Pinned Loading

1. This code is a compilation of utilit... This code is a compilation of utilities for machine learning model evaluation, data analysis reporting, and visualization in Python. It includes functions for inspecting pandas DataFrames, generating evaluation reports for classification and regression models in PDF format, and saving/loading models with joblib. Additionally, it offers tools for dataset normalization, performance metrics visualization, and model comparison through plots. The script leverages popular libraries such as pandas, sklearn, matplotlib, seaborn, and FPDF, covering aspects from data preprocessing to post-training model evaluation.

   1

   import pandas as pd

   2

   from fpdf import FPDF

   3

   from sklearn.metrics import (accuracy_score, classification_report, 

   4

                                roc_auc_score, f1_score, confusion_matrix, 

   5

                                precision_recall_curve, auc, roc_curve)

2. ClusteringBankClients ClusteringBankClients Public

   This repository contains a practical exercise focused on clustering techniques, designed to train and enhance skills in data analysis and machine learning.

   Jupyter Notebook

3. DenguePredictionModels DenguePredictionModels Public

   This repository hosts a collection of ML exercises focused on predicting dengue fever outbreaks. It serves as a practical application for practicing and refining skills in predictive modeling and h…

   Jupyter Notebook 1

4. EarthquakeDamageModels EarthquakeDamageModels Public

   Practical exercise using the "Richter's Predictor: Modeling Earthquake Damage" competition on DrivenData

   Jupyter Notebook