Loading...

Machine Learning - Outliers

General

vastorbit’s outlier plots offer an essential means of identifying and comprehending outliers within your dataset. These plots provide valuable visual insights into data points that significantly deviate from the expected distribution, facilitating the detection of anomalies or potential data errors. Whether through box plots, scatter plots, or other visualizations, vastorbit equips data analysts with powerful tools to enhance outlier detection and data quality assessment.

Let’s begin by importing vastorbit.

import vastorbit as vo

Let’s also import numpy to create a random dataset.

import numpy as np

Let’s generate a dataset using the following data.

# Very tight cluster (makes outliers very obvious)
N_main = 100
x_main = np.random.normal(50, 2, N_main)  # Small std dev
y_main = np.random.normal(50, 2, N_main)  # Small std dev

# Many obvious outliers spread out
outliers_x = np.array([
    20, 25, 30, 80, 75, 70,   # Left and right
    50, 50, 50, 50,            # Top and bottom (same x)
    15, 85, 10, 90,            # Corners
    40, 60, 35, 65             # Diagonal
])

outliers_y = np.array([
    50, 45, 55, 50, 55, 45,   # Middle height
    20, 25, 80, 75,            # Top and bottom
    15, 85, 10, 90,            # Corners
    20, 80, 75, 25             # Diagonal
])

data = vo.VastFrame({
    "x": np.concatenate([x_main, outliers_x]),
    "y": np.concatenate([y_main, outliers_y]),
})

In the context of data visualization, we have the flexibility to harness multiple plotting libraries to craft a wide range of graphical representations. vastorbit, as a versatile tool, provides support for several graphic libraries, such as Matplotlib and Plotly. Each of these libraries offers unique features and capabilities, allowing us to choose the most suitable one for our specific data visualization needs.

_images/plotting_libs.png

Note

To select the desired plotting library, we simply need to use the set_option() function. vastorbit offers the flexibility to smoothly transition between different plotting libraries. In instances where a particular graphic is not supported by the chosen library or is not supported within the vastorbit framework, the tool will automatically generate a warning and then switch to an alternative library where the graphic can be created.

Please click on the tabs to view the various graphics generated by the different plotting libraries.

We can switch to using the plotly module.

vo.set_option("plotting_lib", "plotly")

data.outliers_plot(columns = ["x"])

data.outliers_plot(columns = ["x", "y"])

We can switch to using the matplotlib module.

vo.set_option("plotting_lib", "matplotlib")

data.outliers_plot(columns = ["x"])

data.outliers_plot(columns = ["x", "y"])

Chart Customization

vastorbit empowers users with a high degree of flexibility when it comes to tailoring the visual aspects of their plots. This customization extends to essential elements such as color schemes, text labels, and plot sizes, as well as a wide range of other attributes that can be fine-tuned to align with specific design preferences and analytical requirements. Whether you want to make your visualizations more visually appealing or need to convey specific insights with precision, vastorbit’s customization options enable you to craft graphics that suit your exact needs.

Important

Different customization parameters are available for Plotly and Matplotlib. For a comprehensive list of customization features, please consult the documentation of the respective libraries: plotly, matplotlib.

Colors

Custom colors

data.outliers_plot(
    columns = ["x", "y"],
    color = "green",
    outliers_color = "red",
    inliers_color = "pink",
    inliers_border_color = "yellow"
)

Custom colors

data.outliers_plot(
    columns = ["x", "y"],
    color = "green",
    outliers_color = "red",
    inliers_color = "pink",
    inliers_border_color = "yellow"
)

Size

Custom Width and Height

data.outliers_plot(columns = ["x", "y"], width = 300, height = 300)

Custom Width and Height

data.outliers_plot(columns = ["x", "y"], width = 6, height = 3)

Text

Custom Title

data.outliers_plot(columns = ["x", "y"], ).update_layout(title_text = "Custom Title")

Custom Axis Titles

data.outliers_plot(columns = ["x", "y"], yaxis_title = "Custom Y-Axis Title")

Custom Title Text

data.outliers_plot(columns = ["x", "y"], ).set_title("Custom Title")

Custom Axis Titles

data.outliers_plot(columns = ["x", "y"], ).set_ylabel("Custom Y Axis")