tabs/error.py

import pandas as pd
import gradio as gr
from typing import List
import plotly.express as px
from tabs.tool_win import sort_key


HEIGHT = 600
WIDTH = 1000


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)]
    error = (
        tools_inc.groupby(["tool", "request_month_year_week", "error"])
        .size()
        .unstack()
        .fillna(0)
        .reset_index()
    )
    error["error_perc"] = (error[1] / (error[0] + error[1])) * 100
    error["total_requests"] = error[0] + error[1]
    return error


def get_error_data_by_market(
    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)]
    error = (
        tools_inc.groupby(
            ["tool", "request_month_year_week", "market_creator", "error"], sort=False
        )
        .size()
        .unstack()
        .fillna(0)
        .reset_index()
    )
    error["error_perc"] = (error[1] / (error[0] + error[1])) * 100
    error["total_requests"] = error[0] + error[1]
    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", 1: "sum", 0: "sum"})
        .reset_index()
    )
    error_total["error_perc"] = (error_total[1] / 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 get_error_data_overall_by_market(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", "market_creator"], sort=False)
        .agg({"total_requests": "sum", 1: "sum", 0: "sum"})
        .reset_index()
    )
    error_total["error_perc"] = (error_total[1] / 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_error_data_by_market(error_all_df: pd.DataFrame) -> gr.Plot:

    # Sort the unique values of request_month_year_week
    sorted_categories = sorted(
        error_all_df["request_month_year_week"].unique(), key=sort_key
    )
    # Create a categorical type with a specific order
    error_all_df["request_month_year_week"] = pd.Categorical(
        error_all_df["request_month_year_week"],
        categories=sorted_categories,
        ordered=True,
    )

    # Sort the DataFrame based on the new categorical column
    error_all_df = error_all_df.sort_values("request_month_year_week")

    fig = px.bar(
        error_all_df,
        x="request_month_year_week",
        y="error_perc",
        color="market_creator",
        barmode="group",
        color_discrete_sequence=["purple", "goldenrod", "darkgreen"],
        category_orders={
            "market_creator": ["pearl", "quickstart", "all"],
            "request_month_year_week": sorted_categories,
        },
    )
    fig.update_layout(
        xaxis_title="Week",
        yaxis_title="Error Percentage",
        legend=dict(yanchor="top", y=0.5),
    )
    fig.update_layout(width=WIDTH, height=HEIGHT)
    fig.update_xaxes(tickformat="%b %d\n%Y")
    return gr.Plot(value=fig)


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]
    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_tool_error_data_by_market(error_df: pd.DataFrame, tool: str) -> gr.Plot:
    error_tool = error_df[error_df["tool"] == tool]
    error_tool.columns = error_tool.columns.astype(str)
    error_tool["error_perc"] = error_tool["error_perc"].apply(lambda x: round(x, 4))

    # Sort the unique values of request_month_year_week
    sorted_categories = sorted(
        error_tool["request_month_year_week"].unique(), key=sort_key
    )
    # Create a categorical type with a specific order
    error_tool["request_month_year_week"] = pd.Categorical(
        error_tool["request_month_year_week"],
        categories=sorted_categories,
        ordered=True,
    )

    # Sort the DataFrame based on the new categorical column
    error_tool = error_tool.sort_values("request_month_year_week")

    fig = px.bar(
        error_tool,
        x="request_month_year_week",
        y="error_perc",
        color="market_creator",
        barmode="group",
        color_discrete_sequence=["purple", "goldenrod", "darkgreen"],
        category_orders={
            "market_creator": ["pearl", "quickstart", "all"],
            "request_month_year_week": sorted_categories,
        },
    )
    fig.update_layout(
        xaxis_title="Week",
        yaxis_title="Error Percentage %",
        legend=dict(yanchor="top", y=0.5),
    )
    fig.update_layout(width=WIDTH, height=HEIGHT)
    fig.update_xaxes(tickformat="%b %d\n%Y")
    return gr.Plot(value=fig)


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]
    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,
    )


def plot_week_error_data_by_market(error_df: pd.DataFrame, week: str) -> gr.Plot:
    error_week = error_df[error_df["request_month_year_week"] == week]
    error_week.columns = error_week.columns.astype(str)
    error_week["error_perc"] = error_week["error_perc"].apply(lambda x: round(x, 4))

    fig = px.bar(
        error_week,
        x="tool",
        y="error_perc",
        color="market_creator",
        barmode="group",
        color_discrete_sequence=["purple", "goldenrod", "darkgreen"],
        category_orders={
            "market_creator": ["pearl", "quickstart", "all"],
        },
    )
    fig.update_layout(
        xaxis_title="Tool",
        yaxis_title="Error Percentage %",
        legend=dict(yanchor="top", y=0.5),
    )
    fig.update_layout(width=WIDTH, height=HEIGHT)
    fig.update_xaxes(tickformat="%b %d\n%Y")
    return gr.Plot(value=fig)