From f2e9fecc8d42913e5a32e06bc3a77f0147736b41 Mon Sep 17 00:00:00 2001 From: Marcellus Date: Mon, 9 Mar 2026 14:46:14 +0100 Subject: feat: BDA 09-03 --- BDA/tp_red_dim.py | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 BDA/tp_red_dim.py (limited to 'BDA/tp_red_dim.py') diff --git a/BDA/tp_red_dim.py b/BDA/tp_red_dim.py new file mode 100644 index 0000000..c23b95d --- /dev/null +++ b/BDA/tp_red_dim.py @@ -0,0 +1,35 @@ +import pandas as pd +from sklearn.preprocessing import StandardScaler +from sklearn.decomposition import PCA +from sklearn.datasets import make_moons +from sklearn.manifold import TSNE +import matplotlib.pyplot as plt + +df = pd.read_csv("decathlon.txt", sep='\t') +clean = df.drop(["Points", "Rank", "Competition"], axis="columns") +mat = clean.to_numpy() +scaler = StandardScaler() +normalized = scaler.fit_transform(mat) +pca = PCA(n_components=2) +pca.fit(normalized) +print(pca.explained_variance_ratio_) + +reduction = pca.transform(normalized) +print(reduction) + +#plt.scatter(x=reduction[:,0], y=reduction[:,1], c=df["Rank"]) +#plt.show() +components = pca.components_ +print(components) +#plt.scatter(x=components[0], y=components[1]) +#plt.show() + +print("===============================================") + +X, y = make_moons(n_samples=200, noise=0.1) +#plt.scatter(X[:,0], X[:,1]) +#plt.show() + +scaled = scaler.fit_transform(X) +X_embedded = TSNE(n_components=1).fit_transform(X) +print(X_embedded) -- cgit v1.2.3