数据的标准化

盘荣博/图/例10.py

@@ -25,4 +25,4 @@ nx.draw_networkx_edge_labels(G,pos,edge_labels=w)#绘制标签
 path_edges=list(zip(p,p[1:]))
 print(type(path_edges),"\npath_edges=",path_edges)
 nx.draw_networkx_edges(G,pos,edgelist=path_edges,edge_color="r",width=1)
-plt.savefig("figure10_9.png");plt.show()
+plt.savefig("figure10_9.png",dpi=1000);plt.show()

盘荣博/数据可视化/week1.py

@@ -1,9 +1,42 @@
 import pandas as pd
+from  scipy.stats import zscore
 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")
-plt.plot(df["年份"],df["单产"])
+# plt.plot(df["年份"],df["单产"])
 plt.rcParams['font.sans-serif']="SimHei"
-plt.ylabel('单产')
+# plt.rcParams['size'] =10
-plt.xlabel('年份')
+# plt.ylabel('单产')
+# plt.xlabel('年份')
+
+# print(df)
+d = df.to_numpy()[:,1:]
+print(d)
+plt.subplot(4,1,1)
+plt.scatter(d[:,:1],d[:,1:2],c='r')
+ylabel('原始数据'),plt.title("单产和种子费用的关系")
+#公式调用标准化，遵守标准正态分布
+data = zscore(d)
+print(data)
+plt.subplot(4,1,2)
+plt.scatter(data[:,:1],data[:,1:2],c='b',)
+ylabel('zscore')
+
+print(d.max(axis=0))
+print(d.std(axis=0))
+print(d.mean(axis=0))
+#手写标准正态分布
+data1=(d-d.mean(axis=0))/d.std(axis=0)
+print(data1)
+plt.subplot(4,1,3)
+plt.scatter(data1[:,:1],data1[:,1:2],c='y')
+ylabel('手写标准正态分布')
+
+data2=(d-d.min(axis=0))/(d.max(axis=0)-d.min(axis=0))
+plt.subplot(4,1,4)
+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()
-print(df)