【Golang】バリデーション付き CSV 読み込み機能と DataFrame 機能を持つパッケージを作った話

package csv_test

import (
	"bytes"
	"fmt"

	"github.com/nao1215/csv"
)

func ExampleCSV() {
	input := `id,name,age
1,Gina,23
a,Yulia,25
3,Den1s,30
`
	buf := bytes.NewBufferString(input)
	c, err := csv.NewCSV(buf)
	if err != nil {
		panic(err)
	}

	type person struct {
		ID   int    `validate:"numeric"`
		Name string `validate:"alpha"`
		Age  int    `validate:"gt=24"`
	}
	people := make([]person, 0)

	errs := c.Decode(&people)
	if len(errs) != 0 {
		for _, err := range errs {
			fmt.Println(err.Error())
		}
	}

	// Output:
	// line:2 column age: target is not greater than the threshold value: threshold=24, value=23
	// line:3 column id: target is not a numeric character: value=a
	// line:4 column name: target is not an alphabetic character: value=Den1s
}

func ExampleWithJapaneseLanguage() {
	input := `id,name,age
1,Gina,23
a,Yulia,25
3,Den1s,30
`
	buf := bytes.NewBufferString(input)
	c, err := csv.NewCSV(buf, csv.WithJapaneseLanguage())
	if err != nil {
		panic(err)
	}

	type person struct {
		ID   int    `validate:"numeric"`
		Name string `validate:"alpha"`
		Age  int    `validate:"gt=24"`
	}
	people := make([]person, 0)

	errs := c.Decode(&people)
	if len(errs) != 0 {
		for _, err := range errs {
			fmt.Println(err.Error())
		}
	}

	// Output:
	// line:2 column age: 値がしきい値より大きくありません: threshold=24, value=23
	// line:3 column id: 値が数字ではありません: value=a
	// line:4 column name: 値がアルファベット文字ではありません: value=Den1s
}

# 読み込み対象の data.csv。この行はないものとして考えてください。
name,age,score
Alice,25,70
Bob,32,88
Clara,41,92
Denis,29,60

import pandas as pd

df = pd.read_csv("data.csv")                      # 読み込み
df = df[df["age"] >= 30]                          # フィルタ
df = df.sort_values("score", ascending=False)     # ソート
df = df.assign(age_group=df["age"] // 10 * 10)    # 新しい列
print(df[["name", "age", "score", "age_group"]])  # 必要な列だけ表示

# 結果
    name  age  score  age_group
2  Clara   41     92         40
1    Bob   32     88         30

package csv_test

import (
	"bytes"
	"fmt"
	"os"
	"path/filepath"
	"strings"

	"github.com/nao1215/csv"
)

func ExampleDataFrame_joinFilterSort() {
	users := csv.NewDataFrame(filepath.Join("testdata", "sample.csv")).
		Select("id", "name", "age").
		Mutate("age_bucket", "CASE WHEN age >= 30 THEN '30s' ELSE '20s' END")

	orders := csv.NewDataFrame(filepath.Join("testdata", "orders.csv")).
		Filter("total >= 100").
		Mutate("gross_total", "total + 5")

	depts := csv.NewDataFrame(filepath.Join("testdata", "departments.csv")).
		Select("id", "dept").
		Rename(map[string]string{"dept": "dept_name"})

	df := users.
		Join(orders, "id").
		Join(depts, "id").
		Filter("age >= 23").
		Sort("gross_total", false).
		Select("name", "dept_name", "gross_total", "age_bucket")

	var buf bytes.Buffer
	if err := df.Print(&buf); err != nil {
		panic(err)
	}
	fmt.Print(buf.String())

	// Output:
	// age_bucket  dept_name    gross_total  name
	// 30s         Engineering  155          Denis
	// 20s         Sales        105          Gina
}