python利用K-Means算法实现对数据的聚类案例详解

import matplotlib.pyplot as plt  # 用于可视化
from sklearn.cluster import KMeans  # 用于聚类
import pandas as pd # 用于读取文件

# 读取本地数据文件
df = pd.read_excel("../data/output3.xls", header=0)

plt.scatter(df["光照"], df["CO2"], linewidths=1, alpha=0.8)
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签v
plt.xlabel("光照")
plt.ylabel("CO2")
plt.grid(color="#95a5a6", linestyle="--", linewidth=1, alpha=0.4)
plt.show()

data = df[["光照","CO2"]] # 从原始数据中选择该两项
estimator = KMeans(n_clusters=2)  # 构造聚类器
estimator.fit(data)  # 将数据带入聚类模型

label_pred = estimator.labels_  # 获取聚类标签
centers_ = estimator.cluster_centers_ # 获取聚类中心

x0 = data[label_pred == 0]
x1 = data[label_pred == 1]

plt.scatter(x0["光照"], x0["CO2"],c="red", linewidths=1, alpha=0.8,marker='o', label='label0')
plt.scatter(x1["光照"], x1["CO2"],c="green", linewidths=1, alpha=0.8,marker='+', label='label1')
plt.grid(c="#95a5a6", linestyle="--", linewidth=1, alpha=0.4)
plt.legend()
plt.show()

import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import pandas as pd


df = pd.read_excel("../data/output3.xls", header=0)
plt.scatter(df["光照"], df["CO2"], linewidths=1, alpha=0.8)
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签v
plt.xlabel("光照")
plt.ylabel("CO2")
plt.grid(color="#95a5a6", linestyle="--", linewidth=1, alpha=0.4)
plt.show()

data = df[["光照","CO2"]]
estimator = KMeans(n_clusters=2)  # 构造聚类器
estimator.fit(data)  # 聚类
label_pred = estimator.labels_  # 获取聚类标签
centers_ = estimator.cluster_centers_  # 获取聚类结果
# print("聚类标签",label_pred)
# print("聚类结果",centers_)
# predict = estimator.predict([[787.75862069, 1505]]) # 测试新数据聚类结果
# print(predict)
x0 = data[label_pred == 0]
x1 = data[label_pred == 1]

plt.scatter(x0["光照"], x0["CO2"],c="red", linewidths=1, alpha=0.8,marker='o', label='label0')
plt.scatter(x1["光照"], x1["CO2"],c="green", linewidths=1, alpha=0.8,marker='+', label='label1')
plt.grid(c="#95a5a6", linestyle="--", linewidth=1, alpha=0.4)
plt.legend()
plt.show()