Deploy from GitHub Actions

analysis.py

@@ -501,7 +501,7 @@ def plot_sector_trends(
 
         # For Salinity, exclude Fresh Water Lakes
         if analyte_name == "Salinity":
-            analyte_data = analyte_data[analyte_data["Sector"] != "Fresh Water Lakes"]
+            analyte_data = analyte_data[analyte_data["Sector"] != "Freshwater Lakes"]
 
         # Plot each sector with custom colors
         for sector, color in zip(df["Sector"].unique(), custom_colors):
@@ -2207,7 +2207,7 @@ def plot_grouped_bars(
     parameter: str,
     year_range: tuple[int, int],
     group_by: str = "sector",
-) -> Figure:
+) -> tuple[Figure, pd.DataFrame]:
     """
     Create a grouped bar chart showing means by sector or year for a selected parameter.
 
@@ -2224,8 +2224,9 @@ def plot_grouped_bars(
 
     Returns:
     --------
-    Figure
-        Matplotlib figure containing the grouped bar chart
+    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[
@@ -2330,9 +2331,9 @@ def plot_grouped_bars(
 
     # Customize plot
     unit = plot_df["Org_Result_Unit"].iloc[0]
-    # ax.set_ylabel(f"{parameter} ({unit})")
     ax.set_xlabel(x_label)
-    ax.set_title(f"{parameter} (Mean Annual {unit})")
+    title = f"{parameter} (Mean Annual{' ' + unit if unit else ''})"
+    ax.set_title(title)
 
     # Function to wrap text
     def wrap_labels(text, width=10):
@@ -2359,7 +2360,7 @@ def plot_grouped_bars(
     # Add error bar note with adjusted position
     ax.text(
         0.99,
-        -0.15,  # Moved down slightly to accommodate wrapped labels
+        -0.15,
         "Error bars represent ±1 standard error of the mean",
         ha="right",
         va="top",
@@ -2369,7 +2370,7 @@ def plot_grouped_bars(
     )
 
     # Adjust layout with more vertical space for wrapped labels
-    plt.tight_layout(rect=(0, 0.2, 1, 1))  # Increased bottom padding
+    plt.tight_layout(rect=(0, 0.2, 1, 1))
 
     # Add grid
     ax.grid(True, axis="y", alpha=0.2, linestyle="-", zorder=1)
@@ -2377,12 +2378,10 @@ def plot_grouped_bars(
     # Customize spines
     ax.spines["top"].set_visible(False)
     ax.spines["right"].set_visible(False)
-    ax.spines["left"].set_visible(False)  # Add this line to remove left spine
+    ax.spines["left"].set_visible(False)
 
     # Remove tick marks but keep labels
-    ax.tick_params(
-        axis="y", which="both", length=0
-    )  # Add this line to remove tick marks
+    ax.tick_params(axis="y", which="both", length=0)
 
     ax.legend(
         bbox_to_anchor=(1.02, 1),  # Position at top-right
@@ -2403,7 +2402,8 @@ def plot_grouped_bars(
         ax.set_yscale("log")
         ax.yaxis.set_major_formatter(plt.ScalarFormatter())  # type: ignore
 
-    return fig
+    means_df.insert(0, "parameter", parameter)
+    return fig, means_df
 
