Merge branch 'master' of https://github.com/opensource9ja/danfojs into browser-groupby

Author: steveoni

README.md

@@ -51,7 +51,7 @@ easy and intuitive. It is heavily inspired by [Pandas](https://pandas.pydata.org
 To use Danfo.js via script tags, copy and paste the CDN below to the body of your HTML file
 
 ```html
-    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.3/lib/bundle.min.js"></script> 
+    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.4/lib/bundle.min.js"></script> 
 ```
 
 ### Example Usage in the Browser
@@ -66,7 +66,7 @@ To use Danfo.js via script tags, copy and paste the CDN below to the body of you
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <script src="https://cdn.plot.ly/plotly-1.2.0.min.js"></script> 
-    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.3/lib/bundle.min.js"></script> 
+    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.4/lib/bundle.min.js"></script> 
 
     <title>Document</title>
 </head>

danfojs-browser/README.md

@@ -51,7 +51,7 @@ easy and intuitive. It is heavily inspired by [Pandas](https://pandas.pydata.org
 To use Danfo.js via script tags, copy and paste the CDN below to the body of your HTML file
 
 ```html
-    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.3/lib/bundle.min.js"></script> 
+    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.4/lib/bundle.min.js"></script> 
 ```
 
 ### Example Usage in the Browser
@@ -66,7 +66,7 @@ To use Danfo.js via script tags, copy and paste the CDN below to the body of you
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <script src="https://cdn.plot.ly/plotly-1.2.0.min.js"></script> 
-    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.3/lib/bundle.min.js"></script> 
+    <script src="https://cdn.jsdelivr.net/npm/danfojs@0.2.4/lib/bundle.min.js"></script> 
 
     <title>Document</title>
 </head>

danfojs-browser/lib/bundle.js

@@ -146,6 +146,23 @@
  * =============================================================================
  */
 
+/**
+ * @license
+ * Copyright 2021 Google LLC. All Rights Reserved.
+ * Licensed 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.
+ * =============================================================================
+ */
+
 /**
  * @license Complex.js v2.0.11 11/02/2016
  *

danfojs-browser/lib/bundle.js.LICENSE.txt

@@ -1,6 +1,6 @@
 {
   "name": "danfojs",
-  "version": "0.2.3",
+  "version": "0.2.4",
   "description": "JavaScript library providing high performance, intuitive, and easy to use data structures for manipulating and processing structured data.",
   "main": "lib/bundle.js",
   "types": "types/index.d.ts",
@@ -21,7 +21,7 @@
     "types"
   ],
   "dependencies": {
-    "@tensorflow/tfjs": "2.8.5",
+    "@tensorflow/tfjs": "3.2.0",
     "mathjs": "7.5.1",
     "table": "^5.4.6",
     "xlsx": "^0.16.7"
@@ -33,8 +33,7 @@
     "bundle": "webpack --mode production",
     "coveralls": "cat ./coverage/lcov.info | ./node_modules/.bin/coveralls",
     "coverage": "nyc report --reporter=text-lcov | coveralls && nyc report --reporter=lcov",
-    "patch": "npm version patch",
-    "publish": "npm publish"
+    "patch": "npm version patch"
   },
   "publishConfig": {
     "access": "public",
@@ -86,4 +85,4 @@
     ]
   },
   "sideEffects": false
-}
+}

danfojs-browser/lib/bundle.js.map

@@ -12,7 +12,7 @@
 * limitations under the License.
 */
 
-import { tensor } from "@tensorflow/tfjs";
+import * as tf from "@tensorflow/tfjs";
 import Ndframe from "./generic";
 import { Series } from "./series";
 import { Utils } from "./utils";
@@ -183,7 +183,7 @@ export class DataFrame extends Ndframe {
           index: new_index
         });
       } else {
-        this.row_data_tensor = tensor(new_data);
+        this.row_data_tensor = tf.tensor(new_data);
         this.data = new_data;
         this.__set_index(new_index);
       }
@@ -266,36 +266,24 @@ export class DataFrame extends Ndframe {
 
