def create_scatter_text(writers, names, messages, nonames=False):
my_df = pd.DataFrame({"author": names, "message": messages})
nlp = st.tweet_tokenizier_factory(nltk.tokenize.TweetTokenizer())
my_df['parse'] = my_df['message'].apply(nlp)
corpus = st.CorpusFromParsedDocuments(
my_df, category_col='author',
parsed_col='parse').build().get_unigram_corpus().compact(
st.AssociationCompactor(2000))
if nonames:
html = st.produce_scattertext_explorer(corpus,
category=writers[0],
category_name="Author_0",
not_category_name="Author_1",
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
transform=st.Scalers.dense_rank)
else:
html = st.produce_scattertext_explorer(corpus,
category=writers[0],
category_name=writers[0],
not_category_name=writers[1],
minimum_term_frequency=0,
pmi_threshold_coefficient=0,
width_in_pixels=1000,
transform=st.Scalers.dense_rank)
with open('./demo_compact.html', 'w') as f:
f.write(html)
f.close()
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,
show_diagonal=False,
max_overlapping=3,
vertical_lines=0.5)
open('./demo_vertical_lines.html', 'w').write(html)
print('open ./demo_vertical_lines.html in Chrome')
import scattertext as st
import pandas as pd
df = st.SampleCorpora.RottenTomatoes.get_data()
df['parse'] = df['text'].apply(st.whitespace_nlp_with_sentences)
corpus = (st.CorpusFromParsedDocuments(df, category_col='category', parsed_col='parse')
.build()
.get_unigram_corpus()
.compact(st.AssociationCompactor(1000)))
corpus, axes = st.EmbeddingsResolver(corpus).set_embeddings_model().project_embeddings()
term_colors = st.CategoryColorAssigner(corpus).get_term_colors()
html = st.produce_pca_explorer(corpus,
category='fresh',
not_categories=['rotten'],
neutral_categories=['plot'],
metadata=df['movie_name'],
width_in_pixels=1000,
show_axes=False,
use_full_doc=True,
projection=axes,
term_colors=term_colors,
show_characteristic=False,
show_top_terms=False,
unified_context=True,
show_category_headings=True,
show_cross_axes=False,
include_term_category_counts=True,
color_func="(function(d) {return modelInfo.term_colors[d.term]})",
)
file_name = 'demo_unified_context.html'
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(
st.AssociationCompactor(2000, use_non_text_features=True)
class Stats_Graph_Manager:
def __init__(self):
pass
class graph:
def __init__(self,gdict=None):
if gdict is None:
gdict = []
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,
show_diagonal=True,
max_overlapping=3
)
open('./demo_compact.html', 'w').write(html)
print('open ./demo_compact.html in Chrome')