update

Author: BeardedManZhao

src_code/README-Chinese.md

@@ -665,7 +665,7 @@ import java.sql.SQLException;
 
 
 public class MAIN1 {
- public static void main(String[] args) throws SQLException {
+ public static void main(String[] args) {
  // 将一些图像文件转换成为一个图像矩阵对象
  ColorMatrix colorMatrix1 = ColorMatrix.parseGrayscale("C:\\Users\\Liming\\Desktop\\fsdownload\\test2.bmp");
  // 对图像进行二值化
@@ -677,4 +677,42 @@ public class MAIN1 {
 }
 ```
 
+* 支持列的添加，但是需要注意的是列的添加会返回一个新的 DataFrame DF中的数据将会被浅拷贝出来。
+
+```java
+package zhao.algorithmMagic;
+
+import zhao.algorithmMagic.operands.table.*;
+
+import java.sql.SQLException;
+
+public class MAIN1 {
+ public static void main(String[] args) {
+ // 创建一个空的 DataFrame 对象
+ FDataFrame select = FDataFrame.select(
+ FieldCell.parse("id", "name", "sex", "age"), 1
+ );
+ // 手动插入数据
+ select.insert(
+ FinalSeries.parse("1", "zhao", "M", "19"),
+ FinalSeries.parse("2", "tang", "W", "18"),
+ FinalSeries.parse("3", "yang", "W", "20"),
+ FinalSeries.parse("4", "shen", "W", "19")
+ );
+ // 打印出 DF 对象有关的信息
+ System.out.println(
+ select.desc()
+ );
+ // 添加一列数据，用于表示年龄是否为偶数
+ DataFrame ageIsE = select.insertColGetNew(
+ // 新列的列名称
+ FieldCell.$("AgeIsE"),
+ // 新列的数值生成逻辑 如果第 4 列（index == 3）的数值 % 2 == 0 就是true
+ cells -> cells.getCell(3).getIntValue() % 2 == 0 ? new FinalCell<>(true) : new FinalCell<>(false)
+ );
+ System.out.println(ageIsE);
+ }
+}
+```
+
 ### Version update date : xx xx-xx-xx

src_code/README.md

@@ -667,16 +667,55 @@ import java.sql.SQLException;
 
 
 public class MAIN1 {
- public static void main(String[] args) throws SQLException {
+ public static void main(String[] args) {
  // 将一些图像文件转换成为一个图像矩阵对象
  ColorMatrix colorMatrix1 = ColorMatrix.parseGrayscale("C:\\Users\\Liming\\Desktop\\fsdownload\\test2.bmp");
  // 对图像进行二值化
- colorMatrix1.globalBinary(ColorMatrix._G_, 100 , 0xffffff, 0);
+ colorMatrix1.globalBinary(ColorMatrix._G_, 100, 0xffffff, 0);
  colorMatrix1.show("腐蚀之前的 image");
  // 开始对图像矩阵进行腐蚀操作
  colorMatrix1.erode(2, 2, false).show("腐蚀之后的 image");
  }
 }
 ```
 
+* The addition of columns is supported, but it should be noted that the addition of columns will return a new DataFrame
+ DF in which the data will be lightly copied.
+
+```java
+package zhao.algorithmMagic;
+
+import zhao.algorithmMagic.operands.table.*;
+
+import java.sql.SQLException;
+
+public class MAIN1 {
+ public static void main(String[] args) {
+ // 创建一个空的 DataFrame 对象
+ FDataFrame select = FDataFrame.select(
+ FieldCell.parse("id", "name", "sex", "age"), 1
+ );
+ // 手动插入数据
+ select.insert(
+ FinalSeries.parse("1", "zhao", "M", "19"),
+ FinalSeries.parse("2", "tang", "W", "18"),
+ FinalSeries.parse("3", "yang", "W", "20"),
+ FinalSeries.parse("4", "shen", "W", "19")
+ );
+ // 打印出 DF 对象有关的信息
+ System.out.println(
+ select.desc()
+ );
+ // 添加一列数据，用于表示年龄是否为偶数
+ DataFrame ageIsE = select.insertColGetNew(
+ // 新列的列名称
+ FieldCell.$("AgeIsE"),
+ // 新列的数值生成逻辑 如果第 4 列（index == 3）的数值 % 2 == 0 就是true
+ cells -> cells.getCell(3).getIntValue() % 2 == 0 ? new FinalCell<>(true) : new FinalCell<>(false)
+ );
+ System.out.println(ageIsE);
+ }
+}
+```
+
 ### Version update date : xx xx-xx-xx

