databyjp

fig = px.bar(unigram_df[:20], x='ngram', y='count', title='Counts of top unigrams', template='plotly_white', labels={'ngram': 'Unigram', 'count': 'Count'})
fig.show()

databyjp

fig = px.bar(bigram_df[:20], x='ngram', y='count', title='Counts of top bigrams', template='plotly_white', labels={'ngram': 'Bigram', 'count': 'Count'})
fig.show()

databyjp

fig = px.bar(comp_grp_df, x='portion', y='company', template='plotly_white', orientation='h',
             labels={'portion': '% of Complaints', 'bigram': 'Bigram', 'company': 'Company'},
             color='bigram', color_discrete_sequence=px.colors.qualitative.Safe)
fig.update_layout(font=dict(size=10, color='DarkSlateGray'))
fig.update_layout(width=1200, height=500)
fig.show()

databyjp

NAVBAR = dbc.Navbar(
    children=[
        html.A(
            # Use row and col to control vertical alignment of logo / brand
            dbc.Row(
                [
                    dbc.Col(html.Img(src=PLOTLY_LOGO, height="30px")),
                    dbc.Col(
                        dbc.NavbarBrand("Bank Customer Complaints", className="ml-2")
                    ),

databyjp

fig = px.scatter(embed_df, x='tsne_1', y='tsne_2', hover_name='bigram', text='bigram', size='count', color='words', size_max=45
                 , template='plotly_white', title='Bigram similarity and frequency', labels={'words': 'Avg. Length<BR>(words)'}
                 , color_continuous_scale=px.colors.sequential.Sunsetdark)
fig.update_traces(marker=dict(line=dict(width=1, color='Gray')))
fig.update_xaxes(visible=False)
fig.update_yaxes(visible=False)
fig.show()

databyjp

dbc.Row([
    dbc.Col(['Choose a t-SNE perplexity value:'], md=6),
    dbc.Col([
        dcc.Dropdown(
            id='bigrams-perplex-dropdown',
            options=[{'label': str(i), 'value': i} for i in range(3, 7)],
            value=3
        )], md=3)
]),
dcc.Graph(id="bigrams-scatter"),

databyjp

fig = px.bar(long_bigram_df_tidy, title='Comparision: ' + ngrams_list[0] + ' | ' + ngrams_list[1], x='ngram', y='value'
             , color='variable', template='plotly_white', color_discrete_sequence=px.colors.qualitative.Bold
             , labels={'variable': 'Company:', 'ngram': 'N-Gram'})
fig.update_layout(legend_orientation="h")
fig.update_layout(legend=dict(x=0.1, y=1.1))
fig.update_yaxes(title='', showticklabels=False)
fig.show()

databyjp

>>> nf_df.head()
    show_id     type                                    title                  director                                               cast                                   country         date_added  release_year    rating  duration                           listed_in                                        description
0  81145628    Movie  Norm of the North: King Sized Adventure  Richard Finn, Tim Maltby  Alan Marriott, Andrew Toth, Brian Dobson, Cole...  United States, India, South Korea, China  September 9, 2019          2019     TV-PG    90 min  Children & Family Movies, Comedies  Before planning an awesome wedding for his gra...
1  80117401    Movie               Jandino: Whatever it Takes                       NaN                                   Jandino Asporaat                            United Kingdom  September 9, 2016          2016     TV-MA    94 min                     Stand-Up Comedy  Jandino Asporaat riffs on the challenges of ra...
2  70234439  TV Show                       T

databyjp

>>> nf_df.head()
    show_id  ...                                        description
0  81145628  ...  Before planning an awesome wedding for his gra...
1  80117401  ...  Jandino Asporaat riffs on the challenges of ra...
2  70234439  ...  With the help of three human allies, the Autob...
3  80058654  ...  When a prison ship crash unleashes hundreds of...
4  80125979  ...  When nerdy high schooler Dani finally attracts...

[5 rows x 12 columns]

databyjp

# Avoid accidentally modifying the source object
nf_df = pd.read_csv('srcdata/netflix_titles.csv')
nf_test1_df = nf_df
nf_test1_df['like'] = True
print(len(nf_df.columns))

nf_df = pd.read_csv('srcdata/netflix_titles.csv')
nf_test2_df = nf_df
nf_test2_df = nf_test2_df.assign(like=True)
print(len(nf_df.columns))