   /**
    * Gets [num] number of random rows in a dataframe
-   * @param {rows}  rows --> int
-   * @returns DataFrame
+   * @param {num}  rows --> The number of rows to return
+   * @param {seed}  seed --> (Optional) An integer specifying the random seed that will be used to create the distribution.
+   * @returns {Promise} resolves to a DataFrame object
    */
-  sample(num = 5) {
-    //TODO: Use different sampling strategy
-    if (num > this.values.length || num < 1) {
-      //return all values
-      let config = { columns: this.column_names };
-      return new DataFrame(this.values, config);
-    } else {
-      let values = this.values;
-      let idx = this.index;
-      let new_values = [];
-      let new_idx = [];
-
-      let counts = [ ...Array(idx.length).keys() ]; //set index
-
-      //get random sampled numbers
-      let rand_nums = utils.__sample_from_iter(counts, num, false);
-      rand_nums.map((i) => {
-        new_values.push(values[i]);
-        new_idx.push(idx[i]);
-      });
-
-      let config = { columns: this.column_names, index: new_idx };
-      let df = new DataFrame(new_values, config);
-      return df;
+  async sample(num = -1, seed = 1) {
+    if (num > this.shape[0]) {
+      throw new Error("Sample size n cannot be bigger than size of dataset");
     }
+    if (num < -1 || num == 0) {
+      throw new Error("Sample size cannot be less than -1 or 0");
+    }
+    num = num === -1 ? this.shape[0] : num;
+    const shuffled_index = await tf.data.array(this.index).shuffle(num, seed).take(num).toArray();
+    const df = this.iloc({ rows: shuffled_index });
+    return df;
   }
 
+
   /**
    * Return Addition of DataFrame and other, element-wise (binary operator add).
    * @param {other} DataFrame, Series, Array or Number to add
@@ -916,7 +904,7 @@ export class DataFrame extends Ndframe {
       }
 
       values.map((arr) => {
-        let temp_sum = tensor(arr).sum().arraySync();
+        let temp_sum = tf.tensor(arr).sum().arraySync();
         val_sums.push(Number(temp_sum.toFixed(5)));
       });
 
@@ -940,7 +928,7 @@ export class DataFrame extends Ndframe {
   abs() {
     let data = this.values;
 
-    let tensor_data = tensor(data);
+    let tensor_data = tf.tensor(data);
     let abs_data = tensor_data.abs().arraySync();
     let df = new DataFrame(utils.__round(abs_data, 2, false), {
       columns: this.column_names,
@@ -1406,7 +1394,7 @@ export class DataFrame extends Ndframe {
       }
 
       for (let i = 0; i < df_data.length; i++) {
-        let value = tensor(df_data[i]);
+        let value = tf.tensor(df_data[i]);
         let callable_data;
         try {
           callable_data = callable(value).arraySync();
@@ -1659,18 +1647,18 @@ export class DataFrame extends Ndframe {
               `Shape Error: Operands could not be broadcast together with shapes ${this.shape} and ${val.values.length}.`
             );
           }
-          other = tensor(val.values);
+          other = tf.tensor(val.values);
         } else {
           if (val.values.length != this.shape[1]) {
             throw Error(
               `Shape Error: Operands could not be broadcast together with shapes ${this.shape} and ${val.values.length}.`
             );
           }
-          other = tensor(val.values);
+          other = tf.tensor(val.values);
         }
       } else if (Array.isArray(val)) {
         //Array of Array
-        other = tensor(val);
+        other = tf.tensor(val);
       } else {
         //DataFrame
         other = val.row_data_tensor;
@@ -1679,22 +1667,22 @@ export class DataFrame extends Ndframe {
 
     switch (logical_type) {
     case "lt":
-      int_vals = tensor(this.values).less(other).arraySync();
+      int_vals = tf.tensor(this.values).less(other).arraySync();
       break;
     case "gt":
-      int_vals = tensor(this.values).greater(other).arraySync();
+      int_vals = tf.tensor(this.values).greater(other).arraySync();
       break;
     case "le":
-      int_vals = tensor(this.values).lessEqual(other).arraySync();
+      int_vals = tf.tensor(this.values).lessEqual(other).arraySync();
       break;
     case "ge":
-      int_vals = tensor(this.values).greaterEqual(other).arraySync();
+      int_vals = tf.tensor(this.values).greaterEqual(other).arraySync();
       break;
     case "ne":
-      int_vals = tensor(this.values).notEqual(other).arraySync();
+      int_vals = tf.tensor(this.values).notEqual(other).arraySync();
       break;
     case "eq":
-      int_vals = tensor(this.values).equal(other).arraySync();
+      int_vals = tf.tensor(this.values).equal(other).arraySync();
       break;
     }
     let bool_vals = utils.__map_int_to_bool(int_vals, 2);
@@ -1754,7 +1742,7 @@ export class DataFrame extends Ndframe {
 
