Rohit-Saswadkar/Omdena-Tuberculosis-Analysis-in-Kaduna

# Omdena-Tuberculosis-Analysis-in-Kaduna ## Data Transformation and Model Evaluation ### Data Transformation The dataset underwent several transformations before model evaluation: - **Square Root Transformation**: Applied square root transformation to numerical columns to mitigate skewness. ```python for col in num_cols: df[col] = np.sqrt(df[col]) - 0.01 ``` - **One-Hot Encoding**: Encoded the LGA (Local Government Area) feature to convert categorical data into numerical format. - **Principal Component Analysis (PCA)**: Utilized PCA to reduce dimensionality and extract 30 best components. ### Model Evaluation The performance of a Ridge Regression model was evaluated using the following key metrics: - **Hyperparameter**: Ridge Regression with alpha = 0.1 was chosen. #### RMSE (Root Mean Squared Error) - **Training Set**: 1.45 - **Test Set**: 1.44 #### R-squared (R2) Score - **Training Set**: 0.9447 - **Test Set**: 0.9408 ### Interpretation - The low RMSE values indicate a close alignment between the model's predictions and actual values for both training and test sets. - High R-squared values suggest that a significant portion of the target variable's variance is captured by the model. ### Conclusion The Ridge Regression model, with alpha = 10, demonstrates robust predictive performance on both training and test datasets. Its ability to generalize well is evident from the comparable performance on both sets, minimizing the risk of overfitting. --- # Tuberculosis (TB) Analysis and Recommendations ## Overview This section provides a comprehensive analysis of presumptive TB cases, diagnosed cases, HIV status, and healthcare worker involvement. Key observations and recommendations are outlined based on the analyzed data. ### Presumptive Cases and Examinations - An upward trend in presumptive cases and examinations suggests increased vigilance or targeted testing initiatives. - The surge in 2020 Q3 may be related to a specific public health campaign. …