19 데이터 시각화

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns

pd.set_option('display.precision', 6)

penguins = sns.load_dataset('penguins')
penguins.head()

penguins.info()

penguins = penguins.dropna()
penguins.info()

plt.rc('figure', figsize=(6.4, 4.8))
plt.rc('font',   size=10)
plt.rc('axes',   labelsize=10, titlesize=12)
plt.rc('legend', fontsize=10)
plt.rc('xtick',  labelsize=10)
plt.rc('ytick',  labelsize=10)

plt.hist(penguins['bill_length_mm'], bins=20, edgecolor='black')

plt.xlabel('Bill Length (mm)')
plt.ylabel('Frequency')
plt.title('Bill Length (plt.hist)')
plt.show()

bl_min = penguins['bill_length_mm'].min()
bl_max = penguins['bill_length_mm'].max()
bins = np.arange(bl_min-2, bl_max + 2, 3) # 구간 크기: 3mm

plt.hist(penguins['bill_length_mm'], bins=bins, edgecolor='black')

plt.xlabel('Bill Length (mm)')
plt.ylabel('Frequency')
plt.title('Bill Length (plt.hist)')
plt.show()

penguins['bill_length_mm'].hist(bins=20, edgecolor='black', grid=False)

plt.xlabel('Bill Length (mm)')
plt.ylabel('Frequency')
plt.title('Bill Length (Series.hist)')
plt.show()

sns.histplot(data=penguins, x='bill_length_mm', bins=20, alpha=0.6)

plt.title('Bill Length Distribution')
plt.show()

sns.histplot(data=penguins, x='bill_length_mm', hue='species', bins=20, alpha=0.6)

plt.title('Bill Length Distribution by Species')
plt.show()

penguins.boxplot(
    column=['body_mass_g'],
    grid=False,
    flierprops=dict(marker='o', markerfacecolor='red', markersize=5)
)
plt.show()

penguins.boxplot(
    column=['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g'],
    by='species',
    layout=(2, 2),
    figsize=(8, 6),
    grid=False,
    sharey=False,
    flierprops=dict(marker='o', markerfacecolor='red', markersize=4)
)

plt.suptitle('')   # 전체 제목 제거
plt.tight_layout() # 레이아웃 조정
plt.show()

plt.scatter(penguins['bill_length_mm'], penguins['bill_depth_mm'])

plt.xlabel('Bill Length (mm)')
plt.ylabel('Bill Depth (mm)')
plt.show()

penguins.plot.scatter(x='flipper_length_mm', y='body_mass_g')

plt.show()

sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g', alpha=0.7)

plt.title('Flipper Length vs Body Mass')
plt.xlabel('Flipper Length (mm)')
plt.ylabel('Body Mass (g)')
plt.show()

sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g',
                hue='species', alpha=0.7)

plt.title('Flipper Length vs Body Mass by Species')
plt.xlabel('Flipper Length (mm)')
plt.ylabel('Body Mass (g)')
plt.show()

sns.regplot(data=penguins,
            x='flipper_length_mm',
            y='body_mass_g',
            scatter_kws={'alpha': 0.5})

plt.title('Flipper Length vs Body Mass')
plt.xlabel('Flipper Length (mm)')
plt.ylabel('Body Mass (g)')
plt.show()

sns.regplot(data=penguins,
            x='flipper_length_mm',
            y='body_mass_g',
            scatter_kws={'alpha': 0.5},
            ci=None)  # 신뢰 구간 제거

plt.title('Flipper Length vs Body Mass')
plt.xlabel('Flipper Length (mm)')
plt.ylabel('Body Mass (g)')
plt.show()

sns.lmplot(data=penguins,
           x='bill_length_mm',
           y='bill_depth_mm',
           hue='species',
           height=5,
           aspect=1.5,
           scatter_kws={'alpha': 0.5})

plt.title('Bill Length vs Bill Depth by Species')
plt.xlabel('Bill Length (mm)')
plt.ylabel('Bill Depth (mm)')
plt.show()

