상관 행렬 히트맵

상관행렬이란 무엇인가요

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

# Compute correlation matrix for numeric columns
tips = sns.load_dataset('tips')
corr = tips[['total_bill', 'tip', 'size']].corr()
print(corr.round(2))

상관행렬 계산하기

import pandas as pd
import seaborn as sns

tips = sns.load_dataset('tips')
numeric = tips.select_dtypes(include='number')

# Pearson vs Spearman
pearson = numeric.corr(method='pearson')
spearman = numeric.corr(method='spearman')

print('Pearson:')
print(pearson.round(2))
print('\nSpearman:')
print(spearman.round(2))

sns.heatmap을 사용한 기본 히트맵

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset('tips')
corr = tips.select_dtypes('number').corr()

sns.heatmap(corr, annot=True, fmt='.2f')
plt.title('Correlation Heatmap — Tips Dataset')
plt.tight_layout()
plt.show()

알맞은 색상표 선택하기

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset('tips')
corr = tips.select_dtypes('number').corr()

sns.heatmap(
    corr,
    annot=True,
    fmt='.2f',
    cmap='coolwarm',
    vmin=-1,
    vmax=1,
    center=0
)
plt.title('Correlation Heatmap with Diverging Palette')
plt.tight_layout()
plt.show()

상삼각 영역 마스킹하기

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

tips = sns.load_dataset('tips')
corr = tips.select_dtypes('number').corr()

# Mask the upper triangle (including diagonal)
mask = np.triu(np.ones_like(corr, dtype=bool))

sns.heatmap(
    corr,
    mask=mask,
    annot=True,
    fmt='.2f',
    cmap='coolwarm',
    vmin=-1,
    vmax=1
)
plt.title('Lower-Triangle Correlation Heatmap')
plt.tight_layout()
plt.show()

주석과 셀 크기 사용자 지정하기

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

# Load a wider dataset for a more interesting heatmap
penguins = sns.load_dataset('penguins').select_dtypes('number')
corr = penguins.corr()
mask = np.triu(np.ones_like(corr, dtype=bool))

sns.heatmap(
    corr,
    mask=mask,
    annot=True,
    fmt='.2f',
    cmap='vlag',
    vmin=-1,
    vmax=1,
    linewidths=0.5,
    square=True,
    annot_kws={'size': 10}
)
plt.title('Penguins Correlation Matrix')
plt.tight_layout()
plt.show()

clustermap을 사용한 군집화

import seaborn as sns
import matplotlib.pyplot as plt

penguins = sns.load_dataset('penguins').select_dtypes('number').dropna()
corr = penguins.corr()

sns.clustermap(
    corr,
    cmap='coolwarm',
    vmin=-1,
    vmax=1,
    annot=True,
    fmt='.2f',
    figsize=(6, 6)
)
plt.suptitle('Clustered Correlation Matrix', y=1.02)
plt.show()

피벗 테이블 데이터용 히트맵

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

tips = sns.load_dataset('tips')

# Pivot: average bill by day and time
pivot = tips.pivot_table(
    values='total_bill',
    index='day',
    columns='time',
    aggfunc='mean'
)

sns.heatmap(pivot, annot=True, fmt='.1f', cmap='YlOrRd')
plt.title('Average Bill by Day and Time')
plt.tight_layout()
plt.show()

상관관계 값 해석하기

import pandas as pd
import seaborn as sns

# Find the most correlated pairs
penguins = sns.load_dataset('penguins').select_dtypes('number').dropna()
corr = penguins.corr()

# Unstack to get pairs, remove self-correlations, sort
pairs = (corr
    .unstack()
    .reset_index()
    .rename(columns={'level_0': 'var1', 'level_1': 'var2', 0: 'r'})
    .query('var1 != var2')
    .assign(abs_r=lambda df: df['r'].abs())
    .sort_values('abs_r', ascending=False)
    .drop_duplicates(subset='abs_r')
)
print(pairs.head(6).to_string(index=False))

대규모 데이터셋 히트맵: 부분집합 사용하기

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

# Show only features with |r| > 0.4 with any other feature
penguins = sns.load_dataset('penguins').select_dtypes('number').dropna()
corr = penguins.corr()

# Filter columns that have at least one high correlation (excluding diagonal)
high_corr = (corr.abs() > 0.4).any(axis=1)
filtered = corr.loc[high_corr, high_corr]
mask = np.triu(np.ones_like(filtered, dtype=bool))

sns.heatmap(filtered, mask=mask, annot=True,
            fmt='.2f', cmap='coolwarm', vmin=-1, vmax=1)
plt.title('High-Correlation Subset')
plt.tight_layout()
plt.show()

히트맵을 파일로 저장하기

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

tips = sns.load_dataset('tips')
corr = tips.select_dtypes('number').corr()
mask = np.triu(np.ones_like(corr, dtype=bool))

fig, ax = plt.subplots(figsize=(6, 5))
sns.heatmap(corr, mask=mask, annot=True, fmt='.2f',
            cmap='coolwarm', vmin=-1, vmax=1,
            linewidths=0.5, ax=ax)
ax.set_title('Correlation Heatmap')

# Save to file
plt.savefig('/tmp/correlation_heatmap.png', dpi=150, bbox_inches='tight')
plt.close()
print('Saved to /tmp/correlation_heatmap.png')

빠른 확인

단원 요약