Add all files with LFS support

admin.py

@@ -0,0 +1,49 @@
+import os
+
+import streamlit as st
+
+ADMIN_PASSWORD = os.getenv("ADMIN_PASSWORD", "")
+
+
+def init_admin_state():
+    """Initialize admin-related session state variables"""
+    if "admin_authenticated" not in st.session_state:
+        st.session_state.admin_authenticated = False
+
+    if "ENABLE_TIMING" not in st.session_state:
+        st.session_state.ENABLE_TIMING = False
+
+
+def check_admin_access() -> bool:
+    """Check if admin access is granted"""
+    if not ADMIN_PASSWORD:
+        return False
+    return st.session_state.get("admin_authenticated", False)
+
+
+def render_admin_panel():
+    """Render admin UI elements in the sidebar"""
+    with st.sidebar:
+        st.markdown("---")
+        with st.expander("🔒 Admin", expanded=False):
+            if st.session_state.admin_authenticated:
+                if st.button("Logout"):
+                    st.session_state.admin_authenticated = False
+                    st.rerun()
+            else:
+                password_input = st.text_input("Password", type="password")
+                if st.button("Login"):
+                    if password_input == ADMIN_PASSWORD:
+                        st.session_state.admin_authenticated = True
+                        st.rerun()
+                    else:
+                        st.error("Incorrect password")
+
+            if st.session_state.admin_authenticated:
+                enable_timing = st.toggle(
+                    "Enable Timing",
+                    value=st.session_state.ENABLE_TIMING,
+                    key="timing_toggle",
+                )
+                if enable_timing != st.session_state.ENABLE_TIMING:
+                    st.session_state.ENABLE_TIMING = enable_timing

analytics.py

@@ -0,0 +1,98 @@
+import json
+import uuid
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+import streamlit as st
+
+
+def init_analytics_state() -> None:
+    """Initialize analytics-related session state variables"""
+    if "logged_visit" not in st.session_state:
+        st.session_state.logged_visit = False
+
+    if "visitor_id" not in st.session_state:
+        st.session_state.visitor_id = str(uuid.uuid4())
+
+
+def log_visit(current_section: Optional[str] = None) -> None:
+    """Log visitor analytics including timestamp, user agent, and page info"""
+    if st.session_state.get("admin_authenticated", False):
+        return
+
+    log_file = Path("analytics.json")
+    now = datetime.now()
+    today = now.strftime("%Y-%m-%d")
+
+    try:
+        user_agent = st.context.headers.get("User-Agent", "Unknown")
+    except Exception:
+        user_agent = "Unknown"
+
+    visit_type = (
+        "initial" if not st.session_state.get("logged_visit") else "section_change"
+    )
+
+    visit_data = {
+        "timestamp": now.isoformat(),
+        "date": today,
+        "user_agent": user_agent,
+        "visitor_id": st.session_state.visitor_id,
+        "page_section": current_section
+        or st.session_state.get("current_section", "Overall Summary"),
+        "visit_type": visit_type,
+        "query_params": dict(st.query_params),
+    }
+
+    # Initialize default data structure
+    data = {
+        "visits": [],
+        "daily_counts": {},
+        "section_counts": {},
+        "daily_visitors": {},
+    }
+
+    # Try to load existing data, fallback to default if corrupted
+    if log_file.exists():
+        try:
+            with open(log_file, "r") as f:
+                data = json.load(f)
+                if "visits" not in data:
+                    data["visits"] = []
+                if "daily_counts" not in data:
+                    data["daily_counts"] = {}
+                if "section_counts" not in data:
+                    data["section_counts"] = {}
+                if "daily_visitors" not in data:
+                    data["daily_visitors"] = {}
+        except json.JSONDecodeError:
+            # If file is corrupted, backup the old file and start fresh
+            if log_file.exists():
+                backup_file = log_file.with_suffix(".json.bak")
+                log_file.rename(backup_file)
+
+    if today not in data["daily_visitors"]:
+        data["daily_visitors"][today] = []
+    if st.session_state.visitor_id not in data["daily_visitors"][today]:
+        data["daily_visitors"][today].append(st.session_state.visitor_id)
+        data["daily_counts"][today] = len(data["daily_visitors"][today])
+
+    data["visits"].append(visit_data)
+    current_section = visit_data["page_section"]
+    data["section_counts"][current_section] = (
+        data["section_counts"].get(current_section, 0) + 1
+    )
+
+    with open(log_file, "w") as f:
+        json.dump(data, f, indent=2)
+
+
+def get_analytics_data() -> Dict[str, Any]:
+    """Load and return analytics data from file"""
+    log_file = Path("analytics.json")
+    if not log_file.exists():
+        return {}
+
+    with open(log_file, "r") as f:
+        return json.load(f)

app.py

@@ -1,11 +1,9 @@
 import calendar
 import io
-import json
 import os
 import sys
 import textwrap
 import time
-import uuid
 from datetime import date, datetime
 from functools import wraps
 from pathlib import Path
@@ -19,6 +17,7 @@ from great_tables import GT, html
 from matplotlib import pyplot as plt
 from osgeo import gdal
 
