加入 pca 优化了 knn 运行时间

src/python/getting-started/digit-recognizer/knn-python3.6.py

@@ -7,48 +7,74 @@ Author: 片刻
 Github: https://github.com/apachecn/kaggle
 '''
 
+import os.path
 import csv
 import time
+import numpy as np
 import pandas as pd
-from numpy import shape, ravel
+from sklearn.decomposition import PCA
 from sklearn.neighbors import KNeighborsClassifier
 
+data_dir = '/opt/data/kaggle/getting-started/digit-recognizer/'
+
 
 # 加载数据
 def opencsv():
     # 使用 pandas 打开
-    data = pd.read_csv(
-        'datasets/getting-started/digit-recognizer/input/train.csv')
-    data1 = pd.read_csv(
-        'datasets/getting-started/digit-recognizer/input/test.csv')
+    data = pd.read_csv(os.path.join(data_dir, 'train.csv'))
+    data1 = pd.read_csv(os.path.join(data_dir, 'test.csv'))
 
     train_data = data.values[0:, 1:]  # 读入全部训练数据,  [行，列]
-    train_label = data.values[0:, 0] # 读取列表的第一列
+    train_label = data.values[0:, 0]  # 读取列表的第一列
     test_data = data1.values[0:, 0:]  # 测试全部测试个数据
     return train_data, train_label, test_data
 
 
 def saveResult(result, csvName):
-    with open(csvName, 'w',newline='') as myFile: # 创建记录输出结果的文件（w 和 wb 使用的时候有问题）
-    #python3里面对 str和bytes类型做了严格的区分，不像python2里面某些函数里可以混用。所以用python3来写wirterow时，打开文件不要用wb模式，只需要使用w模式，然后带上newline=''
-        myWriter = csv.writer(myFile) # 对文件执行写入
-        myWriter.writerow(["ImageId", "Label"]) # 设置表格的列名
+    with open(csvName, 'w', newline='') as myFile:  # 创建记录输出结果的文件（w 和 wb 使用的时候有问题）
+        # python3里面对 str和bytes类型做了严格的区分，不像python2里面某些函数里可以混用。所以用python3来写wirterow时，打开文件不要用wb模式，只需要使用w模式，然后带上newline=''
+        myWriter = csv.writer(myFile)  # 对文件执行写入
+        myWriter.writerow(["ImageId", "Label"])  # 设置表格的列名
         index = 0
         for i in result:
             tmp = []
             index = index + 1
             tmp.append(index)
             # tmp.append(i)
-            tmp.append(int(i)) # 测试集的标签值
+            tmp.append(int(i))  # 测试集的标签值
             myWriter.writerow(tmp)
 
 
 def knnClassify(trainData, trainLabel):
-    knnClf = KNeighborsClassifier()   # default:k = 5,defined by yourself:KNeighborsClassifier(n_neighbors=10)
-    knnClf.fit(trainData, ravel(trainLabel)) # ravel Return a contiguous flattened array.
+    knnClf = KNeighborsClassifier()  # default:k = 5,defined by yourself:KNeighborsClassifier(n_neighbors=10)
+    knnClf.fit(trainData, np.ravel(trainLabel))  # ravel Return a contiguous flattened array.
     return knnClf
 
 
+# 数据预处理-降维 PCA主成成分分析
+def dRPCA(x_train, x_test, COMPONENT_NUM):
+    print('dimensionality reduction...')
+    trainData = np.array(x_train)
+    testData = np.array(x_test)
+    '''
+    使用说明：https://www.cnblogs.com/pinard/p/6243025.html
+    n_components>=1
+      n_components=NUM   设置占特征数量比
+    0 < n_components < 1
+      n_components=0.99  设置阈值总方差占比
+    '''
+    pca = PCA(n_components=COMPONENT_NUM, whiten=True)
+    pca.fit(trainData)  # Fit the model with X
+    pcaTrainData = pca.transform(trainData)  # Fit the model with X and 在X上完成降维.
+    pcaTestData = pca.transform(testData)  # Fit the model with X and 在X上完成降维.
+
+    # pca 方差大小、方差占比、特征数量
+    print(pca.explained_variance_, '\n', pca.explained_variance_ratio_, '\n',
+          pca.n_components_)
+    print(sum(pca.explained_variance_ratio_))
+    return pcaTrainData, pcaTestData
+
+
 def dRecognition_knn():
     start_time = time.time()
 
@@ -61,6 +87,9 @@ def dRecognition_knn():
     stop_time_l = time.time()
     print('load data time used:%f' % (stop_time_l - start_time))
 
+    # 降维处理
+    trainData, testData = dRPCA(trainData, testData, 35)
+
     # 模型训练
     knnClf = knnClassify(trainData, trainLabel)
 
@@ -68,10 +97,7 @@ def dRecognition_knn():
     testLabel = knnClf.predict(testData)
 
     # 结果的输出
-    saveResult(
-        testLabel,
-        'datasets/getting-started/digit-recognizer/output/Result_sklearn_knn.csv'
-    )
+    saveResult(testLabel, os.path.join(data_dir, 'Result_sklearn_knn.csv'))
     print("finish!")
     stop_time_r = time.time()
     print('classify time used:%f' % (stop_time_r - start_time))

src/python/getting-started/digit-recognizer/svm-python3.6.py

@@ -79,11 +79,11 @@ def saveResult(result, csvName):
 
 # 分析数据,看数据是否满足要求（通过这些来检测数据的相关性，考虑在分类的时候提取出重要的特征）
 def analyse_data(dataMat):
-    meanVals = np.mean(dataMat, axis=0) # np.mean 求出每列的平均值meanVals
+    meanVals = np.mean(dataMat, axis=0)  # np.mean 求出每列的平均值meanVals
     meanRemoved = dataMat-meanVals # 每一列特征值减去该列的特征值均值
-    #计算协方差矩阵，除数n-1是为了得到协方差的 无偏估计
-    #cov(X,0) = cov(X) 除数是n-1(n为样本个数)
-    #cov(X,1) 除数是n
+    # 计算协方差矩阵，除数n-1是为了得到协方差的 无偏估计
+    # cov(X,0) = cov(X) 除数是n-1(n为样本个数)
+    # cov(X,1) 除数是n
     covMat = np.cov(meanRemoved, rowvar=0) # cov 计算协方差的值,
     # np.mat 是用来生成一个矩阵的
     # 保存特征值(eigvals)和对应的特征向量(eigVects)