from pandas.plotting import scatter_matrix
scatter_matrix(penguins, figsize=(12, 8))

plt.tight_layout()
plt.show()

corr_matrix = penguins.corr(numeric_only=True)

sns.heatmap(corr_matrix,
            annot=True,        # 각 셀에 상관계수 값 표시
            cmap='coolwarm',   # 색상 맵
            fmt='.2f',         # 소수점 둘째 자리까지
            vmin=-1, vmax=1,   # 상관계수 범위 설정
            )  

plt.title('Penguins Correlation Matrix Heatmap')
plt.show()

corr_matrix = penguins.corr(numeric_only=True)
mask = np.triu(np.ones_like(corr_matrix, dtype=bool)) # 상삼각 행렬 마스크 생성

sns.heatmap(corr_matrix,
            annot=True,
            cmap='coolwarm',
            fmt='.2f',
            vmin=-1,
            vmax=1,
            mask=mask)        # 상삼각 행렬만 표시

plt.title('Penguins Correlation Matrix Heatmap')
plt.show()

plt.scatter(penguins['flipper_length_mm'], penguins['body_mass_g'])

plt.xlabel('Flipper Length (mm)')
plt.ylabel('Body Mass (g)')
plt.show()

fig = plt.figure()
ax = fig.add_subplot(1, 1, 1) # 1행 1열의 첫 번째 서브플롯(Axes 객체) 생성

# Axes 객체는 자신 서브플롯에 직접 그래프를 그리는 메서드를 제공
ax.scatter(penguins['flipper_length_mm'], penguins['body_mass_g'])

ax.set_xlabel('Flipper Length (mm)')
ax.set_ylabel('Body Mass (g)')

plt.show()

fig = plt.figure(figsize=(14, 6))

# 왼쪽 도화지
ax1 = fig.add_subplot(1, 2, 1)
# 오른쪽 도화지
ax2 = fig.add_subplot(1, 2, 2)

# 왼쪽: 날개 길이 vs 몸무게
ax1.scatter(penguins['flipper_length_mm'], penguins['body_mass_g'], alpha=0.6)
ax1.set_xlabel('Flipper Length (mm)')
ax1.set_ylabel('Body Mass (g)')
ax1.set_title('Flipper Length vs Body Mass')

# 오른쪽: 부리 길이 vs 몸무게
ax2.scatter(penguins['bill_length_mm'], penguins['body_mass_g'], alpha=0.6, color='orange')
ax2.set_xlabel('Bill Length (mm)')
ax2.set_ylabel('Body Mass (g)')
ax2.set_title('Bill Length vs Body Mass')

plt.suptitle('Penguins Scatter Plots') # 전체 제목
plt.tight_layout() # 레이아웃 조정
plt.show()

fig = plt.figure(figsize=(6, 9))

# 위쪽 도화지
ax1 = fig.add_subplot(2, 1, 1)
# 아래쪽 도화지
ax2 = fig.add_subplot(2, 1, 2)

ax1.hist(penguins['bill_length_mm'], bins=20, edgecolor='black')
ax1.set_xlabel('Bill Length (mm)')
ax1.set_ylabel('Frequency')
ax1.set_title('Bill Length Distribution')

ax2.hist(penguins['bill_depth_mm'], bins=20, edgecolor='black', color='orange')
ax2.set_xlabel('Bill Depth (mm)')
ax2.set_ylabel('Frequency')
ax2.set_title('Bill Depth Distribution')

plt.suptitle('Penguins Histograms')
plt.tight_layout()
plt.show()

fig = plt.figure(figsize=(12, 10))

features = ['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g']
titles = ['Bill Length (mm)', 'Bill Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)']

for i, (feat, title) in enumerate(zip(features, titles), start=1):
    ax = fig.add_subplot(2, 2, i)
    ax.hist(penguins[feat], bins=20, edgecolor='black')
    ax.set_xlabel(title)
    ax.set_ylabel('Frequency')
    ax.set_title(title)

