التحليل الثنائي العددي

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# students-performance.csv ships with the course — load it from the browser file system.
df = pd.read_csv("students-performance.csv")

fig, ax = plt.subplots(figsize=(8, 6))
ax.scatter(df["math score"], df["reading score"], alpha=0.5, edgecolors="black", linewidth=0.5)
ax.set_title("Math vs Reading Scores")
ax.set_xlabel("Math Score")
ax.set_ylabel("Reading Score")
plt.show()

fig, axes = plt.subplots(1, 3, figsize=(15, 5))

pairs = [
    ("math score", "reading score"),
    ("math score", "writing score"),
    ("reading score", "writing score"),
]

for i, (x, y) in enumerate(pairs):
    sns.regplot(data=df, x=x, y=y, ax=axes[i], scatter_kws={"alpha": 0.4})
    axes[i].set_title(f"{x.split()[0].title()} vs {y.split()[0].title()}")

plt.tight_layout()
plt.show()

sns.jointplot(
    data=df,
    x="math score",
    y="reading score",
    kind="scatter",      # or "reg", "kde", "hist"
    height=7,
    alpha=0.4
)
plt.suptitle("Math vs Reading (Joint Plot)", y=1.02)
plt.show()

fig, ax = plt.subplots(figsize=(8, 6))
hb = ax.hexbin(df["math score"], df["reading score"], gridsize=20, cmap="YlOrRd")
ax.set_title("Math vs Reading (Hexbin Density)")
ax.set_xlabel("Math Score")
ax.set_ylabel("Reading Score")
plt.colorbar(hb, label="Count")
plt.show()

fig, axes = plt.subplots(1, 3, figsize=(15, 5))

# Grouped box plots
sns.boxplot(data=df, x="gender", y="math score", ax=axes[0], palette="Set2")
axes[0].set_title("Math Scores by Gender")

# Grouped violin plots
sns.violinplot(data=df, x="lunch", y="reading score", ax=axes[1], palette="Set3")
axes[1].set_title("Reading Scores by Lunch Type")

# Grouped with multiple categories
sns.boxplot(
    data=df,
    x="test preparation course",
    y="writing score",
    hue="gender",
    ax=axes[2],
    palette="Set1"
)
axes[2].set_title("Writing Scores by Test Prep & Gender")

plt.tight_layout()
plt.show()

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Strip plot (jittered points)
sns.stripplot(data=df, x="gender", y="math score", ax=axes[0],
              alpha=0.3, jitter=True, palette="Set2")
axes[0].set_title("Math Scores — Strip Plot")

# Swarm plot (non-overlapping points — slower for large datasets)
sns.swarmplot(data=df, x="gender", y="math score", ax=axes[1],
              size=3, palette="Set2")
axes[1].set_title("Math Scores — Swarm Plot")

plt.tight_layout()
plt.show()

# Highlighting clusters with hue
fig, ax = plt.subplots(figsize=(8, 6))
sns.scatterplot(
    data=df,
    x="math score",
    y="reading score",
    hue="gender",
    style="test preparation course",
    alpha=0.6,
    ax=ax
)
ax.set_title("Math vs Reading: Gender and Test Prep")
plt.show()

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# students-performance.csv ships with the course — load it from the browser file system.
df = pd.read_csv("students-performance.csv")

# Scatter with regression
fig, axes = plt.subplots(1, 2, figsize=(14, 6))

sns.regplot(data=df, x="math score", y="reading score", ax=axes[0],
            scatter_kws={"alpha": 0.3}, line_kws={"color": "red"})
axes[0].set_title("Math vs Reading (Regression)")

sns.jointplot(data=df, x="math score", y="reading score",
              kind="kde", height=7)
plt.suptitle("Math vs Reading (Density)", y=1.02)
plt.show()

# Grouped comparison
fig, axes = plt.subplots(1, 2, figsize=(12, 5))
sns.boxplot(data=df, x="gender", y="math score", ax=axes[0], palette="Set2")
axes[0].set_title("Math by Gender")
sns.violinplot(data=df, x="lunch", y="math score", ax=axes[1], palette="Set3")
axes[1].set_title("Math by Lunch Type")
plt.tight_layout()
plt.show()