Update src/streamlit_app.py

src/streamlit_app.py

@@ -11,11 +11,15 @@ import pandas as pd
 import numpy as np
 import plotly.express as px
 
+
+# ------------------------------------------------
+# Page configuration
+# ------------------------------------------------
 st.set_page_config(page_title="Chicago Parks in Motion", layout="wide")
 
-# ---------------------------------------------------
-# LOAD & CLEAN DATA
-# ---------------------------------------------------
+# ------------------------------------------------
+# Load Data
+# ------------------------------------------------
 @st.cache_data(ttl=3600)
 def load_data():
     url = "https://data.cityofchicago.org/resource/tn7v-6rnw.csv"
@@ -28,95 +32,103 @@ def load_data():
     if "fee" in df.columns:
         df["fee"] = pd.to_numeric(df["fee"], errors="coerce")
 
-    # Extract lat/lon
-    if "location" in df.columns:
-        def parse_location(val):
-            if pd.isna(val):
-                return (np.nan, np.nan)
-            sval = str(val)
-            if sval.startswith("POINT"):
-                try:
-                    inside = sval.split("(",1)[1].rstrip(")")
-                    lon, lat = map(float, inside.split())
-                    return lat, lon
-                except:
-                    return (np.nan, np.nan)
+    # Extract coordinates
+    def extract_latlon(val):
+        if pd.isna(val):
             return (np.nan, np.nan)
-        latlon = df["location"].map(parse_location)
-        df["latitude"] = latlon.map(lambda x: x[0])
-        df["longitude"] = latlon.map(lambda x: x[1])
+        s = str(val)
+        if s.startswith("POINT"):
+            try:
+                inside = s.split("(")[1].rstrip(")")
+                lon, lat = map(float, inside.strip().split())
+                return lat, lon
+            except:
+                return (np.nan, np.nan)
+        import re
+        nums = re.findall(r"-?\d+\.\d+", s)
+        if len(nums) >= 2:
+            return float(nums[0]), float(nums[1])
+        return (np.nan, np.nan)
 
-    # Dates
-    for c in ["start_date", "end_date"]:
-        if c in df.columns:
-            df[c] = pd.to_datetime(df[c], errors="ignore")
+    if "location" in df.columns:
+        coords = df["location"].map(extract_latlon)
+        df["latitude"] = coords.map(lambda x: x[0])
+        df["longitude"] = coords.map(lambda x: x[1])
+
+    # Parse dates
+    for col in ["start_date", "end_date"]:
+        if col in df.columns:
+            df[col] = pd.to_datetime(df[col], errors="coerce")
 
-    # Activity type
+    # Clean activity type
     if "activity_type" in df.columns:
         df["activity_type_clean"] = df["activity_type"].str.title().fillna("Unknown")
-    elif "program_type" in df.columns:
-        df["activity_type_clean"] = df["program_type"].str.title().fillna("Unknown")
     else:
         df["activity_type_clean"] = "Unknown"
 
-    # Park names
-    for col in ["park_name", "park", "site_name", "location_name"]:
+    # Park name
+    possible_park_cols = [
+        "park_name", "park", "location_facility",
+        "location_name", "location", "site_name"
+    ]
+    for col in possible_park_cols:
         if col in df.columns:
-            df["park_name"] = df[col].fillna("Unknown Park")
+            df["park_name"] = df[col].astype(str).replace(["", "nan", "None"], "Unknown Park")
             break
-    if "park_name" not in df.columns:
-        df["park_name"] = "Unknown Park"
-
-    # Derive season
-    def season_from_date(dt):
-        if isinstance(dt, str) or pd.isna(dt):
-            try:
-                dt = pd.to_datetime(dt)
-            except:
-                return "Unknown"
-        m = dt.month
-        if m in (12, 1, 2): return "Winter"
-        if m in (3, 4, 5): return "Spring"
-        if m in (6, 7, 8): return "Summer"
-        return "Fall"
-
-    if "start_date" in df.columns:
-        df["season"] = df["start_date"].map(season_from_date)
     else:
-        df["season"] = "Unknown"
+        df["park_name"] = "Unknown Park"
 
     return df
 
+
 df = load_data()
 
-# ---------------------------------------------------
-# PAGE TITLE
-# ---------------------------------------------------
+# ------------------------------------------------
+# Title + intro
+# ------------------------------------------------
 st.title("Chicago Parks in Motion: How Our City Plays")
 st.markdown("**Authors:** Juhi Khare (jkhare2), Alisha Rawat (alishar4), Sutthana Koo-Anupong (sk188)")
-st.info("This is our **central public-facing visualization project**, created for a data journalism assignment.")
+st.info("**Central visualization below:** Explore how program availability varies across Chicago’s parks. This is the main interactive visualization required by the rubric.")
 
