Spaces:
Sleeping
Sleeping
File size: 3,328 Bytes
d7f893a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
import streamlit as st
import pandas as pd
import numpy as np
import pydeck as pdk
import plotly.express as px
DATE_TIME = "date/time"
DATA_URL = (
"Motor_Vehicle_Collisions_-_Crashes.csv"
)
st.title("Motor Vehicle Collisions in New York City")
st.markdown("This application is a Streamlit dashboard that can be used "
"to analyze motor vehicle collisions in NYC 🗽💥🚗")
@st.cache(persist=True)
def load_data(nrows):
data = pd.read_csv(DATA_URL, nrows=nrows, parse_dates=[['CRASH_DATE', 'CRASH_TIME']])
data.dropna(subset=['LATITUDE', 'LONGITUDE'], inplace=True)
lowercase = lambda x: str(x).lower()
data.rename(lowercase, axis="columns", inplace=True)
data.rename(columns={"crash_date_crash_time": "date/time"}, inplace=True)
#data = data[['date/time', 'latitude', 'longitude']]
return data
data = load_data(100000)
st.header("Where are the most people injured in NYC?")
injured_people = st.slider("Number of persons injured in vehicle collisions", 0, 19)
st.map(data.query("injured_persons >= @injured_people")[["latitude", "longitude"]].dropna(how="any"))
st.header("How many collisions occur during a given time of day?")
hour = st.slider("Hour to look at", 0, 23)
original_data = data
data = data[data[DATE_TIME].dt.hour == hour]
st.markdown("Vehicle collisions between %i:00 and %i:00" % (hour, (hour + 1) % 24))
midpoint = (np.average(data["latitude"]), np.average(data["longitude"]))
st.write(pdk.Deck(
map_style="mapbox://styles/mapbox/light-v9",
initial_view_state={
"latitude": midpoint[0],
"longitude": midpoint[1],
"zoom": 11,
"pitch": 50,
},
layers=[
pdk.Layer(
"HexagonLayer",
data=data[['date/time', 'latitude', 'longitude']],
get_position=["longitude", "latitude"],
auto_highlight=True,
radius=100,
extruded=True,
pickable=True,
elevation_scale=4,
elevation_range=[0, 1000],
),
],
))
if st.checkbox("Show raw data", False):
st.subheader("Raw data by minute between %i:00 and %i:00" % (hour, (hour + 1) % 24))
st.write(data)
st.subheader("Breakdown by minute between %i:00 and %i:00" % (hour, (hour + 1) % 24))
filtered = data[
(data[DATE_TIME].dt.hour >= hour) & (data[DATE_TIME].dt.hour < (hour + 1))
]
hist = np.histogram(filtered[DATE_TIME].dt.minute, bins=60, range=(0, 60))[0]
chart_data = pd.DataFrame({"minute": range(60), "crashes": hist})
fig = px.bar(chart_data, x='minute', y='crashes', hover_data=['minute', 'crashes'], height=400)
st.write(fig)
st.header("Top 5 dangerous streets by affected class")
select = st.selectbox('Affected class', ['Pedestrians', 'Cyclists', 'Motorists'])
if select == 'Pedestrians':
st.write(original_data.query("injured_pedestrians >= 1")[["on_street_name", "injured_pedestrians"]].sort_values(by=['injured_pedestrians'], ascending=False).dropna(how="any")[:5])
elif select == 'Cyclists':
st.write(original_data.query("injured_cyclists >= 1")[["on_street_name", "injured_cyclists"]].sort_values(by=['injured_cyclists'], ascending=False).dropna(how="any")[:5])
else:
st.write(original_data.query("injured_motorists >= 1")[["on_street_name", "injured_motorists"]].sort_values(by=['injured_motorists'], ascending=False).dropna(how="any")[:5])
|