dataframe

package

v0.0.1 Latest Latest Go to latest Published: May 14, 2024 License: MulanPSL-2.0 Imports: 12 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

Repository

gitee.com/jn-qq/pandas

Links

Open Source Insights

Documentation ¶

Index ¶

Constants
func ReadXLSX(filePath string, sheets ...Sheets) (map[string]*DataFrame, error)
type DataFrame
type F
type Order
- func SortByForward(name string) Order
- func SortByReverse(name string) Order
type Sheets

Examples ¶

DataFrame.AddCol
DataFrame.AddRows
DataFrame.Arrange
DataFrame.Concat
DataFrame.FormatCols
DataFrame.Groups
DataFrame.Groups (Two)
DataFrame.Records
DataFrame.Set
DataFrame.WriteToCSV
DataFrame.WriteToXLSX
LoadMap
LoadRecord
New
ReadCSV
ReadXLSX
ReadXLSX (A)

Constants ¶

View Source

const (
	XLSX int = iota
	CSV
)

Variables ¶

This section is empty.

Functions ¶

func ReadXLSX ¶

func ReadXLSX(filePath string, sheets ...Sheets) (map[string]*DataFrame, error)

ReadXLSX 从XLSX中读取表格

Example ¶

dfs, err := ReadXLSX("test.xlsx",
	Sheets{
		SheetName: "Sheet3",
		ColsType:  []series.Type{series.String, series.Int},
	},
)
if err != nil {
	panic(err)
}
for s, frame := range dfs {
	fmt.Println("Sheet Name is", s)
	fmt.Println(frame)
}

Output:

Example (A) ¶

dfs, err := ReadXLSX("test.xlsx",
	Sheets{
		SheetName: "Sheet3",
		SRow:      5,
		SCol:      2,
		ColsType:  []series.Type{series.String, series.Int},
	},
)
if err != nil {
	panic(err)
}
for s, frame := range dfs {
	fmt.Println("Sheet Name is", s)
	fmt.Println(frame)
}

Output:

Types ¶

type DataFrame ¶

type DataFrame struct {
	// contains filtered or unexported fields
}

func LoadMap ¶

func LoadMap(values map[string]any) (*DataFrame, error)

LoadMap 通过列名集合创建表

values map[string]T, T = []int、[]string、[]float64、[]bool

Example ¶

df, _ := LoadMap(map[string]any{
	"name":  data.CreateSlice("Join", 100),
	"phone": data.CreateSlice("15963578965", 100),
})
fmt.Println(df)

Output:

	+------------------------------+
|   DataFrame Size：2 x 100    |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join   | 15963578965 |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
| 6     | Join   | 15963578965 |
| 7     | Join   | 15963578965 |
| 8     | Join   | 15963578965 |
| 9     | Join   | 15963578965 |
| 10    | Join   | 15963578965 |
| 11    | Join   | 15963578965 |
| 12    | Join   | 15963578965 |
| 13    | Join   | 15963578965 |
| 14    | Join   | 15963578965 |
| 15    | Join   | 15963578965 |
| .     | .      | .           |
| .     | .      | .           |
| .     | .      | .           |
| 95    | Join   | 15963578965 |
| 96    | Join   | 15963578965 |
| 97    | Join   | 15963578965 |
| 98    | Join   | 15963578965 |
| 99    | Join   | 15963578965 |
| 100   | Join   | 15963578965 |
+-------+--------+-------------+
| Types | string | string      |
+-------+--------+-------------+

func LoadRecord ¶

func LoadRecord(rows [][]string, colsName []string, colsType []series.Type) (*DataFrame, error)

LoadRecord 用二维字符串切片创建 DataFrame 数据对象

rows: 待输入数据
colsName：每列名称，当为 nil 时，rows[0]作为每列名称
colsType：每列数据类型

Example ¶

df, _ := LoadRecord(
	data.CreateSlice([]string{"Join", "15963578965"}, 100),
	[]string{"name", "phone"},
	[]series.Type{series.String, series.Int},
)
fmt.Println(df)

Output:

