Python Machine Learning Bootcamp

Self-paced lessons

Watch free previews and explore the lessons included with enrollment at Noble Desktop.

• ▶ Play preview

  Python for Machine Learning Introduction

  Lesson 1: Basic Regression Analysis

  2:08

  Cover regression analysis, supervised learning essentials, k-nearest neighbors algorithm, random forest classifiers, and neural networks in a structured course.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Colab Setup

  Lesson 1: Basic Regression Analysis

  3:23

  Download the class files zip archive, extract it, and use Google Colab to upload and connect the first Jupyter Notebook to Google Drive.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Drive Setup

  Lesson 1: Basic Regression Analysis

  3:38

  Upload the Python Machine Learning Bootcamp folder directly to My Drive in Google Drive to ensure all file paths work correctly in Google Colab.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Jupyter Setup

  Lesson 1: Basic Regression Analysis

  10:14

  Learn how to use Jupyter Notebooks for running and explaining Python code blocks in data science and machine learning courses.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Loading The Cars Data

  Lesson 1: Basic Regression Analysis

  7:50

  Summarize the process of setting up and troubleshooting Python imports, URLs, and dataframes in Jupyter Notebooks using statistical libraries and CSV files.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Pandas Dataframe Slices

  Lesson 1: Basic Regression Analysis

  8:06

  Explore subsets of car data using `iloc` for index-based slicing and `loc` for label-based, more human-readable slicing.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Challenge 1 Slices

  Lesson 1: Basic Regression Analysis

  1:01

  Retrieve the last three rows and last three columns of the data frame using both ILOC and LOC methods.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Challenge 1 Slices Solution

  Lesson 1: Basic Regression Analysis

  7:48

  Use iloc or loc to select the last three rows and columns of a DataFrame, ensuring correct index handling and semantic representation for dynamic updates.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Initial Data Analysis Tools

  Lesson 1: Basic Regression Analysis

  11:33

  Analyze statistical data using Python to find minimum, maximum, and mean values from lists and data frames, employing functions like `min()`, `max()`, and NumPy's `.mean()`, while using methods to handle specific data structures like pandas series.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Median

  Lesson 1: Basic Regression Analysis

  6:48

  Explain how the median provides a more accurate representation of typical data than the mean when outliers are present.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Mode

  Lesson 1: Basic Regression Analysis

  2:49

  Explain how to calculate the mode using the `stats.mode` function from SciPy, which returns a tuple with the most frequent value and its count.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Tuples

  Lesson 1: Basic Regression Analysis

  5:43

  Understand and utilize tuple unpacking in Python to efficiently work with multiple returned values from functions, ensuring immutability and correct assignment order.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Averages In Real Data

  Lesson 1: Basic Regression Analysis

  6:35

  Analyze a dataset's central tendencies using pandas methods to calculate the mean, median, and mode, considering the context of outliers and data repetition.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Standard Deviation And The Bell Curve

  Lesson 1: Basic Regression Analysis

  4:42

  Explain standard deviation as a measure of how much values deviate from the mean in a normal distribution, where one standard deviation includes about 68.2% of values, two standard deviations cover 95.4%, and three standard deviations encompass nearly all values.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Calculating Standard Deviation

  Lesson 1: Basic Regression Analysis

  2:17

  Calculate standard deviation using NumPy, adjusting for degrees of freedom if analyzing a sample.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Variance

  Lesson 1: Basic Regression Analysis

  3:04

  Calculate variance as the square of standard deviation, useful for mathematical statistical work.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Percentile

  Lesson 1: Basic Regression Analysis

  2:02

  Calculate percentiles using NumPy's percentile method to understand dataset distribution.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Challenge 2 Percentile From User Input

  Lesson 1: Basic Regression Analysis

  1:28

  Prompt the user for a percentile and print the corresponding age at which that percent of people are younger using the input function and np.percentile.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Challenge 2 Percentile From User Input Solution

