File size: 3,213 Bytes
94d2494 | 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 | """
src.visualisations.regression – Regression-specific charts.
"""
from __future__ import annotations
from typing import Dict
import numpy as np
import pandas as pd
import plotly.graph_objects as go
from sklearn.pipeline import Pipeline
from src import config
from src.visualisations.common import _base_layout
def actual_vs_predicted_chart(
y_true: np.ndarray,
y_pred: np.ndarray,
model_name: str = "Model",
) -> go.Figure:
"""Scatter plot of actual vs predicted values."""
fig = go.Figure()
fig.add_trace(go.Scatter(
x=y_true, y=y_pred, mode="markers",
marker=dict(color="#6C63FF", size=6, opacity=0.6, line=dict(width=0.5, color="#EAEAF5")),
name="Predictions",
))
min_val = min(float(np.min(y_true)), float(np.min(y_pred)))
max_val = max(float(np.max(y_true)), float(np.max(y_pred)))
fig.add_trace(go.Scatter(
x=[min_val, max_val], y=[min_val, max_val],
mode="lines", line=dict(dash="dash", color="#FF6584", width=2),
name="Perfect Prediction",
))
fig.update_layout(
**_base_layout(title=f"🎯 Actual vs Predicted — {model_name}"),
xaxis=dict(title="Actual Values", gridcolor="#2A2E3F"),
yaxis=dict(title="Predicted Values", gridcolor="#2A2E3F"),
)
return fig
def residual_plot(
y_true: np.ndarray,
y_pred: np.ndarray,
model_name: str = "Model",
) -> go.Figure:
"""Residual plot for regression models."""
residuals = y_true - y_pred
fig = go.Figure()
fig.add_trace(go.Scatter(
x=y_pred, y=residuals, mode="markers",
marker=dict(color="#43D8C9", size=6, opacity=0.6, line=dict(width=0.5, color="#EAEAF5")),
name="Residuals",
))
fig.add_hline(y=0, line_dash="dash", line_color="#FF6584", line_width=2,
annotation_text="Zero Error", annotation_position="top right")
fig.update_layout(
**_base_layout(title=f"📉 Residual Plot — {model_name}"),
xaxis=dict(title="Predicted Values", gridcolor="#2A2E3F"),
yaxis=dict(title="Residuals (Actual − Predicted)", gridcolor="#2A2E3F"),
)
return fig
def regression_comparison_chart(
fitted_models: Dict[str, Pipeline],
X_test: pd.DataFrame,
y_test: pd.Series,
) -> go.Figure:
"""Overlay actual vs predicted for all regression models."""
fig = go.Figure()
sort_idx = np.argsort(y_test.values)
x_axis = np.arange(len(y_test))
fig.add_trace(go.Scatter(
x=x_axis, y=y_test.values[sort_idx],
mode="lines", line=dict(color="#EAEAF5", width=2), name="Actual",
))
for i, (name, pipeline) in enumerate(fitted_models.items()):
y_pred = pipeline.predict(X_test)
fig.add_trace(go.Scatter(
x=x_axis, y=y_pred[sort_idx], mode="lines",
line=dict(color=config.COLOR_PALETTE[i % len(config.COLOR_PALETTE)], width=1.5),
name=name, opacity=0.8,
))
fig.update_layout(
**_base_layout(title="📈 Predictions Overlay (sorted by actual)"),
xaxis=dict(title="Sample Index (sorted)", gridcolor="#2A2E3F"),
yaxis=dict(title="Target Value", gridcolor="#2A2E3F"),
)
return fig
|