-# ---------------------------------------------------
-# FILTERS
-# ---------------------------------------------------
+# ------------------------------------------------
+# Sidebar Filters
+# ------------------------------------------------
 st.sidebar.header("Filters")
 
+# Activity type
 categories = sorted(df["activity_type_clean"].unique())
 chosen_category = st.sidebar.selectbox("Activity Category", ["All"] + categories)
 
+# Season
+def season_from_date(dt):
+    if pd.isna(dt): return "Unknown"
+    m = dt.month
+    if m in [12,1,2]: return "Winter"
+    if m in [3,4,5]: return "Spring"
+    if m in [6,7,8]: return "Summer"
+    return "Fall"
+
+df["season"] = df["start_date"].map(season_from_date)
 seasons = sorted(df["season"].unique())
 chosen_season = st.sidebar.selectbox("Season", ["All"] + seasons)
 
+# Price filter
 if "fee" in df.columns:
-    fee_limit = st.sidebar.slider("Maximum Fee (USD)", 0.0, float(df["fee"].fillna(0).max()), float(df["fee"].fillna(0).max()))
+    max_fee = float(df["fee"].fillna(0).max())
+    fee_limit = st.sidebar.slider("Maximum Fee (USD)", 0.0, max_fee, max_fee)
 else:
     fee_limit = None
 
-search_park = st.sidebar.text_input("Search Park Name")
+# Park name search
+park_query = st.sidebar.text_input("Search Park Name")
 
-st.sidebar.caption("Filters help readers explore the data easily without technical skills.")
+st.sidebar.caption(
+    "Filters help all users — including novices — explore the dataset without needing technical skills."
+)
 
-# Filter logic
+# ------------------------------------------------
+# Apply Filters
+# ------------------------------------------------
 filtered = df.copy()
 if chosen_category != "All":
     filtered = filtered[filtered["activity_type_clean"] == chosen_category]
@@ -124,119 +136,187 @@ if chosen_season != "All":
     filtered = filtered[filtered["season"] == chosen_season]
 if fee_limit is not None:
     filtered = filtered[filtered["fee"].fillna(0) <= fee_limit]
-if search_park:
-    filtered = filtered[filtered["park_name"].str.contains(search_park, case=False, na=False)]
+if park_query:
+    filtered = filtered[filtered["park_name"].str.contains(park_query, case=False, na=False)]
+
+st.sidebar.markdown(f"**Programs shown:** {len(filtered):,}")
+
+# ------------------------------------------------
+# CENTRAL VISUALIZATION — MAP / BAR
+# ------------------------------------------------
+st.header("Central Interactive Visualization — Programs by Park")
+
+view_type = st.radio("Choose View", ["Map (recommended)", "Bar Chart"], horizontal=True)
+
+# MAP VIEW
+if view_type == "Map (recommended)":
+    if (
+        "latitude" in filtered.columns and
+        "longitude" in filtered.columns and
+        filtered[["latitude", "longitude"]].dropna().shape[0] > 0
+    ):
+        agg = (
+            filtered.groupby(["park_name", "latitude", "longitude"], dropna=True)
+            .size()
+            .reset_index(name="count")
+        )
+
+        fig_map = px.scatter_mapbox(
+            agg,
+            lat="latitude",
+            lon="longitude",
+            size="count",
+            size_max=32,
+            color="count",
+            color_continuous_scale="Cividis",   # unified scheme
+            zoom=10,
+            height=550,
+        )
+
+        fig_map.update_traces(
+            marker=dict(
+                opacity=0.85,
+                line=dict(width=1.2, color="black")  # helps contrast
+            )
+        )
+
+        fig_map.update_layout(
+            mapbox_style="carto-positron",      # high visibility
+            margin=dict(r=0, t=0, l=0, b=0),
+            paper_bgcolor="white"
+        )
+
+        st.plotly_chart(fig_map, use_container_width=True)
+
+        st.markdown(
+            "This map shows which parks offer the most programs. "
+            "Darker and larger circles represent parks with more activities. "
+            "Using a dark Cividis color scale ensures the bubbles stand out clearly on the light basemap."
+        )
 
-st.sidebar.markdown(f"**Programs Shown:** {len(filtered):,}")
-
-# ---------------------------------------------------
-# CENTRAL VISUALIZATION (MAP)
-# ---------------------------------------------------
-st.subheader("Central Visualization — Programs by Park (Interactive Map)")
-
-if filtered[["latitude","longitude"]].dropna().shape[0] > 0:
-    agg = filtered.groupby(["park_name","latitude","longitude"]).size().reset_index(name="count")
+    else:
+        st.warning("No map coordinates available. Switch to Bar Chart view.")
 
