java手寫邏輯迴歸包括L1,L2正則實現
阿新 • • 發佈:2019-01-24
作為一枚機器學習的愛好者,邏輯迴歸算是一個簡單入門的演算法,原理比較簡單,但是自己手動實現邏輯迴歸有一些要注意的事項:
第一是步長選擇的問題,根據你的資料大小來選擇。
第二是自己手動可選擇加不加入常數項,用於做訓練。
第三是實際寫程式碼用的梯度上升程式碼來求解,演算法原理建議使用梯度下降,但是工程為了方便用梯度上升來求解。
第四是正則化問題,可以選擇L1、L2正則來實現你的程式碼。
第五是終止條件的問題,一般寫工程可以選擇迭代次數,也可以選擇根據最後weights變化來寫終止條件,也可以兩個一起結合一起使用。
第六是優化演算法,可以用批梯度,也可以用隨機梯度,也可以擬牛頓迭代法,原理都較簡單。
基本就是這些,歡迎大牛補充,下面自己用java寫了個,資料來源是python機器學習實戰那本書裡面的資料,java實現就麼有用矩陣,瞭解矩陣演算法背後原理實際用list也是一個性質,不說直接看程式碼。
首先是讀取資料程式碼:
package com.wanda.logistic; import java.io.BufferedReader; import java.io.FileInputStream; import java.io.File; import java.io.IOException; import java.io.InputStreamReader; import java.util.ArrayList; import java.util.Arrays; import java.util.List; public class ReadData { public static final String PATH = "d:\\wilson.zhou\\Desktop\\logistic.txt"; public static List<List<Float>> dataList = new ArrayList<List<Float>>(); public static List<Float> labelList = new ArrayList<Float>(); static { try { init(); } catch (IOException e) { e.printStackTrace(); } } private static void init() throws IOException { BufferedReader buff = new BufferedReader(new InputStreamReader( (new FileInputStream(new File(PATH))))); String str = buff.readLine(); while (str != null) { String[] arr = str.split("\t"); labelList.add(Float.parseFloat(arr[2])); dataList.add(Arrays.asList(Float.parseFloat(arr[0]), Float.parseFloat(arr[1]))); str = buff.readLine(); } buff.close(); } }
邏輯迴歸程式碼:
package com.wanda.logistic; import java.util.Arrays; import java.util.List; public class LogRegression { public static void main(String[] args) { LogRegression lr = new LogRegression(); ReadData instances = new ReadData(); lr.train(instances, 0.001f, 1); // } public void train(ReadData instances, float step, int type) { List<List<Float>> datas = instances.dataList; List<Float> labels = instances.labelList; int size = datas.size(); int dim = datas.get(0).size(); float[] w = new float[dim]; // 初始化權重 float changas = Float.MAX_VALUE; int caculate = 0; switch (type) { case 1: // 批梯度下降的方式 while (changas > 0.0001) { float[] wClone = w.clone(); float[] out = new float[size]; for (int s = 0; s < size; s++) { float lire = innerProduct(w, datas.get(s)); out[s] = sigmoid(lire); } for (int d = 0; d < dim; d++) { float sum = 0; for (int s = 0; s < size; s++) { sum += (labels.get(s) - out[s]) * datas.get(s).get(d); } float q=w[d]; w[d] = (float) (q + step * sum); // w[d] = (float) (q + step * sum-0.01*Math.pow(q,2)); L2正則 // w[d] = (float) (q + step * sum-0.01*Math.abs(q)); L1正則 } changas = changsWeight(wClone, w); caculate++; System.out.println("迭代次數是:" + caculate + " 權重是:" + Arrays.toString(w)); } break; case 2://隨機梯度下降 while (changas > 0.0001) { float[] wClone = w.clone(); for (int s = 0; s < size; s++) { float lire = innerProduct(w, datas.get(s)); float