no documents are present in visualization.
Better axis labeling (see demo_axis_crossbars_and_labels.py).
Pytextrank compatibility
Ensuring Pandas 1.0 compatibility fixing Issue #51 and scikit-learn stopwords import issue in #49.
AssociationCompactorByRank , TermCategoryRanker . terms_to_show parameter use_categories_as_metadata_and_replace_terms to TermDocMatrix .get_metadata_doc_count_df and get_metadata_count_mat to TermDocMatrix produce_pairplot ScatterChart.hide_terms(terms: iter[str]) which enables selected terms to be hidden from the chart.ScatterChartData.score_transform to specify the function which can change an original score into a value between 0 and 1 used for term coloring. alternative_term_func to produce_scattertext_explorer which allows you to inject a function that activates when a term is clicked.HedgesG , and unbiased version of Cohen's d which is a subclass of CohensD .frequency_transform parameter to produce_frequency_explorer . This defaults to a log transform, but allows you to use any way your heart desires to order terms along the x-axis. show_category_headings=True to produce_scattertext_explorer . Setting this to False suppresses the list of categories which will be displayed in the term context area.div_name argument to produce_scattertext_explorer and name-spaced important divs and classes by div_name in HTML templates and Javascript.show_cross_axes=True to produce_scattertext_explorer . Setting this to False prevents the cross axes from being displayed if show_axes is True .TermDocMatrix.get_metadata_freq_df now accepts the label_append argument which by default adds ' freq' to the end of each column.TermDocMatrix.get_num_cateogires returns the number of categories in a term-document matrix. Added the following methods:
TermDocMatrixWithoutCategories.get_num_metadataTermDocMatrix.use_metadata_as_categoriesunified_context argument in produce_scattertext_explorer lists all contexts in a single column. This let's you see snippets organized by multiple categories in a single column. See demo_unified_context.py for an example. Added a series of objects to handle uncategorized corpora. Added section on Document-Based Scatterplots, and the add_doc_names_as_metadata function. CategoryColorAssigner was also added to assign colors to a qualitative categories.
A number of new term scoring approaches including RelativeEntropy (a direct implementation of Frankhauser et al. ( 2014)), and ZScores and implementation of the Z-Score model used in Frankhauser et al.
TermDocMatrix.get_metadata_freq_df() returns a metadata-doc corpus.
CorpusBasedTermScorer.set_ranker allows you to use a different term ranker when finding corpus-based scores. This not only lets these scorers with metadata, but also allows you to integrate once-per-document counts.
Fixed produce_projection_explorer such that it can work with a predefined set of term embeddings. This can allow, for example, the easy exploration of one hot-encoded term embeddings in addition to arbitrary lower-dimensional embeddings.
Added add_metadata to TermDocMatrix in order to inject meta data after a TermDocMatrix object has been created.
Made sure tooltip never started above the top of the web page.
Added DomainCompactor .
Fixed bug #31, enabling context to show when metadata value is clicked.
Enabled display of terms in topic models in explorer, along with the the display of customized topic models. Please see Visualizing topic models for an overview of the additions.
Removed pkg_resources from Phrasemachine, corrected demo_phrase_machine.py
Now compatible with Gensim 3.4.0.
Added characteristic explorer, produce_characteristic_explorer , to plot terms with their characteristic scores on the x-axis and their class-association scores on the y-axis. See Ordering Terms by Corpus Characteristicness for more details.
Added TermCategoryFrequencies in response to Issue 23. Please see Visualizing differences based on only term frequencies for more details.
Added x_axis_labels and y_axis_labels parameters to produce_scattertext_explorer . These let you include evenly-spaced string axis labels on the chart, as opposed to just "Low", "Medium" and "High". These rely on d3's ticks function, which can behave unpredictable. Caveat usor.
Semiotic Squares now look better, and have customizable labels.
Incorporated the General Inquirer lexicon. Apenas para uso não comercial. The lexicon is downloaded from their homepage at the start of each use. See demo_general_inquierer.py .
Incorporated Phrasemachine from AbeHandler (Handler et al. 2016). For the license, please see PhraseMachineLicense.txt . For an example, please see demo_phrase_machine.py .
Added CompactTerms for removing redundant and infrequent terms from term document matrices. These occur if a word or phrase is always part of a larger phrase; the shorter phrase is considered redundant and removed from the corpus. See demo_phrase_machine.py for an example.
Added FourSquare , a pattern that allows for the creation of a semiotic square with separate categories for each corner. Please see demo_four_square.py for an early example.
