Deploy from GitHub Actions

app.py

@@ -7,7 +7,6 @@ from pages import (
     calendar_heatmaps_page,
     dissolved_oxygen_page,
     do_temp_relationship_page,
-    grouped_bar_charts_page,
     home_page,
     nutrient_ratios_page,
     parameter_correlations_page,
@@ -51,7 +50,6 @@ page_dict["Annual Report Draft Charts/Tables"] = [
     seasonal_maps_page,
     sector_compare_page,
     scatter_plots_page,
-    grouped_bar_charts_page,
     parameter_summary_tables_page,
 ]
 

pages.py

@@ -669,11 +669,6 @@ scatter_plots_page = st.Page(
     title="Scatter Plots",
     icon=":material/scatter_plot:",
 )
-grouped_bar_charts_page = st.Page(
-    "ui/pages/grouped_bar_charts.py",
-    title="Grouped Bar Charts",
-    icon=":material/bar_chart:",
-)
 seasonal_line_charts_page = st.Page(
     "ui/pages/seasonal_line_charts.py",
     title="Seasonal Line Charts",
@@ -694,7 +689,6 @@ __all__ = [
     "settings_page",
     "parameter_summary_tables_page",
     "scatter_plots_page",
-    "grouped_bar_charts_page",
     "seasonal_line_charts_page",
     "sector_compare_page",
 ]

plots/base.py

@@ -1,5 +1,4 @@
 import math
-import textwrap
 
 import matplotlib.dates as mdates
 import matplotlib.pyplot as plt
@@ -8,8 +7,6 @@ import pandas as pd
 import seaborn as sns
 from matplotlib.figure import Figure
 
-from utils.data_loading import timer
-
 COLOR_SCALE = [
     "#6D3E91",
     "#C05917",
@@ -707,208 +704,3 @@ def plot_scatter(
 
