You will get a data science project with analysis and machining learning capabilities
Project details
This project focuses on rice type classification and extent prediction using machine learning and deep learning. After performing Exploratory Data Analysis (EDA) with Python, outliers were treated using IQR, leading to some data loss and increased skewness in other features. Feature engineering, normalization, and dimensionality reduction were applied to prepare the data.
KMeans clustering created additional features, with Gradient Boosting Classifier identified as the best model, achieving high precision, recall, and a perfect ROC-AUC score of 1 for rice types "gonen" and "jasmine."
For extent prediction, Linear Regression performed poorly, showing a low R² score, with slight improvement from polynomial features. The deep learning approach resulted in better RMSE (0.0989) for regression analysis.
Models, pipelines, and project files are stored in the project's folders for further exploration.
KMeans clustering created additional features, with Gradient Boosting Classifier identified as the best model, achieving high precision, recall, and a perfect ROC-AUC score of 1 for rice types "gonen" and "jasmine."
For extent prediction, Linear Regression performed poorly, showing a low R² score, with slight improvement from polynomial features. The deep learning approach resulted in better RMSE (0.0989) for regression analysis.
Models, pipelines, and project files are stored in the project's folders for further exploration.
Machine Learning Tools
Keras, Microsoft Power BI, NumPy, pandas, Python, Python Scikit-Learn, scikit-learn, SciPy, TensorFlowWhat's included
| Service Tiers |
Starter
$60
|
Standard
$70
|
Advanced
$150
|
|---|---|---|---|
| Delivery Time | 10 days | 15 days | 20 days |
Number of Revisions | 3 | 3 | 3 |
Number of Model Variations | 3 | 3 | 3 |
Number of Scenarios | 1 | 1 | 1 |
Number of Graphs/Charts | 5 | 5 | 5 |
Model Validation/Testing | |||
Model Documentation | |||
Data Source Connectivity | - | - | - |
Source Code | - | - | - |
About Daniel
Data Scientist & Analytics | Data Cleaning | Web Scraping
Abuja, Nigeria - 1:03 am local time
I’m a passionate data scientist/analyst with expertise in Python and PowerBI, specializing in uncovering insights from complex datasets. From predictive modeling to sentiment analysis, I don't just analyze data—I bring it to life.
If you’re seeking a dynamic force to drive your data science and analytics projects forward, reach out!
Steps for completing your project
After purchasing the project, send requirements so Daniel can start the project.
Delivery time starts when Daniel receives requirements from you.
Daniel works on your project following the steps below.
Revisions may occur after the delivery date.
Data Exploration
Utilise Python for Exploratory Data Analysis (EDA) to understand the dataset.
Pre-processing
Handle outliers using outlier treatment scheme(s), perform feature engineering, normalisation, and dimensionality reduction.