机器学习|河南郑州二手房房价预测机器学习|数据可视化

河南郑州二手房房价预测

数据集
- 数据标准化
- 分割数据集和训练集
- 数据归一化
预测模型
- 数据未归一化前的随机森林预测
- 数据归一化过后的随机森林预测
- SVM径向基核函数预测
- KNN最邻近算法预测
- 决策树回归预测
- 梯度提升决策分类预测
- SVM线性核函数预测
- 使用不同的train_size去训练模型
模型评估
河南郑州二手房房价分析

数据集 【机器学习|河南郑州二手房房价预测】

文章图片

data_all.info()

文章图片

data_all.head()

文章图片

数据标准化特征的归一化

data_all['unit_price'].astype(float)train_data = https://www.it610.com/article/data_all[data_all.columns.delete([0,1,2])] data_temp = data_all[data_all.columns.delete([0,1])] # train_datatitle_list = ['house_region','house_address','house_structure','house_elevator_sytle', 'house_heating_type','elevator','house_transaction_type','house_useage', 'house_years','house_floor_position','house_building_structure','house_orientation', 'house_building_type','house_layout','house_area','house_decoration','house_last_time' ] for item in title_list: pclassDf = pd.DataFrame() #使用get_dummies进行one-hot编码，列名前缀是Pclass pclassDf = pd.get_dummies( data_all[item] , prefix=item ).astype("int") train_data = https://www.it610.com/article/pd.concat([train_data,pclassDf],axis=1) train_data.drop(columns=[item],inplace=True)data_temp = pd.concat([data_temp,pclassDf],axis=1) data_temp.drop(columns=[item],inplace=True)# print(data_all) # print(train_data) # print(train_data.head()) print(data_temp.head())# from sklearn.decomposition import PCA# 主成分分析法，非监督的机器学习方法# model = PCA(n_components=1, random_state=25)# n_components PCA算法中所要保留的主成分个数n，也即保留下来的特征个数n # # 多变量之间可能存在相关性，从而增加了问题分析的复杂性。 # # 在减少需要分析的指标同时，尽量减少原指标包含信息的损失，以达到对所收集数据进行全面分析的目的。 # house_train = model.fit_transform(house_train)# fit_transform是fit和transform的组合，既包括了训练又包含了转换。训练PCA模型，同时返回降维后的数据# model1 = PCA(n_components=1, random_state=25)# n_components PCA算法中所要保留的主成分个数n，也即保留下来的特征个数n # house_test_label = model1.fit_transform(house_test_label) # house_train # house_test_label

文章图片

分割数据集和训练集

from sklearn.model_selection import train_test_split# train_data = https://www.it610.com/article/data_all.iloc[:, 3:31] # train_data = data_all[data_all.columns.delete([0,1,2])] train_label = data_all.iloc[:, 2] house_train, house_test, house_train_label, house_test_label = train_test_split / (train_data, train_label, test_size=0.2, random_state=42) print("训练数据集：",house_train) print("训练数据标签：",house_train_label) print() print("测试数据集：",house_test) print("测试数据标签：",house_test_label) print(data_all.info())

文章图片

数据归一化

from sklearn.model_selection import train_test_split from sklearn.preprocessing import MinMaxScaler# 归一化 # data_temp.info() scaler_train_data = https://www.it610.com/article/MinMaxScaler() scaler_train_data.fit(data_temp) scaler_train_data_features = scaler_train_data.transform(data_temp) scaler_train_data_features = pd.DataFrame(scaler_train_data_features) scaler_train_data_features.columns = data_temp.columns print(scaler_train_data_features)train_data = scaler_train_data_features[scaler_train_data_features.columns.delete([0])] train_label = scaler_train_data_features.iloc[:, 0] house_train, house_test, house_train_label, house_test_label = train_test_split / (train_data, train_label, test_size=0.2, random_state=25) print("训练数据集：",house_train) print("训练数据标签：",house_train_label) print() print("测试数据集：",house_test) print("测试数据标签：",house_test_label)

文章图片

house_test.head()

文章图片

house_test_label.head()

文章图片

house_test.info()

文章图片

预测模型数据未归一化前的随机森林预测

from sklearn.ensemble import RandomForestRegressor rfr = RandomForestRegressor() # 随机森林，基于树的方法是不需要进行特征的归一化 rfr.fit(house_train,house_train_label) rfr.score(house_test,house_test_label)

