gen_htmls.py

import pandas as pd
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import sys

# Load data
df = pd.read_csv(sys.argv[1])

# Clean up
df = df.drop(columns=['Unnamed: 5'])

# Sort
# df = df.sort_values(by='citations', ascending=False)

# Shorten titles for axis
df['Title_Short'] = df['Title'].apply(lambda x: str(x)[:40] + '...' if len(str(x)) > 40 else str(x))

# Create figure
fig = make_subplots(specs=[[{"secondary_y": True}]])

# Bar trace for Citations
fig.add_trace(
    go.Bar(
        x=df['Title_Short'],
        y=df['citations'],
        name="Citations",
        marker_color='rgb(55, 83, 109)',
        customdata=df[['Title', '% of total', 'Cummulative']],
        hovertemplate="<b>%{customdata[0]}</b><br>" +
                      "Citations: %{y}<br>" +
                      "% of Total: %{customdata[1]:.2%}<br>" +
                      "Cumulative: %{customdata[2]:.2%}<extra></extra>"
    ),
    secondary_y=False,
)

# Line trace for Cumulative %
fig.add_trace(
    go.Scatter(
        x=df['Title_Short'],
        y=df['Cummulative'],
        name="Cumulative %",
        marker_color='rgb(26, 118, 255)',
        mode='lines+markers',
        customdata=df[['Title']],
        hovertemplate="<b>%{customdata[0]}</b><br>Cumulative: %{y:.2%}<extra></extra>"
    ),
    secondary_y=True,
)

# Layout
fig.update_layout(
    title_text="Citation Counts and Cumulative Distribution (" + sys.argv[2] + ")",
    xaxis_title="Paper Title",
    hovermode="x unified",
    legend=dict(x=0.7, y=0.9),
    margin=dict(b=150)
)

fig.update_xaxes(tickangle=45)
fig.update_yaxes(title_text="<b>Citation Count</b>", secondary_y=False)
fig.update_yaxes(title_text="<b>Cumulative %</b>", secondary_y=True, tickformat='.0%')
# Update the primary y-axis (Citations) to use a log scale
fig.update_yaxes(
    title_text="<b>Citation Count</b>", 
    secondary_y=False, 
    type="log"  # <--- Add this line
)

# The secondary y-axis (Cumulative %) remains linear
fig.update_yaxes(
    title_text="<b>Cumulative %</b>", 
    secondary_y=True, 
    tickformat='.0%'
)

# Save
# output_file = 'citation_visualization.html'
output_file = sys.argv[3]
fig.write_html(output_file)

print(f"File saved: {output_file}")