From 7c694554d44b302ec0bac96b954049d0409addda Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=9B=98=E8=8D=A3=E5=8D=9A?= <2858829498@qq.com>
Date: Sat, 20 Jul 2024 14:02:27 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 盘荣博/数据可视化/week1.py | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/盘荣博/数据可视化/week1.py b/盘荣博/数据可视化/week1.py
index 74a1462..6e9c134 100644
--- a/盘荣博/数据可视化/week1.py
+++ b/盘荣博/数据可视化/week1.py
@@ -1,5 +1,7 @@
 import pandas as pd
+import numpy as np
 from  scipy.stats import zscore
+from sklearn.decomposition import PCA
 import matplotlib.pyplot as plt
 from matplotlib.pyplot import ylabel
 df = pd.read_excel("棉花产量论文作业的数据.xlsx")
@@ -38,5 +40,22 @@ plt.scatter(data2[:,:1],data2[:,1:2],c='g')
 plt.xlabel('压缩到0~1')
 print(data==data1)
 
-plt.savefig("shuju.jpg",dpi=2000)
-plt.show()
\ No newline at end of file
+# plt.savefig("shuju.jpg",dpi=2000)
+# plt.show()
+md= PCA().fit(data)
+cf = np.cov(data.T)#求协方差矩阵
+print(cf)
+c, d= np.linalg.eig(cf)
+print("特征值：\n",c)
+print(md.explained_variance_)
+e=c/c.sum()
+# for _ in range(len(e)):
+#     if(_!=0):
+#         e[_]+=e[_-1]
+print('贡献率：')
+print(e)
+print(md.explained_variance_ratio_)
+print('特征向量：')
+print(d.T)
+print(md.components_)
+print(md.components_-d.T<=0.1)
\ No newline at end of file