File size: 8,041 Bytes
e2483e1 a035e35 e2483e1 73f4a97 e2483e1 73f4a97 e2483e1 73f4a97 a035e35 e2483e1 73f4a97 e2483e1 73f4a97 e2483e1 73f4a97 a035e35 e2483e1 73f4a97 e2483e1 73f4a97 a035e35 e2483e1 73f4a97 e2483e1 73f4a97 e2483e1 73f4a97 a035e35 73f4a97 e2483e1 73f4a97 a035e35 e2483e1 73f4a97 e2483e1 73f4a97 e2483e1 73f4a97 a035e35 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 |
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)
|