Streamlit visualization of Vancouver Crime Data

vpd_crime.py

from io import BytesIO
from zipfile import ZipFile

import pandas as pd
import requests
import streamlit as st
from colorhash import ColorHash
from pyproj import Proj

st.title("Vancouver Crime Data")

DATE_COLUMN = "date"


@st.cache_data
def load_data():
    with requests.get(
        "https://geodash.vpd.ca/opendata/crimedata_download/AllNeighbourhoods_AllYears/crimedata_csv_AllNeighbourhoods_AllYears.zip",
        stream=True,
    ) as r:
        with ZipFile(BytesIO(r.content)) as z:
            with z.open("crimedata_csv_AllNeighbourhoods_AllYears.csv") as f:
                data = pd.read_csv(f)
    return data


data_load_state = st.text("Loading data...")
data = load_data()

data[DATE_COLUMN] = pd.to_datetime(data[["YEAR", "MONTH", "DAY", "HOUR", "MINUTE"]])

p = Proj("+proj=utm +zone=10 +datum=WGS84 +units=m +no_defs +type=crs")
data.X.replace(0, None, inplace=True)
data.Y.replace(0, None, inplace=True)
data["lon"], data["lat"] = p(data.X, data.Y, inverse=True, errcheck=True)

data_load_state.text("Done! (using st.cache_data)")

if st.checkbox("Show raw data"):
    st.subheader("Raw data")
    st.write(data)

year_range = st.slider(
    "Year range", data.YEAR.min(), data.YEAR.max(), (data.YEAR.min(), data.YEAR.max())
)

crime_types = st.multiselect("Types of crimes", data.TYPE.unique())

filtered_data = data[
    data.YEAR.between(*year_range) & ((not crime_types) | (data.TYPE.isin(crime_types)))
]

st.subheader("Crimes by hour")
st.bar_chart(filtered_data.HOUR.value_counts())

st.subheader("Crimes by year")
st.bar_chart(filtered_data.YEAR.value_counts())


COLOR_COLUMN = "TYPE"
COLOR_MAP = {k: ColorHash(k).hex for k in filtered_data[COLOR_COLUMN].unique()}

st.subheader("Crimes by type")
type_data = filtered_data.TYPE.value_counts().to_frame()
type_data["color"] = type_data.index.map(COLOR_MAP)
st.bar_chart(type_data, y="count", color="color")


map_data = filtered_data[filtered_data["lat"].notna() & filtered_data["lon"].notna()]
map_data["color"] = map_data[COLOR_COLUMN].map(COLOR_MAP)

st.subheader("Map of crimes")
st.map(
    map_data.value_counts(["lat", "lon", "color"]).to_frame().reset_index(),
    size="count",
    color="color",
)