tabs/error.py

import pandas as pd
import gradio as gr
from typing import List


HEIGHT=600
WIDTH=1000

def set_error(row: pd.Series) -> bool:
    """Sets the error for the given row."""
    if row.error not in [True, False]:
        if not row.prompt_response:
            return True
        return False
    return row.error

def get_error_data(tools_df: pd.DataFrame, inc_tools: List[str]) -> pd.DataFrame:
    """Gets the error data for the given tools and calculates the error percentage."""
    tools_inc = tools_df[tools_df['tool'].isin(inc_tools)].copy()
    tools_inc['error'] = tools_inc.apply(set_error, axis=1)
    error = tools_inc.groupby(['tool', 'request_month_year_week', 'error']).size().unstack().fillna(0).reset_index()
    error['error_perc'] = (error[True] / (error[False] + error[True])) * 100
    error['total_requests'] = error[False] + error[True]
    return error

def get_error_data_overall(error_df: pd.DataFrame) -> pd.DataFrame:
    """Gets the error data for the given tools and calculates the error percentage."""
    error_total = error_df.groupby('request_month_year_week').agg({'total_requests': 'sum', False: 'sum', True: 'sum'}).reset_index()
    error_total['error_perc'] = (error_total[True] / error_total['total_requests']) * 100
    error_total.columns = error_total.columns.astype(str)
    error_total['error_perc'] = error_total['error_perc'].apply(lambda x: round(x, 4))
    return error_total

def plot_error_data(error_all_df: pd.DataFrame) -> gr.BarPlot:
    """Plots the error data for the given tools and calculates the error percentage."""
    return gr.BarPlot(
        value=error_all_df,
        x="request_month_year_week",
        y="error_perc",
        title="Error Percentage",
        x_title="Week",
        y_title="Error Percentage",
        show_label=True,
        interactive=True,
        show_actions_button=True,
        tooltip=["request_month_year_week", "error_perc"],
        height=HEIGHT,
        width=WIDTH
    )

def plot_tool_error_data(error_df: pd.DataFrame, tool: str) -> gr.BarPlot:
    """Plots the error data for the given tool."""
    error_tool = error_df[error_df['tool'] == tool].copy()
    error_tool.columns = error_tool.columns.astype(str)
    error_tool['error_perc'] = error_tool['error_perc'].apply(lambda x: round(x, 4))
                
    return gr.BarPlot(
            title="Error Percentage", 
            x_title="Week", 
            y_title="Error Percentage", 
            show_label=True,
            interactive=True,
            show_actions_button=True,
            tooltip=["request_month_year_week", "error_perc"],
            value=error_tool,
            x="request_month_year_week",
            y="error_perc",
            height=HEIGHT,
            width=WIDTH
    )

def plot_week_error_data(error_df: pd.DataFrame, week: str) -> gr.BarPlot:
    """Plots the error data for the given week."""
    error_week = error_df[error_df['request_month_year_week'] == week].copy()
    error_week.columns = error_week.columns.astype(str)
    error_week['error_perc'] = error_week['error_perc'].apply(lambda x: round(x, 4))
    return gr.BarPlot(
        value=error_week,
        x="tool",
        y="error_perc",
        title="Error Percentage",
        x_title="Tool",
        y_title="Error Percentage",
        show_label=True,
        interactive=True,
        show_actions_button=True,
        tooltip=["tool", "error_perc"],
        height=HEIGHT,
        width=WIDTH
    )