 
 def plot_seasonal_line(
@@ -2687,3 +2687,212 @@ def plot_seasonal_line(
         plt.tight_layout(rect=(0, 0, 0.9, 1))
     stats_df.insert(0, "parameter", parameter)
     return fig, param_data, stats_df
+
+
+@timer(include_params=True)
+def plot_sector_line_charts(
+    df: pd.DataFrame,
+    parameter: str,
+    show_sem: bool = True,
+    panel_chart: bool = False,
+) -> tuple[Figure, pd.DataFrame, pd.DataFrame]:
+    """
+    Create a plot of mean annual parameter trends by sector.
+
+    Parameters:
+    -----------
+    df : pd.DataFrame
+        Input dataframe
+    parameter : str
+        Name of the parameter to plot
+    show_sem : bool, default=True
+        Whether to show the standard error of the mean bands
+    panel_chart : bool, default=False
+        If True, creates a grid of individual sector charts instead of overlapping lines
+
+    Returns:
+    --------
+    tuple[Figure, pd.DataFrame, pd.DataFrame]
+        - Figure: Matplotlib figure containing the line chart(s)
+        - DataFrame: Filtered dataframe containing the data used in the plot
+        - DataFrame: Contains the plotted data points with means and standard errors
+    """
+    # Filter data for parameter
+    param_data = df[df["Org_Analyte_Name"] == parameter].copy()
+
+    # For Salinity, exclude Freshwater Lakes
+    if parameter == "Salinity":
+        param_data = param_data[param_data["Sector"] != "Freshwater Lakes"]
+
+    # Get unique sectors and years
+    sectors = sorted(param_data["Sector"].unique())
+    years = sorted(param_data["Reporting_Year"].unique())
+    n_sectors = len(sectors)
+
+    # Calculate grid dimensions for panel chart
+    if panel_chart:
+        n_cols = min(3, n_sectors)  # Maximum 3 columns
+        n_rows = (n_sectors + n_cols - 1) // n_cols
+        fig = plt.figure(figsize=(5 * n_cols, 3 * n_rows))
+    else:
+        fig, ax = plt.subplots(figsize=(14, 4))
+
+    custom_colors = [
+        "#1f77b4",  # blue
+        "#ff7f0e",  # orange
+        "#2ca02c",  # green
+        "#d62728",  # red
+        "#9467bd",  # purple
+        "#8c564b",  # brown
+        "#e377c2",  # pink
+        "#7f7f7f",  # gray
+    ]
+
+    # Initialize empty list to store sector data
+    all_sector_data = []
+
+    # Get global y-axis limits for consistent scaling
+    y_min = float("inf")
+    y_max = float("-inf")
+
+    # First pass to get y-axis limits
+    for sector in sectors:
+        sector_data = (
+            param_data[param_data["Sector"] == sector]
+            .groupby("Reporting_Year", observed=True)["Org_Result_Value"]
+            .agg(["mean", "sem"])
+            .reset_index()
+        )
+        if not sector_data.empty:
+            y_min = min(y_min, (sector_data["mean"] - sector_data["sem"]).min())
+            y_max = max(y_max, (sector_data["mean"] + sector_data["sem"]).max())
+
+    # Plot each sector
+    for i, (sector, color) in enumerate(zip(sectors, custom_colors)):
+        sector_data = (
+            param_data[param_data["Sector"] == sector]
+            .groupby("Reporting_Year", observed=True)["Org_Result_Value"]
+            .agg(["mean", "sem"])
+            .reset_index()
+        )
+
+        # Add sector column to the data
+        sector_data["Sector"] = sector
+        all_sector_data.append(sector_data)
+
+        if not sector_data.empty:
+            if panel_chart:
+                ax = fig.add_subplot(n_rows, n_cols, i + 1)
+
+                # Plot mean line with error bands for this sector
+                ax.plot(
+                    sector_data["Reporting_Year"],
+                    sector_data["mean"],
+                    "-o",
+                    color=color,
+                    markersize=4,
+                    linewidth=2,
+                )
+
+                if show_sem:
+                    ax.fill_between(
+                        sector_data["Reporting_Year"],
+                        sector_data["mean"] - sector_data["sem"],
+                        sector_data["mean"] + sector_data["sem"],
+                        color=color,
+                        alpha=0.15,
+                    )
+
+                # Customize individual panel
+                ax.set_title(sector, pad=10, fontsize=10)
+                ax.grid(True, axis="y", alpha=0.2, linestyle="--")
+                ax.spines["top"].set_visible(False)
+                ax.spines["right"].set_visible(False)
+                ax.spines["left"].set_visible(False)
+                ax.tick_params(axis="y", which="both", length=0)
+                ax.set_xticks(years)
+                ax.set_xticklabels(years, rotation=45)
+
+                # Set consistent y-axis limits
+                if parameter in [
+                    "Turbidity",
+                    "Fecal Coliform (MPN)",
+                    "Total Nitrogen",
+                    "Total Phosphorus",
+                ]:
+                    ax.set_yscale("log")
+                else:
+                    ax.set_ylim(y_min * 0.95, y_max * 1.05)
+
+            else:
+                # Original single-panel plotting code
+                ax.plot(
+                    sector_data["Reporting_Year"],
+                    sector_data["mean"],
+                    "-o",
+                    color=color,
+                    label=sector,
+                    markersize=4,
+                    linewidth=2,
+                )
+
+                if show_sem:
+                    ax.fill_between(
+                        sector_data["Reporting_Year"],
+                        sector_data["mean"] - sector_data["sem"],
+                        sector_data["mean"] + sector_data["sem"],
+                        color=color,
+                        alpha=0.15,
+                    )
+
+    # Get parameter unit
+    param_unit = param_data["Org_Result_Unit"].iloc[0] if not param_data.empty else ""
+
+    if panel_chart:
+        # Add common title and labels
+        fig.suptitle(f"{parameter} ({param_unit})", fontsize=14, y=1.02)
+        fig.text(0.5, 0.02, "Year", ha="center", fontsize=12)
+        fig.text(
+            0.02,
+            0.5,
+            f"Value ({param_unit})",
+            va="center",
+            rotation="vertical",
+            fontsize=12,
+        )
+    else:
+        # Original single-panel customization
+        ax.set_title(parameter, pad=10, fontsize=14, fontweight="normal")
+        ax.set_xlabel("Year", fontsize=12)
+        ax.set_ylabel(f"{parameter} ({param_unit})", fontsize=12)
+        ax.set_xticks(years)
+        ax.set_xticklabels(years)
+        ax.grid(True, axis="y", alpha=0.2, linestyle="--")
+        ax.spines["top"].set_visible(False)
+        ax.spines["right"].set_visible(False)
+        ax.spines["left"].set_visible(False)
+        ax.tick_params(axis="y", which="both", length=0)
+        ax.legend(
+            bbox_to_anchor=(1.05, 1),
+            loc="upper left",
+            borderaxespad=0.0,
+            frameon=False,
+            fontsize=9,
+        )
+
+        if parameter in [
+            "Turbidity",
+            "Fecal Coliform (MPN)",
+            "Total Nitrogen",
+            "Total Phosphorus",
+        ]:
+            ax.set_yscale("log")
+
+    # Adjust layout
+    plt.tight_layout()
+
+    # Combine all sector data into a single dataframe
+    plot_data = pd.concat(all_sector_data, ignore_index=True)
+    plot_data.insert(0, "parameter", parameter)
+
+    return fig, param_data, plot_data