+from admin import check_admin_access, init_admin_state, render_admin_panel
 from analysis import (
     altair_plot_do_temp_relationship,
     altair_plot_np_ratios,
@@ -31,6 +30,15 @@ from analysis import (
     plot_seasonal_salinity_for_bays,
     plot_sector_trends,
 )
+from analytics import get_analytics_data, init_analytics_state, log_visit
+from components import (
+    get_reporting_year_info_message,
+    on_date_change,
+    render_date_filters,
+    render_filtered_data_preview,
+    render_sidebar_analyte_multiselect,
+    render_sidebar_position_filter_selectbox,
+)
 from main import (
     create_multiindex_columns,
     create_overall_summary,
@@ -47,6 +55,8 @@ if os.getenv("DEBUG", "false").lower() == "true":
 else:
     st.session_state.DEBUG = False
 
+init_admin_state()
+
 if "ENABLE_TIMING" not in st.session_state:
     st.session_state.ENABLE_TIMING = False
 
@@ -71,139 +81,12 @@ if "logged_visit" not in st.session_state:
 if "current_section" not in st.session_state:
     st.session_state.current_section = "Overall Summary"
 
-
-def log_visit():
-    """Log visitor analytics including timestamp, user agent, and page info"""
-    if st.session_state.get("admin_authenticated", False):
-        return
-    log_file = Path("analytics.json")
-    now = datetime.now()
-    today = now.strftime("%Y-%m-%d")
-
-    if "visitor_id" not in st.session_state:
-        st.session_state.visitor_id = str(uuid.uuid4())
-
-    try:
-        user_agent = st.context.headers.get("User-Agent", "Unknown")
-    except Exception:
-        user_agent = "Unknown"
-
-    visit_type = (
-        "initial" if not st.session_state.get("logged_visit") else "section_change"
-    )
-
-    visit_data = {
-        "timestamp": now.isoformat(),
-        "date": today,
-        "user_agent": user_agent,
-        "visitor_id": st.session_state.visitor_id,
-        "page_section": st.session_state.get("current_section", "Overall Summary"),
-        "visit_type": visit_type,
-        "query_params": dict(st.query_params),
-    }
-
-    # Initialize default data structure
-    data = {
-        "visits": [],
-        "daily_counts": {},
-        "section_counts": {},
-        "daily_visitors": {},
-    }
-
-    # Try to load existing data, fallback to default if corrupted
-    if log_file.exists():
-        try:
-            with open(log_file, "r") as f:
-                data = json.load(f)
-                if "visits" not in data:
-                    data["visits"] = []
-                if "daily_counts" not in data:
-                    data["daily_counts"] = {}
-                if "section_counts" not in data:
-                    data["section_counts"] = {}
-                if "daily_visitors" not in data:
-                    data["daily_visitors"] = {}
-        except json.JSONDecodeError:
-            # If file is corrupted, backup the old file and start fresh
-            if log_file.exists():
-                backup_file = log_file.with_suffix(".json.bak")
-                log_file.rename(backup_file)
-            # Continue with default data structure
-
-    if today not in data["daily_visitors"]:
-        data["daily_visitors"][today] = []
-    if st.session_state.visitor_id not in data["daily_visitors"][today]:
-        data["daily_visitors"][today].append(st.session_state.visitor_id)
-        data["daily_counts"][today] = len(data["daily_visitors"][today])
-
-    data["visits"].append(visit_data)
-    current_section = visit_data["page_section"]
-    data["section_counts"][current_section] = (
-        data["section_counts"].get(current_section, 0) + 1
-    )
-
-    with open(log_file, "w") as f:
-        json.dump(data, f, indent=2)
-
+init_analytics_state()
 
 if not st.session_state.get("logged_visit"):
     log_visit()
     st.session_state["logged_visit"] = True
 
