Pair Plots & Scatter Analysis

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_iris

# PAIR PLOT -- classic starting point
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df["species"] = pd.Categorical.from_codes(iris.target, iris.target_names)

# sns.pairplot -- full scatter matrix
pair_plot = sns.pairplot(
    df,
    hue="species",
    diag_kind="kde",           # diagonal: kernel density estimate
    plot_kws={"alpha": 0.6},
    palette="tab10",
)
pair_plot.fig.suptitle("Iris Pair Plot - All Feature Combinations", y=1.02)
plt.savefig("pairplot.png", dpi=80, bbox_inches="tight")
plt.show()

# READING THE PAIR PLOT:
interpretation = {
    "Diagonal (KDE)":    "Distribution of each feature -- look for multi-modal (class separation) or skewness",
    "Off-diagonal":      "Scatter plot of two features -- look for linear patterns and cluster separation",
    "Well-separated clusters": "Features form clear groups by color -> high discriminative power",
    "Overlapping clouds":      "Features do NOT separate classes well -> low predictive value",
}
print("Pair plot interpretation guide:")
for element, meaning in interpretation.items():
    print(f"  {element:30s}: {meaning}")

# FOCUSED SCATTER: best features only
fig, axes = plt.subplots(1, 3, figsize=(15, 5))
best_pairs = [
    ("petal length (cm)", "petal width (cm)"),
    ("sepal length (cm)", "petal length (cm)"),
    ("sepal width (cm)",  "petal length (cm)"),
]

for ax, (x_col, y_col) in zip(axes, best_pairs):
    for species, color in zip(iris.target_names, ["#2196F3", "#FF5722", "#4CAF50"]):
        subset = df[df["species"] == species]
        ax.scatter(subset[x_col], subset[y_col], label=species, color=color, alpha=0.7, s=40)
    ax.set_xlabel(x_col.split(" (")[0])
    ax.set_ylabel(y_col.split(" (")[0])
    ax.legend(fontsize=8)
    ax.set_title(f"{x_col.split(' (')[0]}\nvs\n{y_col.split(' (')[0]}")

plt.tight_layout()
plt.savefig("scatter_pairs.png", dpi=100, bbox_inches="tight")
plt.show()

# QUANTIFY CLASS SEPARABILITY
print("\nBetween-class distance (Fisher score -- higher = more separable):")
numeric_cols = [c for c in df.columns if c != "species"]
for col in numeric_cols:
    overall_mean = df[col].mean()
    groups = [df[df["species"] == s][col] for s in iris.target_names]
    between = sum(len(g) * (g.mean() - overall_mean)**2 for g in groups) / len(df)
    within  = sum(g.var() for g in groups) / 3
    fisher_score = between / (within + 1e-10)
    print(f"  {col:25s}: {fisher_score:.2f}")