app.py

import pandas as pd
import streamlit as st
import matplotlib.pyplot as plt

# Read the CSV file into a Pandas DataFrame
df = pd.read_csv('cph_airbnb_listings.csv')

# Create a Streamlit app
st.title('AirBnB bookings in Copenhagen')

# Allow user to add filters for neighbourhoods
selected_neighbourhoods = st.sidebar.multiselect('Select Neighbourhood(s)', df['neighbourhood'].unique())

# Allow user to add filter for room type
selected_room_type = st.sidebar.selectbox('Select Room Type', ['Private room', 'Entire home/apt'])

# Allow user to set a price range filter
price_range = st.sidebar.slider('Select Price Range', min_value=0, max_value=1000, step=10, value=(0, 1000))

# Filter the DataFrame based on selected filters
filtered_df = df.copy()
if selected_neighbourhoods:
    filtered_df = filtered_df[filtered_df['neighbourhood'].isin(selected_neighbourhoods)]
if selected_room_type:
    filtered_df = filtered_df[filtered_df['room_type'] == selected_room_type]
filtered_df = filtered_df[(filtered_df['price'] >= price_range[0]) & (filtered_df['price'] <= price_range[1])]

# Display the filtered DataFrame
st.write('Below is the sorted and filtered data:')
st.write(filtered_df)

# Calculate the average price for each selected neighbourhood
avg_prices = filtered_df.groupby(['neighbourhood', 'room_type'])['price'].mean().reset_index()

# Pivot the DataFrame to have neighbourhoods as index and room types as columns
avg_prices_pivot = avg_prices.pivot(index='neighbourhood', columns='room_type', values='price')

# Plot a histogram for each neighbourhood
if not avg_prices_pivot.empty:
    st.write('Histogram of Average Price for Each Neighbourhood:')
    fig, ax = plt.subplots()
    avg_prices_pivot.plot(kind='bar', ax=ax)
    ax.set_xlabel('Neighbourhood')
    ax.set_ylabel('Average Price')
    plt.xticks(rotation=45, ha='right')
    st.pyplot(fig)
else:
    st.write('No data available for selected filters.')