Appendix. Scatterplot

1. Scatterplot

1.1 seaborn.scatterplot

seaborn.scatterplot(data=None, x=None, y=None, hue=None, size=None, sizes=None, legend='auto')

• data: 적용할 데이터
• x, y: x, y축 값
• hue: 색상 나눌 값
• size: 사이즈 정할 값
• sizes: 사이즈의 범주
• legend: 범례 확인 표 유무

1.2 plotly.express.scatter

plotly.express.scatter(data_frame=None, x=None, y=None, color=None, size=None)

• data_frame: 적용할 데이터프레임
• x, y: x, y축 값
• color: 색상 나눌 값
• size: 사이즈 정할 값

2. scatterplot 예시

예시 1: 펭귄 데이터

df = sns.load_dataset('penguins')
df

numerical_columns = df.columns[2:6]
numerical_columns

# 결과값:
# Index(['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g'], dtype='object')

sns.scatterplot(data=df, x=numerical_columns[0], y=numerical_columns[1], hue='species', size=numerical_columns[3], sizes=(10, 200))
plt.show()

sns.scatterplot(data=df, x=numerical_columns[0], y=numerical_columns[1], hue='sex', size=numerical_columns[3], sizes=(10, 200))
plt.show()

import plotly.express as px

fig = px.scatter(df.dropna(), x=numerical_columns[0], y=numerical_columns[1], color='species', size=numerical_columns[3])
fig.update_layout(width=1000, height=600)
fig.show()

fig = px.scatter(df.dropna(), x=numerical_columns[0], y=numerical_columns[1], color='species', size=numerical_columns[3])
fig.update_layout(width=1000, height=600)
fig.show()

예시 2: iris 데이터

df = sns.load_dataset('iris')
df

numerical_columns = df.columns[:4]
numerical_columns

# 결과값:
# Index(['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], dtype='object')

sns.scatterplot(data=df, x=numerical_columns[0], y=numerical_columns[1], hue='species', size=numerical_columns[3], sizes=(10, 200))
plt.show()

fig = px.scatter(df, x=numerical_columns[0], y=numerical_columns[1], color='species', size=numerical_columns[3])
fig.update_layout(width=1000, height=600)
fig.show()

예시 3: 시계열 데이터 - 비행기 탑승자 데이터

df = sns.load_dataset('flights')
df

def monthToNum(month):
    month_dict = {
        'Jan': 1,
        'Feb': 2,
        'Mar': 3,
        'Apr': 4,
        'May': 5,
        'Jun': 6,
        'Jul': 7,
        'Aug': 8,
        'Sep': 9,
        'Oct': 10,
        'Nov': 11,
        'Dec': 12
    }
    return month_dict.get(month)

df['month'] = df['month'].apply(monthToNum)
df

sns.scatterplot(data=df, x='year', y='month', hue='passengers', size='passengers', sizes=(10, 200), legend=False, palette='RdYlBu_r')
plt.show()

fig = px.scatter(df, x='year', y='month', color='passengers', size='passengers')
fig.update_layout(width=1000, height=600)
fig.show()