Machine Learning: تقليل الأبعاد

from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(X_50d)

# PCA: سريع، يحافظ على التباين العام
X_pca = PCA(n_components=2).fit_transform(X_scaled)

# t-SNE: بطيء، يحافظ على البنية المحلية
X_tsne = TSNE(n_components=2, perplexity=30).fit_transform(X_scaled)

import numpy as np

rng = np.random.default_rng(42)

for dim in [2, 10, 50, 100, 500]:
    n = 1000
    X = rng.uniform(0, 1, (n, dim))

    # حساب المسافات الزوجية
    from sklearn.metrics import pairwise_distances
    dists = pairwise_distances(X)

    np.fill_diagonal(dists, np.inf)
    min_dist = dists.min()
    max_dist = dists.max()
    ratio = (max_dist - min_dist) / max_dist

    print(f"Dim={dim:4d}: min={min_dist:.3f}, max={max_dist:.3f}, "
          f"relative_range={ratio:.4f}")

# Runs successfully

from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
import numpy as np

X, y = load_iris(return_X_y=True)

# وحّد أولًا (PCA حساس للمقياس)
X_scaled = StandardScaler().fit_transform(X)

# PCA بجميع المكونات لرؤية التباين المفسّر
pca_full = PCA()
pca_full.fit(X_scaled)

print("Explained variance ratio:")
for i, (evr, cum) in enumerate(zip(pca_full.explained_variance_ratio_,
                                     pca_full.explained_variance_ratio_.cumsum())):
    print(f"  PC{i+1}: {evr:.3f} (cumulative: {cum:.3f})")

# قلل إلى 2D
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)
print(f"\n2D PCA preserves {pca.explained_variance_ratio_.sum():.1%} variance")

# تصور
fig, ax = plt.subplots(figsize=(8, 6))
for target in np.unique(y):
    mask = y == target
    ax.scatter(X_pca[mask, 0], X_pca[mask, 1], label=load_iris().target_names[target], s=40)
ax.set_xlabel(f"PC1 ({pca.explained_variance_ratio_[0]:.1%})")
ax.set_ylabel(f"PC2 ({pca.explained_variance_ratio_[1]:.1%})")
ax.set_title("PCA of Iris Dataset")
ax.legend()
plt.tight_layout()
plt.savefig("pca_iris.png", dpi=150)

Explained variance ratio:

from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
import numpy as np

rng = np.random.default_rng(42)
n, p = 500, 50
X = rng.standard_normal((n, p))
# اجعل أول 5 أبعاد تحمل إشارة أكثر
X[:, :5] *= 3

X_scaled = StandardScaler().fit_transform(X)
pca = PCA().fit(X_scaled)

fig, ax = plt.subplots(figsize=(10, 5))
cumvar = pca.explained_variance_ratio_.cumsum()
ax.plot(range(1, len(cumvar)+1), cumvar, "b-o", markersize=3)
ax.axhline(0.95, color="red", linestyle="--", label="95% variance")
ax.axhline(0.90, color="orange", linestyle="--", label="90% variance")
ax.set_xlabel("Number of Components")
ax.set_ylabel("Cumulative Explained Variance")
ax.set_title("PCA Explained Variance")
ax.legend()
n_95 = (cumvar < 0.95).sum() + 1
print(f"Components for 95% variance: {n_95}")
plt.tight_layout()
plt.savefig("pca_variance.png", dpi=150)

# Runs successfully

from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_digits
import matplotlib.pyplot as plt
import numpy as np

X, y = load_digits(return_X_y=True)
X_scaled = StandardScaler().fit_transform(X)

# t-SNE بقيم حيرة مختلفة
fig, axes = plt.subplots(1, 3, figsize=(18, 5))

for ax, perplexity in zip(axes, [5, 30, 50]):
    tsne = TSNE(n_components=2, perplexity=perplexity, random_state=42, init="pca")
    X_tsne = tsne.fit_transform(X_scaled)

    scatter = ax.scatter(X_tsne[:, 0], X_tsne[:, 1], c=y, cmap="tab10", s=5, alpha=0.7)
    ax.set_title(f"t-SNE (perplexity={perplexity})")
    ax.set_xlabel("t-SNE 1")
    ax.set_ylabel("t-SNE 2")

plt.tight_layout()
plt.savefig("tsne_perplexity.png", dpi=150)

# Runs successfully

from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import numpy as np

rng = np.random.default_rng(42)
X = rng.standard_normal((5000, 50))

# t-SNE مباشر (بطيء)
# tsne = TSNE(n_components=2, random_state=42)
# X_tsne = tsne.fit_transform(X)  # بطيء جدًا على 5000x50!

# أفضل ممارسة: PCA أولًا، ثم t-SNE
X_scaled = StandardScaler().fit_transform(X)
X_pca_30 = PCA(n_components=30).fit_transform(X_scaled)  # PCA سريع إلى 30D
X_tsne = TSNE(n_components=2, perplexity=30, random_state=42,
              init="pca", learning_rate="auto").fit_transform(X_pca_30)

print(f"PCA→t-SNE shape: {X_tsne.shape}")

# Runs successfully

from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import numpy as np

rng = np.random.default_rng(42)
n = 3000

# توليد بيانات سلوك المستخدم 50-بعدًا مع 3 مجموعات طبيعية
group1 = rng.normal(loc=2, scale=1, size=(800, 50))   # مستخدمون عاليو القيمة
group2 = rng.normal(loc=0, scale=1.5, size=(1200, 50)) # مستخدمون عاديون
group3 = rng.normal(loc=-2, scale=0.8, size=(1000, 50)) # مستخدمون خاملون
X = np.vstack([group1, group2, group3])

# أضف أبعاد ضوضاء
X[:, 20:] += rng.normal(0, 3, (n, 30))

# توحيد
X_scaled = StandardScaler().fit_transform(X)

# PCA إلى 2D
X_pca = PCA(n_components=2).fit_transform(X_scaled)

# t-SNE إلى 2D (مع معالجة PCA مسبقة)
X_pca30 = PCA(n_components=30).fit_transform(X_scaled)
X_tsne = TSNE(n_components=2, perplexity=30, random_state=42,
              init="pca", learning_rate="auto").fit_transform(X_pca30)

# تسميات K-Means كمرجع
labels = KMeans(n_clusters=3, random_state=42, n_init=10).fit_predict(X_scaled)

# تصور
fig, axes = plt.subplots(1, 2, figsize=(16, 6))

for ax, X_2d, title in [(axes[0], X_pca, "PCA"), (axes[1], X_tsne, "t-SNE")]:
    scatter = ax.scatter(X_2d[:, 0], X_2d[:, 1], c=labels, cmap="Set1", s=8, alpha=0.6)
    ax.set_title(title)
    ax.set_xlabel(f"{title} 1")
    ax.set_ylabel(f"{title} 2")

plt.tight_layout()
plt.savefig("user_behavior_dim_reduction.png", dpi=150)

# Runs successfully