app.py

import altair as alt
# import numpy as np  # Removed as it is not accessed
import pandas as pd
import streamlit as st
import geopandas as gpd
import matplotlib.pyplot as plt
import seaborn as sns
import ipywidgets

st.title("Crime Data Analysis")


# Load the dataset.
df = pd.read_csv("crime_data.csv")

# Check NaN values and types.
# df.isna().sum() # No NaN value in our dataframe.
# df.dtypes # Only "crm_cd_desc" is categorical variable(object).

# Test code.
df.head(5)

# Plot 1: Pie chart.
# Data filteration.
crm_tot = df["crm_cd_desc"].value_counts()

# Calculate the mean of crime cases.
mean_crm = crm_tot.mean()

# Filter out the crime cases that are below the mean of the crime cases.
crm_tot_filtered = crm_tot[crm_tot > mean_crm]

# Method comes from: https://matplotlib.org/stable/gallery/pie_and_polar_charts/pie_features.html.
plt.figure(figsize=(12, 12))
fig, ax = plt.subplots()
ax.pie(crm_tot_filtered, labels=crm_tot_filtered.index, autopct='%1.1f%%', labeldistance=1.5, pctdistance=1.2)

#-----

### Use this one!!!
# A more detailed version pie chart based on the previous one.
# Filter the top 10 crime type.
top_crimes = (
    df["crm_cd_desc"]
    .value_counts()
    .nlargest(10)
    .reset_index()
    .rename(columns={"index": "Crime Type", "crm_cd_desc": "Count"})
)

# Calculate the percentage of ecah kind of crime.
top_crimes["Percentage"] = top_crimes["Count"] / top_crimes["Count"].sum()


# Create the pie chart.
chart = alt.Chart(top_crimes).mark_arc(innerRadius=50).encode(
    theta=alt.Theta(field="Count", type="quantitative"),
    color=alt.Color(field="Crime Type", type="nominal", legend=alt.Legend(title="Crime Type")),
    tooltip=["Crime Type", "Count", alt.Tooltip("Percentage:Q", format=".1%")]
).properties(
    title="Top 10 Crime Types Distribution"
)

# Display the plot.
st.altair_chart(chart, theme="streamlit", use_container_width=True)


#------

### Use this one!!!
# Count the crime type and list out the top 10 crime type that have the most cases.
top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
df_top = df[df['crm_cd_desc'].isin(top_crimes)]

# Group by crime type and year.
heatmap1_data = df_top.groupby(['crm_cd_desc', 'year']).size().unstack(fill_value=0)

# Create the heat map.
plt.figure(figsize=(10, 6))
sns.heatmap(heatmap1_data, annot=True, fmt="d", cmap="YlOrRd")
plt.title("Top 10 Crime Types by Year")
plt.xlabel("Year")
plt.ylabel("Crime Type")
plt.tight_layout()
plt.show()

st.altair_chart(heatmap1_data, theme="streamlit", use_container_width=True)


#------

### Use this one!!!
# Count the crime type and list out the top 10 crime type that have the most cases.
top_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index
df = df[df['year'] != 2025]
df_top = df[df['crm_cd_desc'].isin(top_crimes)]

# Group by crime type and year.
stacked_year_df = df_top.groupby(['year', 'crm_cd_desc']).size().reset_index(name='count')

# Create the stacked bar chart.
bar_chart = alt.Chart(stacked_year_df).mark_bar().encode(
    x=alt.X('year:O', title='Year'),
    y=alt.Y('count:Q', stack='zero', title='Number of Incidents'),
    color=alt.Color('crm_cd_desc:N', title='Crime Type'),
    tooltip=['year', 'crm_cd_desc', 'count']
).properties(
    width=600,
    height=400,
    title='Stacked Crime Composition by Year (Top 10 Crime Types)'
)

st.altair_chart(bar_chart, theme="streamlit", use_container_width=True)


#----

### Use this one!!!
# Plot 3: Line chart.
df = df[df['year'] != 2025] # 2025 is not end, so the trend can't be see

# Group the each crime type by year.
yearly_crime_counts = (
    df.groupby(["year", "crm_cd_desc"])
    .size()
    .reset_index(name="Count")
)

# Filter the crime types that have the most top 5 cases.
top5_crimes = df["crm_cd_desc"].value_counts().nlargest(5).index
filtered_crimes = yearly_crime_counts[yearly_crime_counts["crm_cd_desc"].isin(top5_crimes)]

# Plot the line plot.
line_chart = alt.Chart(filtered_crimes).mark_line(point=True).encode(
    x=alt.X("year:O", title="Year"),
    y=alt.Y("Count:Q", title="Number of Incidents"),
    color=alt.Color("crm_cd_desc:N", title="Crime Type"),
    tooltip=["year", "crm_cd_desc", "Count"]
).properties(
    title="Yearly Trends of Top 5 Crime Types",
    width=700,  
    height=400
)

# Display the plot.
st.altair_chart(line_chart, theme="streamlit", use_container_width=True)

#----
# Plot 4: Map.
# Load geojson file.
gdf_counties = gpd.read_file("County_Boundary.geojson")
    
# Creat dropdown menu.
year_dropdown = ipywidgets.Dropdown(
    options= sorted(df['year'].unique()),
    description='Year:'
)

# Create the map.
def crime_map(year):
    # df_filtered = df[df['year'] == year].sample(n=500, random_state=1)
    # df_filtered = df[df['year'] == year].sample(n=100, random_state=1)
    df_filtered = df[df['year'] == year].sample(n=300, random_state=1)
    gdf_points = gpd.GeoDataFrame(
        df_filtered,
        geometry=gpd.points_from_xy(df_filtered['lon'], df_filtered['lat']),
        crs="EPSG:4326"
    )
    
    fig, ax = plt.subplots(figsize=(10, 10))
    gdf_counties.plot(ax=ax, color='lightgray', edgecolor='white')
    gdf_points.plot(ax=ax, color='red', markersize=10, alpha=0.6)
    ax.set_title(f"Crime Map - {year}")
    ax.set_xlabel("Longitude")
    ax.set_ylabel("Latitude")
    plt.grid(True)
    plt.show()
    
# Displat the plot.
ipywidgets.interact(crime_map, year=year_dropdown)




### Use this one!!!
# Loading in the map.
gdf_counties = gpd.read_file("County_Boundary.geojson")

# Identify top 10 crime types
top_10_crimes = df['crm_cd_desc'].value_counts().nlargest(10).index.tolist()

# Filter the main DataFrame to include only top 10 crimes
df_top = df[df['crm_cd_desc'].isin(top_10_crimes)]

# Create the dropdown.
crime_dropdown = ipywidgets.Dropdown(
    options= sorted(top_10_crimes),
    description="Crime Type:")

# Create the map.
def crime_map(year, crime):
    df_filtered = df[(df['year'] == year) & (df['crm_cd_desc'] == crime)].sample(n=300, random_state=1)
    gdf_points = gpd.GeoDataFrame(
        df_filtered,
        geometry=gpd.points_from_xy(df_filtered['lon'], df_filtered['lat']),
        crs="EPSG:4326"
    )
    
    fig, ax = plt.subplots(figsize=(10, 10))
    gdf_counties.plot(ax=ax, color='lightgray', edgecolor='white')
    gdf_points.plot(ax=ax, color='red', markersize=10, alpha=0.6)
    ax.set_title(f"{crime} - {year}")
    ax.set_xlabel("Longitude")
    ax.set_ylabel("Latitude")
    plt.grid(True)
    plt.show()
    
# Displat the plot.
ipywidgets.interact(crime_map, year=year_dropdown, crime=crime_dropdown)