Spaces:
Sleeping
Sleeping
File size: 4,145 Bytes
0e7cb64 |
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 |
from pathlib import Path
import gradio as gr
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
CSV_PATH = Path("metrics.csv")
def load_data() -> pd.DataFrame:
df = pd.read_csv(CSV_PATH)
# Normalize/parse columns
if "date" not in df.columns:
raise ValueError("Expected a 'date' column in metrics.csv")
df["date"] = pd.to_datetime(df["date"], errors="coerce")
df = df.sort_values("date").reset_index(drop=True)
# Ensure numeric columns are numeric
for c in df.columns:
if c == "date":
continue
df[c] = pd.to_numeric(df[c], errors="coerce")
return df
def line_figure(df: pd.DataFrame, cols: list[str], title: str, yaxis_title: str = "") -> go.Figure:
if not cols:
# Empty placeholder so the UI doesn't error
fig = go.Figure()
fig.update_layout(title=f"{title} (no series selected)")
return fig
fig = px.line(
df,
x="date",
y=cols,
markers=True,
title=title,
)
# Improve layout for time series
fig.update_layout(
legend_title_text="Series",
xaxis_title="Date",
yaxis_title=yaxis_title,
hovermode="x unified",
margin={"l": 50, "r": 20, "t": 50, "b": 40},
)
return fig
TAB_SPEC = {
"Docstrings": [
"docstring coverage",
"docstring missing",
],
"Size (Lines/Statements/Expressions/Parameters)": [
"lines mean",
"lines max",
"lines 90th-percentile",
"statements mean",
"statements max",
"statements 90th-percentile",
"expressions mean",
"expressions max",
"expressions 90th-percentile",
"parameters mean",
"parameters max",
"parameters 90th-percentile",
],
"Complexity": [
"cyclomatic_complexity mean",
"cyclomatic_complexity max",
"cyclomatic_complexity 90th-percentile",
],
"Typing": [
"type_coverage mean",
"type_coverage min",
"type_coverage 50th-percentile",
],
"Duplication": [
"duplication.score mean",
"duplication.score max",
"duplication.score 90th-percentile",
"duplication.score 50th-percentile",
"duplication.duplicated-lines total",
],
"TODOs": [
"todo_comments total",
],
"CLOC (Repository scope)": [
"files",
"lines blank",
"lines comment",
"lines code",
],
}
Y_LABELS = {
"Docstrings": "value",
"Size (Lines/Statements/Expressions/Parameters)": "count",
"Complexity": "complexity",
"Typing": "fraction / coverage",
"Duplication": "score / lines",
"TODOs": "count",
"CLOC (Repository scope)": "lines / files",
}
DF = load_data()
with gr.Blocks(title="Code Metrics – Time Series", fill_height=True) as demo:
gr.Markdown(
"## Diffusers Code Metrics Over Time\n"
f"Loaded **{CSV_PATH}** with {len(DF)} rows spanning "
f"{DF['date'].min().date()} → {DF['date'].max().date()}.\n\n"
"Use each tab to pick the series you want to plot."
)
with gr.Tabs():
tab_controls = []
tab_plots = []
for tab_name, series in TAB_SPEC.items():
available = [s for s in series if s in DF.columns] # guard against missing cols
with gr.Tab(tab_name):
with gr.Row():
sel = gr.CheckboxGroup(
choices=available,
value=available,
label="Series",
)
plot = gr.Plot(
value=line_figure(DF, available, tab_name, Y_LABELS.get(tab_name, "")),
show_label=False,
)
sel.change(
fn=lambda cols, t=tab_name: line_figure(DF, cols, t, Y_LABELS.get(t, "")),
inputs=sel,
outputs=plot,
)
tab_controls.append(sel)
tab_plots.append(plot)
if __name__ == "__main__":
demo.launch()
|