R, Python 분석과 프로그래밍의 친구 (by R Friend)

# importing libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [10, 8] # setting figure size

# loading 'iris' dataset from seaborn

iris = sns.load_dataset('iris')

iris.shape

(150, 5)

iris.head()

iris.groupby('species').size()

species setosa 50 versicolor 50 virginica 50 dtype: int64

  (1) matplotlib 으로 그룹별 산점도 그리기 (scatter plot by groups via matplotlib)

# Scatter plot with a different color by groups

groups = iris.groupby('species')

fig, ax = plt.subplots()

for name, group in groups:

    ax.plot(group.petal_length, 

            group.petal_width, 

            marker='o', 

            linestyle='',

            label=name)

ax.legend(fontsize=12, loc='upper left') # legend position

plt.title('Scatter Plot of iris by matplotlib', fontsize=20)

plt.xlabel('Petal Length', fontsize=14)

plt.ylabel('Petal Width', fontsize=14)

plt.show()

  (2) seaborn 으로 그룹별 산점도 그리기 (scatter plot by groups via seaborn)

# Scatter plot by Groups

sns.scatterplot(x='petal_length', 

                y='petal_width', 

                hue='species', # different colors by group

                style='species', # different shapes by group

                s=100, # marker size

                data=iris)

plt.show()

# error: AttributeError: module 'seaborn' has no attribute 'scatterplot' 

# solution: upgrade seaborn

pip install --upgrade seaborn

  (3) pandas로 그룹별 산점도 그리기 (scatter plot by groups via pandas)

# adding 'color' column

iris['color'] = np.where(iris.species == 'setosa', 'red', 

                         np.where(iris.species =='versicolor', 

                         'green', 

                         'blue'))

# scatter plot

iris.plot(kind='scatter',

          x='petal_length', 

          y='petal_width', 

          s=50, # marker size

          c=iris['color']) # marker color by group

plt.title('Scatter Plot of iris by pandas', fontsize=20)

plt.xlabel('Petal Length', fontsize=14)

plt.ylabel('Petal Width', fontsize=14)

plt.show()