Simple-Data-visualization-using-Streamlit/app.py at master · Ares358/Simple-Data-visualization-using-Streamlit · GitHub

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
89
90
91
92
93
94
95
96
import streamlit as st
import pandas as pd
import numpy as np
import pydeck as pdk
import plotly.express as px

DATA_URL = ("Motor_Vehicle_Collisions_-_Crashes.csv")

st.title("Motor Vehicle Collisions in NYC")
st.markdown("Streamlit app that can be used to analyse 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.rename(columns={'number of persons injured': 'injured_persons'}, inplace=True)
    data.rename(columns={'number of pedestrians injured': 'injured_pedestrians'}, inplace=True)
    data.rename(columns={'number of cyclist injured': 'injured_cyclists'}, inplace=True)
    data.rename(columns={'number of motorist injured': 'injured_motorists'}, inplace=True)
    return data

data = load_data(100000)
original_data=data

st.header("Where are the most ppl injured in NYC?")
injured_people = st.slider("No. of persons injured in Vehicular collisions",0, 19)

st.map(data.query("injured_persons >= @injured_people")[["latitude","longitude"]].dropna(how="any"))


st.header("How many colliusions occur during a given time of the day?")
hour = st.slider("Hour to look at",0,23)
data = data[data['date/time'].dt.hour == hour]


st.markdown("Vehicle collisions between %i:00 & %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'],
        radius=100,
        extruded=True,
        pickable=True,
        elevation_scale=4,
        elevation_range=[0,1000],


        )

    ]

))

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 type")
select= st.selectbox('Affected Type of people',['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])


if st.checkbox("Show Raw Data", False):
    st.subheader('Raw data')
    st.write(data)