plt.suptitle('Penguins Histograms')
plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(12, 10))

pairs = [
    ('flipper_length_mm', 'body_mass_g'),
    ('bill_length_mm', 'bill_depth_mm'),
    ('bill_length_mm', 'body_mass_g'),
    ('bill_depth_mm', 'flipper_length_mm'),
]
colors = {'Adelie': 'tab:blue', 'Chinstrap': 'tab:orange', 'Gentoo': 'tab:green'}

for ax, (x, y) in zip(axes.flat, pairs):
    for sp, group in penguins.groupby('species'):
        ax.scatter(group[x], group[y], alpha=0.6, label=sp, color=colors[sp])
    ax.set_xlabel(x)
    ax.set_ylabel(y)
    ax.legend(fontsize=8)

plt.suptitle('Penguins Scatter Plots')
plt.tight_layout()
plt.show()

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

# 왼쪽: 방식 1
axes[0].scatter(penguins['flipper_length_mm'], penguins['body_mass_g'], alpha=0.6)
axes[0].set_xlabel('Flipper Length (mm)')
axes[0].set_ylabel('Body Mass (g)')
axes[0].set_title('ax.scatter()')

# 가운데: 방식 2
penguins.plot.scatter(x='flipper_length_mm', y='body_mass_g',
                      alpha=0.6, ax=axes[1])
axes[1].set_title('df.plot.scatter()')

# 오른쪽: 방식 3
sns.scatterplot(data=penguins, x='flipper_length_mm', y='body_mass_g',
                hue='species', ax=axes[2])
axes[2].set_title('sns.scatterplot()')

plt.suptitle('Penguins Scatter Plots')
plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(12, 10))

# (0, 0) 방식 1: 어레이로 직접 산점도
axes[0, 0].scatter(penguins['bill_length_mm'].values,
                   penguins['bill_depth_mm'].values, alpha=0.5)
axes[0, 0].set_xlabel('Bill Length (mm)')
axes[0, 0].set_ylabel('Bill Depth (mm)')
axes[0, 0].set_title('ax.scatter()')

# (0, 1) 방식 2: 데이터프레임 메서드 산점도
penguins.plot.scatter(x='flipper_length_mm', y='body_mass_g',
                      alpha=0.5, ax=axes[0, 1])
axes[0, 1].set_title('df.plot.scatter()')

# (1, 0) 방식 3: 종별 히스토그램
sns.histplot(data=penguins, x='bill_length_mm', hue='species',
             bins=20, alpha=0.6, ax=axes[1, 0])
axes[1, 0].set_title('sns.histplot(hue="species")')

# (1, 1) 방식 3: 종별 상자 그림
sns.boxplot(data=penguins, x='species', y='body_mass_g', ax=axes[1, 1])
axes[1, 1].set_title('sns.boxplot()')

plt.suptitle('Penguins Data Visualization Examples')
plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(12, 10))
features = ['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g']

for ax, feat in zip(axes.flat, features):
    sns.histplot(data=penguins, x=feat, hue='species',
                 bins=20, alpha=0.6, ax=ax)
    ax.set_title(feat)

plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# 좌상단: 종별 부리 길이 히스토그램
sns.histplot(data=penguins, x='bill_length_mm', hue='species',
             bins=20, alpha=0.6, ax=axes[0, 0])
axes[0, 0].set_title('Bill Length by Species')

# 우상단: 종별 몸무게 상자 그림
penguins.boxplot(column='body_mass_g', by='species',
                 grid=False, ax=axes[0, 1],
                 flierprops=dict(marker='o', markerfacecolor='red', markersize=4))
axes[0, 1].set_title('Body Mass by Species')
axes[0, 1].set_xlabel('Species')
axes[0, 1].set_ylabel('Body Mass (g)')

