Deploy from GitHub Actions

analysis.py

@@ -2745,11 +2745,11 @@ def plot_sector_line_charts(
         - DataFrame: Filtered dataframe containing the data used in the plot
         - DataFrame: Contains the plotted data points with means and standard errors
     """
-    GREY10 = "#1a1a1a"
-    GREY30 = "#4d4d4d"
-    GREY40 = "#666666"
-    GREY75 = "#bfbfbf"
-    GREY91 = "#e8e8e8"
+    GREY10 = "#1a1a1a"  # noqa: F841
+    GREY30 = "#4d4d4d"  # noqa: F841
+    GREY40 = "#666666"  # noqa: F841
+    GREY75 = "#bfbfbf"  # noqa: F841
+    GREY91 = "#e8e8e8"  # noqa: F841
 
     # 1. Data preparation
     param_data = df[df["Org_Analyte_Name"] == parameter].copy()
@@ -3008,9 +3008,11 @@ def plot_sector_box_charts(
     df: pd.DataFrame,
     parameter: str,
     color_scale: list[str] = COLOR_SCALE,
+    show_trend: bool = True,  # New parameter
 ) -> tuple[Figure, pd.DataFrame, pd.DataFrame]:
     """
-    Create box plots showing the distribution of parameter values by sector and year.
+    Create box plots showing the distribution of parameter values by sector and year,
+    with optional trend lines and statistics.
 
     Parameters:
     -----------
@@ -3020,6 +3022,8 @@ def plot_sector_box_charts(
         Parameter to plot
     color_scale : list[str]
         List of colors to use for sectors
+    show_trend : bool, default=True
+        Whether to show trend lines and statistics
 
     Returns:
     --------
@@ -3028,12 +3032,11 @@ def plot_sector_box_charts(
         - DataFrame: Filtered dataframe containing the raw data used in the plot
         - DataFrame: Contains the plotted data points: mean, median, and quartiles
     """
+    from scipy import stats
+
     # Define consistent colors for styling
-    GREY10 = "#1a1a1a"
     GREY30 = "#4d4d4d"
     GREY40 = "#666666"
-    GREY75 = "#bfbfbf"
-    GREY91 = "#e8e8e8"
 
     # Filter data for parameter
     param_data = df[df["Org_Analyte_Name"] == parameter].copy()
@@ -3063,7 +3066,7 @@ def plot_sector_box_charts(
         ax = plt.subplot(len(sectors), 1, idx + 1)
         sector_data = param_data[param_data["Sector"] == sector]
 
-        bp = ax.boxplot(
+        bp = ax.boxplot(  # noqa: F841
             [
                 sector_data[sector_data["Reporting_Year"] == year][
                     "Org_Result_Value"
@@ -3084,6 +3087,45 @@ def plot_sector_box_charts(
             positions=range(len(years)),
         )
 
+        # Only add trend line and stats if show_trend is True
+        if show_trend:
+            # Calculate annual means for trend line
+            annual_means = [
+                sector_data[sector_data["Reporting_Year"] == year][
+                    "Org_Result_Value"
+                ].mean()
+                for year in years
+            ]
+
+            # Remove any NaN values for regression
+            valid_points = [
+                (x, y) for x, y in enumerate(annual_means) if not np.isnan(y)
+            ]
+            if valid_points:
+                x_valid, y_valid = zip(*valid_points)
+
+                # Perform linear regression
+                slope, intercept, r_value, p_value, std_err = stats.linregress(
+                    x_valid, y_valid
+                )
+
+                # Plot trend line
+                line_x = np.array(x_valid)
+                line_y = slope * line_x + intercept
+                ax.plot(line_x, line_y, "--", color="red", alpha=0.7, linewidth=1.5)
+
+                # Add statistics text
+                stats_text = f"R² = {r_value**2:.3f}\np = {p_value:.3f}"  # type: ignore
+                ax.text(
+                    0.02,
+                    0.98,
+                    stats_text,
+                    transform=ax.transAxes,
+                    verticalalignment="top",
+                    fontsize=8,
+                    bbox=dict(facecolor="white", alpha=0.8, edgecolor="none"),
+                )
+
         # Set proper x-axis limits with padding
         ax.set_xlim(-0.5, len(years) - 0.5)
 

ui/pages/sector_compare.py

@@ -27,7 +27,7 @@ chart_type = st.sidebar.radio(
 )
 
 # Only show relevant controls based on chart type
-if chart_type in ["Line Charts", "Heatmap"]:
+if chart_type in ["Line Charts", "Heatmap", "Box and Whisker"]:
     st.sidebar.markdown("#### Chart Specific Options")
 if chart_type == "Line Charts":
     show_sem = st.sidebar.checkbox(
@@ -43,6 +43,13 @@ elif chart_type == "Heatmap":
         help="Display mean values inside each cell",
         key="sector_compare_show_values",
     )
+elif chart_type == "Box and Whisker":
+    show_trend = st.sidebar.checkbox(
+        "Show Trend Line",
+        value=True,
+        help="Display trend line with R² and p-values",
+        key="sector_compare_show_trend",
+    )
 
 selected_parameter = st.sidebar.selectbox(
     "Parameter:",
@@ -89,7 +96,7 @@ try:
     elif chart_type == "Box and Whisker":
         # Add box plots
         fig, param_data, plot_data = plot_sector_box_charts(
-            filtered_raw_df, selected_parameter
+            filtered_raw_df, selected_parameter, show_trend=show_trend
         )
         st.pyplot(fig)
     else:  # Heatmap