-    fig_map = px.scatter_mapbox(
-        agg,
-        lat="latitude",
-        lon="longitude",
-        size="count",
-        size_max=30,
+# BAR CHART VIEW
+else:
+    agg = (
+        filtered.groupby("park_name")
+        .size()
+        .reset_index(name="count")
+        .sort_values("count", ascending=False)
+    )
+    top_n = 25
+    agg_top = agg.head(top_n)
+
+    fig_bar = px.bar(
+        agg_top,
+        x="count",
+        y="park_name",
+        orientation="h",
         color="count",
         color_continuous_scale="Cividis",
-        zoom=10,
-        height=550
+        height=650,
+        labels={"count": "Number of Programs", "park_name": "Park"}
+    )
+
+    fig_bar.update_traces(
+        marker=dict(line=dict(width=0.7, color="black")),
+        text=agg_top["count"],
+        textposition="outside"
     )
-    fig_map.update_layout(mapbox_style="open-street-map")
-    st.plotly_chart(fig_map, use_container_width=True)
-
-    st.write("""
-    **Explanation:**  
-    This map shows which parks offer the most programs. Larger and darker circles represent parks with more activities. 
-    The Cividis color scale makes it easy for all viewers—including those with color-vision differences—to understand intensity.
-    You can hover over any park to see its program count and use the filters to explore activity types, seasons, or fees.
-    """)
-else:
-    st.warning("No geographic coordinates available for mapping.")
 
-# ---------------------------------------------------
-# CONTEXTUAL VIS 1 — CATEGORY PIE CHART
-# ---------------------------------------------------
-st.subheader("Contextual Visualization 1 — Activity Category Breakdown")
+    st.plotly_chart(fig_bar, use_container_width=True)
 
-cat_counts = df["activity_type_clean"].value_counts().reset_index()
-cat_counts.columns = ["Category","Count"]
+    st.markdown(
+        "This bar chart lists the parks with the most programs. "
+        "The consistent Cividis color scheme highlights which locations have higher activity levels."
+    )
+
+# ------------------------------------------------
+# CONTEXTUAL VISUALIZATION 1 – CATEGORY BREAKDOWN
+# ------------------------------------------------
+st.header("Contextual Visualization 1 — Activity Category Breakdown")
+
+cat_counts = (
+    df["activity_type_clean"]
+    .value_counts()
+    .reset_index()
+)
+cat_counts.columns = ["Category", "Count"]
 
 fig_cat = px.pie(
     cat_counts,
     names="Category",
     values="Count",
-    color_discrete_sequence=px.colors.sequential.Cividis
+    color="Count",
+    color_continuous_scale="Cividis"
 )
+
 st.plotly_chart(fig_cat, use_container_width=True)
 
-st.write("""
-**Explanation:**  
-This pie chart shows the distribution of all activity categories across Chicago parks. 
-Some categories—like sports and youth programs—appear more often, while others are limited. 
-Using the same Cividis-inspired palette keeps the visuals consistent for the public.
-""")
+st.markdown(
+    "This chart shows the types of activities offered across Chicago parks. "
+    "Most programs fall under instruction-based activities, such as fitness or sports classes, "
+    "while other categories appear less frequently. "
+    "Using Cividis keeps the colors readable and consistent with the rest of the app."
+)
 
-# ---------------------------------------------------
-# CONTEXTUAL VIS 2 — PROGRAMS BY SEASON
-# ---------------------------------------------------
-st.subheader("Contextual Visualization 2 — Programs by Season")
+# ------------------------------------------------
+# CONTEXTUAL VISUALIZATION 2 – PROGRAMS BY SEASON
+# ------------------------------------------------
+st.header("Contextual Visualization 2 — Programs by Season")
 