	+------------------------------+
|   DataFrame Size：2 x 100    |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join   | 15963578965 |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
| 6     | Join   | 15963578965 |
| 7     | Join   | 15963578965 |
| 8     | Join   | 15963578965 |
| 9     | Join   | 15963578965 |
| 10    | Join   | 15963578965 |
| 11    | Join   | 15963578965 |
| 12    | Join   | 15963578965 |
| 13    | Join   | 15963578965 |
| 14    | Join   | 15963578965 |
| 15    | Join   | 15963578965 |
| .     | .      | .           |
| .     | .      | .           |
| .     | .      | .           |
| 95    | Join   | 15963578965 |
| 96    | Join   | 15963578965 |
| 97    | Join   | 15963578965 |
| 98    | Join   | 15963578965 |
| 99    | Join   | 15963578965 |
| 100   | Join   | 15963578965 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func New ¶

func New(columns []any, colsName []string) (*DataFrame, error)

New 创建 DataFrame 数据对象

columns: 待输入数据，可以为 []any 。series.Series / []int / []float64 / []string / []bool
colsName: 列名，当 columns 为 series.Series 可为nil

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 100), data.CreateSlice(15963578965, 100)},
	[]string{"name", "phone"},
)
fmt.Println(df)

Output:

	+------------------------------+
|   DataFrame Size：2 x 100    |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join   | 15963578965 |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
| 6     | Join   | 15963578965 |
| 7     | Join   | 15963578965 |
| 8     | Join   | 15963578965 |
| 9     | Join   | 15963578965 |
| 10    | Join   | 15963578965 |
| 11    | Join   | 15963578965 |
| 12    | Join   | 15963578965 |
| 13    | Join   | 15963578965 |
| 14    | Join   | 15963578965 |
| 15    | Join   | 15963578965 |
| .     | .      | .           |
| .     | .      | .           |
| .     | .      | .           |
| 95    | Join   | 15963578965 |
| 96    | Join   | 15963578965 |
| 97    | Join   | 15963578965 |
| 98    | Join   | 15963578965 |
| 99    | Join   | 15963578965 |
| 100   | Join   | 15963578965 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func ReadCSV ¶

func ReadCSV(filePath string, sheet Sheets) (*DataFrame, error)

ReadCSV 从CSV中读取表格

Example ¶

readCSV, err := ReadCSV("test.csv", Sheets{
	ColsType: []series.Type{series.String, series.Int},
})
if err != nil {
	panic(err)
}
fmt.Println(readCSV)

Output:

func (*DataFrame) AddCol ¶

func (df *DataFrame) AddCol(name string, values any, defaultValue any) error

AddCol 添加列

name：列名。如果已存在更新，否则添加
values：可选 series.Series []E {int | float64 | bool | string}
defaultValue：当 values 长度不足时，自动添加

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 5), data.CreateSlice(15963578965, 5)},
	[]string{"name", "phone"},
)
_ = df.AddCol("addr", data.CreateSlice("xxxxx", 5), nil)
fmt.Println(df)
_ = df.AddCol("addr", data.CreateSlice("yyyy", 1), "yyy")
fmt.Println(df)

Output:

+---------------------------------------+
|         DataFrame Size：3 x 5         |
+-------+--------+-------------+--------+
| Index | name   | phone       | addr   |
+-------+--------+-------------+--------+
| 1     | Join   | 15963578965 | xxxxx  |
| 2     | Join   | 15963578965 | xxxxx  |
| 3     | Join   | 15963578965 | xxxxx  |
| 4     | Join   | 15963578965 | xxxxx  |
| 5     | Join   | 15963578965 | xxxxx  |
+-------+--------+-------------+--------+
| Types | string | int         | string |
+-------+--------+-------------+--------+

+---------------------------------------+
|         DataFrame Size：3 x 5         |
+-------+--------+-------------+--------+
| Index | name   | phone       | addr   |
+-------+--------+-------------+--------+
| 1     | Join   | 15963578965 | yyyy   |
| 2     | Join   | 15963578965 | yyy    |
| 3     | Join   | 15963578965 | yyy    |
| 4     | Join   | 15963578965 | yyy    |
| 5     | Join   | 15963578965 | yyy    |
+-------+--------+-------------+--------+
| Types | string | int         | string |
+-------+--------+-------------+--------+

func (*DataFrame) AddRows ¶

func (df *DataFrame) AddRows(values [][]any) error

AddRows 向列表末尾添加行

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 5), data.CreateSlice(15963578965, 5)},
	[]string{"name", "phone"},
)
_ = df.AddRows([][]any{{"name1", 12345678}, {"name1", 12345678}, {"name1", 12345678}})
fmt.Println(df)

