Tag: classification

Binary Class Tabular Model for Kaggle Playground Series Season 3 Episode 2 Using Python and XGBoost

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 Kaggle Playground Series Season 3 Episode 2 dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Kaggle wants to provide an approachable environment for relatively new people in their data science journey. Since January 2021, they have hosted playground-style competitions to give the Kaggle community a variety of reasonably lightweight challenges that can be used to learn and sharpen skills in different aspects of machine learning and data science. The dataset for this competition was generated from a deep learning model trained on the Stroke Prediction Dataset. Feature distributions are close to but different from the original.

ANALYSIS: The performance of the preliminary XGBoost model achieved a ROC/AUC benchmark of 0.8772 after training. When we processed the test dataset with the final model, the model achieved a ROC/AUC score of 0.8730.

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

Dataset Used: Playground Series Season 3, Episode 2

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

Dataset Reference: https://www.kaggle.com/competitions/playground-series-s3e2

One source of potential performance benchmarks: https://www.kaggle.com/competitions/playground-series-s3e2/leaderboard

The HTML formatted report can be found here on GitHub.

Binary Class Tabular Model for Kaggle Playground Series Season 3 Episode 2 Using Python and TensorFlow Decision Forests

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 Kaggle Playground Series Season 3 Episode 2 dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Kaggle wants to provide an approachable environment for relatively new people in their data science journey. Since January 2021, they have hosted playground-style competitions to give the Kaggle community a variety of reasonably lightweight challenges that can be used to learn and sharpen skills in different aspects of machine learning and data science. The dataset for this competition was generated from a deep learning model trained on the Stroke Prediction Dataset. Feature distributions are close to but different from the original.

ANALYSIS: The Random Forest model performed the best with the training dataset. The model achieved a ROC/AUC benchmark of 0.9914. When we processed the test dataset with the final model, the model achieved a ROC/AUC score of 0.8731.

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

Dataset Used: Playground Series Season 3, Episode 2

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

Dataset Reference: https://www.kaggle.com/competitions/playground-series-s3e2

One source of potential performance benchmarks: https://www.kaggle.com/competitions/playground-series-s3e2/leaderboard

The HTML formatted report can be found here on GitHub.

Binary Class Tabular Model for Kaggle Playground Series Season 3 Episode 2 Using Python and Scikit-Learn

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 Kaggle Playground Series Season 3 Episode 2 dataset is a binary-class modeling situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: Kaggle wants to provide an approachable environment for relatively new people in their data science journey. Since January 2021, they have hosted playground-style competitions to give the Kaggle community a variety of reasonably lightweight challenges that can be used to learn and sharpen skills in different aspects of machine learning and data science. The dataset for this competition was generated from a deep learning model trained on the Stroke Prediction Dataset. Feature distributions are close to but different from the original.

ANALYSIS: The average performance of the machine learning algorithms achieved an AUC/ROC benchmark of 0.7836 after training. Furthermore, we selected Logistic Regression as the final model as it processed the training dataset with an AUC/ROC score of 0.8735. When we processed the test dataset with the final model, the model achieved an AUC/ROC score of 0.8662.

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

Dataset Used: Playground Series Season 3, Episode 2

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

Dataset Reference: https://www.kaggle.com/competitions/playground-series-s3e2

One source of potential performance benchmarks: https://www.kaggle.com/competitions/playground-series-s3e2/leaderboard

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Grapevine Leaves Image Using TensorFlow Take 5

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 Grapevine Leaves Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. Therefore, the species of grapevine leaves are essential factors in price and taste. The research team deployed deep learning-based classification models in this study to identify grapevine leaves. For this study, 500 images of vine leaves make up the dataset.

ANALYSIS: The EfficientNetV2L model’s performance achieved an accuracy score of 90.89% after 30 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 90.00%.

CONCLUSION: In this iteration, the TensorFlow EfficientNetV2L CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Grapevine Leaves Image Dataset

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.1016/j.measurement.2021.110425

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Grapevine Leaves Image Using TensorFlow Take 4

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 Grapevine Leaves Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. Therefore, the species of grapevine leaves are essential factors in price and taste. The research team deployed deep learning-based classification models in this study to identify grapevine leaves. For this study, 500 images of vine leaves make up the dataset.

ANALYSIS: The InceptionV3 model’s performance achieved an accuracy score of 94.89% after 30 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 92.00%.

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: Grapevine Leaves Image Dataset

Dataset Reference: https://www.muratkoklu.com/datasets/

One source of potential performance benchmarks: https://doi.org/10.1016/j.measurement.2021.110425

The HTML formatted report can be found here on GitHub.