src_code/src/main/java/zhao/algorithmMagic/MAIN1.java

@@ -1,23 +1,20 @@
 package zhao.algorithmMagic;
-
-import zhao.algorithmMagic.operands.table.FDataFrame;
-import zhao.algorithmMagic.operands.table.FinalSeries;
-
-import java.sql.SQLException;
+import zhao.algorithmMagic.operands.table.*;
 
 public class MAIN1 {
- public static void main(String[] args) throws SQLException {
+ public static void main(String[] args) {
  // 创建一个空的 DataFrame 对象
  FDataFrame select = FDataFrame.select(
- FinalSeries.parse("id", "name", "sex", "age"), 1
+ FieldCell.parse("id", "name", "sex", "age"), 1
  );
  // 手动插入数据
  select.insert(
  FinalSeries.parse("1", "zhao", "M", "19"),
- FinalSeries.parse("1", "tang", "W", "18"),
- FinalSeries.parse("1", "yang", "W", "20")
+ FinalSeries.parse("2", "tang", "W", "18"),
+ FinalSeries.parse("3", "yang", "W", "20"),
+ FinalSeries.parse("4", "shen", "W", "19")
  );
-
- System.out.println(select);
+ // 将数据的HTML网页表格输出到磁盘中
+ select.into_outHtml("C:\\Users\\zhao\\Desktop\\out\\res.html", "数据表名称");
  }
 }

src_code/src/main/java/zhao/algorithmMagic/operands/matrix/ColorMatrix.java

@@ -1100,7 +1100,7 @@ public void globalBinary(byte Mode, int colorBoundary, int trueColor, int falseC
  /**
  * 基于坐标周边点进行图像二值化的计算，该操作与全局二值化操作做之间最大的差别在于，其中的与阈值进行比对的数值并不是所有坐标点，而是当前坐标点的周边坐标点的对应通道的颜色数值，能够有效的将二值化体现出来。
  * <p>
- * The biggest difference between the calculation of image binarization based on coordinate peripheral points and the global binarization operation is that the value compared to the threshold value is not all coordinate points, but the color value of the corresponding channel of the peripheral coordinate points of the current coordinate point, which can effectively reflect binarization.
+ * The biggest difference between the calculation of image binary based on coordinate peripheral points and the global binary operation is that the value compared to the threshold value is not all coordinate points, but the color value of the corresponding channel of the peripheral coordinate points of the current coordinate point, which can effectively reflect binary.
  *
  * @param Mode 在进行通道色彩的获取的时候，需要指定规整时的颜色通道标准，在指定通道的基础上进行规整，该参数可以直接从 ColorMatrix 类中获取到。
  * <p>

src_code/src/main/java/zhao/algorithmMagic/operands/table/DataFrame.java

@@ -168,6 +168,23 @@ public interface DataFrame extends AggDataFrameData, Iterable<Series>, Serializa
  */
  DataFrame insert(Series... rowSeries);
 
+ /**
+ * 以当前数据集为基准，添加一列新数据，并将添加列数据之后的 Data Frame 对象返回出来。
+ * <p>
+ * Based on the current dataset, add a new column of data, and return the Data Frame object after adding the column data.
+ *
+ * @param fieldName 需要被添加的列数据所对应的列名称，要求不得与已有的DataFrame字段名称重名！
+ * <p>
+ * The column name corresponding to the column data to be added must not duplicate the existing DataFrame field name!
+ * @param transformation 在添加的列新数据的过程中，提供一个新数据的生成函数，函数中的参数是每行数据的系列对象，您可以根据行数据生成新数值，也可以根据自己的规则生成新数据。
+ * <p>
+ * During the process of adding new data for a column, a new data generation function is provided. The parameters in the function are a series of objects for each row of data. You can generate new values based on the row data or generate new data based on your own rules.
+ * @return 添加了列字段与列数据之后的DataFrame对象。
+ * <p>
+ * The DataFrame object after adding column fields and column data.
+ */
+ DataFrame insertColGetNew(FieldCell fieldName, Transformation<Series, Cell<?>> transformation);
+
  /**
  * 将一列字段对应的所有数据按照指定的函数进行更新。
  * <p>

src_code/src/main/java/zhao/algorithmMagic/operands/table/FDataFrame.java

@@ -311,7 +311,7 @@ public DataFrame where(Condition whereClause) {
  for (Series cells : this.list) {
  if (whereClause.isComplianceEvents(cells)) arrayList.add(cells);
  }
- return new FDataFrame(this.colNameRow, this.primaryIndex, arrayList.toArray(new Series[0]))
+ return new FDataFrame(this.colNameRow, this.primaryIndex, arrayList)
  .refreshField(true, false);
  }
 