-ADMIN_PASSWORD = os.getenv("ADMIN_PASSWORD", "")
-
-
-def check_admin_access():
-    """Handle admin authentication logic only"""
-    if not ADMIN_PASSWORD:
-        return False
-
-    if "admin_authenticated" not in st.session_state:
-        st.session_state.admin_authenticated = False
-
-    return st.session_state.admin_authenticated
-
-
-def render_admin_panel():
-    """Handle admin UI elements only"""
-    with st.sidebar:
-        st.markdown("---")
-        with st.expander("🔒 Admin", expanded=False):
-            if st.session_state.admin_authenticated:
-                if st.button("Logout"):
-                    st.session_state.admin_authenticated = False
-                    st.rerun()
-            else:
-                password_input = st.text_input("Password", type="password")
-                if st.button("Login"):
-                    if password_input == ADMIN_PASSWORD:
-                        st.session_state.admin_authenticated = True
-                        st.rerun()
-                    else:
-                        st.error("Incorrect password")
-
-            if st.session_state.admin_authenticated:
-                enable_timing = st.toggle(
-                    "Enable Timing",
-                    value=st.session_state.ENABLE_TIMING,
-                    key="timing_toggle",
-                )
-                if enable_timing != st.session_state.ENABLE_TIMING:
-                    st.session_state.ENABLE_TIMING = enable_timing
-
-
-def get_reporting_year_info_message() -> str:
-    """Generate standardized info message about reporting year grouping."""
-    example_year = st.session_state.dataset_end_date.year
-    return f"""
-        📅 **Data is grouped by reporting years**:
-        -     Each reporting year ends in **{calendar.month_name[st.session_state.reporting_month]}**.
-        -     Example: Reporting year **{example_year}** covers 
-        **{calendar.month_abbr[st.session_state.reporting_month + 1 if st.session_state.reporting_month < 12 else 1]}. {example_year - 1 if st.session_state.reporting_month < 12 else example_year}** 
-        through **{calendar.month_abbr[st.session_state.reporting_month]}. {example_year}**.
-        - &nbsp;&nbsp;&nbsp;&nbsp;**Note**: You can change the reporting year end month in the **Dataset Settings** in the sidebar.
-        """
-
 
 st.set_page_config(
     page_title="Water Quality Summary",
@@ -600,39 +483,9 @@ with st.sidebar:
             day=calendar.monthrange(raw_end.year, raw_end.month)[1]
         )
 
-        def on_date_change():
-            """Callback for date input changes"""
-            start = st.session_state.dataset_start_date
-            end = st.session_state.dataset_end_date
-
-            if start > end:
-                st.error("Start date must be before end date")
-                return
-
-            st.session_state.start_date = start
-            st.session_state.end_date = end
-
-        col1, col2 = st.columns(2)
-        with col1:
-            start_date = st.date_input(
-                "Start Date",
-                value=min_date,
-                min_value=min_date,
-                max_value=max_date,
-                format="MM/DD/YYYY",
-                key="dataset_start_date",
-                on_change=on_date_change,
-            )
-        with col2:
-            end_date = st.date_input(
-                "End Date",
-                value=max_date,
-                min_value=min_date,
-                max_value=max_date,
-                format="MM/DD/YYYY",
-                key="dataset_end_date",
-                on_change=on_date_change,
-            )
+        start_date, end_date = render_date_filters(
+            min_date, max_date, key_prefix="dataset", on_change=on_date_change
+        )
 
         reporting_month = st.selectbox(
             "Last Month of Reporting Year",
@@ -779,8 +632,12 @@ elif section == "Summary by Station":
 
 elif section == "Trends by Station":
     st.title("Trends by Station")
-    st.info(get_reporting_year_info_message())
-    analyte_names = [
+    st.info(
+        get_reporting_year_info_message(
+            st.session_state.reporting_month, st.session_state.dataset_end_date.year
+        )
+    )
+    default_analytes = [
         "Dissolved Oxygen",
         "Salinity",
         "pH",
@@ -790,6 +647,11 @@ elif section == "Trends by Station":
         "Total Nitrogen",
         "Total Phosphorus",
     ]
+    all_analytes = default_analytes + [
+        x
+        for x in sorted(data["raw_df"]["Org_Analyte_Name"].unique())
+        if x not in default_analytes
+    ]
     st.sidebar.markdown("### Filter Options")
 
