Visualizing distributions

Introduction to Data Visualization with Julia

Gustavo Vieira Suñe

Data Analyst

Onion and wheat prices in Kerala, India

kerala DataFrame:

Date	Centre	Commodity	Price
JAN-2001	Ernakulam	Onion	10.0
JAN-2001	Ernakulam	Wheat	12.5
JAN-2001	Khozhikode	Onion	9.0
JAN-2001	Khozhikode	Wheat	14.0
...	...	...	...
MAR-2021	Trivandrum	Onion	45.0
MAR-2021	Trivandrum	Wheat	34.0

How much did the prices of onions and wheat differ?

Commodity	Mean Price
Onion	25.7442
Wheat	20.6261

Visualizing distributions with histograms

A histogram displaying the distribution of onion and wheat prices.

Distribution of onion and wheat prices

# Plot a histogram
histogram(
    kerala[:, :Price],

    # Add a label
    label="Onion and Wheat",
    # Choose bar color
    color=:darkseagreen1,
)

# Add axis labels
xlabel!("Price (Rupees)")
ylabel!("Frequency")

A histogram displaying the distribution of onion and wheat prices.

Number of bins

# Plot a histogram
histogram(
    kerala[:, :Price],
    # Add a label
    label="Onion and Wheat",
    # Choose bar color
    color=:darkseagreen1,

    # Number of bins
    bins=20,
)
# Add axis labels
xlabel!("Price (Rupees)")
ylabel!("Frequency")

A histogram displaying the distribution of onion and wheat prices, with a smaller number of bins.

Number of bins

# Plot a histogram
histogram(
    kerala[:, :Price],
    # Add a label
    label="Onion and Wheat",
    # Choose bar color
    color=:darkseagreen1,
    # Number of bins
    bins=range(0, 150, 75),
)
# Add axis labels
xlabel!("Price (Rupees)")
ylabel!("Frequency")

A histogram displaying the distribution of onion and wheat prices, with a larger number of bins.

Normalized histogram

# Plot a normalized histogram
histogram(
    kerala[:, :Price],
    # Add a label
    label="Onion and Wheat",
    # Choose bar color
    color=:darkseagreen1,

    # Normalize it
    normalize=true,
)
# Add axis labels
xlabel!("Price (Rupees)")
ylabel!("Probability")

A normalized histogram displaying the distribution of onion and wheat prices.

Probability distribution

using StatsPlots


density!(
    kerala[:, :Price],
    color=:black,
    linewidth=3,
    label=false
)

A histogram displaying onion and wheat prices with a density plot superimposed showing the probability distribution.

Prices per commodity

using StatsPlots

# Grouped histogram
groupedhist(
    kerala[:, :Price],

    # Group by commodity
    group=kerala[:, "Commodity"],

    # Select colors
    color=[:deeppink3 :wheat2]
)
xlabel!("Price (Rupees)")
ylabel!("Frequency")

A grouped histogram displaying onion and wheat prices separately with bars side-by-side.

Stacked histogram

using StatsPlots

# Stacked histogram
groupedhist(
    kerala[:, :Price],
    # Group by commodity
    group=kerala[:, "Commodity"],
    # Select colors
    color=[:deeppink3 :wheat2]

    # Stack the bars
    bar_position=:stack,
)

xlabel!("Price (Rupees)")
ylabel!("Frequency")

A grouped histogram displaying onion and wheat prices separately with bars stacked on top of each other.

A subtle difference

A grouped histogram displaying onion and wheat prices separately with bars stacked on top of each other.

The peak prices appear to be very similar.

Commodity	Mean Price
Onion	25.7442
Wheat	20.6261

Onion prices exhibit a long tail.
Median prices are almost the same.

Commodity	Median Price
Onion	20.0
Wheat	19.5

Difference in means is cause by the tail!

Let's practice!

Introduction to Data Visualization with Julia