     plt.tight_layout()
     return (fig, param_data)
-
-
-@timer(include_params=True)
-def plot_grouped_bars(
-    df: pd.DataFrame,
-    parameter: str,
-    year_range: tuple[int, int],
-    group_by: str = "sector",
-) -> tuple[Figure, pd.DataFrame]:
-    """
-    Create a grouped bar chart showing means by sector or year for a selected parameter.
-
-    Parameters:
-    -----------
-    df : pd.DataFrame
-        Input dataframe containing water quality measurements
-    parameter : str
-        Name of the parameter to plot
-    year_range : tuple[int, int]
-        Start and end years to include in plot
-    group_by : str
-        How to group the bars - either "sector" (default) or "year"
-
-    Returns:
-    --------
-    tuple[Figure, pd.DataFrame]
-        - Figure: Matplotlib figure containing the grouped bar chart
-        - DataFrame: Contains the plotted data points with means and standard errors
-    """
-    # Filter data for parameter and year range
-    plot_df = df[
-        (df["Org_Analyte_Name"] == parameter)
-        & (df["Reporting_Year"] >= year_range[0])
-        & (df["Reporting_Year"] <= year_range[1])
-    ].copy()
-
-    if plot_df.empty:
-        raise ValueError(
-            f"No data available for {parameter} between {year_range[0]}-{year_range[1]}"
-        )
-
-    # Calculate annual means by sector
-    means_df = (
-        plot_df.groupby(["Reporting_Year", "Sector"], observed=True)["Org_Result_Value"]
-        .agg(["mean", "sem"])
-        .reset_index()
-    )
-
-    # Get unique years and sectors for plotting
-    years = sorted(means_df["Reporting_Year"].unique())
-    sectors = sorted(means_df["Sector"].unique())
-
-    # Determine primary and secondary categories based on grouping
-    if group_by == "year":
-        primary_categories = sectors
-        secondary_categories = years
-        x_values = years
-        group_column = "Reporting_Year"
-        category_column = "Sector"
-        x_label = "Reporting Year"
-        legend_title = "Sector"
-    else:  # group_by == "sector"
-        primary_categories = years
-        secondary_categories = sectors
-        x_values = sectors  # noqa: F841
-        group_column = "Sector"  # noqa: F841
-        category_column = "Reporting_Year"
-        x_label = "Sector"
-        legend_title = "Year"  # noqa: F841
-
-    n_groups = len(primary_categories)
-
-    colors = [
-        "#E69F00",  # Orange
-        "#56B4E9",  # Sky Blue
-        "#009E73",  # Bluish Green
-        "#F0E442",  # Yellow
-        "#0072B2",  # Blue
-        "#D55E00",  # Vermilion
-        "#CC79A7",  # Reddish Purple
-        "#999999",  # Gray
-        "#F5C710",  # Golden Yellow
-        "#93AA00",  # Lime Green
-        "#482677",  # Dark Purple
-        "#DA5724",  # Rust
-        "#5082CF",  # Steel Blue
-        "#CD9BCD",  # Lavender
-        "#C1A43A",  # Olive Green
-    ]
-
-    # Create figure
-    fig, ax = plt.subplots(figsize=(12, 6))
-
-    # Calculate bar positions
-    bar_width = 0.8 / n_groups  # Standard bar width
-
-    # Calculate center positions for x-axis labels
-    group_centers = (
-        np.arange(len(secondary_categories)) + (bar_width * (n_groups - 1)) / 2
-    )
-
-    # Plot bars for each primary category
-    for i, (category, color) in enumerate(zip(primary_categories, colors)):
-        category_data = means_df[means_df[category_column] == category]
-
-        # Create bars with simple offset calculation
-        bars = ax.bar(  # noqa: F841
-            np.arange(len(secondary_categories)) + i * bar_width,
-            category_data["mean"],
-            bar_width,
-            label=str(category),
-            color=color,
-            alpha=0.7,
-            zorder=2,
-        )
-
-        # Add error bars
-        ax.errorbar(
-            np.arange(len(secondary_categories)) + i * bar_width,
-            category_data["mean"],
-            yerr=category_data["sem"],
-            fmt="none",
-            color="black",
-            capsize=3,
-            capthick=1,
-            linewidth=1,
-            alpha=0.5,
-            zorder=3,
-        )
-
-    # Customize plot
-    unit = plot_df["Org_Result_Unit"].iloc[0]
-    ax.set_xlabel(x_label)
-    title = f"{parameter} (Mean Annual{' ' + unit if unit else ''})"
-    ax.set_title(title)
-
-    # Function to wrap text
-    def wrap_labels(text, width=10):
-        """Wrap text at specified width using textwrap."""
-        # Convert to string and wrap if needed
-        text_str = str(text)
-        if len(text_str) > width:
-            return textwrap.fill(text_str, width=width)
-        return text_str
-
-    # Set x-axis ticks and labels with wrapping using centered positions
-    ax.set_xticks(group_centers)
-    wrapped_labels = [wrap_labels(str(label)) for label in secondary_categories]
-    ax.set_xticklabels(
-        wrapped_labels,
-        ha="center",
-        va="top",
-        rotation=0,
-    )
-
-    # Remove x-axis tick marks
-    ax.tick_params(axis="x", length=0)
-
-    # Add error bar note with adjusted position
-    ax.text(
-        0.99,
-        -0.15,
-        "Error bars represent ±1 standard error of the mean",
-        ha="right",
-        va="top",
-        transform=ax.transAxes,
-        fontsize=9,
-        fontstyle="italic",
-    )
-
-    # Adjust layout with more vertical space for wrapped labels
-    plt.tight_layout(rect=(0, 0.2, 1, 1))
-
-    # Add grid
-    ax.grid(True, axis="y", alpha=0.2, linestyle="-", zorder=1)
-
-    # Customize spines
-    ax.spines["top"].set_visible(False)
-    ax.spines["right"].set_visible(False)
-    ax.spines["left"].set_visible(False)
-
-    # Remove tick marks but keep labels
-    ax.tick_params(axis="y", which="both", length=0)
-
-    ax.legend(
-        bbox_to_anchor=(1.02, 1),  # Position at top-right
-        loc="upper left",
-        frameon=False,
-        ncol=1,
-        handletextpad=0.5,
-        fontsize=9,
-    )
-
-    # Determine if log scale should be used
-    if parameter in [
-        # "Turbidity",
-        "Fecal Coliform (MPN)",
-        "Total Nitrogen",
-        "Total Phosphorus",
-    ]:
-        ax.set_yscale("log")
-        ax.yaxis.set_major_formatter(plt.ScalarFormatter())  # type: ignore
-
-    means_df.insert(0, "parameter", parameter)
-    return fig, means_df