     selected_station = st.sidebar.selectbox(
@@ -804,6 +666,9 @@ elif section == "Trends by Station":
         selection_mode="single",
     )
     selected_position = selected_position or "All"
+    selected_analytes = render_sidebar_analyte_multiselect(
+        all_analytes, default_analytes, key_prefix="station_trends"
+    )
     filtered_df = data["raw_df"].query("Station_Number == @selected_station")
     if selected_position != "All":
         filtered_df = filtered_df.query("Sample_Position == @selected_position")
@@ -818,7 +683,6 @@ elif section == "Trends by Station":
     )
 
     with st.sidebar.expander("Preview Filtered Data"):
-        st.markdown(f"**{len(filtered_df):,}** records")
         display_columns = [
             "Activity_Start_Date_Time",
             "Sample_Position",
@@ -827,16 +691,10 @@ elif section == "Trends by Station":
             "Org_Result_Unit",
             "Reporting_Year",
         ]
-        preview_df = filtered_df[["Station_Number"] + display_columns].copy()
-        preview_df.set_index("Station_Number", inplace=True)
-        st.dataframe(
-            preview_df.style.format(precision=2),
-            use_container_width=True,
-            height=300,
-        )
+        render_filtered_data_preview(filtered_df, display_columns)
 
     if not filtered_df.empty:
-        fig = plot_analyte_trends(filtered_df, analyte_names, selected_position)
+        fig = plot_analyte_trends(filtered_df, selected_analytes, selected_position)
         st.pyplot(fig)
     else:
         st.warning(
@@ -848,7 +706,11 @@ elif section == "Sector Trends":
     st.session_state.ENABLE_ALTAIR = st.sidebar.toggle(
         "Interactive Plots", value=st.session_state.ENABLE_ALTAIR
     )
-    st.info(get_reporting_year_info_message())
+    st.info(
+        get_reporting_year_info_message(
+            st.session_state.reporting_month, st.session_state.dataset_end_date.year
+        )
+    )
     default_analytes = [
         "Dissolved Oxygen",
         "Salinity",
@@ -862,12 +724,8 @@ elif section == "Sector Trends":
         if x not in default_analytes
     ]
 
-    selected_analytes = st.sidebar.multiselect(
-        "Select Analytes:",
-        options=all_analytes,
-        default=default_analytes,
-        key="sector_analyte_select",
-        help="Choose one or more analytes to plot.",
+    selected_analytes = render_sidebar_analyte_multiselect(
+        all_analytes, default_analytes, key_prefix="sector_trends"
     )
     if selected_analytes and not data["raw_df"].empty:
         if st.session_state.ENABLE_ALTAIR:
@@ -885,8 +743,8 @@ elif section == "Parameter Correlations":
     st.title("Parameter Correlations")
     subset_by = "Sector"
     st.sidebar.markdown("### Filter Options")
-    position_filter = st.sidebar.selectbox(
-        "Sample Position:", ["All", "Surface", "Bottom"], index=0
+    position_filter = render_sidebar_position_filter_selectbox(
+        key_prefix="parameter_correlation"
     )
     with st.spinner("Loading data for correlation plots..."):
         analyte_names = [
@@ -988,7 +846,6 @@ elif section == "Parameter Correlations":
             cols[idx % 2].pyplot(fig)
             plt.close()
             with cols[idx % 2].expander(f"View {subset} Data"):
-                st.markdown(f"**{len(subset_df):,}** records")
                 display_columns = [
                     "Activity_Start_Date_Time",
                     "Station_Number",
@@ -997,11 +854,7 @@ elif section == "Parameter Correlations":
                     "Org_Result_Value",
                     "Org_Result_Unit",
                 ]
-                st.dataframe(
-                    subset_df[display_columns].style.format(precision=2),
-                    use_container_width=True,
-                    height=300,
-                )
+                render_filtered_data_preview(subset_df, display_columns)
                 csv_buffer = io.StringIO()
                 subset_df.to_csv(csv_buffer, index=False)
                 st.download_button(
@@ -1053,12 +906,11 @@ elif section == "Calendar Heatmaps":
         for x in sorted(raw_df["Org_Analyte_Name"].unique())
         if x not in default_analytes
     ]
-    selected_analytes = st.sidebar.multiselect(
-        "Select Analytes:",
-        options=all_analytes,
-        default=default_analytes,
-        key="calendar_analyte_select",
-        help="Choose one or more analytes to display in the heatmap.",
+    selected_analytes = render_sidebar_analyte_multiselect(
+        all_analytes=all_analytes,
+        default_analytes=default_analytes,
+        key_prefix="calendar",
+        help_text="Choose one or more analytes to display in the heatmap.",
     )
 