@@ -440,7 +440,7 @@ public DataFrame insert(Series rowSeries) {
  */
  @Override
  public DataFrame insert(Series... rowSeries) {
- int startLen = this.list.size() - 1;
+ int startLen = this.list.size();
  this.list.addAll(Arrays.asList(rowSeries));
  // 增量更新行索引
  for (int i = startLen, count = 0; count < rowSeries.length; count++, i++) {
@@ -452,6 +452,38 @@ public DataFrame insert(Series... rowSeries) {
  return this;
  }
 
+ /**
+ * 以当前数据集为基准，添加一列新数据，并将添加列数据之后的 Data Frame 对象返回出来。
+ * <p>
+ * Based on the current dataset, add a new column of data, and return the Data Frame object after adding the column data.
+ *
+ * @param fieldName 需要被添加的列数据所对应的列名称，要求不得与已有的DataFrame字段名称重名！
+ * <p>
+ * The column name corresponding to the column data to be added must not duplicate the existing DataFrame field name!
+ * @param transformation 在添加的列新数据的过程中，提供一个新数据的生成函数，函数中的参数是每行数据的系列对象，您可以根据行数据生成新数值，也可以根据自己的规则生成新数据。
+ * <p>
+ * During the process of adding new data for a column, a new data generation function is provided. The parameters in the function are a series of objects for each row of data. You can generate new values based on the row data or generate new data based on your own rules.
+ * @return 添加了列字段与列数据之后的DataFrame对象。
+ * <p>
+ * The DataFrame object after adding column fields and column data.
+ */
+ @Override
+ public DataFrame insertColGetNew(FieldCell fieldName, Transformation<Series, Cell<?>> transformation) {
+ ArrayList<Series> arrayList = new ArrayList<>(this.list.size() + 10);
+ for (Series cells : this.list) {
+ arrayList.add(FinalSeries.merge(
+ cells, transformation.function(cells)
+ ));
+ }
+ return new FDataFrame(
+ FinalSeries.merge(this.colNameRow, fieldName),
+ this.primaryIndex,
+ arrayList,
+ this.rowHashMap,
+ new HashMap<>(this.colHashMap.size() + 1)
+ );
+ }
+
  /**
  * 将一列字段对应的所有数据按照指定的函数进行更新。
  * <p>
@@ -563,7 +595,7 @@ public DataFrame into_outHtml(String outPath, String tableName) {
  bufferedWriter.newLine();
  bufferedWriter.write("<meta charset=\"UTF-8\"><title>");
  bufferedWriter.write(tableName);
- bufferedWriter.write("Title</title>");
+ bufferedWriter.write("</title>");
  bufferedWriter.newLine();
  bufferedWriter.write("</head>");
  bufferedWriter.newLine();
@@ -608,27 +640,6 @@ public DataFrame into_outHtml(String outPath, String tableName) {
  return this;
  }
 
- /**
- * Returns a string representation of the object. In general, the
- * {@code toString} method returns a string that
- * "textually represents" this object. The result should
- * be a concise but informative representation that is easy for a
- * person to read.
- * It is recommended that all subclasses override this method.
- * <p>
- * The {@code toString} method for class {@code Object}
- * returns a string consisting of the name of the class of which the
- * object is an instance, the at-sign character `{@code @}', and
- * the unsigned hexadecimal representation of the hash code of the
- * object. In other words, this method returns a string equal to the
- * value of:
- * <blockquote>
- * <pre>
- * getClass().getName() + '@' + Integer.toHexString(hashCode())
- * </pre></blockquote>
- *
- * @return a string representation of the object.
- */
  @Override
  public String toString() {
  StringBuilder stringBuilder = new StringBuilder();

src_code/src/main/java/zhao/algorithmMagic/operands/table/FinalGroupTable.java

@@ -43,7 +43,7 @@ public FinalGroupTable(Series colNameRow, int primaryIndex, int index, DataFrame
  }
  hashMap = new HashMap<>();
  hashMap1.forEach((key, value) -> {
- hashMap.put(key, new FDataFrame(colNameRow, primaryIndex, value.toArray(new Series[0])));
+ hashMap.put(key, new FDataFrame(colNameRow, primaryIndex, value));
  value.clear();
  });
  groupKey = colNameRow.getCell(index);
@@ -79,7 +79,7 @@ public FinalGroupTable(Series colNameRow, int primaryIndex, int index, DataFrame
  }
  hashMap = new HashMap<>();
  hashMap1.forEach((key, value) -> {
- hashMap.put(key, new FDataFrame(colNameRow, primaryIndex, value.toArray(new Series[0])));
+ hashMap.put(key, new FDataFrame(colNameRow, primaryIndex, value));
  value.clear();
  });
  groupKey = colNameRow.getCell(index);

src_code/src/main/java/zhao/algorithmMagic/operands/table/FinalSeries.java

@@ -1,6 +1,7 @@
 package zhao.algorithmMagic.operands.table;
 
 import zhao.algorithmMagic.exception.OperatorOperationException;
+import zhao.algorithmMagic.utils.ASClass;
 import zhao.algorithmMagic.utils.Event;
 import zhao.algorithmMagic.utils.transformation.Transformation;
 