plots/sector.py

@@ -1,3 +1,5 @@
+import textwrap
+
 import altair as alt
 import matplotlib.pyplot as plt
 import numpy as np
@@ -809,3 +811,175 @@ def plot_sector_trends(
     # Adjust layout with more vertical space between subplots
     plt.tight_layout(rect=(0, 0, 0.85, 1), h_pad=2.0)
     return fig
+
+
+@timer(include_params=True)
+def plot_grouped_bars(
+    df: pd.DataFrame,
+    parameter: str,
+    year_range: tuple[int, int],
+    group_by: str = "sector",
+) -> tuple[Figure, pd.DataFrame]:
+    """Create a grouped bar chart showing means by sector or year.
+
+    Parameters:
+    -----------
+    df : pd.DataFrame
+        Input dataframe containing water quality measurements
+    parameter : str
+        Name of the parameter to plot
+    year_range : tuple[int, int]
+        Start and end years to include in plot
+    group_by : str
+        How to group the bars - either "sector" (default) or "year"
+
+    Returns:
+    --------
+    tuple[Figure, pd.DataFrame]
+        - Figure: Matplotlib figure containing the grouped bar chart
+        - DataFrame: Contains the plotted data points with means and standard errors
+    """
+    # Define consistent colors for styling
+    GREY30 = "#4d4d4d"
+    GREY40 = "#666666"
+
+    # Filter data for parameter and year range
+    plot_df = df[
+        (df["Org_Analyte_Name"] == parameter)
+        & (df["Reporting_Year"] >= year_range[0])
+        & (df["Reporting_Year"] <= year_range[1])
+    ].copy()
+
+    if plot_df.empty:
+        raise ValueError(
+            f"No data available for {parameter} between {year_range[0]}-{year_range[1]}"
+        )
+
+    # Calculate annual means by sector
+    means_df = (
+        plot_df.groupby(["Reporting_Year", "Sector"], observed=True)["Org_Result_Value"]
+        .agg(["mean", "sem"])
+        .reset_index()
+    )
+
+    # Create figure with standard dimensions
+    fig, ax = plt.subplots(figsize=(12, 6))
+
+    # Setup grouping logic
+    years = sorted(means_df["Reporting_Year"].unique())
+    sectors = sorted(means_df["Sector"].unique())
+
+    if group_by == "year":
+        primary_cats = sectors
+        secondary_cats = years
+        x_label = "Reporting Year"
+        category_col = "Sector"
+    else:
+        primary_cats = years
+        secondary_cats = sectors
+        x_label = "Sector"
+        category_col = "Reporting_Year"
+
+    # Calculate bar positions
+    n_groups = len(primary_cats)
+    bar_width = 0.8 / n_groups
+    group_centers = np.arange(len(secondary_cats)) + (bar_width * (n_groups - 1)) / 2
+
+    # Plot bars for each primary category
+    for i, category in enumerate(primary_cats):
+        category_data = means_df[means_df[category_col] == category]
+
+        # Create bars
+        ax.bar(
+            np.arange(len(secondary_cats)) + i * bar_width,
+            category_data["mean"],
+            bar_width,
+            label=str(category),
+            color=COLOR_SCALE[i % len(COLOR_SCALE)],
+            alpha=0.7,
+            zorder=2,
+        )
+
+        # Add error bars
+        ax.errorbar(
+            np.arange(len(secondary_cats)) + i * bar_width,
+            category_data["mean"],
+            yerr=category_data["sem"],
+            fmt="none",
+            color=GREY40,
+            capsize=3,
+            capthick=1,
+            linewidth=1,
+            alpha=0.5,
+            zorder=3,
+        )
+
+    # Configure axes and spines
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    ax.spines["left"].set_visible(False)
+    ax.spines["bottom"].set_color(GREY40)
+    ax.spines["bottom"].set_linewidth(0.5)
+
+    # Configure grid
+    ax.grid(True, axis="y", alpha=0.15, linestyle="-", color="gray", zorder=1)
+
+    # Configure ticks
+    ax.tick_params(axis="both", which="both", length=0, colors=GREY40)
+
+    # Set x-axis ticks and wrapped labels
+    ax.set_xticks(group_centers)
+    wrapped_labels = [textwrap.fill(str(label), width=10) for label in secondary_cats]
+    ax.set_xticklabels(wrapped_labels, ha="center", va="top", color=GREY40)
+
+    # Add titles and labels
+    unit = plot_df["Org_Result_Unit"].iloc[0] if not plot_df.empty else ""
+    ax.set_title(
+        f"{parameter} (Mean Annual{' ' + unit if unit else ''})",
+        pad=10,
+        fontsize=12,
+        color=GREY30,
+    )
+    ax.set_xlabel(x_label, color=GREY40, fontsize=10)
+
+    # Configure legend
+    ax.legend(
+        bbox_to_anchor=(1.02, 1),
+        loc="upper left",
+        frameon=False,
+        fontsize=9,
+        handletextpad=0.5,
+    )
+
+    # Add error bar note
+    ax.text(
+        0.99,
+        -0.15,
+        "Error bars represent ±1 standard error of the mean",
+        ha="right",
+        va="top",
+        transform=ax.transAxes,
+        fontsize=8,
+        fontstyle="italic",
+        color=GREY40,
+    )
+
+    # Set log scale if needed
+    if parameter in [
+        "Fecal Coliform (MPN)",
+        "Total Nitrogen",
+        "Total Phosphorus",
+    ]:
+        ax.set_yscale("log")
+        ax.yaxis.set_major_formatter(plt.ScalarFormatter())  # type: ignore
+    # Special case for pH
+    elif parameter == "pH":
+        ax.set_ylim(5.5, 8.5)
+        ax.yaxis.set_major_locator(plt.MultipleLocator(1))  # type: ignore
+        ax.yaxis.set_minor_locator(plt.MultipleLocator(0.5))  # type: ignore
+
+    plt.tight_layout(rect=(0, 0.2, 1, 1))
+
+    # Prepare return data
+    means_df.insert(0, "parameter", parameter)
+    return fig, means_df

