التحليل العددي أحادي المتغير

import pandas as pd
import numpy as np

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

scores = df["math score"]

# Central tendency
print(f"Mean:   {scores.mean():.2f}")
print(f"Median: {scores.median():.2f}")

# Spread
print(f"Std:    {scores.std():.2f}")
print(f"IQR:    {scores.quantile(0.75) - scores.quantile(0.25):.2f}")
print(f"Range:  {scores.max() - scores.min()}")

# Shape
print(f"Skewness:  {scores.skew():.2f}")
print(f"Kurtosis:  {scores.kurtosis():.2f}")

import matplotlib.pyplot as plt
import seaborn as sns

fig, axes = plt.subplots(1, 2, figsize=(12, 5))

# Basic histogram
axes[0].hist(scores, bins=20, edgecolor="black", alpha=0.7)
axes[0].set_title("Math Score Distribution (histogram)")
axes[0].set_xlabel("Math Score")
axes[0].set_ylabel("Frequency")

# Histogram with KDE overlay
sns.histplot(scores, kde=True, bins=20, ax=axes[1], color="steelblue")
axes[1].set_title("Math Score Distribution (histogram + KDE)")

plt.tight_layout()
plt.show()

fig, ax = plt.subplots(figsize=(8, 5))

# Single KDE
sns.kdeplot(scores, fill=True, alpha=0.5, ax=ax)
ax.set_title("Math Score KDE")
ax.set_xlabel("Math Score")
plt.show()

# Compare distributions
fig, ax = plt.subplots(figsize=(8, 5))
for subject in ["math score", "reading score", "writing score"]:
    sns.kdeplot(df[subject], fill=True, alpha=0.3, label=subject, ax=ax)
ax.set_title("Score Distributions by Subject")
ax.legend()
plt.show()

fig, ax = plt.subplots(figsize=(8, 5))

sns.boxplot(x=scores, ax=ax, color="lightblue", flierprops=dict(marker="o", markersize=5))
ax.set_title("Math Score Box Plot")
ax.set_xlabel("Math Score")
plt.show()

fig, ax = plt.subplots(figsize=(8, 5))

sns.violinplot(x=scores, ax=ax, inner="quartile", color="lightgreen")
ax.set_title("Math Score Violin Plot")
ax.set_xlabel("Math Score")
plt.show()

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

for i, subject in enumerate(["math score", "reading score", "writing score"]):
    sns.boxplot(data=df, x="gender", y=subject, ax=axes[i])
    axes[i].set_title(subject.replace(" score", " Scores").title())

plt.tight_layout()
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")

reading = df["reading score"]

# Summary statistics
print("Summary Statistics:")
print(f"  Mean:   {reading.mean():.2f}")
print(f"  Median: {reading.median():.2f}")
print(f"  Std:    {reading.std():.2f}")
print(f"  Skew:   {reading.skew():.2f}")

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

sns.histplot(reading, kde=True, bins=20, ax=axes[0], color="steelblue")
axes[0].set_title("Histogram + KDE")

sns.kdeplot(reading, fill=True, ax=axes[1], color="coral")
axes[1].set_title("KDE Only")

sns.boxplot(x=reading, ax=axes[2], color="lightgreen")
axes[2].set_title("Box Plot")

plt.tight_layout()
plt.show()