การแสดงภาพข้อมูลด้วย Matplotlib และ Seaborn

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

# Set seaborn theme for all plots
sns.set_theme(style='whitegrid', palette='muted')

# Load a built-in dataset
df = sns.load_dataset('tips')
print(df.head())

import matplotlib.pyplot as plt
import seaborn as sns

df = sns.load_dataset('tips')

fig, axes = plt.subplots(1, 2, figsize=(12, 4))

# Raw distribution (right-skewed)
axes[0].hist(df['total_bill'], bins=30, edgecolor='white')
axes[0].set_title('Total Bill Distribution (Raw)')

# After log transform
import numpy as np
axes[1].hist(np.log(df['total_bill']), bins=30, edgecolor='white')
axes[1].set_title('Total Bill Distribution (Log Transformed)')

plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

df = sns.load_dataset('tips')

# Scatter plot with hue encoding
sns.scatterplot(
    data=df,
    x='total_bill',
    y='tip',
    hue='time',      # encode meal time as colour
    size='size',     # encode party size as dot size
    alpha=0.7
)
plt.title('Tip vs Total Bill (coloured by Meal Time)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

df = sns.load_dataset('tips')

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

sns.boxplot(data=df, x='day', y='total_bill', ax=axes[0])
axes[0].set_title('Bill by Day of Week')

sns.boxplot(data=df, x='smoker', y='tip', hue='sex', ax=axes[1])
axes[1].set_title('Tip by Smoking Status and Sex')

plt.tight_layout()
plt.show()

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

df = pd.read_csv('titanic.csv')

# Compute correlation matrix
corr = df[['Survived', 'Pclass', 'Age', 'SibSp', 'Parch', 'Fare']].corr()

# Plot heatmap
plt.figure(figsize=(8, 6))
sns.heatmap(
    corr,
    annot=True,     # show correlation values
    fmt='.2f',      # 2 decimal places
    cmap='RdYlGn',  # red-yellow-green colour scale
    vmin=-1, vmax=1
)
plt.title('Feature Correlation Matrix')
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

# Use the iris dataset (classic ML benchmark)
df = sns.load_dataset('iris')

# Pair plot coloured by species
sns.pairplot(
    df,
    hue='species',
    diag_kind='kde',    # KDE on diagonal
    plot_kws={'alpha': 0.6}
)
plt.suptitle('Iris Dataset Pair Plot', y=1.02)
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

df = sns.load_dataset('titanic')

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

# Class distribution (check balance)
sns.countplot(data=df, x='survived', ax=axes[0])
axes[0].set_title('Survival Count')

# Class by passenger class and sex
sns.countplot(data=df, x='class', hue='sex', ax=axes[1])
axes[1].set_title('Class Distribution by Sex')

plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import learning_curve
from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_breast_cancer

X, y = load_breast_cancer(return_X_y=True)
train_sizes, train_scores, val_scores = learning_curve(
    DecisionTreeClassifier(max_depth=5), X, y, cv=5
)

plt.plot(train_sizes, train_scores.mean(axis=1), label='Training Score')
plt.plot(train_sizes, val_scores.mean(axis=1), label='Validation Score')
plt.xlabel('Training Set Size')
plt.ylabel('Accuracy')
plt.legend()
plt.title('Learning Curve')
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

model = DecisionTreeClassifier(max_depth=3)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.title('Confusion Matrix')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

# Create figure and axes explicitly
fig, ax = plt.subplots(figsize=(8, 5))

x = np.linspace(0, 10, 100)
ax.plot(x, np.sin(x), label='sin(x)', linewidth=2)
ax.plot(x, np.cos(x), label='cos(x)', linewidth=2, linestyle='--')

# Customise
ax.set_xlabel('x', fontsize=13)
ax.set_ylabel('y', fontsize=13)
ax.set_title('Sine and Cosine', fontsize=15, fontweight='bold')
ax.legend(fontsize=12)
ax.grid(True, alpha=0.3)

# Save
fig.savefig('plot.png', dpi=150, bbox_inches='tight')
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

df = sns.load_dataset('tips')

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

# Violin plot
sns.violinplot(data=df, x='day', y='total_bill', hue='sex',
               split=True, inner='quart', ax=axes[0])
axes[0].set_title('Bill Distribution by Day (Violin)')

# KDE distribution comparison
sns.kdeplot(data=df, x='tip', hue='time', fill=True, alpha=0.4, ax=axes[1])
axes[1].set_title('Tip Distribution by Meal Time (KDE)')

plt.tight_layout()
plt.show()