plotting_style_guide.md

@@ -0,0 +1,163 @@
+# State of the Bay Plotting Style Guide
+
+This guide ensures consistency across all data visualizations in the State of the Bay project.
+
+## 1. Layout and Sizing
+
+### Figure Dimensions
+- Standard plots: `figsize=(12, 8)`
+- Panel/faceted plots: `figsize=(15, 2.5 * n_panels)`
+- Use `plt.tight_layout()` for proper spacing
+- Arrange multi-panel plots vertically for better comparison
+
+## 2. Colors and Visual Elements
+
+### Color Palette
+- Use predefined `COLOR_SCALE` for consistency
+- Grey tones:
+  ```python
+  GREY30 = "#4d4d4d"  # Dark grey for titles
+  GREY40 = "#666666"  # Medium grey for axes and labels
+  ```
+- Use alpha transparency (0.5-0.7) for overlays
+
+### Line Styles
+- Trend lines: dashed (`--`), red, `alpha=0.7`, `linewidth=1.5`
+- Grid lines: light grey, `alpha=0.15`
+
+## 3. Axes and Spines
+
+### Spine Configuration
+```python
+# Remove unnecessary spines
+ax.spines["top"].set_visible(False)
+ax.spines["right"].set_visible(False)
+
+# Style bottom spine
+ax.spines["bottom"].set_color(GREY40)
+ax.spines["bottom"].set_linewidth(0.5)
+
+# Remove tick marks but keep labels
+ax.tick_params(axis="both", which="both", length=0, colors=GREY40)
+```
+
+## 4. Grid Lines
+
+### Configuration
+```python
+ax.grid(True, axis="y", alpha=0.15, linestyle="-", color="gray")
+```
+
+## 5. Text Elements
+
+### Typography
+- Main titles: centered, size 12
+- Panel titles: size 10, `color=GREY30`, `pad=10`
+- Axis labels: size 10, `color=GREY40`
+
+### Statistics and Annotations
+```python
+ax.text(
+    0.02, 0.98,
+    stats_text,
+    transform=ax.transAxes,
+    verticalalignment="top",
+    fontsize=8,
+    bbox=dict(facecolor="white", alpha=0.8, edgecolor="none")
+)
+```
+
+## 6. Data Visualization
+
+### Line Charts
+- Include confidence intervals (shaded regions)
+- Solid lines for main trends
+- Consistent line thickness
+
+### Box Plots
+```python
+boxplot_props = {
+    "patch_artist": True,
+    "medianprops": dict(color="black"),
+    "flierprops": dict(
+        marker="o",
+        markerfacecolor=color_scale[idx],
+        alpha=0.5,
+        markersize=4
+    ),
+    "boxprops": dict(facecolor=color_scale[idx], alpha=0.6),
+    "widths": 0.6
+}
+```
+
+## 7. Scales and Ranges
+
+### Automatic Log Scaling
+```python
+use_log_scale = parameter in [
+    "Turbidity",
+    "Fecal Coliform (MPN)",
+    "Total Nitrogen",
+    "Total Phosphorus",
+]
+```
+
+### Best Practices
+- Add padding to axis limits
+- Use consistent y-axis ranges across comparison panels
+- Handle edge cases gracefully
+
+## 8. Function Structure
+
+### Return Values
+```python
+def plot_function(df: pd.DataFrame, parameter: str) -> tuple[Figure, pd.DataFrame, pd.DataFrame]:
+    """
+    Create a visualization.
+
+    Parameters:
+    -----------
+    df : pd.DataFrame
+        Input dataframe
+    parameter : str
+        Parameter to plot
+
+    Returns:
+    --------
+    tuple[Figure, pd.DataFrame, pd.DataFrame]
+        - Figure: Matplotlib figure
+        - DataFrame: Raw data used in plot
+        - DataFrame: Processed data points
+    """
+    # ... plotting code ...
+    return fig, raw_data, plot_data
+```
+
+## 9. Error Handling
+
+### Guidelines
+- Handle missing data gracefully
+- Include data validation
+- Provide appropriate fallbacks for edge cases
+- Log warnings for potential issues
+
+## 10. Optional Features
+
+### Configurable Elements
+```python
+def plot_function(
+    df: pd.DataFrame,
+    parameter: str,
+    show_sem: bool = True,
+    show_trend: bool = True,
+    panel_chart: bool = False,
+    color_scale: list[str] = COLOR_SCALE,
+) -> tuple[Figure, pd.DataFrame, pd.DataFrame]:
+    """..."""
+```
+
+### Common Options
+- `show_sem`: Toggle standard error margins
+- `show_trend`: Toggle trend lines and statistics
+- `panel_chart`: Toggle between single and multi-panel layouts
+- `color_scale`: Override default color palette 