# 좌하단: 날개 길이 vs 몸무게 산점도 (종별 색상)
colors = {'Adelie': 'tab:blue', 'Chinstrap': 'tab:orange', 'Gentoo': 'tab:green'}
for sp, group in penguins.groupby('species'):
    axes[1, 0].scatter(group['flipper_length_mm'], group['body_mass_g'],
                       alpha=0.6, label=sp, color=colors[sp])
axes[1, 0].set_xlabel('Flipper Length (mm)')
axes[1, 0].set_ylabel('Body Mass (g)')
axes[1, 0].set_title('Flipper Length vs Body Mass')
axes[1, 0].legend()

# 우하단: 부리 길이 vs 부리 두께 산점도 (종별 색상)
for sp, group in penguins.groupby('species'):
    axes[1, 1].scatter(group['bill_length_mm'], group['bill_depth_mm'],
                       alpha=0.6, label=sp, color=colors[sp])
axes[1, 1].set_xlabel('Bill Length (mm)')
axes[1, 1].set_ylabel('Bill Depth (mm)')
axes[1, 1].set_title('Bill Length vs Bill Depth')
axes[1, 1].legend()

plt.suptitle('')    # boxplot이 자동으로 만든 상위 제목 제거
plt.tight_layout()
plt.show()

tips = sns.load_dataset('tips')
tips.head()

plt.rc('figure', figsize=(8, 6))
plt.rc('font',   size=12)
plt.rc('axes',   labelsize=14, titlesize=14)
plt.rc('legend', fontsize=12)
plt.rc('xtick',  labelsize=12)
plt.rc('ytick',  labelsize=12)

tb = tips['total_bill']
bins = np.arange(tb.min(), tb.max() + 2, 2)

plt.hist(tb, bins=bins, edgecolor='black')

plt.xlabel('Total Bill ($)')
plt.ylabel('Frequency')
plt.title('Total Bill Histogram')
plt.show()

sns.histplot(data=tips, x='total_bill', hue='smoker', bins=20, alpha=0.6)

plt.title('Total Bill Distribution by Smoker')
plt.show()

tips.boxplot(
    column=['tip'],
    by='day',
    grid=False,
    flierprops=dict(marker='o', markerfacecolor='red', markersize=5)
)

plt.suptitle('')
plt.title('Tip by Day')
plt.xlabel('Day')
plt.ylabel('Tip ($)')
plt.show()

plt.figure(figsize=(6, 4))
sns.regplot(data=tips, x='total_bill', y='tip', scatter_kws={'alpha': 0.5})

plt.title('Total Bill vs Tip')
plt.show()

sns.lmplot(data=tips,
           x='total_bill',
           y='tip',
           hue='smoker',
           height=5,
           aspect=1.5,
           scatter_kws={'alpha': 0.5})

plt.title('Total Bill vs Tip by Smoker')
plt.show()

corr_matrix = tips.corr(numeric_only=True)
mask = np.triu(np.ones_like(corr_matrix, dtype=bool))

plt.figure(figsize=(6, 5))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f',
            vmin=-1, vmax=1, mask=mask)
plt.title('Tips Correlation Heatmap')
plt.show()

fig = plt.figure(figsize=(14, 6))

ax1 = fig.add_subplot(1, 2, 1)
ax1.hist(tips['total_bill'], bins=20, edgecolor='black')
ax1.set_xlabel('Total Bill ($)')
ax1.set_ylabel('Frequency')
ax1.set_title('Total Bill')

ax2 = fig.add_subplot(1, 2, 2)
ax2.hist(tips['tip'], bins=20, edgecolor='black', color='orange')
ax2.set_xlabel('Tip ($)')
ax2.set_ylabel('Frequency')
ax2.set_title('Tip')

plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(14, 12.5))

configs = [
    ('total_bill', 'sex'),
    ('tip',        'sex'),
    ('total_bill', 'smoker'),
    ('tip',        'smoker'),
]

for ax, (feat, hue) in zip(axes.flat, configs):
    sns.histplot(data=tips, x=feat, hue=hue, bins=20, alpha=0.6, ax=ax)
    ax.set_title(f'{feat} by {hue}')

plt.suptitle('Tips Distribution by Group')
plt.tight_layout()
plt.show()