正确率：

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = rfr.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

数据归一化过后的随机森林预测

from sklearn.ensemble import RandomForestRegressor rfr = RandomForestRegressor() # 随机森林，基于树的方法是不需要进行特征的归一化 rfr.fit(house_train,house_train_label) rfr.score(house_test,house_test_label)

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = rfr.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

SVM径向基核函数预测

r_svr = SVR(kernel="rbf")#径向基核函数 r_svr.fit(house_train,house_train_label) r_svr.score(house_test,house_test_label)

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = r_svr.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

KNN最邻近算法预测

from sklearn.neighbors import KNeighborsRegressor knn = KNeighborsRegressor(weights="uniform")#K临近回归器 knn.fit(house_train,house_train_label) knn.score(house_test,house_test_label)

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = knn.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

决策树回归预测

from sklearn.tree import DecisionTreeRegressor #决策树回归 dt = DecisionTreeRegressor() dt.fit(house_train,house_train_label) dt.score(house_test,house_test_label)

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = dt.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

梯度提升决策分类预测

from sklearn.ensemble import GradientBoostingRegressor#提升树 gbr = GradientBoostingRegressor() gbr.fit(house_train,house_train_label) gbr.score(house_test,house_test_label)

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = gbr.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

SVM线性核函数预测

from sklearn.svm import SVR l_svr = SVR(kernel='linear')#线性核函数 l_svr.fit(house_train,house_train_label) l_svr.score(house_test,house_test_label) print(l_svr.score(house_test,house_test_label))

文章图片

plt.figure(figsize=(12, 6),facecolor='white') y_pre = l_svr.predict(house_test) plt.scatter(y_pre,house_test_label,marker='o') plt.scatter(house_test_label,house_test_label) plt.show()

文章图片

使用不同的train_size去训练模型

#建立模型用的训练数据集和测试数据集 from sklearn.svm import SVR from sklearn.ensemble import RandomForestRegressor size=np.arange(0.6,1,0.1) scorelist=[[],[],[],[],[],[]] from sklearn.model_selection import train_test_split for i in range(0,4):house_train, house_test, house_train_label, house_test_label = train_test_split \ (train_data , train_label,train_size=size[i],random_state=5) print("size: ",size[i])model = SVR(kernel='linear')#线性核函数 model.fit(house_train,house_train_label) print("线性核函数",model.score(house_test,house_test_label)) scorelist[0].append(model.score(house_test , house_test_label ))model = RandomForestRegressor() # 随机森林，基于树的方法是不需要进行特征的归一化 model.fit(house_train,house_train_label) model.score(house_test,house_test_label) print("随机森林",model.score(house_test,house_test_label)) scorelist[1].append(model.score(house_test , house_test_label ))model = SVR(kernel="rbf")#径向基核函数 model.fit(house_train,house_train_label) scorelist[2].append(model.score(house_test , house_test_label )) print("径向基核函数",model.score(house_test,house_test_label))model = KNeighborsRegressor(weights="uniform")#K临近回归器 model.fit(house_train,house_train_label) scorelist[3].append(model.score(house_test , house_test_label )) print("K临近回归器",model.score(house_test,house_test_label))#决策树回归 model = DecisionTreeRegressor() model.fit(house_train,house_train_label) scorelist[4].append(model.score(house_test , house_test_label )) print("决策树回归",model.score(house_test,house_test_label))model = GradientBoostingRegressor() model.fit(house_train,house_train_label) scorelist[5].append(model.score(house_test , house_test_label )) print("梯度提升决策分类",model.score(house_test,house_test_label))

文章图片

模型评估

plt.figure(figsize=(12, 6),facecolor='white')plt.rcParams['font.sans-serif'] = 'SimHei' plt.rcParams['axes.unicode_minus'] = False color_list = ('red', 'blue', 'lightgreen', 'cornflowerblue', 'turquoise', 'magenta') for i in range(0,6): #print(size,scorelist[i]) #print(scorelist[i]) plt.plot(size,scorelist[i],color=color_list[i])plt.legend(['SVM线性核函数', '随机森林','SVM径向基核函数','KNN最近邻','决策树回归','梯度提升决策分类']) plt.xlabel('训练集占比') plt.ylabel('准确率') plt.title('不同的模型随着训练集占比变化曲线') plt.show()