Contents

1 scatter plot: matplotlib

2 scatter plot: seaborn

3 R의 pairs와 유사한 그림

#two_moon 데이터 셋
from sklearn.datasets import make_moons
import pandas as pd
X, y = make_moons(n_samples=200, noise=0.05, random_state=0)

df = pd.DataFrame(X, columns=["x", "y"])
df["group"] = y
df[:5]

import matplotlib.pyplot as plt
plt.scatter(x=df.x, y=df.y, c=df.group)

#<scatter plot>: 여기부터
import matplotlib.pyplot as plt
plt.scatter(x=df.x, y=df.y, c=df.group)

fig, ax = plt.subplots()
colors = {1:'red', 0:'blue'}

grouped = df.groupby('group')
for key, group in grouped:
    group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
plt.show()
#</scatter plot>: 여기까지 한번에 실행

#iris 데이터세트 만들기
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
iris = load_iris()
iris.data
iris.feature_names
iris.target
iris.target_names


iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
iris_df["target"] = iris.target 
iris_df["target_names"] = iris.target_names[iris.target]

#scatter plot
import seaborn as sns
sns.pairplot(x_vars=["sepal length (cm)"], y_vars=["petal length (cm)"], data=iris_df, hue="target_names", size=5)

#iris 데이터세트 만들기
import pandas as pd
from sklearn.datasets import load_iris

iris = load_iris()
iris.data
iris.feature_names
iris.target
iris.target_names


iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
iris_df["target"] = iris.target 
iris_df["target_names"] = iris.target_names[iris.target]

#scatter plot
import mglearn
pd.tools.plotting.scatter_matrix(iris_df, c=iris_df.target, 
                                 figsize=(15,15), marker="o", 
                                 hist_kwds={"bins":20},s=60, alpha=0.8, cmap=mglearn.cm3)

#s: marker 크기
#cmap: color map