TensorFlow基础1（波士顿房价/鸢尾花数据集可视化）

记录TensorFlow听课笔记

---

一，波士顿房价数据集可视化

1.1介绍波士顿房价数据集

1.2波士顿房价数据集加载

import tensorflow as tf
boston_housing=tf.keras.datasets.boston_housing
(train_x,train_y),(_,_)=boston_housing.load_data(test_split=0)    
#表示测试集为零 都用来做训练集 下划线为测试集的名称

1.3将平均房间数与房价之间的关系可视化

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
boston_housing=tf.keras.datasets.boston_housing
(train_x,train_y),(_,_)=boston_housing.load_data(test_split=0)    #表示测试集为零 都用来做训练集 下划线为测试集的名称
plt.figure(figsize=(5,5))                                         #画布尺寸
plt.scatter(train_x[:,5],train_y)                                 #散点图 train_x[:,5]表示房间数据第五个属性 train_y对应的价格
plt.xlabel("RM")                              #设置x轴标签文本
plt.ylabel("price($1000's)")                  #设置y轴标签文本
plt.title("s.RM-Price")                       #设置标题
plt.show()                                    #显示绘图

1.4将所有属性与房价 之间的关系可视化

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
boston_housing=tf.keras.datasets.boston_housing
(train_x,train_y),(_,_)=boston_housing.load_data(test_split=0)    #表示测试集为零 都用来做训练集 下划线为测试集的名称
plt.rcParams["font.sans-serif"]="SimHei"          #黑体
plt.rcParams["axes.unicode_minus"]=False          #正常显示负号
titles=["CRIM","ZN","INDUS","CHAS","NOX","RM","AGE","DIS","RAD","TAX","PTRATIO","B-1000","LSTAT","MEDV"]
plt.figure(figsize=(12,12))                       #画布尺寸12英寸
for i in range(13):
    plt.subplot(4,4,(i+1))                        #划分子图
    plt.scatter(train_x[:,i],train_y)
    plt.xlabel(titles[i])
    plt.ylabel("price($1000's)")
    plt.title(str(i+1)+"."+titles[i]+"- price")
plt.tight_layout(rect=[0,0,1,0.9])
plt.suptitle("各属性与房间关系",x=0.5,y=0.95,fontsize=20)
plt.show()

二，鸢尾花数据集可视化

2.1介绍鸢尾花数据集

2.2鸢尾花数据集可视化

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import pandas as pd 
TRAIN_URL="http://download.tensorflow.org/data/iris_training.csv"
train_path=tf.keras.utils.get_file(TRAIN_URL.split('/')[-1],TRAIN_URL)         #下载数据集
COLUMN_NAMES=['SepalLength','SepalWidth','PetalLength','PetalWidth','Species'] #列标题
df_iris=pd.read_csv(train_path,names=COLUMN_NAMES,header=0)                     #读取
iris=np.array(df_iris)                                                         #将二维数据表转化为二numpy维数组
def fun1():
    fig=plt.figure("Iris Data",figsize=(15,3))                                     #画布尺寸
    fig.suptitle("Anderson's Iris Data Set\n(Bule->Setosa |Red->Versicolor|Green->Virginica)")
    for i in range(4):
        plt.subplot(1,4,i+1)
        if(i==0):
            plt.text(0.3,0.5,COLUMN_NAMES[0],fontsize=15)
        else:
            plt.scatter(iris[:,i],iris[:,0],c=iris[:,4],cmap='brg')
        plt.title(COLUMN_NAMES[i])
        plt.title(COLUMN_NAMES[0])
def fun2():
    for i in range(4):
        for j in range(4):
            plt.subplot(4,4,4*i+(j+1))
            if(i==j):
                plt.text(0.3,0.4,COLUMN_NAMES[i],fontsize=15)
            else:
                plt.scatter(iris[:,j],iris[:,i],c=iris[:,4],cmap='brg')
            if(i==0):
                plt.title(COLUMN_NAMES[j])
            if(j==0):
                plt.title(COLUMN_NAMES[i])   
fun2()
plt.tight_layout(rect=[0,0,1,0.9])
plt.show()