  Lesson 1: Basic Regression Analysis

  3:18

  Create an input box to enter a percentile and calculate the corresponding age using NumPy's percentile function.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Uniform Distribution Histograms

  Lesson 1: Basic Regression Analysis

  7:13

  Comment out the code to avoid repeated prompts, and create histograms using NumPy and PyPlot to visualize the frequency distribution of uniformly distributed random numbers, showing smoother distributions with larger sample sizes.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Normal Distribution Histograms

  Lesson 1: Basic Regression Analysis

  4:11

  Illustrate a normal distribution using NumPy to generate 250,000 random scores centered around a mean of 100 with a standard deviation of 15, and visualize the data with a histogram to show the bell curve.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Linear Regression

  Lesson 1: Basic Regression Analysis

  2:43

  Predict the relationship between x and y variables using linear regression by minimizing the variance, or the sum of squared differences, between the line and data points.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Plotting Attendance Against Concessions

  Lesson 1: Basic Regression Analysis

  5:56

  Perform a linear regression to predict concessions revenue based on baseball game attendance data using NumPy's polyfit function and visualize it with a line plot.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Using Pandas For Vector Operations

  Lesson 1: Basic Regression Analysis

  2:02

  Create a data frame using pandas to perform vector operations on attendance and concessions data for predictive analysis.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  A Prediction Concessions Function

  Lesson 1: Basic Regression Analysis

  4:50

  Create a Python function called `predict_concessions` to calculate expected concession revenue based on attendance, using a linear regression formula, and ensure the result is rounded to the nearest dollar for readability and ease of updates in one place.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Predicting Concessions From User Input

  Lesson 1: Basic Regression Analysis

  3:32

  Create a program that allows ballpark employees to input attendance numbers to predict concessions revenue using a predefined formula.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Adding Predictions To Our Data

  Lesson 1: Basic Regression Analysis

  2:50

  Add predicted concessions values to the data frame by mapping the `predict_concessions` function over the attendance column.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Polynomial Regressions

  Lesson 1: Basic Regression Analysis

  8:45

  Implement polynomial regression to fit a curve to the data, but avoid overfitting by not using too many polynomial degrees.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Supervised Learning Intro

  Lesson 2: Supervised Learning Essentials

  7:45

  Set up your notebook for machine learning by importing necessary libraries and preparing data for supervised learning, including splitting it into training and testing sets.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Car Data Overview

  Lesson 2: Supervised Learning Essentials

  4:37

  Predict car sales using a linear regression model, analyze and clean data using Scikit-learn and Pandas, and determine important features through visualization and correlation matrices.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Picking Features From Domain Knowledge

  Lesson 2: Supervised Learning Essentials

  4:10

  Determine which data is important for training the model by analyzing both domain knowledge and data analysis.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Correlation Matrixes

  Lesson 2: Supervised Learning Essentials

  5:29

  Analyze the correlation matrix to determine that "sales in thousands" is not significantly correlated with other variables and may not be essential for model training.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Pair Plots Intro

  Lesson 2: Supervised Learning Essentials

  1:41

  Visualize data relationships using a Seaborn pair plot to display scatter plots for correlations and histograms for individual variables.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Pair Plot Analysis

  Lesson 2: Supervised Learning Essentials

  4:02

  Create a Seaborn pair plot to visually explore relationships and distributions between variables in a dataset.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Cleaning Data

  Lesson 2: Supervised Learning Essentials

  7:29

  Clean data, select features (fuel efficiency, engine size, horsepower), split into training/testing sets, and prepare for linear regression model training to predict car prices.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Splitting Training Data From Test Data

  Lesson 2: Supervised Learning Essentials

  6:11

  Split data into training and testing sets using `train-test-split` to ensure 80% for training and 20% for testing.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Scaling the Data

