rowboat 0.1.0

A package for working with row/column/cell structured data AKA dataframe.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151

use chrono::NaiveDateTime;
use rowboat::dataframe::*;
use serde::Deserialize;

// Using rowboat to explore and transform a csv

#[derive(Deserialize, ToRow)]
struct Employee {
    id: u32,
    first_name: String,
    last_name: String,
    start_date: String,
    salary: u32,
    department_id: u32,
    active: bool,
}
#[derive(Deserialize, ToRow)]
struct Department {
    id: u32,
    department_name: String,
    budget: u32,
    capacity: u32,
}
pub fn main() {
    // Load data
    let mut dep_df = Dataframe::from_csv::<Department>("./tests/example/department.csv").unwrap();
    let mut emp_df = Dataframe::from_csv::<Employee>("./tests/example/employee.csv").unwrap();

    // Describe the employee data
    emp_df.describe().print();

    // Make date-time column from string timestamps
    emp_df
        .add_col(
            "start_date_time",
            emp_df
                .col_values("start_date")
                .unwrap()
                .iter()
                .map(|date_cell| {
                    if let Cell::Str(val) = date_cell {
                        Some(NaiveDateTime::parse_from_str(val, "%Y-%m-%d %H:%M:%SZ").unwrap())
                    } else {
                        None
                    }
                })
                .collect(),
        )
        .unwrap();

    // Drop string timestamps
    emp_df.drop_cols(["start_date"].into());

    // Make full_name column
    emp_df
        .add_col(
            "full_name",
            emp_df
                .col_slice(["first_name", "last_name"].into())
                .unwrap()
                .iter()
                .map(|row| {
                    match (
                        row.get("first_name").unwrap(),
                        row.get("last_name").unwrap(),
                    ) {
                        (Cell::Str(first), Cell::Str(last)) => format!("{first} {last}"),
                        _ => String::from(""),
                    }
                })
                .collect(),
        )
        .unwrap();

    // Sort by department and start date
    emp_df = emp_df
        .into_sort()
        .sort("department_id", Desc)
        .sort("start_date_time", Desc)
        .collect()
        .unwrap();

    // Display
    dep_df.print();
    emp_df.print();

    // Rename id column for uniqueness and join dataframes together
    dep_df.rename_col("id", "department_id").unwrap();
    let join_df = emp_df
        .join(&dep_df, "department_id", "department_id")
        .unwrap();

    // Filter out non active employee rows
    let mut filter_df = join_df.filter(exp("active", Eq, true)).unwrap();

    // Reshape
    filter_df.retain_cols(
        [
            "id",
            "full_name",
            "start_date_time",
            "salary",
            "department_name",
            "budget",
        ]
        .into(),
    );

    // Display
    filter_df.print();

    // Group by departments
    let mut grouped_df = filter_df
        .group_by("department_name")
        .select("department_name", Coalesce, "department")
        .select("budget", Coalesce, "budget")
        .select("full_name", Count, "employee_count")
        .select("salary", Sum, "expense")
        .to_dataframe()
        .unwrap();

    // Add an over_budget column
    grouped_df
        .add_col(
            "over_budget",
            grouped_df
                .col_slice(["budget", "expense"].into())
                .unwrap()
                .iter()
                .map(
                    |row| match (row.get("budget").unwrap(), row.get("expense").unwrap()) {
                        (Cell::Uint(budget), Cell::Float(expense)) => *expense > *budget as f64,
                        _ => false,
                    },
                )
                .collect(),
        )
        .unwrap();

    // Sort by budget
    grouped_df.sort("budget", Desc).unwrap();

    // Display
    grouped_df.print();

    // Filter and display rows that are over budget
    grouped_df
        .filter(exp("over_budget", Eq, true))
        .unwrap()
        .print();
}