     # Filter Options
@@ -1069,12 +921,7 @@ elif section == "Calendar Heatmaps":
         index=0,
         key="calendar_sector_select",
     )
-    position_filter = st.sidebar.selectbox(
-        "Position:",
-        ["All", "Surface", "Bottom"],
-        index=0,
-        key="calendar_position_select",
-    )
+    position_filter = render_sidebar_position_filter_selectbox(key_prefix="calendar")
 
     def format_colormap_option(option):
         append = ""
@@ -1237,63 +1084,58 @@ elif section == "Raw Data":
 
 elif section == "Analytics":
     st.title("Analytics")
+    analytics_data = get_analytics_data()
 
-    log_file = Path("analytics.json")
-    if log_file.exists():
-        with open(log_file, "r") as f:
-            analytics_data = json.load(f)
+    col1, col2 = st.columns(2)
 
-        col1, col2 = st.columns(2)
+    with col1:
+        visits_df = pd.DataFrame(analytics_data["visits"])
+        visits_df["timestamp"] = pd.to_datetime(visits_df["timestamp"])
 
-        with col1:
-            visits_df = pd.DataFrame(analytics_data["visits"])
-            visits_df["timestamp"] = pd.to_datetime(visits_df["timestamp"])
+        daily_visits_df = (
+            visits_df.groupby("date")["visitor_id"]
+            .agg(["nunique", "count"])
+            .reset_index()
+            .rename(columns={"nunique": "Unique Visitors", "count": "Total Views"})
+        )
+        daily_visits_df["date"] = pd.to_datetime(daily_visits_df["date"])
+        daily_visits_df = daily_visits_df.sort_values("date")
 
-            daily_visits_df = (
-                visits_df.groupby("date")["visitor_id"]
-                .agg(["nunique", "count"])
-                .reset_index()
-                .rename(columns={"nunique": "Unique Visitors", "count": "Total Views"})
-            )
-            daily_visits_df["date"] = pd.to_datetime(daily_visits_df["date"])
-            daily_visits_df = daily_visits_df.sort_values("date")
+        total_unique_visitors = visits_df["visitor_id"].nunique()
+        total_views = len(visits_df)
+        avg_views_per_visitor = total_views / total_unique_visitors
 
-            total_unique_visitors = visits_df["visitor_id"].nunique()
-            total_views = len(visits_df)
-            avg_views_per_visitor = total_views / total_unique_visitors
+        st.subheader("Visitor Metrics")
+        metrics_col1, metrics_col2, metrics_col3 = st.columns(3)
+        metrics_col1.metric("Total Unique Visitors", total_unique_visitors)
+        metrics_col2.metric("Total Page Views", total_views)
+        metrics_col3.metric("Avg Views per Visitor", f"{avg_views_per_visitor:.1f}")
 
-            st.subheader("Visitor Metrics")
-            metrics_col1, metrics_col2, metrics_col3 = st.columns(3)
-            metrics_col1.metric("Total Unique Visitors", total_unique_visitors)
-            metrics_col2.metric("Total Page Views", total_views)
-            metrics_col3.metric("Avg Views per Visitor", f"{avg_views_per_visitor:.1f}")
+        st.subheader("Daily Statistics")
+        st.dataframe(
+            daily_visits_df.style.format(
+                {"Unique Visitors": "{:,.0f}", "Total Views": "{:,.0f}"}
+            ),
+            hide_index=True,
+        )
 
-            st.subheader("Daily Statistics")
-            st.dataframe(
-                daily_visits_df.style.format(
-                    {"Unique Visitors": "{:,.0f}", "Total Views": "{:,.0f}"}
-                ),
-                hide_index=True,
-            )
+    with col2:
+        section_visits_df = pd.DataFrame(
+            {
+                "Section": analytics_data["section_counts"].keys(),
+                "Views": analytics_data["section_counts"].values(),
+            }
+        )
+        section_visits_df = section_visits_df.sort_values("Views", ascending=True)
 
-        with col2:
-            section_visits_df = pd.DataFrame(
-                {
-                    "Section": analytics_data["section_counts"].keys(),
-                    "Views": analytics_data["section_counts"].values(),
-                }
-            )
-            section_visits_df = section_visits_df.sort_values("Views", ascending=True)
+        st.subheader("Total Section Views")
+        st.bar_chart(section_visits_df.set_index("Section"))
 