app.py

@@ -16,6 +16,7 @@ from pages import (
     scatter_plots_page,
     seasonal_line_charts_page,
     seasonal_trends_page,
+    sector_compare_page,
     sector_trends_page,
     settings_page,
     trends_by_station_page,
@@ -47,6 +48,7 @@ page_dict = {}
 
 page_dict["Annual Report Draft Charts/Tables"] = [
     seasonal_line_charts_page,
+    sector_compare_page,
     scatter_plots_page,
     grouped_bar_charts_page,
     parameter_summary_tables_page,

pages.py

@@ -855,6 +855,12 @@ def trends_by_station_section():
         )
 
 
+sector_compare_page = st.Page(
+    "ui/pages/sector_compare.py",
+    title="Sector Comparison",
+    icon=":material/ssid_chart:",
+)
+
 home_page = st.Page(
     home_section,
     title="Home",
@@ -953,4 +959,5 @@ __all__ = [
     "scatter_plots_page",
     "grouped_bar_charts_page",
     "seasonal_line_charts_page",
+    "sector_compare_page",
 ]

ui/pages/grouped_bar_charts.py

@@ -1,7 +1,10 @@
+import io
+
 import pandas as pd
 import streamlit as st
 
 from analysis import plot_grouped_bars
+from components import render_filtered_data_preview
 from dashboard_analytics import log_visit
 
 st.title("Grouped Bar Charts")
@@ -46,7 +49,56 @@ else:
     year_range = (min(years), max(years))
 
 try:
-    fig = plot_grouped_bars(raw_df, selected_parameter, year_range, group_by)
+    fig, means_df = plot_grouped_bars(raw_df, selected_parameter, year_range, group_by)
     st.pyplot(fig)
+
+    # Add Chart Data expander
+    with st.expander("Chart Data"):
+        render_filtered_data_preview(
+            means_df, display_columns=means_df.columns.tolist()
+        )
+
+        # Add CSV download button for chart data
+        csv_buffer = io.StringIO()
+        means_df.to_csv(csv_buffer, index=False)
+        st.download_button(
+            label=f"Download Chart Data for {selected_parameter} (CSV)",
+            data=csv_buffer.getvalue(),
+            file_name=f"{selected_parameter}_grouped_by_{group_by}_year-{year_range[0]}-{year_range[1]}_chart_data.csv",
+            mime="text/csv",
+        )
+
+    # Add Raw Data expander
+    with st.expander("Raw Data"):
+        # Filter raw data for the selected parameter and year range
+        filtered_df = raw_df[
+            (raw_df["Org_Analyte_Name"] == selected_parameter)
+            & (raw_df["Activity_Start_Date_Time"].dt.year >= year_range[0])
+            & (raw_df["Activity_Start_Date_Time"].dt.year <= year_range[1])
+        ]
+
+        # Display filtered data preview
+        render_filtered_data_preview(
+            filtered_df,
+            [
+                "Date",
+                "Sector",
+                "Station_Number",
+                "Sample_Position",
+                "Org_Analyte_Name",
+                "Org_Result_Value",
+            ],
+        )
+
+        # Add CSV download button for raw data
+        csv_buffer = io.StringIO()
+        filtered_df.to_csv(csv_buffer, index=False)
+        st.download_button(
+            label=f"Download Raw Data for {selected_parameter} (CSV)",
+            data=csv_buffer.getvalue(),
+            file_name=f"{selected_parameter}_grouped_by_{group_by}_year-{year_range[0]}-{year_range[1]}_raw_data.csv",
+            mime="text/csv",
+        )
+
 except ValueError as e:
     st.warning(str(e))

