streamlit_app.py

# -*- coding: utf-8 -*-
# Copyright 2018-2022 Streamlit Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""An example of showing geographic data."""

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

from pdb import set_trace

os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = ""

# SETTING PAGE CONFIG TO WIDE MODE AND ADDING A TITLE AND FAVICON
st.set_page_config(layout="wide", page_title="ニューヨーク市でのウーバー使用状況", page_icon=":taxi:")

# LOAD DATA ONCE
@st.cache_resource
def load_data():
    data = pd.read_csv(
        "uber-raw-data-sep14.csv.gz",
        nrows=100000,  # approx. 10% of data
        names=[
            "date/time",
            "lat",
            "lon",
        ],  # specify names directly since they don't change
        skiprows=1,  # don't read header since names specified directly
        usecols=[0, 1, 2],  # doesn't load last column, constant value "B02512"
        parse_dates=[
            "date/time"
        ],  # set as datetime instead of converting after the fact
    )

    return data


# FUNCTION FOR AIRPORT MAPS
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,
                ),
            ],
        )
    )


# FILTER DATA FOR A SPECIFIC HOUR, CACHE
@st.cache_data
def filterdata(df, hour_selected):
    return df[df["date/time"].dt.hour == hour_selected]


# CALCULATE MIDPOINT FOR GIVEN SET OF DATA
@st.cache_data
def mpoint(lat, lon):
    return (np.average(lat), np.average(lon))


# FILTER DATA BY HOUR
@st.cache_data
def histdata(df, hr):
    filtered = data[
        (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({"分": range(60), "件数": hist})


# STREAMLIT APP LAYOUT
data = load_data()

# SEE IF THERE'S A QUERY PARAM IN THE URL (e.g. ?pickup_hour=2)
# THIS ALLOWS YOU TO PASS A STATEFUL URL TO SOMEONE WITH A SPECIFIC HOUR SELECTED,
# E.G. https://share.streamlit.io/streamlit/demo-uber-nyc-pickups/main?pickup_hour=2
if not st.session_state.get("url_synced", False):
    try:
        pickup_hour = int(st.experimental_get_query_params()["pickup_hour"][0])
        st.session_state["pickup_hour"] = pickup_hour
        st.session_state["url_synced"] = True
    except KeyError:
        pass

# IF THE SLIDER CHANGES, UPDATE THE QUERY PARAM
def update_query_params():
    hour_selected = st.session_state["pickup_hour"]
    st.experimental_set_query_params(pickup_hour=hour_selected)

# LAYING OUT THE TOP SECTION OF THE APP
row1_1, row1_2 = st.columns((2, 2))

with row1_1:
    st.title("ニューヨーク市でのウーバー使用状況")


with row1_2:
    st.write(
        """
    ##
    0時から23時のうち、1時間の時間帯を指定してください。
    """
    )
    hour_selected = st.slider(
        "時間帯", 0, 23, key="pickup_hour", on_change=update_query_params
    )

# LAYING OUT THE MIDDLE SECTION OF THE APP WITH THE MAPS
row2_1, row2_2, row2_3, row2_4 = st.columns((2, 1, 1, 1))

# SETTING THE ZOOM LOCATIONS FOR THE AIRPORTS
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"""**{hour_selected}:00 〜 {(hour_selected + 1) % 24}:00**"""
    )
    map(filterdata(data, hour_selected), midpoint[0], midpoint[1], 11)

with row2_2:
    st.write("**La Guardia 空港**")
    map(filterdata(data, hour_selected), la_guardia[0], la_guardia[1], zoom_level)

with row2_3:
    st.write("**JFK 空港**")
    map(filterdata(data, hour_selected), jfk[0], jfk[1], zoom_level)

with row2_4:
    st.write("**Newark 空港**")
    map(filterdata(data, hour_selected), newark[0], newark[1], zoom_level)

# CALCULATING DATA FOR THE HISTOGRAM
chart_data = histdata(data, hour_selected)

# LAYING OUT THE HISTOGRAM SECTION
st.write(
    f"""**毎分の使用状況：{hour_selected}:00 〜 {(hour_selected + 1) % 24}:00**"""
)

st.altair_chart(
    alt.Chart(chart_data)
    .mark_area(
        interpolate="step-after",
    )
    .encode(
        x=alt.X("分:Q", scale=alt.Scale(nice=False)),
        y=alt.Y("件数:Q"),
        tooltip=["分", "件数"],
    )
    .configure_mark(opacity=0.2, color="red"),
    use_container_width=True,
)