Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,136 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import altair as alt
+from pathlib import Path
+import plotly.express as px
 
+# ── 0. Page configuration ──
+st.set_page_config(
+    page_title="Analyze Crime Distributions", 
+    page_icon="📊", 
+    layout="wide"
+)
+st.markdown("""
+        <style>
+        .title {
+            text-align: center;
+            padding: 25px;
+        }
+        </style>
+        """, unsafe_allow_html=True)
+    
+st.markdown("<div class='title'><h1> LAPD Crime Insights Dashboard </h1></div>", unsafe_allow_html=True)
+
+# 1. Page title
+st.markdown(""" This application provides a suite of interactive visualizations—pie charts, bar charts, scatter plots, and more—that let you explore crime patterns in the LAPD dataset from multiple angles. Quickly see which offense categories dominate, compare arrest rates against non-arrests, track how crime volumes change over time, and examine geographic hotspots. These insights can help police departments, community organizations, and policymakers allocate resources more effectively and design targeted strategies to improve public safety.""")
+            
+# 2. Data info & load
+st.header("Dataset Information")
+st.markdown(
+    """
+- **Source:** LAPD crime incidents dataset  
+- **Rows:** incidents (one per row)  
+- **Columns:** e.g. `crm_cd_desc` (crime type), `arrest` (boolean), `date`, `location_description`, etc.  
+- **Purpose:** Interactive exploration of top crime categories and arrest rates.
 """
-# Welcome to Streamlit!
+)
 
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# 1. Resolve the path to the CSV next to this script
+DATA_PATH = Path(__file__).parent / "crime_data.csv"        # /app/src/crime_data.csv
 
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
+@st.cache_data
+def load_data():
+    return pd.read_csv(DATA_PATH)
+    
+if st.button("🔄"):
+    st.cache_data.clear()  # Clear the cache
+    st.toast("Data is refreshed",icon="✅")  # Reload the data
+    
+# 2. Load and early‐exit if missing
+df = load_data()
+if df.empty:
+    st.stop()
+    
+# 3. Data preview
+st.header("Data Preview")
+st.write(f"Total records: {df.shape[0]}  |  Total columns: {df.shape[1]}")
+st.dataframe(df.head())
+
+# Pie Chart 1: Top 10 Crime Types
+st.markdown("<div class='title'><h1> Top 10 Crime Type </h1></div>", unsafe_allow_html=True)
+
+years = sorted(df["year"].dropna().astype(int).unique())
+# Prepend an “All” option
+options = ["All"] + years
+
+# Year filter (shorter, above chart)
+col_empty, col_filter = st.columns([3,1])
+with col_filter:
+    selected_year = st.selectbox(
+        "Select Year",
+        options=options,
+        index=0,  # default to “All”
+        key="year_filter"
+    )
+
+# Filter according to selection
+if selected_year == "All":
+    filtered = df.copy()
+else:
+    filtered = df[df["year"] == selected_year]
+
+# Compute top 10 crime types for that year ──
+top_crimes = (
+    filtered["crm_cd_desc"]
+      .value_counts()
+      .nlargest(10)
+      .rename_axis("Crime Type")
+      .reset_index(name="Count")
+)
+top_crimes["Percentage"] = top_crimes["Count"] / top_crimes["Count"].sum()
+
+#Key Metrics
+st.markdown("### Key Metrics", unsafe_allow_html=True)
+col1, col2, col3 = st.columns(3)
+col1.metric(
+    label="Total Incidents",
+    value=f"{len(filtered):,}"
+)
+col2.metric(
+    label="Unique Crime Types",
+    value=f"{filtered['crm_cd_desc'].nunique():,}"
+)
+# compute share of the top crime
+top_share = top_crimes.iloc[0]["Percentage"]  
+col3.metric(
+    label=f"Share of Top Crime ({top_crimes.iloc[0]['Crime Type']})",
+    value=f"{top_share:.1%}"
+)
+
+# Plotly donut chart ──
+fig = px.pie(
+    top_crimes,
+    names="Crime Type",
+    values="Count",
+    hole=0.4,
+    color_discrete_sequence=px.colors.sequential.Agsunset,
+    title="  "
+)
+
+fig.update_traces(
+    textposition="outside",
+    textinfo="label+percent",
+    pull=[0.05] * len(top_crimes),
+    marker=dict(line=dict(color="white", width=2))
+)
+
+fig.update_layout(
+    legend_title_text="Crime Type",
+    margin=dict(t=60, b=20, l=20, r=20),
+    height=700,
+    title_x=0.5
+)
+
+st.plotly_chart(fig, use_container_width=True)
+st.markdown(""" The donut chart shows the share of the ten most frequent crime categories in the selected year. At the center, you can see that Vehicle ­– Stolen is the single largest slice, accounting for roughly 18.7% of all incidents, The remaining five categories each represent between 3%–5% of total incidents—these include miscellaneous crimes, criminal threats, assault with a deadly weapon, burglary, and minor vandalism. By displaying both slice size and percentage labels, the chart makes it easy to compare how dominant property‐related offenses are, versus violent or lesser‐common crimes, in that year’s LAPD data. """)
 
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))