-            st.subheader("Total Section Views")
-            st.bar_chart(section_visits_df.set_index("Section"))
+    with st.expander("Raw Visit Data"):
+        visits_df = pd.DataFrame(analytics_data["visits"])
+        visits_df["timestamp"] = pd.to_datetime(visits_df["timestamp"])
+        st.dataframe(visits_df)
 
-        with st.expander("Raw Visit Data"):
-            visits_df = pd.DataFrame(analytics_data["visits"])
-            visits_df["timestamp"] = pd.to_datetime(visits_df["timestamp"])
-            st.dataframe(visits_df)
-    else:
-        st.warning("No analytics data available.")
 
 if st.session_state.ENABLE_TIMING:
     st.markdown("---")

components.py

@@ -0,0 +1,119 @@
+import calendar
+import datetime
+from typing import List, Optional, Tuple
+
+import pandas as pd
+import streamlit as st
+
+
+def on_date_change():
+    """Callback for date input changes"""
+    start = st.session_state.dataset_start_date
+    end = st.session_state.dataset_end_date
+
+    if start > end:
+        st.error("Start date must be before end date")
+        return
+
+    st.session_state.start_date = start
+    st.session_state.end_date = end
+
+
+def get_reporting_year_info_message(reporting_month: int, example_year: int) -> str:
+    """Generate standardized info message about reporting year grouping."""
+    return f"""
+        📅 **Data is grouped by reporting years**:
+        -     Each reporting year ends in **{calendar.month_name[reporting_month]}**.
+        -     Example: Reporting year **{example_year}** covers 
+        **{calendar.month_abbr[reporting_month + 1 if reporting_month < 12 else 1]}. {example_year - 1 if reporting_month < 12 else example_year}** 
+        through **{calendar.month_abbr[reporting_month]}. {example_year}**.
+        - &nbsp;&nbsp;&nbsp;&nbsp;**Note**: You can change the reporting year end month in the **Dataset Settings** in the sidebar.
+        """
+
+
+def render_date_filters(
+    min_date: datetime.date,
+    max_date: datetime.date,
+    key_prefix: str = "dataset",
+    on_change=None,
+) -> Tuple[datetime.date, datetime.date]:
+    """Render date range filter controls"""
+    col1, col2 = st.columns(2)
+
+    with col1:
+        start_date = st.date_input(
+            "Start Date",
+            value=min_date,
+            min_value=min_date,
+            max_value=max_date,
+            format="MM/DD/YYYY",
+            key=f"{key_prefix}_start_date",
+            on_change=on_change,
+        )
+        if not isinstance(start_date, datetime.date):
+            raise TypeError("Expected start_date to be a datetime.date")
+    with col2:
+        end_date = st.date_input(
+            "End Date",
+            value=max_date,
+            min_value=min_date,
+            max_value=max_date,
+            format="MM/DD/YYYY",
+            key=f"{key_prefix}_end_date",
+            on_change=on_change,
+        )
+        if not isinstance(end_date, datetime.date):
+            raise TypeError("Expected end_date to be a datetime.date")
+
+    return start_date, end_date
+
+
+def render_sidebar_position_filter_selectbox(
+    key_prefix: str = "", default: str = "All"
+) -> str:
+    """Render sample position filter"""
+    return st.sidebar.selectbox(
+        "Sample Position:",
+        ["All", "Surface", "Bottom"],
+        index=["All", "Surface", "Bottom"].index(default),
+        key=f"{key_prefix}_position_filter",
+    )
+
+
+def render_sidebar_analyte_multiselect(
+    all_analytes: List[str],
+    default_analytes: Optional[List[str]] = None,
+    key_prefix: str = "",
+    help_text: str = "Choose one or more analytes to display.",
+) -> List[str]:
+    """Render analyte multi-select"""
+    if default_analytes is None:
+        default_analytes = []
+
+    return st.sidebar.multiselect(
+        "Select Analytes:",
+        options=all_analytes,
+        default=default_analytes,
+        key=f"{key_prefix}_analyte_select",
+        help=help_text,
+    )
+
+
+def render_filtered_data_preview(
+    df: pd.DataFrame,
+    display_columns: List[str],
+    set_index_col: str | None = None,
+    height: int = 300,
+) -> None:
+    """Render preview of filtered dataset"""
+    if set_index_col:
+        df = df.set_index(set_index_col)
+    else:
+        df = df.reset_index()
+
+    st.markdown(f"**{len(df):,}** records")
+    st.dataframe(
+        df[display_columns].style.format(precision=2),
+        use_container_width=True,
+        height=height,
+    )