Graph a GitHub Workflow using plotnine

graph_workflow.py

import pandas as pd
from plotnine import ggplot, aes, geom_line, theme, labs, scale_x_datetime, element_text, geom_point
import json
from datetime import datetime

#  $ gh run list --workflow buildAndTestBazel.yml --repo openxla/stablehlo --json startedAt,updatedAt --status completed --branch main --limit 100 > json_data.json
# Assuming `json_data` is your JSON data loaded into a variable
# If your JSON is in a file, you can load it with:
with open('json_data.json', 'r') as f:
    json_data = json.load(f)

# Convert JSON data to DataFrame
df = pd.DataFrame(json_data)

# Convert the startedAt and updatedAt columns to datetime
df['startedAt'] = pd.to_datetime(df['startedAt'])
df['updatedAt'] = pd.to_datetime(df['updatedAt'])

# Calculate the elapsed time in seconds
df['elapsedTime'] = (df['updatedAt'] - df['startedAt']).dt.total_seconds()

# If your datetimes are in UTC, ensure the comparison Timestamp is also in UTC
now = pd.Timestamp.utcnow()
one_month_ago = now - pd.DateOffset(months=1)

# Filter data to the last month, ensuring both datetimes are timezone-aware or both are naive
df_last_month = df[df['startedAt'].dt.tz_localize(None) >= one_month_ago.tz_localize(None)]

# Plot using plotnine
plot = (ggplot(df_last_month, aes('startedAt', 'elapsedTime')) +
        geom_line() +
        theme(axis_text_x=element_text(rotation=90, hjust=1)) +
        labs(x='Date Workflow Started', y='Elapsed Time (seconds)', title='Elapsed Time Series') +
        scale_x_datetime(date_breaks='1 day', date_labels='%Y-%m-%d')) + geom_point()

# Display or save the plot
# To display the plot in a Jupyter notebook or similar environment, just use:
print(plot)

# To save the plot to a file, use:
plot.save("elapsed_time_series.png", width=10, height=6, dpi=300)