Getting started with Streamlit in Domino

USER root
RUN pip install -U streamlit starlette

import os
import altair as alt
import numpy as np
import pandas as pd
import pydeck as pdk
import streamlit as st

st.set_page_config(layout="wide", page_title="NYC Ridesharing Demo", page_icon=":taxi:")

@st.cache_resource
def load_data():
    path = "uber-raw-data-sep14.csv.gz"
    if not os.path.isfile(path):
        path = f"https://github.com/streamlit/demo-uber-nyc-pickups/raw/main/{path}"
    data = pd.read_csv(
        path,
        nrows=100000,
        names=["date/time", "lat", "lon"],
        skiprows=1,
        usecols=[0, 1, 2],
        parse_dates=["date/time"],
    )
    return data

def map(data, lat, lon, zoom):
    st.write(pdk.Deck(
        map_style="mapbox://styles/mapbox/light-v9",
        initial_view_state={"latitude": lat, "longitude": lon, "zoom": zoom, "pitch": 50},
        layers=[pdk.Layer("HexagonLayer", data=data, get_position=["lon", "lat"],
            radius=100, elevation_scale=4, elevation_range=[0, 1000],
            pickable=True, extruded=True)],
    ))

@st.cache_data
def filterdata(df, hour_selected):
    return df[df["date/time"].dt.hour == hour_selected]

@st.cache_data
def mpoint(lat, lon):
    return (np.average(lat), np.average(lon))

@st.cache_data
def histdata(df, hr):
    filtered = df[(df["date/time"].dt.hour >= hr) & (df["date/time"].dt.hour < (hr + 1))]
    hist = np.histogram(filtered["date/time"].dt.minute, bins=60, range=(0, 60))[0]
    return pd.DataFrame({"minute": range(60), "pickups": hist})

data = load_data()
row1_1, row1_2 = st.columns((2, 3))

if not st.session_state.get("url_synced", False):
    try:
        pickup_hour = int(st.query_params["pickup_hour"][0])
        st.session_state["pickup_hour"] = pickup_hour
        st.session_state["url_synced"] = True
    except KeyError:
        pass

def update_query_params():
    st.query_params["pickup_hour"] = st.session_state["pickup_hour"]

with row1_1:
    st.title("NYC Uber Ridesharing Data")
    hour_selected = st.slider("Select hour of pickup", 0, 23,
        key="pickup_hour", on_change=update_query_params)

with row1_2:
    st.write("""
## Examining how Uber pickups vary over time in New York City
    and at its major regional airports.""")

row2_1, row2_2, row2_3, row2_4 = st.columns((2, 1, 1, 1))
la_guardia = [40.7900, -73.8700]
jfk = [40.6650, -73.7821]
newark = [40.7090, -74.1805]
zoom_level = 12
midpoint = mpoint(data["lat"], data["lon"])

with row2_1:
    st.write(f"**All NYC from {hour_selected}:00 to {(hour_selected + 1) % 24}:00**")
    map(filterdata(data, hour_selected), midpoint[0], midpoint[1], 11)
with row2_2:
    st.write("**La Guardia Airport**")
    map(filterdata(data, hour_selected), la_guardia[0], la_guardia[1], zoom_level)
with row2_3:
    st.write("**JFK Airport**")
    map(filterdata(data, hour_selected), jfk[0], jfk[1], zoom_level)
with row2_4:
    st.write("**Newark Airport**")
    map(filterdata(data, hour_selected), newark[0], newark[1], zoom_level)

chart_data = histdata(data, hour_selected)
st.write(f"**Rides per minute between {hour_selected}:00 and {(hour_selected + 1) % 24}:00**")
st.altair_chart(
    alt.Chart(chart_data).mark_area(interpolate="step-after")
    .encode(x=alt.X("minute:Q", scale=alt.Scale(nice=False)),
            y=alt.Y("pickups:Q"), tooltip=["minute", "pickups"])
    .configure_mark(opacity=0.2, color="red"),
    use_container_width=True,
)

#!/bin/bash
set -x
streamlit run streamlit_app.py \
    --server.port 8888 \
    --server.address 0.0.0.0 \
    --server.headless true

streamlit run streamlit_app.py