Output:

+------------------------------+
|    DataFrame Size：2 x 8     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join   | 15963578965 |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
| 6     | name1  | 12345678    |
| 7     | name1  | 12345678    |
| 8     | name1  | 12345678    |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func (*DataFrame) Arrange ¶

func (df *DataFrame) Arrange(order ...Order) error

Arrange 排序

Example ¶

df, _ := New(
	[]any{
		[]string{"伏旭歆", "管原炳", "仰芝凤", "万茵瑾", "左芊筱", "俞淑允", "宗茹淳", "卓虹", "司丽瑾", "岑泳继"},
		[]int{13935531105, 15665203778, 14583084372, 14779318181, 17606363473, 18950385204, 18659058185, 16628908658, 17590257481, 17254554855},
		[]int{35, 36, 42, 13, 20, 20, 14, 20, 30, 36},
	},
	[]string{"name", "phone", "age"},
)
_ = df.Arrange(SortByForward("name"), Order{ColumnName: "age", Reverse: true})
fmt.Println(df)

Output:

+------------------------------------+
|       DataFrame Size：3 x 10       |
+-------+--------+-------------+-----+
| Index | name   | phone       | age |
+-------+--------+-------------+-----+
| 1     | 仰芝凤 | 14583084372 | 42  |
| 2     | 岑泳继 | 17254554855 | 36  |
| 3     | 管原炳 | 15665203778 | 36  |
| 4     | 伏旭歆 | 13935531105 | 35  |
| 5     | 司丽瑾 | 17590257481 | 30  |
| 6     | 卓虹   | 16628908658 | 20  |
| 7     | 左芊筱 | 17606363473 | 20  |
| 8     | 俞淑允 | 18950385204 | 20  |
| 9     | 宗茹淳 | 18659058185 | 14  |
| 10    | 万茵瑾 | 14779318181 | 13  |
+-------+--------+-------------+-----+
| Types | string | int         | int |
+-------+--------+-------------+-----+

func (*DataFrame) Cell ¶

func (df *DataFrame) Cell(r int, name string) series.Element

Cell 返回指定单元格元素

func (*DataFrame) Columns ¶

func (df *DataFrame) Columns(name string) (series.Series, error)

Columns 返回列

func (*DataFrame) Concat ¶

func (df *DataFrame) Concat(x DataFrame, isColumn bool) error

Concat 合并两个表

isColumn：是否合并在右侧 ，如果两个表列名相同，则更新原表列

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 3), data.CreateSlice(15963578965, 3)},
	[]string{"name", "phone"},
)
df1, _ := New(
	[]any{data.CreateSlice("Mary", 3), data.CreateSlice(19645698705, 3)},
	[]string{"name", "phone"},
)
_ = df.Concat(*df1, false)
fmt.Println(df)

Output:

+------------------------------+
|    DataFrame Size：2 x 6     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join   | 15963578965 |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Mary   | 19645698705 |
| 5     | Mary   | 19645698705 |
| 6     | Mary   | 19645698705 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func (*DataFrame) Copy ¶

func (df *DataFrame) Copy() *DataFrame

Copy 复制

func (*DataFrame) DropCols ¶

func (df *DataFrame) DropCols(names ...string)

DropCols 批量删除

func (*DataFrame) Filter ¶

func (df *DataFrame) Filter(filters ...F) (*DataFrame, error)

Filter 过滤

func (*DataFrame) FormatCols ¶

func (df *DataFrame) FormatCols(f func(index int, elem series.Element) series.Element, cols ...string) error

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 5), data.CreateSlice(15963578965, 5)},
	[]string{"name", "phone"},
)
err := df.FormatCols(func(index int, elem series.Element) series.Element {
	elem.Set(elem.Records() + strconv.Itoa(index))
	return elem
}, "name")
if err != nil {
	panic(err)
}
fmt.Println(df)

Output:

+------------------------------+
|    DataFrame Size：2 x 5     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Join0  | 15963578965 |
| 2     | Join1  | 15963578965 |
| 3     | Join2  | 15963578965 |
| 4     | Join3  | 15963578965 |
| 5     | Join4  | 15963578965 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func (*DataFrame) Groups ¶

func (df *DataFrame) Groups(names ...string) (map[string]*DataFrame, error)