Finally, added a way to easily perform T-SNE-style visualizations on a categorized corpus. This uses, by default, the umap-learn package. Please see demo_tsne_style.py.
Fixed to ScaledFScorePresets(one_to_neg_one=True) , added UnigramsFromSpacyDoc .
Now, when using CorpusFromPandas , a CorpusDF object is returned, instead of a Corpus object. This new type of object keeps a reference to the source data frame, and returns it via the CorpusDF.get_df() method.
The factory CorpusFromFeatureDict was added. It allows you to directly specify term counts and metadata item counts within the dataframe. Please see test_corpusFromFeatureDict.py for an example.
Added a very semiotic square creator.
The idea to build a semiotic square that contrasts two categories in a Term Document Matrix while using other categories as neutral categories.
See Creating semiotic squares for an overview on how to use this functionality and semiotic squares.
Added a parameter to disable the display of the top-terms sidebar, eg, produce_scattertext_explorer(..., show_top_terms=False, ...) .
An interface to part of the subjectivity/sentiment dataset from Bo Pang and Lillian Lee. ``A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts''. ACL. 2004. See SampleCorpora.RottenTomatoes .
Fixed bug that caused tooltip placement to be off after scrolling.
Made category_name and not_category_name optional in produce_scattertext_explorer etc.
Created the ability to customize tooltips via the get_tooltip_content argument to produce_scattertext_explorer etc., control axes labels via x_axis_values and y_axis_values . The color_func parameter is a Javascript function to control color of a point. Function takes a parameter which is a dictionary entry produced by ScatterChartExplorer.to_dict and returns a string.
Integration with Scikit-Learn's text-analysis pipeline led the creation of the CorpusFromScikit and TermDocMatrixFromScikit classes.
The AutoTermSelector class to automatically suggest terms to appear in the visualization.
This can make it easier to show large data sets, and remove fiddling with the various minimum term frequency parameters.
For an example of how to use CorpusFromScikit and AutoTermSelector , please see demo_sklearn.py
Also, I updated the library and examples to be compatible with spaCy 2.
Fixed bug when processing single-word documents, and set the default beta to 2.
Added produce_frequency_explorer function, and adding the PEP 369-compliant __version__ attribute as mentioned in #19. Fixed bug when creating visualizations with more than two possible categories. Now, by default, category names will not be title-cased in the visualization, but will retain their original case.
If you'd still like to do this this, use ScatterChart (or a descendant).to_dict(..., title_case_names=True) . Fixed DocsAndLabelsFromCorpus for Py 2 compatibility.
Fixed bugs in chinese_nlp when jieba has already been imported and in p-value computation when performing log-odds-ratio w/ prior scoring.
Added demo for performing a Monroe et. al (2008) style visualization of log-odds-ratio scores in demo_log_odds_ratio_prior.py .
Breaking change: pmi_filter_thresold has been replaced with pmi_threshold_coefficient .
Added Emoji and Tweet analysis. See Emoji analysis.
Characteristic terms falls back ot "Most frequent" if no terms used in the chart are present in the background corpus.
Fixed top-term calculation for custom scores.
Set scaled f-score's default beta to 0.5.
Added --spacy_language_model argument to the CLI.
Added the alternative_text_field option in produce_scattertext_explorer to show an alternative text field when showing contexts in the interactive HTML visualization.
Updated ParsedCorpus.get_unigram_corpus to allow for continued alternative_text_field functionality.
Added ability to for Scattertext to use noun chunks instead of unigrams and bigrams through the FeatsFromSpacyDocOnlyNounChunks class. In order to use it, run your favorite Corpus or TermDocMatrix factory, and pass in an instance of the class as a parameter:
st.CorpusFromParsedDocuments(..., feats_from_spacy_doc=st.FeatsFromSpacyDocOnlyNounChunks())
Fixed a bug in corpus construction that occurs when the last document has no features.
Now you don't have to install tinysegmenter to use Scattertext. But you need to install it if you want to parse Japanese. This caused a problem when Scattertext was being installed on Windows.
Added TermDocMatrix.get_corner_score , giving an improved version of the Rudder Score. Exposing whitespace_nlp_with_sentences . It's a lightweight bad regex sentence splitter built a top a bad regex tokenizer that somewhat apes spaCy's API. Use it if you don't have spaCy and the English model downloaded or if you care more about memory footprint and speed than accuracy.
It's not compatible with word_similarity_explorer but is compatible with `word_similarity_explorer_gensim'.
