我将以下pandas数据框按“名称”分组,然后对“值”应用几个lambda函数以生成其他列。 是否可以一次应用这些lambda函数以提高效率?
public class XLSXToCSVConverter {
public InputStream convertxlstoCSV(InputStream inputStream) throws IOException, InvalidFormatException {
Workbook wb = WorkbookFactory.create(inputStream);
return csvConverter(wb.getSheetAt(0));
}
private InputStream csvConverter(Sheet sheet) {
Row row = null;
String str = new String();
for (int i = 0; i < sheet.getLastRowNum()+1; i++) {
row = sheet.getRow(i);
String rowString = new String();
for (int j = 0; j < 3; j++) {
if(row.getCell(j)==null) {
rowString = rowString + Utility.BLANK_SPACE + Utility.COMMA;
}
else {
rowString = rowString + row.getCell(j)+ Utility.COMMA;
}
}
str = str + rowString.substring(0,rowString.length()-1)+ Utility.NEXT_LINE_OPERATOR;
}
System.out.println(str);
return new ByteArrayInputStream(str.getBytes(StandardCharsets.UTF_8));
}
}
输出:
import pandas as pd
df = pd.DataFrame({'name': ['A','A', 'B','B','B','B', 'C','C','C'],
'value': [1, 3, 1, 2, 3, 1, 2, 3, 3], })
df['Diff'] = df.groupby('name')['value'].transform(lambda x: x - x.iloc[0])
df['Count'] = df.groupby('name')['value'].transform(lambda x: x.count())
df['Index'] = df.groupby('name')['value'].transform(lambda x: x.index - x.index[0] + 1)
print(df)
答案 0 :(得分:3)
这里可以将GroupBy.apply
与一个功能一起使用,但不确定是否有更好的性能:
org.eclipse.e4.ui.internal.workbench.swt.PartRenderingEngine