Example ¶

df, _ := New(
	[]any{
		[]string{"喻靖元", "尤淇方", "方文栋", "郝晨轩", "养海露", "弘展鹏", "滕安平", "谷灵雁", "陶海露", "乔瀚天"},
		[]string{"男", "男", "男", "男", "女", "男", "男", "女", "女", "男"},
		[]int{51, 29, 44, 21, 26, 29, 68, 21, 29, 52},
	},
	[]string{"name", "sex", "age"},
)
group, _ := df.Groups("sex")
for s, frame := range group {
	fmt.Println("group_name is " + s)
	fmt.Println(frame)
}

Output:

group_name is 男
+-------------------------------+
|     DataFrame Size：3 x 7     |
+-------+--------+--------+-----+
| Index | name   | sex    | age |
+-------+--------+--------+-----+
| 1     | 喻靖元 | 男     | 51  |
| 2     | 尤淇方 | 男     | 29  |
| 3     | 方文栋 | 男     | 44  |
| 4     | 郝晨轩 | 男     | 21  |
| 5     | 弘展鹏 | 男     | 29  |
| 6     | 滕安平 | 男     | 68  |
| 7     | 乔瀚天 | 男     | 52  |
+-------+--------+--------+-----+
| Types | string | string | int |
+-------+--------+--------+-----+

group_name is 女
+-------------------------------+
|     DataFrame Size：3 x 3     |
+-------+--------+--------+-----+
| Index | name   | sex    | age |
+-------+--------+--------+-----+
| 1     | 养海露 | 女     | 26  |
| 2     | 谷灵雁 | 女     | 21  |
| 3     | 陶海露 | 女     | 29  |
+-------+--------+--------+-----+
| Types | string | string | int |
+-------+--------+--------+-----+

Example (Two) ¶

df, _ := New(
	[]any{
		[]string{"喻靖元", "尤淇方", "方文栋", "郝晨轩", "养海露", "弘展鹏", "滕安平", "谷灵雁", "陶海露", "乔瀚天"},
		[]string{"男", "男", "男", "男", "女", "男", "男", "女", "女", "男"},
		[]int{51, 29, 44, 21, 26, 29, 68, 21, 29, 52},
	},
	[]string{"name", "sex", "age"},
)
group, _ := df.Groups("sex", "age")
for s, frame := range group {
	fmt.Println("group_name is " + s)
	fmt.Println(frame)
}

Output:

group_name is 男51
+-------------------------------+
|     DataFrame Size：3 x 1     |
+-------+--------+--------+-----+
| Index | name   | sex    | age |
+-------+--------+--------+-----+
| 1     | 喻靖元 | 男     | 51  |
+-------+--------+--------+-----+
| Types | string | string | int |
+-------+--------+--------+-----+

	......

group_name is 男29
+-------------------------------+
|     DataFrame Size：3 x 2     |
+-------+--------+--------+-----+
| Index | name   | sex    | age |
+-------+--------+--------+-----+
| 1     | 尤淇方 | 男     | 29  |
| 2     | 弘展鹏 | 男     | 29  |
+-------+--------+--------+-----+
| Types | string | string | int |
+-------+--------+--------+-----+

group_name is 男21
+-------------------------------+
|     DataFrame Size：3 x 1     |
+-------+--------+--------+-----+
| Index | name   | sex    | age |
+-------+--------+--------+-----+
| 1     | 郝晨轩 | 男     | 21  |
+-------+--------+--------+-----+
| Types | string | string | int |
+-------+--------+--------+-----+

func (*DataFrame) NCols ¶

func (df *DataFrame) NCols() int

func (*DataFrame) NRows ¶

func (df *DataFrame) NRows() int

func (*DataFrame) Names ¶

func (df *DataFrame) Names() []string

Names 返回列名

func (*DataFrame) Print ¶

func (df *DataFrame) Print(isComplete bool) (str string)

func (*DataFrame) Records ¶

func (df *DataFrame) Records(isRow bool, hasColName bool) [][]string

Records 返回字符串切片

isRow = false 返回列切片 isRow = true  返回行切片
hasColName 是否返回列名，第一个元素，或切片

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 5), data.CreateSlice(15963578965, 5)},
	[]string{"name", "phone"},
)
fmt.Println(df.Records(false, false))
fmt.Println(df.Records(false, true))
fmt.Println(df.Records(true, true))