  Lesson 2: Supervised Learning Essentials

  6:23

  Scale the X train and X test data using scikit-learn's StandardScaler to ensure all features have a mean of zero and are measured in standard deviations, preventing the model from detecting false patterns based on varying scales.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Linear Regression Model Intro

  Lesson 2: Supervised Learning Essentials

  2:50

  Use a linear regression model to perform continuous classification by predicting numeric values from data.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training the Linear Regression Model

  Lesson 2: Supervised Learning Essentials

  1:24

  Train the model using model.fit with X train and Y train data for linear regression.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Comparing Predictions to Test Data

  Lesson 2: Supervised Learning Essentials

  2:55

  Evaluate the model's predictions against test data by comparing predicted values to actual values.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Accuracy Score

  Lesson 2: Supervised Learning Essentials

  3:39

  Evaluate the accuracy of the linear regression model by comparing its predictions to the mean prediction, resulting in a 69% improvement.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Removing Outliers

  Lesson 2: Supervised Learning Essentials

  5:17

  Improve accuracy by removing outliers from the dataset before splitting it into training and testing sets.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Filtering Outliers Out

  Lesson 2: Supervised Learning Essentials

  1:59

  Filter car sales data to exclude rows with a price over 80,000 and an engine size over 7, reducing the dataset to 150 rows for model retraining.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training and Testing a Second Model

  Lesson 2: Supervised Learning Essentials

  8:15

  Try removing outliers and using larger datasets to improve model accuracy.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Logistic Regression Intro

  Lesson 2: Supervised Learning Essentials

  3:53

  Use logistic regression to predict whether employees will stay or leave based on HR data.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Hr Data Overview

  Lesson 2: Supervised Learning Essentials

  2:35

  Check for null values and visualize how many people left or stayed using HR data, revealing that 11,428 stayed and 3,571 left.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Data Analysis Crosstabs

  Lesson 2: Supervised Learning Essentials

  2:16

  Crosstabulate the "left" and "salary" columns in the HR data using Pandas to analyze the impact of salary on employee retention.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Making Our Crosstab More Readable

  Lesson 2: Supervised Learning Essentials

  4:11

  Rename indices to "stayed" and "left," move "high" column to the left, and convert categorical values to numerical data for computer processing.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  One Hot Encoding

  Lesson 2: Supervised Learning Essentials

  3:57

  Convert categorical salary data into numerical format using one-hot encoding with Pandas get_dummies, creating separate columns for low, medium, and high values.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Concatenating Ohe Data

  Lesson 2: Supervised Learning Essentials

  1:45

  Concatenate the high, low, and medium columns to the right side of the data frame before splitting it into testing and training data.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training a Logistic Regression Model

  Lesson 2: Supervised Learning Essentials

  4:26

  Create and evaluate a logistic regression model using the specified columns for predicting whether employees left or stayed, scaling the data as needed.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Measuring Accuracy

  Lesson 2: Supervised Learning Essentials

  5:42

  Evaluate the model's predictions to identify true positives, true negatives, false positives, and false negatives, achieving a 77% overall accuracy.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Confusion Matrix

  Lesson 2: Supervised Learning Essentials

  4:35

  Analyze the confusion matrix to identify where the model misclassified predictions, particularly noting that it accurately predicted only 25% of those who actually left.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Precision and Recall

  Lesson 2: Supervised Learning Essentials

  5:22

  Evaluate model performance using precision and recall, noting high accuracy in predicting who stayed but poor recall for those who left, highlighting the importance of directionality in errors depending on use case.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Knn Intro

  Lesson 3: K-Nearest Neighbors

  2:13

  Explore the k-nearest neighbors (KNN) algorithm to classify data points based on the values of their nearest existing points.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Visualizing Knn

  Lesson 3: K-Nearest Neighbors

  2:04

  Classify new data points by identifying the class of the majority among their k-nearest neighbors.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Plotting Training Data

  Lesson 3: K-Nearest Neighbors

  3:02

  Visualize k-nearest neighbors by plotting categorized x and y coordinates using pyplot's scatter plot function.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Creating and Training Our Knn Model

  Lesson 3: K-Nearest Neighbors

  3:13

  Train a k-neighbors classifier using a k-value of three on saved data points and classes, then test its prediction on a new data point.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Visualizing Our New Point

  Lesson 3: K-Nearest Neighbors

  4:41

  Visualize the new data point with a unique class and predict its class using the KNN model.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Visualizing the Prediction

  Lesson 3: K-Nearest Neighbors

  2:06

  Append the integer prediction to the classes list and visualize the newly classified point using k-nearest neighbors.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Iris Knn Intro

  Lesson 3: K-Nearest Neighbors

  2:29

  Apply K-Nearest Neighbors to the iris dataset using sepal and petal measurements to classify flowers with high accuracy.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Visualizing Multi Dimensional Datasets

  Lesson 3: K-Nearest Neighbors

  2:43

  Visualize and analyze iris species data using K-Nearest Neighbors across multiple dimensions to classify new samples.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Loading and Reviewing Iris Data

  Lesson 3: K-Nearest Neighbors

  2:40

  Load and explore the Iris dataset using sklearn to understand its structure, including data arrays, target classifications, and target names.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Creating Iris Dataframe

  Lesson 3: K-Nearest Neighbors

  8:29

  Convert the iris dataset into a pandas DataFrame, add a target column with numerical values (0, 1, 2), and then apply a function or lambda to map these target values to their corresponding species names, creating a new 'species' column for human readability.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Prepping Our Data for Knn

  Lesson 3: K-Nearest Neighbors

  2:58

  Prepare the dataset by splitting it into training and testing sets for features (X) and targets (Y) using 20% of the data for testing.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training and Testing Our Knn Model

  Lesson 3: K-Nearest Neighbors

  1:58

  Train the k-neighbors classifier with 3 neighbors on the training data and compare predictions against actual test data.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Creating a Classification Report

  Lesson 3: K-Nearest Neighbors

  3:08

  Score the model by calculating accuracy and generating a classification report to identify prediction errors.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Analyzing and Summing Up Knn Results

  Lesson 3: K-Nearest Neighbors

  3:07

  Identify a virginica misclassified as a versicolor due to its closeness to the versicolor group.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Titanic Dataset Intro

  Lesson 4: Titanic Survival Prediction

  2:13

  Predict Titanic survival using a random forest classifier with the Kaggle dataset.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Titanic Dataset Closer Look

  Lesson 4: Titanic Survival Prediction

  2:23

  Analyze and clean the Titanic dataset by addressing missing values in age and embarked columns while ignoring the cabin data.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Filling in Na Values

  Lesson 4: Titanic Survival Prediction

  8:43

  Fill missing ages in the Titanic dataset with gender-specific mean values and replace missing 'embarked' entries with the mode 'S'.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Plotting Survived vs Perished

  Lesson 4: Titanic Survival Prediction

  2:00

  Analyze the survival rates and passenger class distribution of Titanic data using Seaborn count plots.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Plotting by 2 Columns

  Lesson 4: Titanic Survival Prediction

  3:37

  Graph passenger class distribution and survival rates by class using Seaborn to identify potential predictive features for analysis.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Plotting More Data

  Lesson 4: Titanic Survival Prediction

  2:10

  Analyze Titanic survival rates by gender and port of embarkation to identify potential influential factors.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Graphing a Combined Column

  Lesson 4: Titanic Survival Prediction

  5:37

  Combine passenger class and gender into a new categorical column "p-class sex" in the Titanic dataset to analyze survival patterns based on these combined factors.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Label Encoding

  Lesson 4: Titanic Survival Prediction

  3:31

  Use LabelEncoder to transform categorical variables into numerical values for easier processing.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Splitting and Scaling Our Data

  Lesson 4: Titanic Survival Prediction

  4:40

  Split and scale the Titanic dataset using standard scaler before applying random forest classifiers.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Random Forest Classifiers

  Lesson 4: Titanic Survival Prediction

  4:42

  Explain how random forest classifiers use multiple decision trees to make predictions by averaging diverse subsets of data.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Creating and Training Our Model

  Lesson 4: Titanic Survival Prediction

  0:53

  Create and train a random forest classifier model with the training data, then proceed to test it.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Cleaning Up the Test Data

  Lesson 4: Titanic Survival Prediction

  8:01

  Prepare and clean the X test data by filling missing ages with mean values by gender and filling the missing fare with the mean fare before labeling, encoding, scaling, and submitting the predictions to Kaggle.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Label Encoding and Scaling Our Test Data

  Lesson 4: Titanic Survival Prediction

  4:50

  Label, encode, and scale the specified columns in the dataset to prepare for model submission.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Fixing Column Order Error

  Lesson 4: Titanic Survival Prediction

  1:09

  Correct the column order by moving age to the fourth position and rerun the code to ensure accuracy.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Submitting to Kaggle

  Lesson 4: Titanic Survival Prediction

  7:49

  Create a predictions array from the model, form a data frame with passenger IDs and predictions, save it as a CSV without an index, and submit it to Kaggle for scoring.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Neural Networks Intro

  Lesson 5: Neural Networks

  4:30

  Explore neural networks, focusing on translating handwritten digits using TensorFlow and Keras, while learning data visualization, normalization, and model training techniques.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Notebook Setup

  Lesson 5: Neural Networks

  1:15

  Import libraries and set up Google Drive and TensorFlow for the neural network.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Task Intro

  Lesson 5: Neural Networks

  2:16

  Analyze the MNIST dataset of handwritten digits to train a machine learning model for accurate digit recognition.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Analyzing the Shape of Our Data

  Lesson 5: Neural Networks

  6:09

  Analyze the MNIST dataset from TensorFlow to understand its structure as immutable tuples containing training and testing data divided into images and labels.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Unpacking All Our Data

  Lesson 5: Neural Networks

  2:41

  Unpack the data into training and testing images and labels to confirm their shapes and types.

  View enrollment options at Noble Desktop
• ▶ Play preview

  Looking at a Digit Array Part 1

  Lesson 5: Neural Networks

  5:28

  Explore how to train a neural network model using 60,000 grayscale 28x28 pixel images of handwritten digits represented as NumPy arrays.

  This preview is temporarily unavailable. Please try again later.

• 

  Enrollment required

  Looking at a Digit Array Part 2

  Lesson 5: Neural Networks

  1:59

  Visualize the array as a stretched-out image to see it resembles a 5.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training and Testing Review

  Lesson 5: Neural Networks

  3:51

  Train the model using 60,000 handwritten digit images to recognize patterns and improve accuracy before testing with 10,000 new images.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Normalizing Our Data

  Lesson 5: Neural Networks

  5:18

  Normalize data by dividing each pixel value by 255 to scale them between zero and one for both training and testing images.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Building a Neural Network

  Lesson 5: Neural Networks

  12:06

  Build a three-layer neural network using a sequential Keras model with an input layer that flattens a 28x28 input, a dense hidden layer with 128 neurons using the ReLU activation function, and an output layer with 10 neurons using the softmax activation.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Training Our Model

  Lesson 5: Neural Networks

  4:37

  Compile the neural network model, train it over multiple epochs, and observe accuracy improvements and loss reductions.

  View enrollment options at Noble Desktop
• 

  Enrollment required

  Analyzing Predictions

  Lesson 5: Neural Networks

  11:22

  Analyze the predictions' accuracy by comparing predicted digits to correct labels and preparing for further evaluation and tuning in the next lesson.

  View enrollment options at Noble Desktop