Description

Requirement

Installation

pip install nlplot

Quick start - Data Preparation

# sample datatarget_col="text"texts= ["Think rich look poor","When you come to a roadblock, take a detour","When it is dark enough, you can see the stars","Never let your memories be greater than your dreams","Victory is sweetest when you’ve known defeat"    ]df=pd.DataFrame({target_col:texts})df.head()

Quick start - Python API

importnlplotimportpandasaspdimportplotlyfromplotly.subplotsimportmake_subplotsfromplotly.offlineimportiplotimportmatplotlib.pyplotasplt%matplotlibinline# target_col as a list type or a string separated by a space.npt=nlplot.NLPlot(df,target_col='text')# Stopword calculations can be performed.stopwords=npt.get_stopword(top_n=30,min_freq=0)# 1. N-gram bar chartfig_unigram=npt.bar_ngram(title='uni-gram',xaxis_label='word_count',yaxis_label='word',ngram=1,top_n=50,width=800,height=1100,color=None,horizon=True,stopwords=stopwords,verbose=False,save=False,)fig_unigram.show()fig_bigram=npt.bar_ngram(title='bi-gram',xaxis_label='word_count',yaxis_label='word',ngram=2,top_n=50,width=800,height=1100,color=None,horizon=True,stopwords=stopwords,verbose=False,save=False,)fig_bigram.show()# 2. N-gram tree Mapfig_treemap=npt.treemap(title='Tree map',ngram=1,top_n=50,width=1300,height=600,stopwords=stopwords,verbose=False,save=False)fig_treemap.show()# 3. Histogram of the word countfig_histgram=npt.word_distribution(title='word distribution',xaxis_label='count',yaxis_label='',width=1000,height=500,color=None,template='plotly',bins=None,save=False,)fig_histgram.show()# 4. wordcloudfig_wc=npt.wordcloud(width=1000,height=600,max_words=100,max_font_size=100,colormap='tab20_r',stopwords=stopwords,mask_file=None,save=False)plt.figure(figsize=(15,25))plt.imshow(fig_wc,interpolation="bilinear")plt.axis("off")plt.show()# 5. co-occurrence networksnpt.build_graph(stopwords=stopwords,min_edge_frequency=10)# The number of nodes and edges to which this output is plotted.# If this number is too large, plotting will take a long time, so adjust the [min_edge_frequency] well.# >> node_size:70, edge_size:166fig_co_network=npt.co_network(title='Co-occurrence network',sizing=100,node_size='adjacency_frequency',color_palette='hls',width=1100,height=700,save=False)iplot(fig_co_network)# 6. sunburst chartfig_sunburst=npt.sunburst(title='sunburst chart',colorscale=True,color_continuous_scale='Oryel',width=1000,height=800,save=False)fig_sunburst.show()# other# The original data frame of the co-occurrence network can also be accesseddisplay(npt.node_df.head(),npt.node_df.shape,npt.edge_df.head(),npt.edge_df.shape)

Document

Test

cd testspytest

Other