Output:

[[Join ... Join] [15963578965 ... 15963578965]]
[[name Join ... Join] [phone 15963578965 ... 15963578965]]
[[name phone] [Join 15963578965] ... [Join 15963578965]]

func (*DataFrame) Rename ¶

func (df *DataFrame) Rename(cols map[string]string)

Rename 批量命名

func (*DataFrame) Rows ¶

func (df *DataFrame) Rows(r int) map[string]series.Element

Rows 返回行

func (*DataFrame) SelectCols ¶

func (df *DataFrame) SelectCols(names ...string) *DataFrame

func (*DataFrame) Set ¶

func (df *DataFrame) Set(index int, values any) error

Set 设置 index 行的值

values：可选[]any、map[string]any ,[]any要更改行的所有元素
index < DataFrame.rows 更新行，index >= DataFrame.rows 添加行

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 5), data.CreateSlice(15963578965, 5)},
	[]string{"name", "phone"},
)
_ = df.Set(0, []any{"Andy", 1111111111})
fmt.Println(df)
_ = df.Set(2, map[string]any{"phone": 222222222})
fmt.Println(df)
_ = df.Set(df.rows, []any{"Andy", 1111111111})
fmt.Println(df)

Output:

+------------------------------+
|    DataFrame Size：2 x 5     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Andy   | 1111111111  |
| 2     | Join   | 15963578965 |
| 3     | Join   | 15963578965 |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

+------------------------------+
|    DataFrame Size：2 x 5     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Andy   | 1111111111  |
| 2     | Join   | 15963578965 |
| 3     | Join   | 222222222   |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

+------------------------------+
|    DataFrame Size：2 x 6     |
+-------+--------+-------------+
| Index | name   | phone       |
+-------+--------+-------------+
| 1     | Andy   | 1111111111  |
| 2     | Join   | 15963578965 |
| 3     | Join   | 222222222   |
| 4     | Join   | 15963578965 |
| 5     | Join   | 15963578965 |
| 6     | Andy   | 1111111111  |
+-------+--------+-------------+
| Types | string | int         |
+-------+--------+-------------+

func (*DataFrame) Size ¶

func (df *DataFrame) Size() (cols, rows int)

Size 更新并返回二维数组大小

func (*DataFrame) String ¶

func (df *DataFrame) String() string

自定义输出

func (*DataFrame) SubSet ¶

func (df *DataFrame) SubSet(indexes ...int) (*DataFrame, error)

func (*DataFrame) Types ¶

func (df *DataFrame) Types() []string

Types 返回列类型

func (*DataFrame) WriteToCSV ¶

func (df *DataFrame) WriteToCSV(p string) error

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 100), data.CreateSlice(15963578965, 100)},
	[]string{"name", "phone"},
)
err := df.WriteToCSV("test.csv")
if err != nil {
	panic(err)
}

Output:

func (*DataFrame) WriteToXLSX ¶

func (df *DataFrame) WriteToXLSX(p, sheetName string) error

Example ¶

df, _ := New(
	[]any{data.CreateSlice("Join", 100), data.CreateSlice(15963578965, 100)},
	[]string{"name", "phone"},
)
err := df.WriteToXLSX("test.xlsx", "Sheet3")
if err != nil {
	panic(err)
}

Output:

type F ¶

type F struct {
	Column   string
	Operator series.RelationalOperator

	OR bool
	// contains filtered or unexported fields
}

F 过滤条件

OR与前一个过滤的关系

type Order ¶

type Order struct {
	// 列名
	ColumnName string
	// 倒叙
	Reverse bool
}

Order 排序结构

func SortByForward ¶

func SortByForward(name string) Order

SortByForward 正序

func SortByReverse ¶

func SortByReverse(name string) Order

SortByReverse 倒叙

type Sheets ¶

type Sheets struct {
	SCol      int           // 开始列, 默认 1
	SRow      int           // 开始行, 默认 1
	ECol      int           // 结束列, 默认最后一列
	ERow      int           // 结束行, 默认最后一行
	Header    []string      // 表头，默认第一行
	SheetName string        // 工作部名 XLSX 特有
	ColsType  []series.Type // 列类型
}

Sheets 数据对象

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL