Binary-Class Tabular Model for Liver Disease Patients Using Python and Scikit-Learn

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Liver Disease Patients dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: This dataset contains over 30,000 cases of liver disease diagnosis results. The researcher trained machine learning models using this dataset to test the feasibility of applying machine learning techniques for making diagnostic predictions.

ANALYSIS: The average performance of the machine learning algorithms achieved an accuracy benchmark of 93.79% after training. Furthermore, we selected Random Forest as the final model as it processed the training dataset with an accuracy score of 99.82% using the 10-fold cross-validation method.

CONCLUSION: In this iteration, the Random Forest model appeared to be a suitable algorithm for modeling this dataset.

Dataset Used: Liver Disease Patients Dataset

Dataset ML Model: Binary-Class classification with numerical and categorical features

Dataset Reference: https://www.kaggle.com/datasets/abhi8923shriv/liver-disease-patient-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/abhi8923shriv/liver-disease-patient-dataset/code

The HTML formatted report can be found here on GitHub.

Michael Bungay Stanier on Do More Great Work, Part 3

In the book, Do More Great Work.: Stop the Busywork, and Start the Work that Matters, Michael Bungay Stanier shares his inspiration and techniques to help us do more work that matters.

These are some of my favorite takeaways from reading the book.

Map 2: What’s Great?

While past performance is no indicator of future results for many investments, that is not true regarding Great Work. Past peak moments of engagement and meaning are an excellent indicator of future Great Work that we can do.

A peak moment is when we can see and feel ourselves doing something more than we typically do. On those occasions, we step beyond where we usually stay and do something new or try something different. As a result, we also made an impact.

Acknowledging our past peak moments can help us clarify our definition of success. Michael suggests the following tactics for completing the mapping of this exercise:

  1. Think back and remember three or four peak moments in our working life.
  2. Add one or two peak moments outside our work life.
  3. Give each one of the peak moments a title and write them down.
  4. Write a sentence about what happened during those peak moments.
  5. Review the peak-moment stories and get insights from the map.
    1. As we remember those peak moments, what did they feel like for us?
    1. Take our list of themes and discuss it with someone who knows us well.
    1. Retrace the steps that got us there to those peak moments of Great Work.

Here are some Great Work wisdom nuggets from Penelope Trunk about taking a leap of faith.

“Ultimately, you are left with you. So really, doing Great Work is about knowing who you are and what you want. And here’s the crux of the matter: We can never know that for sure. You’ll never know everything about who you are, and you’ll never be able to completely describe what you want.”

“But we can’t wait forever. So we have to guess and take the plunge. Stepping forward to do more Great Work is in fact about a leap of faith that we take because the alternatives are so disappointing.”

有個什麼名詞嗎?

(從我一個尊敬的作家,賽斯·高汀

專家對此有個專業名詞。如果它是重要的、概念性的或經常討論的,則可能有一個專家理解的基於領域的名詞。特殊詞彙的精確度使他們能夠做得更好。

但是…

僅僅因為某人知道這個名詞並不意味著他們完全理解,或者他們是一個有用的專家。

何況…

如果有人不知道這個名詞,那麼可能值得調查他們其他不知道的內容。

領域知識和經驗是種強大的工具。

Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 5

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The InceptionV3 model’s performance achieved an accuracy score of 99.56% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 100%.

CONCLUSION: In this iteration, the TensorFlow InceptionV3 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 4

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The NASNetMobile model’s performance achieved an accuracy score of 99.65% after ten epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 86.93%.

CONCLUSION: In this iteration, the TensorFlow NASNetMobile CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 3

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The ResNet50V2 model’s performance achieved an accuracy score of 98.96% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 98.81%.

CONCLUSION: In this iteration, the TensorFlow ResNet50V2 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 2

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The EfficientNetV2M model’s performance achieved an accuracy score of 98.22% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 99.01%.

CONCLUSION: In this iteration, the TensorFlow EfficientNetV2M CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Lemon Quality Detection Using TensorFlow Take 1

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Lemon Quality Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains 2,533 images of lemons on concrete surfaces. The research team collected these images to investigate the possibilities of enforcing a fruit quality control system. The images can be broken down into three different labels: good quality, bad quality, and empty background.

ANALYSIS: The VGG19 model’s performance achieved an accuracy score of 99.31% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 98.81%.

CONCLUSION: In this iteration, the TensorFlow VGG19 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Lemon Quality Dataset

Dataset Reference: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset

One source of potential performance benchmarks: https://www.kaggle.com/datasets/yusufemir/lemon-quality-dataset/code

The HTML formatted report can be found here on GitHub.