app.py

import streamlit as st

import pandas as pd
import numpy as np
import altair as alt
import pydeck as pdk

@st.experimental_singleton
 def get_database_session(_sessionmaker, url):
     # Create a database connection object that points to the URL.
     return connection

s1 = get_database_session(create_sessionmaker(), st.session_state.qp))
# Actually executes the function, since this is the first time it was
# encountered.

s2 = get_database_session(create_sessionmaker(), st.session_state.qp))
# Does not execute the function. Instead, returns its previously computed
# value - even though the _sessionmaker parameter was different
# in both calls.



# callback to update query param on selectbox change
def update_params():
    st.experimental_set_query_params(option=st.session_state.qp)
    get_database_session(st.session_state.qp)

options = st.selectbox(
    "Param", ["cat", "dog", "mouse", "bat", "duck"], key="qp", on_change=update_params
)

query_params = st.experimental_get_query_params()

# set the initial query param on first run
# based on the default option in selectbox
if not query_params:
    st.experimental_set_query_params(option=st.session_state.qp)

# display for debugging purposes
query_params = st.experimental_get_query_params()
st.write(query_params)



# SETTING PAGE CONFIG TO WIDE MODE AND ADDING A TITLE AND FAVICON
st.set_page_config(layout="wide", page_title="NYC Ridesharing Demo", page_icon=":taxi:")

# LOAD DATA ONCE
@st.experimental_singleton
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.experimental_memo
def filterdata(df, hour_selected):
    return df[df["date/time"].dt.hour == hour_selected]


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


# FILTER DATA BY HOUR
@st.experimental_memo
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({"minute": range(60), "pickups": hist})


# STREAMLIT APP LAYOUT
data = load_data()

# LAYING OUT THE TOP SECTION OF THE APP
row1_1, row1_2 = st.columns((2, 3))

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

with row1_2:
    st.write(
        """
    ##
    Examining how Uber pickups vary over time in New York City's and at its major regional airports.
    By sliding the slider on the left you can view different slices of time and explore different transportation trends.
    """
    )

# 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"""**All New York City from {hour_selected}:00 and {(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)

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

# LAYING OUT THE HISTOGRAM SECTION
st.write(
    f"""**Breakdown of 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,
)


@st.experimental_memo
def foo(x):
    return x**2

if st.button("Clear Foo"):
    # Clear foo's memoized values:
    foo.clear()

if st.button("Clear All"):
	  # Clear values from *all* memoized functions:
		st.experimental_memo.clear()