out = sigmoid(lire); float error = labels.get(s) - out; for (int d = 0; d < dim; d++) { w[d] += step * error * datas.get(s).get(d); } } changas = changsWeight(wClone, w); caculate++; System.out.println("迭代次數是:" + caculate + " 權重是:" + Arrays.toString(w)); } break; default: break; } } private float changsWeight(float[] wClone, float[] w) { float changs = 0; for (int i = 0; i < w.length; i++) { changs += Math.pow(w[i] - wClone[i], 2); } return (float) Math.sqrt(changs); } private float innerProduct(float[] w, List<Float> x) { float sum = 0; for (int i = 0; i < w.length; i++) { sum += w[i] * x.get(i); } return sum; } private float sigmoid(float src) { return (float) (1.0 / (1 + Math.exp(-src))); } }
資料:
-0.017612 14.053064 0
-1.395634 4.662541 1
-0.752157 6.538620 0
-1.322371 7.152853 0
0.423363 11.054677 0
0.406704 7.067335 1
0.667394 12.741452 0
-2.460150 6.866805 1
0.569411 9.548755 0
-0.026632 10.427743 0
0.850433 6.920334 1
1.347183 13.175500 0
1.176813 3.167020 1
-1.781871 9.097953 0
-0.566606 5.749003 1
0.931635 1.589505 1
-0.024205 6.151823 1
-0.036453 2.690988 1
-0.196949 0.444165 1
1.014459 5.754399 1
1.985298 3.230619 1
-1.693453 -0.557540 1
-0.576525 11.778922 0
-0.346811 -1.678730 1
-2.124484 2.672471 1
1.217916 9.597015 0
-0.733928 9.098687 0
-3.642001 -1.618087 1
0.315985 3.523953 1
1.416614 9.619232 0
-0.386323 3.989286 1
0.556921 8.294984 1
1.224863 11.587360 0
-1.347803 -2.406051 1
1.196604 4.951851 1
0.275221 9.543647 0
0.470575 9.332488 0
-1.889567 9.542662 0
-1.527893 12.150579 0
-1.185247 11.309318 0
-0.445678 3.297303 1
1.042222 6.105155 1
-0.618787 10.320986 0
1.152083 0.548467 1
0.828534 2.676045 1
-1.237728 10.549033 0
-0.683565 -2.166125 1
0.229456 5.921938 1
-0.959885 11.555336 0
0.492911 10.993324 0
0.184992 8.721488 0
-0.355715 10.325976 0
-0.397822 8.058397 0
0.824839 13.730343 0
1.507278 5.027866 1
0.099671 6.835839 1
-0.344008 10.717485 0
1.785928 7.718645 1
-0.918801 11.560217 0
-0.364009 4.747300 1
-0.841722 4.119083 1
0.490426 1.960539 1
-0.007194 9.075792 0
0.356107 12.447863 0
0.342578 12.281162 0
-0.810823 -1.466018 1
2.530777 6.476801 1
1.296683 11.607559 0
0.475487 12.040035 0
-0.783277 11.009725 0
0.074798 11.023650 0
-1.337472 0.468339 1
-0.102781 13.763651 0
-0.147324 2.874846 1
0.518389 9.887035 0
1.015399 7.571882 0
-1.658086 -0.027255 1
1.319944 2.171228 1
2.056216 5.019981 1
-0.851633 4.375691 1
-1.510047 6.061992 0
-1.076637 -3.181888 1
1.821096 10.283990 0
3.010150 8.401766 1
-1.099458 1.688274 1
-0.834872 -1.733869 1
-0.846637 3.849075 1
1.400102 12.628781 0
1.752842 5.468166 1
0.078557 0.059736 1
0.089392 -0.715300 1
1.825662 12.693808 0
0.197445 9.744638 0
0.126117 0.922311 1
-0.679797 1.220530 1
0.677983 2.556666 1
0.761349 10.693862 0
-2.168791 0.143632 1
1.388610 9.341997 0
0.317029 14.739025 0