Tweaked scaled f-score normalization.
Fixed Javascript bug when clicking on '$'.
Fixed bug in Scaled F-Score computations, and changed computation to better score words that are inversely correlated to category.
Added Word2VecFromParsedCorpus to automate training Gensim word vectors from a corpus, and
word_similarity_explorer_gensim to produce the visualization.
See demo_gensim_similarity.py for an example.
Added the d3_url and d3_scale_chromatic_url parameters to produce_scattertext_explorer . This provides a way to manually specify the paths to "d3.js" (ie, the file from "https://cdnjs.cloudflare.com/ajax/libs/d3/4.6.0/d3.min.js") and "d3-scale-chromatic.v1.js" (ie, the file from "https://d3js.org/d3-scale-chromatic.v1.min.js").
This is important if you're getting the error:
Javascript error adding output!
TypeError: d3.scaleLinear is not a function
See your browser Javascript console for more details.
It also lets you use Scattertext if you're serving in an environment with no (or a restricted) external Internet connection.
For example, if "d3.min.js" and "d3-scale-chromatic.v1.min.js" were present in the current working directory, calling the following code would reference them locally instead of the remote Javascript files. See Visualizing term associations for code context.
>>> html = st.produce_scattertext_explorer(corpus,
... category='democrat',
... category_name='Democratic',
... not_category_name='Republican',
... width_in_pixels=1000,
... metadata=convention_df['speaker'],
... d3_url='d3.min.js',
... d3_scale_chromatic_url='d3-scale-chromatic.v1.min.js')
Fixed a bug in 0.0.2.6.0 that transposed default axis labels.
Added a Japanese mode to Scattertext. See demo_japanese.py for an example of how to use Japanese. Please run pip install tinysegmenter to parse Japanese.
Also, the chiense_mode boolean parameter in produce_scattertext_explorer has been renamed to asian_mode .
For example, the output of demo_japanese.py is:
Custom term positions and axis labels. Although not recommended, you can visualize different metrics on each axis in visualizations similar to Monroe et al. (2008). Please see Custom term positions for more info.
Enhanced the visualization of query-based categorical differences, aka the word_similarity_explorer function. When run, a plot is produced that contains category associated terms colored in either red or blue hues, and terms not associated with either class colored in greyscale and slightly smaller. The intensity of each color indicates association with the query term. Por exemplo:
Some minor bug fixes, and added a minimum_not_category_term_frequency parameter. This fixes a problem with visualizing imbalanced datasets. It sets a minimum number of times a word that does not appear in the target category must appear before it is displayed.
Added TermDocMatrix.remove_entity_tags method to remove entity type tags from the analysis.
Fixed matched snippet not displaying issue #9, and fixed a Python 2 issue in created a visualization using a ParsedCorpus prepared via CorpusFromParsedDocuments , mentioned in the latter part of the issue #8 discussion.
Again, Python 2 is supported in experimental mode only.
Corrected example links on this Readme.
Fixed a bug in Issue 8 where the HTML visualization produced by produce_scattertext_html would fail.
Fixed a couple issues that rendered Scattertext broken in Python 2. Chinese processing still does not work.
Note: Use Python 3.4+ if you can.
Fixed links in Readme, and made regex NLP available in CLI.
Added the command line tool, and fixed a bug related to Empath visualizations.
Ability to see how a particular term is discussed differently between categories through the word_similarity_explorer function.
Specialized mode to view sparse term scores.
Fixed a bug that was caused by repeated values in background unigram counts.
Added true alphabetical term sorting in visualizations.
Added an optional save-as-SVG button.
Addition option of showing characteristic terms (from the full set of documents) being considered. The option ( show_characteristic in produce_scattertext_explorer ) is on by default, but currently unavailable for Chinese. If you know of a good Chinese wordcount list, please let me know. The algorithm used to produce these is F-Score.
See this and the following slide for more details
Added document and word count statistics to main visualization.
Added preliminary support for visualizing Empath (Fast 2016) topics categories instead of emotions. See the tutorial for more information.
Improved term-labeling.
Addition of strip_final_period param to FeatsFromSpacyDoc to deal with spaCy tokenization of all-caps documents that can leave periods at the end of terms.
I've added support for Chinese, including the ChineseNLP class, which uses a RegExp-based sentence splitter and Jieba for word segmentation. To use it, see the demo_chinese.py file. Note that CorpusFromPandas currently does not support ChineseNLP.
In order for the visualization to work, set the asian_mode flag to True in produce_scattertext_explorer .
