eda.py

import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
from PIL import Image

st.set_page_config(
    page_title = 'NYC TAXI - EDA',
    layout = 'wide',
    initial_sidebar_state = 'expanded'
    )

def run():
    # Membuat Title
    st.title('NYC Taxi Price Prediction')

    # Membuat Sub Header
    st.subheader('EDA for NYC Yellow Taxi Analysis')

    # Menambahkan Gambar
    image = Image.open('taxi.jpeg')
    st.image(image, caption='NYC Taxi')

    # Menambahkan Deskripsi
    st.write('This page created by **Imam Zarkasie**')
    st.write('### Hello!')
    st.write('#### The traffic in New York City makes residents choose taxis to travel around the city.')
    st.write('##### In this page we can explore some of the segmentation of taxi passengers in New York City')


    # Membuat Garis Lurus
    st.markdown('---')

    # Magic Syntax
    '''
    On this page, the author will do a simple exploration.
    The dataset used is the NYC Yellow Taxi dataset.
    This dataset comes from the website Google BigQuery.
    '''

    # Show DataFrame
    data = pd.read_csv('taxi_dataset.csv')
    st.dataframe(data)


    st.write('####  Some description for features that have a class:')
    st.write('#####  trip_type:')
    st.write('#####  1: Standard Rate')
    st.write('#####  2: JFK Airport and Others')
    st.write('#####  payment_type:')
    st.write('#####  1: Credit Card')
    st.write('#####  2: Cash')

    #Make price histogram plots and scatter plots to compare
    fig = plt.figure(figsize=(15, 5))
    plt.subplot(1, 2, 1)
    sns.histplot(data['trip_price'], kde=True, bins=30)
    plt.title('Histogram of trip_price')

    plt.subplot(1, 2, 2)
    sns.scatterplot(x='trip_distance', y='trip_price', data=data)
    plt.title('trip_distance vs trip_price')
    
    st.pyplot(fig)

    # Create the payment_type pie plot

    # Convert 'payment_type' column to int if it's not already
    data['payment_type'] = data['payment_type'].astype(int)

    # Calculate the counts of each payment type
    method_payment_type = data['payment_type']
    method_counts_payment_type = method_payment_type.value_counts()

    fig, ax = plt.subplots(figsize=(8, 3))
    method_counts_payment_type.plot(kind='pie',
                                    autopct='%1.1f%%',
                                    startangle=90,
                                    shadow=True,
                                    ax=ax)
    plt.title('Pie Plot User Payment Type')
    plt.axis('equal')

    # Menambahkan legend dengan keterangan untuk setiap kelas
    labels_payment_type = {1: 'Credit Card', 2: 'Cash', 3: 'No Charge', 4: 'Dispute'}
    plt.legend(labels=[labels_payment_type[i] for i in method_counts_payment_type.index], loc='upper right')
    
    plt.tight_layout() 
    st.pyplot(fig)

    #Create pie plot trip_type
    method_trip_type = data['trip_type']
    method_counts_trip_type = method_trip_type.value_counts()

    fig, ax = plt.subplots(figsize=(8, 3))
    method_counts_trip_type.plot(kind='pie',
                                    autopct='%1.1f%%',
                                    startangle=90,
                                    shadow=True,
                                    ax=ax)
    plt.title('Pie Plot User Trip Type')
    plt.axis('equal')

    # Menambahkan legend dengan keterangan untuk setiap kelas
    labels = {1: 'Standard Rate', 2: 'JFK Airport', 5: 'Negotiated Fare', 4: 'westchester', 3: 'Newark'}
    plt.legend(labels=[labels[i] for i in method_counts_trip_type.index], loc='upper right')

    st.pyplot(fig)
    
    #Passenger Count Histogram
    passenger_count = data['passenger_count']
    unique_counts = passenger_count.unique()

    n_bins = 10
    colors = ['steelblue', 'orange', 'green', 'red', 'purple', 'crimson', 'yellow']
    bar_width = 0.8

    fig =plt.figure(figsize=(8, 2))

    for i, count in enumerate(unique_counts):
        counts = passenger_count[passenger_count == count]
        plt.hist(counts, bins=n_bins, color=colors[i], alpha=0.7, width=bar_width)

    plt.title('Histogram of Passenger Count')
    plt.xlabel('Passenger Count')
    plt.ylabel('Frequency')

    st.pyplot(fig)

if __name__=='__main__':
    run()