ui/pages/sector_compare.py

@@ -0,0 +1,112 @@
+import io
+
+import pandas as pd
+import streamlit as st
+
+from analysis import plot_sector_line_charts
+from components import render_filtered_data_preview
+from dashboard_analytics import log_visit
+
+st.title("Sector Comparison Charts")
+log_visit("Sector Comparison Charts")
+
+# Get data from session state
+raw_df = st.session_state.data["raw_df"]
+raw_df["Date"] = pd.to_datetime(raw_df["Activity_Start_Date_Time"]).dt.date
+
+# Create sidebar controls
+selected_parameter = st.sidebar.selectbox(
+    "Parameter:",
+    options=sorted(raw_df["Org_Analyte_Name"].unique()),
+    index=sorted(raw_df["Org_Analyte_Name"].unique()).index("Temperature, Water")
+    if "Temperature, Water" in raw_df["Org_Analyte_Name"].unique()
+    else 0,
+    help="Select a parameter to display.",
+    key="sector_compare_parameter_select",
+)
+
+# Add show_sem checkbox
+show_sem = st.sidebar.checkbox(
+    "Show Standard Error",
+    value=True,
+    help="Display standard error bands around the mean lines",
+    key="sector_compare_show_sem",
+)
+
+# Add year filter slider
+years = sorted(raw_df["Activity_Start_Date_Time"].dt.year.unique())
+default_min_year = min(years)
+if len(years) >= 2:
+    year_range = st.sidebar.slider(
+        "Year Range:",
+        min_value=min(years),
+        max_value=max(years),
+        value=(default_min_year, max(years)),
+        key="sector_compare_year_range",
+    )
+else:
+    year_range = (min(years), max(years))
+
+# Filter data based on year range
+filtered_raw_df = raw_df[
+    (raw_df["Activity_Start_Date_Time"].dt.year >= year_range[0])
+    & (raw_df["Activity_Start_Date_Time"].dt.year <= year_range[1])
+]
+
+try:
+    fig, param_data, plot_data = plot_sector_line_charts(
+        filtered_raw_df, selected_parameter, show_sem=show_sem
+    )
+    st.pyplot(fig)
+
+    fig, _, _ = plot_sector_line_charts(
+        filtered_raw_df, selected_parameter, show_sem=show_sem, panel_chart=True
+    )
+    st.pyplot(fig)
+
+    # Add Chart Data expander
+    with st.expander("Chart Data"):
+        render_filtered_data_preview(
+            plot_data, display_columns=plot_data.columns.tolist()
+        )
+
+        # Add CSV download button for chart data
+        csv_buffer = io.StringIO()
+        plot_data.to_csv(csv_buffer, index=False)
+        st.download_button(
+            label=f"Download Chart Data for {selected_parameter} (CSV)",
+            data=csv_buffer.getvalue(),
+            file_name=f"{selected_parameter}_sector_comparison_year-{year_range[0]}-{year_range[1]}_chart_data.csv",
+            mime="text/csv",
+        )
+
+    # Add Raw Data expander
+    with st.expander("Raw Data"):
+        # Filter raw data for the selected parameter
+        filtered_df = param_data.copy()
+
+        # Display filtered data preview
+        render_filtered_data_preview(
+            filtered_df,
+            [
+                "Date",
+                "Sector",
+                "Station_Number",
+                "Sample_Position",
+                "Org_Analyte_Name",
+                "Org_Result_Value",
+            ],
+        )
+
+        # Add CSV download button for raw data
+        csv_buffer = io.StringIO()
+        filtered_df.to_csv(csv_buffer, index=False)
+        st.download_button(
+            label=f"Download Raw Data for {selected_parameter} (CSV)",
+            data=csv_buffer.getvalue(),
+            file_name=f"{selected_parameter}_sector_comparison_year-{year_range[0]}-{year_range[1]}_raw_data.csv",
+            mime="text/csv",
+        )
+
+except ValueError as e:
+    st.warning(str(e))