File size: 3,529 Bytes
7aa8120 2fd0c51 7aa8120 2fd0c51 | 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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | import streamlit as st
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import numpy as np
# Page config
st.set_page_config(
page_title="Uber NYC Pickups",
page_icon="🚕",
layout="wide",
initial_sidebar_state="expanded"
)
# Header with required link
st.title("🚕 Uber NYC Pickups")
st.markdown("[Built with anycoder](https://huggingface.co/spaces/akhaliq/anycoder)")
# Load data (simulate as if from the repo; in practice, download or use cached)
@st.cache_data
def load_data():
# For demo purposes, generate sample data similar to uber-raw-data-sep14.csv
# In a real app, load from 'https://github.com/streamlit/demo-uber-nyc-pickups/raw/master/uber-raw-data-sep14.csv'
np.random.seed(42)
n_points = 10000
dates = pd.date_range('2014-09-01', periods=n_points, freq='min')
lats = np.random.normal(40.75, 0.1, n_points)
lons = np.random.normal(-73.97, 0.1, n_points)
df = pd.DataFrame({
'Date/Time': dates,
'Lat': lats,
'Lon': lons,
'Base': np.random.choice(['B02512', 'B02598'], n_points)
})
return df
df = load_data()
# Sidebar filters
st.sidebar.header("Filters")
date_range = st.sidebar.slider(
"Select Date Range",
min_value=df['Date/Time'].min(),
max_value=df['Date/Time'].max(),
value=(df['Date/Time'].min(), df['Date/Time'].max()),
format="YYYY-MM-DD HH:MM"
)
hour_filter = st.sidebar.slider("Select Hour of Day", 0, 23, (0, 23))
base_filter = st.sidebar.multiselect(
"Select Base",
options=df['Base'].unique(),
default=df['Base'].unique()
)
# Filter data
filtered_df = df[
(df['Date/Time'] >= date_range[0]) &
(df['Date/Time'] <= date_range[1]) &
(df['Date/Time'].dt.hour.between(hour_filter[0], hour_filter[1])) &
(df['Base'].isin(base_filter))
].copy()
# Metrics
col1, col2, col3 = st.columns(3)
with col1:
st.metric("Total Pickups", len(filtered_df))
with col2:
avg_hour = filtered_df['Date/Time'].dt.hour.mean()
st.metric("Average Hour", f"{avg_hour:.0f}")
with col3:
unique_bases = filtered_df['Base'].nunique()
st.metric("Unique Bases", unique_bases)
# Visualizations
if len(filtered_df) > 0:
# Map
st.subheader("Pickups Map")
fig_map = px.scatter_mapbox(
filtered_df,
lat="Lat",
lon="Lon",
color="Base",
hover_data=["Date/Time"],
zoom=10,
height=500,
mapbox_style="carto-positron"
)
st.plotly_chart(fig_map, use_container_width=True)
# Time series
st.subheader("Pickups Over Time")
filtered_df['Date'] = filtered_df['Date/Time'].dt.date
hourly_data = filtered_df.groupby(filtered_df['Date/Time'].dt.hour).size().reset_index(name='Count')
fig_time = px.line(hourly_data, x='Date/Time', y='Count', title="Pickups by Hour")
st.plotly_chart(fig_time, use_container_width=True)
# Hourly heatmap
st.subheader("Hourly Distribution")
hourly_dist = filtered_df.groupby('Date/Time').size().reset_index(name='Count')
fig_heatmap = px.density_heatmap(
filtered_df,
x=filtered_df['Date/Time'].dt.hour,
y=filtered_df['Date/Time'].dt.date,
z=filtered_df.groupby([filtered_df['Date/Time'].dt.date, filtered_df['Date/Time'].dt.hour]).size().values.reshape(-1, 24),
color_continuous_scale="Viridis"
)
st.plotly_chart(fig_heatmap, use_container_width=True)
else:
st.info("No data matches the selected filters.") |