Spaces:
Sleeping
Sleeping
File size: 9,960 Bytes
be5030f |
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 |
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
import { Table } from '../table';
import { IntVector } from '../vector/int';
import { Field, Schema } from '../schema';
import { Col } from './predicate';
import { RecordBatch } from '../recordbatch';
import { DataType } from '../type';
Table.prototype.countBy = function (name) { return new DataFrame(this.chunks).countBy(name); };
Table.prototype.scan = function (next, bind) { return new DataFrame(this.chunks).scan(next, bind); };
Table.prototype.scanReverse = function (next, bind) { return new DataFrame(this.chunks).scanReverse(next, bind); };
Table.prototype.filter = function (predicate) { return new DataFrame(this.chunks).filter(predicate); };
export class DataFrame extends Table {
filter(predicate) {
return new FilteredDataFrame(this.chunks, predicate);
}
scan(next, bind) {
const batches = this.chunks, numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
if (bind) {
bind(batch);
}
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
next(index, batch);
}
}
}
scanReverse(next, bind) {
const batches = this.chunks, numBatches = batches.length;
for (let batchIndex = numBatches; --batchIndex >= 0;) {
// load batches
const batch = batches[batchIndex];
if (bind) {
bind(batch);
}
// yield all indices
for (let index = batch.length; --index >= 0;) {
next(index, batch);
}
}
}
countBy(name) {
const batches = this.chunks, numBatches = batches.length;
const count_by = typeof name === 'string' ? new Col(name) : name;
// Assume that all dictionary batches are deltas, which means that the
// last record batch has the most complete dictionary
count_by.bind(batches[numBatches - 1]);
const vector = count_by.vector;
if (!DataType.isDictionary(vector.type)) {
throw new Error('countBy currently only supports dictionary-encoded columns');
}
const countByteLength = Math.ceil(Math.log(vector.length) / Math.log(256));
const CountsArrayType = countByteLength == 4 ? Uint32Array :
countByteLength >= 2 ? Uint16Array : Uint8Array;
const counts = new CountsArrayType(vector.dictionary.length);
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
// rebind the countBy Col
count_by.bind(batch);
const keys = count_by.vector.indices;
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
let key = keys.get(index);
if (key !== null) {
counts[key]++;
}
}
}
return new CountByResult(vector.dictionary, IntVector.from(counts));
}
}
/** @ignore */
export class CountByResult extends Table {
constructor(values, counts) {
const schema = new Schema([
new Field('values', values.type),
new Field('counts', counts.type)
]);
super(new RecordBatch(schema, counts.length, [values, counts]));
}
toJSON() {
const values = this.getColumnAt(0);
const counts = this.getColumnAt(1);
const result = {};
for (let i = -1; ++i < this.length;) {
result[values.get(i)] = counts.get(i);
}
return result;
}
}
/** @ignore */
export class FilteredDataFrame extends DataFrame {
constructor(batches, predicate) {
super(batches);
this._predicate = predicate;
}
scan(next, bind) {
// inlined version of this:
// this.parent.scan((idx, columns) => {
// if (this.predicate(idx, columns)) next(idx, columns);
// });
const batches = this._chunks;
const numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
const predicate = this._predicate.bind(batch);
let isBound = false;
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
if (predicate(index, batch)) {
// bind batches lazily - if predicate doesn't match anything
// in the batch we don't need to call bind on the batch
if (bind && !isBound) {
bind(batch);
isBound = true;
}
next(index, batch);
}
}
}
}
scanReverse(next, bind) {
const batches = this._chunks;
const numBatches = batches.length;
for (let batchIndex = numBatches; --batchIndex >= 0;) {
// load batches
const batch = batches[batchIndex];
const predicate = this._predicate.bind(batch);
let isBound = false;
// yield all indices
for (let index = batch.length; --index >= 0;) {
if (predicate(index, batch)) {
// bind batches lazily - if predicate doesn't match anything
// in the batch we don't need to call bind on the batch
if (bind && !isBound) {
bind(batch);
isBound = true;
}
next(index, batch);
}
}
}
}
count() {
// inlined version of this:
// let sum = 0;
// this.parent.scan((idx, columns) => {
// if (this.predicate(idx, columns)) ++sum;
// });
// return sum;
let sum = 0;
const batches = this._chunks;
const numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
const predicate = this._predicate.bind(batch);
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
if (predicate(index, batch)) {
++sum;
}
}
}
return sum;
}
*[Symbol.iterator]() {
// inlined version of this:
// this.parent.scan((idx, columns) => {
// if (this.predicate(idx, columns)) next(idx, columns);
// });
const batches = this._chunks;
const numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
// TODO: bind batches lazily
// If predicate doesn't match anything in the batch we don't need
// to bind the callback
const predicate = this._predicate.bind(batch);
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
if (predicate(index, batch)) {
yield batch.get(index);
}
}
}
}
filter(predicate) {
return new FilteredDataFrame(this._chunks, this._predicate.and(predicate));
}
countBy(name) {
const batches = this._chunks, numBatches = batches.length;
const count_by = typeof name === 'string' ? new Col(name) : name;
// Assume that all dictionary batches are deltas, which means that the
// last record batch has the most complete dictionary
count_by.bind(batches[numBatches - 1]);
const vector = count_by.vector;
if (!DataType.isDictionary(vector.type)) {
throw new Error('countBy currently only supports dictionary-encoded columns');
}
const countByteLength = Math.ceil(Math.log(vector.length) / Math.log(256));
const CountsArrayType = countByteLength == 4 ? Uint32Array :
countByteLength >= 2 ? Uint16Array : Uint8Array;
const counts = new CountsArrayType(vector.dictionary.length);
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const batch = batches[batchIndex];
const predicate = this._predicate.bind(batch);
// rebind the countBy Col
count_by.bind(batch);
const keys = count_by.vector.indices;
// yield all indices
for (let index = -1, numRows = batch.length; ++index < numRows;) {
let key = keys.get(index);
if (key !== null && predicate(index, batch)) {
counts[key]++;
}
}
}
return new CountByResult(vector.dictionary, IntVector.from(counts));
}
}
//# sourceMappingURL=dataframe.mjs.map
|