pandrs 0.3.0

A high-performance DataFrame library for Rust, providing pandas-like API with advanced features including SIMD optimization, parallel processing, and distributed computing capabilities
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237

use pandrs::error::Result;
use pandrs::{Column, Int64Column, OptimizedDataFrame, StringColumn};

#[test]
#[allow(clippy::result_large_err)]
fn test_inner_join() -> Result<()> {
    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("id", Column::Int64(id_col))?;

    // Name column
    let name_col = StringColumn::new(vec![
        "Alice".to_string(),
        "Bob".to_string(),
        "Charlie".to_string(),
        "Dave".to_string(),
    ]);
    left_df.add_column("name", Column::String(name_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 5, 6]);
    right_df.add_column("id", Column::Int64(id_col))?;

    // Value column
    let value_col = Int64Column::new(vec![100, 200, 500, 600]);
    right_df.add_column("value", Column::Int64(value_col))?;

    // Inner join
    let joined = left_df.inner_join(&right_df, "id", "id")?;

    // Validation - inner join only includes matching rows (id=1 and 2)
    assert_eq!(joined.row_count(), 2);
    assert_eq!(joined.column_count(), 3); // id, name, value

    Ok(())
}

#[test]
#[allow(clippy::result_large_err)]
fn test_left_join() -> Result<()> {
    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("id", Column::Int64(id_col))?;

    // Name column
    let name_col = StringColumn::new(vec![
        "Alice".to_string(),
        "Bob".to_string(),
        "Charlie".to_string(),
        "Dave".to_string(),
    ]);
    left_df.add_column("name", Column::String(name_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 5, 6]);
    right_df.add_column("id", Column::Int64(id_col))?;

    // Value column
    let value_col = Int64Column::new(vec![100, 200, 500, 600]);
    right_df.add_column("value", Column::Int64(value_col))?;

    // Left join
    let joined = left_df.left_join(&right_df, "id", "id")?;

    // Validation - left join includes all rows from left (id=1,2,3,4) and matching right rows
    assert_eq!(joined.row_count(), 4);
    assert_eq!(joined.column_count(), 3); // id, name, value

    Ok(())
}

#[test]
#[allow(clippy::result_large_err)]
fn test_right_join() -> Result<()> {
    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("id", Column::Int64(id_col))?;

    // Name column
    let name_col = StringColumn::new(vec![
        "Alice".to_string(),
        "Bob".to_string(),
        "Charlie".to_string(),
        "Dave".to_string(),
    ]);
    left_df.add_column("name", Column::String(name_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 5, 6]);
    right_df.add_column("id", Column::Int64(id_col))?;

    // Value column
    let value_col = Int64Column::new(vec![100, 200, 500, 600]);
    right_df.add_column("value", Column::Int64(value_col))?;

    // Right join
    let joined = left_df.right_join(&right_df, "id", "id")?;

    // Validation - right join includes all rows from right (id=1,2,5,6) and matching left rows
    assert_eq!(joined.row_count(), 4);
    assert_eq!(joined.column_count(), 3); // id, name, value

    Ok(())
}

#[test]
#[allow(clippy::result_large_err)]
fn test_outer_join() -> Result<()> {
    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("id", Column::Int64(id_col))?;

    // Name column
    let name_col = StringColumn::new(vec![
        "Alice".to_string(),
        "Bob".to_string(),
        "Charlie".to_string(),
        "Dave".to_string(),
    ]);
    left_df.add_column("name", Column::String(name_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 5, 6]);
    right_df.add_column("id", Column::Int64(id_col))?;

    // Value column
    let value_col = Int64Column::new(vec![100, 200, 500, 600]);
    right_df.add_column("value", Column::Int64(value_col))?;

    // Outer join
    let joined = left_df.outer_join(&right_df, "id", "id")?;

    // Validation - outer join includes all rows (id=1,2,3,4,5,6)
    assert_eq!(joined.row_count(), 6);
    assert_eq!(joined.column_count(), 3); // id, name, value

    Ok(())
}

#[test]
#[allow(clippy::result_large_err)]
fn test_join_different_column_names() -> Result<()> {
    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // Left ID column
    let left_id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("left_id", Column::Int64(left_id_col))?;

    // Name column
    let name_col = StringColumn::new(vec![
        "Alice".to_string(),
        "Bob".to_string(),
        "Charlie".to_string(),
        "Dave".to_string(),
    ]);
    left_df.add_column("name", Column::String(name_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // Right ID column
    let right_id_col = Int64Column::new(vec![1, 2, 5, 6]);
    right_df.add_column("right_id", Column::Int64(right_id_col))?;

    // Value column
    let value_col = Int64Column::new(vec![100, 200, 500, 600]);
    right_df.add_column("value", Column::Int64(value_col))?;

    // Inner join on different column names
    let joined = left_df.inner_join(&right_df, "left_id", "right_id")?;

    // Validation - inner join only includes matching rows (id=1 and 2)
    assert_eq!(joined.row_count(), 2);
    assert_eq!(joined.column_count(), 3); // left_id, name, value

    Ok(())
}

#[test]
#[allow(clippy::result_large_err)]
fn test_empty_join() -> Result<()> {
    // Join with empty DataFrames
    let empty_df = OptimizedDataFrame::new();
    let result = empty_df.inner_join(&empty_df, "id", "id");

    // Should error because trying to join on non-existent columns
    assert!(result.is_err());

    // Left dataframe
    let mut left_df = OptimizedDataFrame::new();

    // ID column
    let id_col = Int64Column::new(vec![1, 2, 3, 4]);
    left_df.add_column("id", Column::Int64(id_col))?;

    // Right dataframe
    let mut right_df = OptimizedDataFrame::new();

    // Non-matching ID column
    let id_col = Int64Column::new(vec![5, 6, 7, 8]);
    right_df.add_column("id", Column::Int64(id_col))?;

    // Inner join (no matching rows)
    let joined = left_df.inner_join(&right_df, "id", "id")?;

    // Validation - empty dataframe as no matching rows
    assert_eq!(joined.row_count(), 0);
    // Implementation might vary: could be an empty DataFrame or a DataFrame with just columns
    // So we only verify row count is 0

    Ok(())
}