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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335

//! String operation helper functions

use crate::core::error::Result;
use crate::dataframe::DataFrame;
use crate::series::Series;

/// Convert string column to lowercase
pub fn str_lower(df: &DataFrame, column: &str) -> Result<DataFrame> {
    let vals = df.get_column_string_values(column)?;
    let lowered: Vec<String> = vals.iter().map(|s| s.to_lowercase()).collect();

    let mut result = DataFrame::new();
    for col in df.column_names() {
        if col == column {
            result.add_column(
                col.clone(),
                Series::new(lowered.clone(), Some(col.clone()))?,
            )?;
        } else if let Ok(v) = df.get_column_numeric_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        } else if let Ok(v) = df.get_column_string_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        }
    }

    Ok(result)
}

/// Convert string column to uppercase
pub fn str_upper(df: &DataFrame, column: &str) -> Result<DataFrame> {
    let vals = df.get_column_string_values(column)?;
    let uppered: Vec<String> = vals.iter().map(|s| s.to_uppercase()).collect();

    let mut result = DataFrame::new();
    for col in df.column_names() {
        if col == column {
            result.add_column(
                col.clone(),
                Series::new(uppered.clone(), Some(col.clone()))?,
            )?;
        } else if let Ok(v) = df.get_column_numeric_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        } else if let Ok(v) = df.get_column_string_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        }
    }

    Ok(result)
}

/// Strip whitespace from string column
pub fn str_strip(df: &DataFrame, column: &str) -> Result<DataFrame> {
    let vals = df.get_column_string_values(column)?;
    let stripped: Vec<String> = vals.iter().map(|s| s.trim().to_string()).collect();

    let mut result = DataFrame::new();
    for col in df.column_names() {
        if col == column {
            result.add_column(
                col.clone(),
                Series::new(stripped.clone(), Some(col.clone()))?,
            )?;
        } else if let Ok(v) = df.get_column_numeric_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        } else if let Ok(v) = df.get_column_string_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        }
    }

    Ok(result)
}

/// Check if string column contains pattern (returns boolean column)
pub fn str_contains(df: &DataFrame, column: &str, pattern: &str) -> Result<Vec<bool>> {
    let vals = df.get_column_string_values(column)?;
    Ok(vals.iter().map(|s| s.contains(pattern)).collect())
}

/// Replace pattern in string column
pub fn str_replace(
    df: &DataFrame,
    column: &str,
    pattern: &str,
    replacement: &str,
) -> Result<DataFrame> {
    let vals = df.get_column_string_values(column)?;
    let replaced: Vec<String> = vals
        .iter()
        .map(|s| s.replace(pattern, replacement))
        .collect();

    let mut result = DataFrame::new();
    for col in df.column_names() {
        if col == column {
            result.add_column(
                col.clone(),
                Series::new(replaced.clone(), Some(col.clone()))?,
            )?;
        } else if let Ok(v) = df.get_column_numeric_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        } else if let Ok(v) = df.get_column_string_values(&col) {
            result.add_column(col.clone(), Series::new(v, Some(col.clone()))?)?;
        }
    }

    Ok(result)
}

/// Split string column on delimiter
pub fn str_split(df: &DataFrame, column: &str, delimiter: &str) -> Result<Vec<Vec<String>>> {
    let vals = df.get_column_string_values(column)?;
    Ok(vals
        .iter()
        .map(|s| s.split(delimiter).map(|p| p.to_string()).collect())
        .collect())
}

/// Get length of strings in column
pub fn str_len(df: &DataFrame, column: &str) -> Result<Vec<usize>> {
    let vals = df.get_column_string_values(column)?;
    Ok(vals.iter().map(|s| s.len()).collect())
}

/// Check if string column starts with prefix
pub fn str_startswith(df: &DataFrame, column: &str, prefix: &str) -> Result<Vec<bool>> {
    let values = df.get_column_string_values(column)?;
    Ok(values.iter().map(|s| s.starts_with(prefix)).collect())
}

/// Check if string column ends with suffix
pub fn str_endswith(df: &DataFrame, column: &str, suffix: &str) -> Result<Vec<bool>> {
    let values = df.get_column_string_values(column)?;
    Ok(values.iter().map(|s| s.ends_with(suffix)).collect())
}

/// Pad strings on the left to specified width
pub fn str_pad_left(
    df: &DataFrame,
    column: &str,
    width: usize,
    fillchar: char,
) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let padded: Vec<String> = values
        .iter()
        .map(|s| {
            if s.len() >= width {
                s.clone()
            } else {
                format!("{}{}", fillchar.to_string().repeat(width - s.len()), s)
            }
        })
        .collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(padded.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}

/// Pad strings on the right to specified width
pub fn str_pad_right(
    df: &DataFrame,
    column: &str,
    width: usize,
    fillchar: char,
) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let padded: Vec<String> = values
        .iter()
        .map(|s| {
            if s.len() >= width {
                s.clone()
            } else {
                format!("{}{}", s, fillchar.to_string().repeat(width - s.len()))
            }
        })
        .collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(padded.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}

/// Slice strings from start to end position
pub fn str_slice(
    df: &DataFrame,
    column: &str,
    start: usize,
    end: Option<usize>,
) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let sliced: Vec<String> = values
        .iter()
        .map(|s| {
            let end_idx = end.unwrap_or(s.len()).min(s.len());
            let start_idx = start.min(s.len());
            s.chars()
                .skip(start_idx)
                .take(end_idx - start_idx)
                .collect()
        })
        .collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(sliced.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}

/// Count occurrences of a pattern in string column
pub fn str_count(df: &DataFrame, column: &str, pattern: &str) -> Result<Vec<usize>> {
    let values = df.get_column_string_values(column)?;
    Ok(values.iter().map(|s| s.matches(pattern).count()).collect())
}

/// Repeat strings n times
pub fn str_repeat(df: &DataFrame, column: &str, n: usize) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let repeated: Vec<String> = values.iter().map(|s| s.repeat(n)).collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(repeated.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}

/// Center strings in width with fillchar
pub fn str_center(df: &DataFrame, column: &str, width: usize, fillchar: char) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let centered: Vec<String> = values
        .iter()
        .map(|s| {
            if s.len() >= width {
                s.clone()
            } else {
                let padding = width - s.len();
                let left = padding / 2;
                let right = padding - left;
                format!(
                    "{}{}{}",
                    fillchar.to_string().repeat(left),
                    s,
                    fillchar.to_string().repeat(right)
                )
            }
        })
        .collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(centered.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}

/// Zero-fill strings to width
pub fn str_zfill(df: &DataFrame, column: &str, width: usize) -> Result<DataFrame> {
    let values = df.get_column_string_values(column)?;
    let filled: Vec<String> = values
        .iter()
        .map(|s| {
            if s.len() >= width {
                s.clone()
            } else {
                format!("{}{}", "0".repeat(width - s.len()), s)
            }
        })
        .collect();

    let mut result = DataFrame::new();
    for col_name in df.column_names() {
        if &col_name == column {
            result.add_column(
                col_name.clone(),
                Series::new(filled.clone(), Some(col_name))?,
            )?;
        } else if let Ok(vals) = df.get_column_numeric_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        } else if let Ok(vals) = df.get_column_string_values(&col_name) {
            result.add_column(col_name.clone(), Series::new(vals, Some(col_name.clone()))?)?;
        }
    }
    Ok(result)
}