ui/pages/sector_compare.py

@@ -6,12 +6,14 @@ import streamlit as st
 from components import render_filtered_data_preview
 from dashboard_analytics import log_visit
 from plots.sector import (
+    plot_grouped_bars,
     plot_sector_box_charts,
     plot_sector_heatmap,
     plot_sector_line_charts,
 )
 
 st.title("Sector Comparison Charts")
+st.info("👈 Select a chart type and parameter from the sidebar")
 log_visit("Sector Comparison Charts")
 
 # Get data from session state
@@ -21,13 +23,13 @@ raw_df["Date"] = pd.to_datetime(raw_df["Activity_Start_Date_Time"]).dt.date
 # Create sidebar controls
 chart_type = st.sidebar.radio(
     "Chart Type:",
-    options=["Line Charts", "Box and Whisker", "Heatmap"],
+    options=["Line Charts", "Box and Whisker", "Heatmap", "Grouped Bars"],
     help="Select the type of chart to display.",
     key="sector_compare_chart_type",
 )
 
 # Only show relevant controls based on chart type
-if chart_type in ["Line Charts", "Heatmap", "Box and Whisker"]:
+if chart_type in ["Line Charts", "Heatmap", "Box and Whisker", "Grouped Bars"]:
     st.sidebar.markdown("#### Chart Specific Options")
 if chart_type == "Line Charts":
     show_sem = st.sidebar.checkbox(
@@ -50,6 +52,14 @@ elif chart_type == "Box and Whisker":
         help="Display trend line with R² and p-values",
         key="sector_compare_show_trend",
     )
+elif chart_type == "Grouped Bars":
+    group_by = st.sidebar.radio(
+        "Group bars by:",
+        options=["Sector", "Year"],
+        index=0,
+        key="sector_compare_group_by",
+        help="Choose how to group the bars.",
+    ).lower()
 
 selected_parameter = st.sidebar.selectbox(
     "Parameter:",
@@ -99,6 +109,15 @@ try:
             filtered_raw_df, selected_parameter, show_trend=show_trend
         )
         st.pyplot(fig)
+    elif chart_type == "Grouped Bars":
+        # Create grouped bar charts
+        fig, plot_data = plot_grouped_bars(
+            filtered_raw_df, selected_parameter, year_range, group_by
+        )
+        st.pyplot(fig)
+        param_data = filtered_raw_df[
+            filtered_raw_df["Org_Analyte_Name"] == selected_parameter
+        ].copy()
     else:  # Heatmap
         # Create heatmap
         fig, param_data, plot_data = plot_sector_heatmap(