         this_tensor = tensors[0].row_data_tensor; //tensorflow uses 1 for rows axis and 0 for column axis
         if (tensors[1].series) {
-          other_tensor = tensor(tensors[1].values, [
+          other_tensor = tf.tensor(tensors[1].values, [
             1,
             tensors[1].values.length
           ]);
@@ -1771,7 +1759,7 @@ export class DataFrame extends Ndframe {
 
         this_tensor = tensors[0].row_data_tensor;
         if (tensors[1].series) {
-          other_tensor = tensor(tensors[1].values, [
+          other_tensor = tf.tensor(tensors[1].values, [
             tensors[1].values.length,
             1
           ]);

danfojs-browser/package.json

@@ -14,8 +14,8 @@
 */
 
 
-import { tensor, round } from "@tensorflow/tfjs";
-import { variance, std } from 'mathjs';
+import * as tf from "@tensorflow/tfjs";
+import { variance, std, median, mode } from 'mathjs';
 import { Utils } from "./utils";
 import { Str } from "./strings";
 import NDframe from "./generic";
@@ -55,7 +55,7 @@ export class Series extends NDframe {
     * @returns {1D Tensor}
     */
   get tensor() {
-    return tensor(this.values).asType(this.dtypes[0]);
+    return tf.tensor(this.values).asType(this.dtypes[0]);
   }
 
 
@@ -95,30 +95,22 @@ export class Series extends NDframe {
   }
 
   /**
-    * Returns n number of random rows in a Series
-    * @param {rows} number of rows to return
-    * @returns {Series}
+   * Gets [num] number of random rows in a dataframe
+   * @param {num}  rows --> The number of rows to return
+   * @param {seed}  seed --> (Optional) An integer specifying the random seed that will be used to create the distribution.
+   * @returns {Promise} resolves to a Series object
     */
-  sample(num = 5) {
-    if (num > this.values.length || num < 1) {
-      let config = { columns: this.column_names };
-      return new Series(this.values, config);
-    } else {
-      let values = this.values;
-      let idx = this.index;
-      let new_values = [];
-      let new_idx = [];
-      let rand_nums = utils.__shuffle(num, idx);
-
-      rand_nums.forEach((i) => {
-        new_values.push(values[i]);
-        new_idx.push(idx[i]);
-      });
-      let config = { columns: this.column_names, index: new_idx };
-      let sf = new Series(new_values, config);
-      return sf;
-
+  async sample(num = 5, seed = 1) {
+    if (num > this.shape[0]) {
+      throw new Error("Sample size n cannot be bigger than size of dataset");
+    }
+    if (num < -1 || num == 0) {
+      throw new Error("Sample size cannot be less than -1 or 0");
     }
+    num = num === -1 ? this.shape[0] : num;
+    const shuffled_index = await tf.data.array(this.index).shuffle(num, seed).take(num).toArray();
+    const sf = this.iloc(shuffled_index);
+    return sf;
   }
 
   /**
@@ -250,7 +242,7 @@ export class Series extends NDframe {
   mean() {
     utils._throw_str_dtype_error(this, 'mean');
     let values = utils._remove_nans(this.values);
-    let mean = tensor(values).mean().arraySync();
+    let mean = tf.tensor(values).mean().arraySync();
     return mean;
   }
 
@@ -261,9 +253,9 @@ export class Series extends NDframe {
     */
   median() {
     utils._throw_str_dtype_error(this, 'median');
-    let values = this.values;
-    let median = utils.__median(values, true);
-    return median;
+    let values = utils._remove_nans(this.values);
+    let median_val = median(values);
+    return median_val;
   }
 
 
@@ -272,10 +264,10 @@ export class Series extends NDframe {
     * @returns {Number}
     */
   mode() {
-    utils._throw_str_dtype_error(this, 'mode');
-    let values = this.values;
-    let mode = utils.__mode(values);
-    return mode;
+    utils._throw_str_dtype_error(this, 'median');
+    let values = utils._remove_nans(this.values);
+    let modal_val = mode(values);
+    return modal_val;
   }
 
 
@@ -382,7 +374,7 @@ export class Series extends NDframe {
   round(dp) {
     if (utils.__is_undefined(dp)) {
       //use tensorflow round function to roound to the nearest whole number
-      let result = round(this.row_data_tensor).arraySync();
+      let result = tf.round(this.row_data_tensor).arraySync();
       return new Series(result, { columns: this.column_names, index: this.index });
 
     } else {