Skip to content
Live Training: Data[…]lity=public
  • AI Chat
  • Code
  • Report
  • Spinner

    Data Visualization for absolute beginners

    This live training covers the basics of how to create an interactive plot using Plotly. We will visualize Seoul bike sharing data using bar plots, scatter plots, and line plots using Plotly as well as DataCamp Workspace's no-code chart cell. In the process, we’ll tease out how Seoul weather is impacting bike sharing trends.

    Load in required packages

    import pandas as pd
    from datetime import datetime, timedelta
    import as px

    Load and clean the data

    The dataset consists of the number of public bikes rented in Seoul's bike sharing system at each hour. It also includes information about the weather and the time, such as whether it was a public holiday. Source of dataset.

    # Import CSV with renamed columns
    df = pd.read_csv('data/seoul_bike_data_renamed.csv')
    # Clean up some columns
    df["date"] = pd.to_datetime(df["date"], format="%d/%m/%Y")
    df["datetime"] = df.apply(
        lambda row: row["date"] + timedelta(hours=row["hour"]), axis=1
    df["is_holiday"] = df["is_holiday"].map({"No Holiday": False, "Holiday": True})
    # Similar to is_holiday, map is_functioning to True and False
    df["is_functioning"] = df["is_functioning"].map({"Yes": True, "No": False})
    # Only keep observations where the system is functioning
    df = df.query('is_functioning')
    # Print out the result

    Visualize bike rentals over time

    # Create a line plot of rented bikes over time
    px.line(df, x="datetime", y="n_rented_bikes")
    # Calculate the total number of rented bikes per day
    by_day = df \
    	.groupby(by="date", as_index=False) \
    	.sum("n_rented_bikes") \
    	[["date", "n_rented_bikes"]]
    # Create a line plot showing total number of bikes per day over time
    px.line(by_day, x='date', y='n_rented_bikes')
    # Copy the previous chain of manipulations and add season as a variable to group by
    by_day_season = df \
    	.groupby(by=['date', 'season'], as_index=False) \
    	.sum("n_rented_bikes") \
    	[['date', 'n_rented_bikes', 'season']]
    # Copy the code for the previous line plot and map season to color
    px.line(by_day_season, x='date', y='n_rented_bikes', color='season')

    Explore the relation between weather and rentals

    # Query df to only keep observations at noon
    noon_rides = df.query('hour == 12')
    # Create a scatter plot showing temperature against number of rented bikes
    # Add a trendline if you feel like it
    px.scatter(noon_rides, x='temperature_celsius', y='n_rented_bikes', trendline='lowess')
    # Copy and update the code for the previous scatter plot 
    # to investigate relation with other weather parameters
    # px.scatter(noon_rides, x='wind_speed_mps', y='n_rented_bikes', trendline='lowess')
    # px.scatter(noon_rides, x='humidity_pct', y='n_rented_bikes', trendline='lowess')
    # px.scatter(noon_rides, x='visibility_10m', y='n_rented_bikes', trendline='lowess')
    # px.scatter(noon_rides, x='rainfall_mm', y='n_rented_bikes', trendline='lowess')
    # px.scatter(noon_rides, x='snowfall_cm', y='n_rented_bikes', trendline='lowess')

    Explore typical daily usage pattern

    # Calculate the average number of rented bikes per hour
    time_of_day = df \
    	.groupby(by = ['hour'], as_index=False) \
    	.mean("n_rented_bikes") \
    	[['hour', 'n_rented_bikes']]
    # Create a bar chart showing the usage pattern, x='hour', y='n_rented_bikes')
    # Copy and adapt the previous query to take into account the season
    time_of_day_season = df \
    	.groupby(by = ['hour', 'season'], as_index=False) \
    	.mean("n_rented_bikes") \
    	[['hour', 'season', 'n_rented_bikes']]
    # Copy and adapt the code for the previous bar chart to show usage pattern per season, x='hour', y='n_rented_bikes', color='season', facet_col="season")