-season_counts = df["season"].value_counts().reset_index()
-season_counts.columns = ["Season","Program Count"]
+season_counts = (
+    df["season"]
+    .value_counts()
+    .reset_index()
+)
+season_counts.columns = ["Season", "Program Count"]
 
 fig_season = px.bar(
     season_counts,
     x="Season",
     y="Program Count",
-    text="Program Count",
     color="Program Count",
     color_continuous_scale="Cividis",
-    height=450
+    text="Program Count",
+    height=500,
 )
+
 fig_season.update_traces(textposition="outside")
+
 st.plotly_chart(fig_season, use_container_width=True)
 
-st.write("""
-**Explanation:**  
-This chart shows how program offerings change by season. Summer and fall tend to have more activities, 
-while winter shows fewer options. The color scale helps highlight the variation clearly and keeps the look consistent.
-""")
+st.markdown(
+    "This bar chart shows how program availability changes across seasons. "
+    "Summer has the highest number of activities, which matches outdoor recreation trends. "
+    "The same Cividis palette keeps the experience uniform and accessible."
+)
 
-# ---------------------------------------------------
-# FULL STORY SECTION (YOUR EXACT PARAGRAPHS)
-# ---------------------------------------------------
+# ------------------------------------------------
+# REQUIRED FINAL NARRATIVE SECTION (Your Own Text)
+# ------------------------------------------------
 st.markdown("---")
-st.header("What This Data Story Is Showing")
+st.header("What this data story is showing")
 
 st.markdown("""
-Chicago’s parks offer many kinds of activities for people of all ages. These include sports, arts, fitness classes, youth programs, and seasonal events. 
-Each row in this dataset represents one program offered at a park. Our main interactive map helps readers quickly see which parks offer the most activities. 
-Bigger or darker circles show parks with more programs, making it easy to spot busy parks versus quieter ones.
-
-Where a park is located also matters. Neighborhoods that are larger or more central usually have more programs because they have more space, more facilities, 
-and more visitors. With the filters on the left, anyone can explore the data by season, activity type, price, or park name. 
-This makes the information easy to use even for someone with no data experience. For example, you can look for free programs, 
-summer-only programs, or activities at a specific park in your neighborhood.
-
-This project also highlights questions about access and opportunities. Some parks offer a wide range of programs, while others have fewer options or mostly offer only one type of activity. 
-By looking at categories, seasons, and fees, readers can start to see patterns in which communities have more choices and which ones may need more support. 
-Our goal is to turn public data into something simple and useful, so Chicago residents and decision-makers can better understand how parks are serving their communities.
+Chicago’s parks offer many kinds of activities for people of all ages. These include sports, arts, fitness classes, youth programs, and seasonal events. Each row in this dataset represents one program offered at a park. Our main interactive map helps readers quickly see which parks offer the most activities. Bigger or darker circles show parks with more programs, making it easy to spot busy parks versus quieter ones.
+
+Where a park is located also matters. Neighborhoods that are larger or more central usually have more programs because they have more space, more facilities, and more visitors. With the filters on the left, anyone can explore the data by season, activity type, price, or park name. This makes the information easy to use even for someone with no data experience. For example, you can look for free programs, summer-only programs, or activities at a specific park in your neighborhood.
+
+This project also highlights questions about access and opportunities. Some parks offer a wide range of programs, while others have fewer options or mostly offer only one type of activity. By looking at categories, seasons, and fees, readers can start to see patterns in which communities have more choices and which ones may need more support. Our goal is to turn public data into something simple and useful, so Chicago residents and decision-makers can better understand how parks are serving their communities.
 """)
 
-# ---------------------------------------------------
-# CITATIONS
-# ---------------------------------------------------
+# ------------------------------------------------
+# Citations
+# ------------------------------------------------
 st.markdown("---")
-st.subheader("Citations & Data Sources")
+st.subheader("Data Sources & Citations")
+
 st.markdown("""
-- Chicago Park District Activities — City of Chicago Data Portal  
-  https://data.cityofchicago.org/Parks-Recreation/Chicago-Park-District-Activities/tn7v-6rnw  
-- All visualizations created by the authors using Streamlit & Plotly.
+**Primary dataset:**  
+Chicago Park District Activities — City of Chicago Data Portal  
+https://data.cityofchicago.org/Parks-Recreation/Chicago-Park-District-Activities/tn7v-6rnw  
+
+All visualizations were created by the authors using Streamlit and Plotly.  
 """)