generate_datasets.py

"""Generate CSV datasets from sklearn built-in datasets for ML projects."""
import pandas as pd
from sklearn.datasets import load_breast_cancer, load_iris, load_wine, load_digits, load_diabetes

datasets = {
    "Machine-Learning/Classification/Logistic_Regression/dataset/breast_cancer.csv": load_breast_cancer,
    "Machine-Learning/Classification/Decision_Tree/dataset/iris.csv": load_iris,
    "Machine-Learning/Classification/KNN/dataset/iris.csv": load_iris,
    "Machine-Learning/Classification/Random_Forest/dataset/wine.csv": load_wine,
    "Machine-Learning/Classification/Naive_Bayes/dataset/wine.csv": load_wine,
    "Machine-Learning/Classification/SVM/dataset/digits.csv": load_digits,
    "Machine-Learning/Dimensionality_Reduction/PCA/dataset/wine.csv": load_wine,
    "Machine-Learning/Dimensionality_Reduction/LDA/dataset/iris.csv": load_iris,
    "Machine-Learning/Dimensionality_Reduction/t-SNE/dataset/digits.csv": load_digits,
    "Machine-Learning/Ensemble_Methods/Gradient_Boosting/dataset/diabetes.csv": load_diabetes,
    "Machine-Learning/Ensemble_Methods/AdaBoost/dataset/iris.csv": load_iris,
    "Machine-Learning/Ensemble_Methods/Bagging/dataset/wine.csv": load_wine,
}

for path, loader in datasets.items():
    data = loader()
    df = pd.DataFrame(data.data, columns=data.feature_names)
    df["target"] = data.target
    df.to_csv(path, index=False)
    print(f"Saved {path} ({df.shape[0]} rows, {df.shape[1]} cols)")

# Titanic from seaborn
import seaborn as sns
titanic = sns.load_dataset("titanic")
titanic.to_csv("Data-Preprocessing-and-EDA/Titanic_EDA/dataset/titanic.csv", index=False)
print(f"Saved titanic.csv ({titanic.shape[0]} rows, {titanic.shape[1]} cols)")

print("\nAll datasets generated!")