@@ -32,6 +33,21 @@ public FinalSeries(Cell<?>... cells) {
  }
  }
 
+ /**
+ * 将一个Series 和很多个单元格进行数据合并
+ *
+ * @param finalSeries 需要被合并的Series对象
+ * @param cells 合需要被合并的所有单元格
+ * @return 合并之后的数据对象
+ */
+ public static FinalSeries merge(Series finalSeries, Cell<?>... cells) {
+ Cell<?>[] cells1 = finalSeries.toArray();
+ int length1 = cells1.length;
+ Cell<?>[] res = new Cell[length1 + cells.length];
+ ASClass.mergeArray(res, cells1, cells);
+ return new FinalSeries(res);
+ }
+
  public static FinalSeries parse(String... arr) {
  return new FinalSeries(
  Arrays.stream(arr).map(FinalCell::new)

src_code/src/main/java/zhao/algorithmMagic/operands/vector/SparkVector.scala

@@ -77,14 +77,6 @@ final class SparkVector(sparkContext: SparkContext, vector: org.apache.spark.mll
  else throw new OperatorOperationException("'DoubleVector1 innerProduct DoubleVector2' 时，两个'DoubleVector'的向量所包含的数量不同，DoubleVector1=[" + doubles1.length + "]，DoubleVector2=[" + doubles2.length + "]\n" + "When 'DoubleVector1 innerProduct DoubleVector2', the two vectors of 'DoubleVector' contain different quantities, DoubleVector1=[" + doubles1.length + "], DoubleVector2=[" + doubles2.length + "]")
  }
 
- /**
- *
- * @return 将本对象中存储的向量序列数组拷贝到一个新数组并将新数组返回，这里返回的是一个新数组，支持修改等操作。
- *
- * Copy the vector sequence array stored in this object to a new array and return the new array. Here, a new array is returned, which supports modification and other operations.
- */
- override def copyToNewArray(): Array[Double] = vector.toArray
-
  /**
  * @return 该类的实现类对象，用于拓展该接口的子类
  */
@@ -115,6 +107,21 @@ final class SparkVector(sparkContext: SparkContext, vector: org.apache.spark.mll
  else throw new OperatorOperationException("'DoubleVector1 add DoubleVector2' 时，两个'DoubleVector'的向量所包含的数量不同，DoubleVector1=[" + numberOfDimensions1 + "]，DoubleVector2=[" + numberOfDimensions2 + "]\n" + "When 'DoubleVector1 add DoubleVector2', the two vectors of 'DoubleVector' contain different quantities, DoubleVector1=[" + numberOfDimensions1 + "], DoubleVector2=[" + numberOfDimensions2 + "]")
  }
 
+ /**
+ * @return 向量中包含的维度数量
+ * <p>
+ * the number of dimensions contained in the vector
+ */
+ override def getNumberOfDimensions: Int = size
+
+ /**
+ *
+ * @return 将本对象中存储的向量序列数组拷贝到一个新数组并将新数组返回，这里返回的是一个新数组，支持修改等操作。
+ *
+ * Copy the vector sequence array stored in this object to a new array and return the new array. Here, a new array is returned, which supports modification and other operations.
+ */
+ override def copyToNewArray(): Array[Double] = vector.toArray
+
  /**
  * 在两个操作数之间做差的方法，具体用法请参阅API说明。
  * <p>
@@ -139,13 +146,6 @@ final class SparkVector(sparkContext: SparkContext, vector: org.apache.spark.mll
  else throw new OperatorOperationException("'DoubleVector1 diff DoubleVector2' 时，两个'DoubleVector'的向量所包含的数量不同，DoubleVector1=[" + numberOfDimensions1 + "]，DoubleVector2=[" + numberOfDimensions2 + "]\n" + "When 'DoubleVector1 diff DoubleVector2', the two vectors of 'DoubleVector' contain different quantities, DoubleVector1=[" + numberOfDimensions1 + "], DoubleVector2=[" + numberOfDimensions2 + "]")
  }
 
- /**
- * @return 向量中包含的维度数量
- * <p>
- * the number of dimensions contained in the vector
- */
- override def getNumberOfDimensions: Int = size
-
  /**
  *
  * @return 第三方向量中所维护的向量序列，通过此函数您可以直接获取到第三方库中的对象。