Pandas 我想加上一句；球体“；到我的数据群集

我想在我的数据集群中添加一种“球体”

我的数据集群是这样的，它没有“球体”

这是我的密码

import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use('ggplot')
import pandas as pd
from sklearn.cluster import KMeans

MY_FILE='total_watt.csv'
date = []
consumption = []

df = pd.read_csv(MY_FILE, parse_dates=[0], index_col=[0])
df = df.resample('1D', how='sum')
df = df.dropna()

date = df.index.tolist()
date = [x.strftime('%Y-%m-%d') for x in date]
from sklearn.preprocessing import LabelEncoder

encoder = LabelEncoder()
date_numeric = encoder.fit_transform(date)
consumption = df[df.columns[0]].values

X = np.array([date_numeric, consumption]).T

kmeans = KMeans(n_clusters=3)
kmeans.fit(X)

centroids = kmeans.cluster_centers_
labels = kmeans.labels_

print(centroids)
print(labels)

fig, ax = plt.subplots(figsize=(10,8))
rect = fig.patch
rect.set_facecolor('#2D2B2B')



colors = ["b.","r.","g."]

for i in range(len(X)):
    print("coordinate:",encoder.inverse_transform(X[i,0].astype(int)), X[i,1], "label:", labels[i])
    ax.plot(X[i][0], X[i][1], colors[labels[i]], markersize = 10)
ax.scatter(centroids[:, 0],centroids[:, 1], marker = "x", s=150, linewidths = 5, zorder = 10)
a = np.arange(0, len(X), 5)
ax.set_xticks(a)
ax.set_xticklabels(encoder.inverse_transform(a.astype(int)))
ax.tick_params(axis='x', colors='lightseagreen')
ax.tick_params(axis='y', colors='lightseagreen')
plt.scatter(centroids[:, 0],centroids[:, 1], marker = "x", s=100, c="black", linewidths = 5, zorder = 10)
ax.set_title('Energy consumptions Clusters (high/medium/low)', color='gold')
ax.set_xlabel('time', color='gold')
ax.set_ylabel('date(year 2011)', color='gold')


plt.show()

“球体”是周围绘制（簇）的区域，如图所示

我试着用谷歌搜索它

---

但是当我键入“matplotlib spheres”时，我无法得到任何结果。

您帖子中的示例图看起来像是由

广义高斯混合

生成的，其中每个球体都是高斯二维密度

我将很快编写一个示例代码，演示如何在数据集上使用

GMM

，并进行这种绘图

import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use('ggplot')
import pandas as pd
# code changes here
# ===========================================
from sklearn.mixture import GMM
# ===========================================
from sklearn.preprocessing import LabelEncoder

# replace it with you file path
MY_FILE='/home/Jian/Downloads/total_watt.csv'

df = pd.read_csv(MY_FILE, parse_dates=[0], index_col=[0])
df = df.resample('1D', how='sum')
df = df.dropna()

date = df.index.tolist()
date = [x.strftime('%Y-%m-%d') for x in date]

encoder = LabelEncoder()
date_numeric = encoder.fit_transform(date)
consumption = df[df.columns[0]].values

X = np.array([date_numeric, consumption]).T


# code changes here
# ===========================================
gmm = GMM(n_components=3, random_state=0)
gmm.fit(X)
y_pred = gmm.predict(X)

# the center is given by mean
gmm.means_

# ===========================================

import matplotlib as mpl
fig, ax = plt.subplots(figsize=(10,8))

for i, color in enumerate('rgb'):
    # sphere background
    width, height = 2 * 1.96 * np.sqrt(np.diagonal(gmm._get_covars()[i]))
    ell = mpl.patches.Ellipse(gmm.means_[i], width, height, color=color)
    ell.set_alpha(0.1)
    ax.add_artist(ell)
    # data points
    X_data = X[y_pred == i]
    ax.scatter(X_data[:,0], X_data[:,1], color=color)
    # center
    ax.scatter(gmm.means_[i][0], gmm.means_[i][1], marker='x', s=100, c=color)


ax.set_title('Energy consumptions Clusters (high/medium/low)', color='gold')
ax.set_xlabel('time', color='gold')
ax.set_ylabel('date(year 2011)', color='gold')
a = np.arange(0, len(X), 5)
ax.set_xticks(a)
ax.set_xticklabels(encoder.inverse_transform(a.astype(int)))
ax.tick_params(axis='x', colors='lightseagreen')
ax.tick_params(axis='y', colors='lightseagreen')

---

@SuzukiSoma刚刚更新了我的帖子。请看一看。：-@SuzukiSoma非常欢迎你。很高兴它帮了你。如果你想花点时间学习

sci工具包

，你可以从它的在线用户指南开始，那里有很多有用的概念和示例代码。顺便问一下，为什么你要设置2*1.96？？？@SuzukiSoma都很好。下面我们的目标是设置一个双边置信区间。1.96是高斯分布的2个标准偏差。再乘以2，它就是双边的。你也可以用

Kmeans

，计算每个簇中的点与其质心之间的

x

和

y

方向的标准偏差，然后绘制对应的椭圆。