DAC 111 - Chapter 10 & 11

Supervised Learning

Type of machine learning where expected prediction is available for each sample when fitting the model

Unsupervised Learning

Type of machine learning where expected prediction isn't available for each sample when fitting the model, often used for clustering and detecting outliers

Overfitting

Occurs when a machine learning model matches the training data so closely that the model fails to make correct predictions on generalized data

Training/Testing Split

Splits the data randomly at specified amounts

.fit()

scikit-learn method that learns from training data set to predict value for testing data set

.predict(x)

scikit-learn method that given x will return predicted values

Logistic Regression Classifier

Machine learning algorithm that predicts probability with binary outcome

MinMaxScaler

Transforms features by scaling those features to the given range

k-means Clustering

Groups similar data points into clusters based on distance to the center

Model Evaluation Metrics

Assesses performance and effectiveness of statistical or machine learning models

Handle Categorical Predictors with Dummy Coding

Make the variable equal to 1 if it exists, otherwise equal to 0

Tokenization

Text mining with NLTK that splits text into words/sentences

Stop-Word Removal

Text mining with NLTK that filters commonly used words

Stemming

Text mining with NLTK that reduces the variation of a word

Sentiment Analysis using VADER

Gives score ranging -1 to +1 ~ summing valence with adjustment to VADER

tkinter

Python library for creating GUI applications.

Tk root window

The initial window in GUI

Tk()

Method that instantiate the main root window

mainloop()

Method that enters the event loop; keeps the GUI responsive

title()

Method that sets the window title bar text

geometry()

Method that specifies window size and position

Label

Widget that displays static text or images

Button

Widget that triggers a function when clicked

Entry

Widget that is a single-line text input field

Listbox

Widget that displays a list of selectable items

Canvas

Widget that is a drawing area for shapes, images, or custom graphics

Frame

Widget that is a container for grouping related widgets

Checkbutton

Widget that allows selection of multiple options using checkboxes

Radiobutton

Widget that allows selection of one option from a set (mutually exclusive)

Combobox

Widget that is a dropdown menu for selecting one item from a list

Scrollbar

Widget that provides vertical or horizontal scrolling capabilities for widgets like Text, Canvas, or Listbox

text

Widget option that is a string displayed on the widget (e.g. button label)

bg

Widget option that is the background color of the widget

fg

Widget option that is the foreground (text) color

font

Widget option that is the font family, size, style for widget text

width

Widget option that is the widgets width (characters or pixels, widget-dependent)

height

Widget option that is the widgets height (lines or pixels)

justify

Widget option that is the alignment of multi-line text within the widget (left, center, right)

StringVar

Variable class that stores text strings

IntVar

Variable class that stores integer values

DoubleVar

Variable class that stores floating-point numbers

BooleanVar

Variable class that stores boolean flags (True/False)

pack

Layout manager with placement of side/top/bottom stacking with padding

grid

Layout manager with row/column placement --> uses row, column, sticky

place

Layout manager uses absolute or relative x/y coordinates for placement

sticky

Layout manager with placement alignment inside a grid cell (NSEW)

.destroy()

Method that destroys the specified widget (or root) immediately

.quit()

Exits mainloop() but keeps window objects alive