Getting Started
Installation guides for Node and Browser based environments, including a quick 10 minute walk through of danfo.js
There are two ways to get danfo.js. We built an optimized and fast version for node.js and its available under the danfojs-node namespace. To install it via npm, you can do the following:
npm install danfojs-node
You can also install and use it in the browsers by using the CDN below:
<script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script>
To play with Danfo.js in a Notebook-like environment without doing an local installation, use Dnotebooks here
This is a short introduction to danfo.js, and its flow is adapted from the official 10 minutes to Pandas
We will show you how to use danfo.js in both browser environment and Node.js environment. Most functions except plotting which require a DOM works the same way in both environments.
Node
Browser
Node
const dfd = require("danfojs-node")
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script></head><body><script>//danfo is exposed on dfd namespaces = new dfd.Series([1,2,3,4,5])</script></body></html>
Creating a Series by passing a list of values, letting danfo.js create a default integer index:
Node
Browser
Node
s = new dfd.Series([1, 3, 5, undefined, 6, 8])s.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>s = new dfd.Series([1, 3, 5, undefined, 6, 8])s.print()</script></body></html>
//output╔═══╤══════════════════════╗║ │ 0 ║╟───┼──────────────────────╢║ 0 │ 1 ║╟───┼──────────────────────╢║ 1 │ 3 ║╟───┼──────────────────────╢║ 2 │ 5 ║╟───┼──────────────────────╢║ 3 │ NaN ║╟───┼──────────────────────╢║ 4 │ 6 ║╟───┼──────────────────────╢║ 5 │ 8 ║╚═══╧══════════════════════╝
Creating a Series from a tensor
Node
Browser
Node
const dfd = require("danfojs-node")const tf = require("@tensorflow/tfjs-node")let tensor_arr = tf.tensor([12,34,56,2])let s = new dfd.Series(tensor_arr)s.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script><title>Document</title></head><body><script>const tf = dfd.tf //get tensorflow lib from danfolet tensor_arr = tf.tensor([12,34,56,2])let s = new dfd.Series(tensor_arr)s.print()</script></body></html>
╔═══╤══════════════════════╗║ │ 0 ║╟───┼──────────────────────╢║ 0 │ 12 ║╟───┼──────────────────────╢║ 1 │ 34 ║╟───┼──────────────────────╢║ 2 │ 56 ║╟───┼──────────────────────╢║ 3 │ 2 ║╚═══╧══════════════════════╝
Creating a DataFrame by passing a JSON object:
Node
Browser
Node
const dfd = require("danfojs-node")json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df.print()</script></body></html>
Creating a DataFrame from a 2D tensor
Node
Browser
Node
const dfd = require("danfojs-node")const tf = require("@tensorflow/tfjs-node")let tensor_arr = tf.tensor2d([[12, 34, 2.2, 2], [30, 30, 2.1, 7]])let df = new dfd.DataFrame(tensor_arr, {columns: ["A", "B", "C", "D"]})df.print()df.ctypes.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df.print()</script></body></html>
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C │ D ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ 12 │ 34 │ 2.20000004768... │ 2 ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ 30 │ 30 │ 2.09999990463... │ 7 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝╔═══╤══════════════════════╗║ │ 0 ║╟───┼──────────────────────╢║ A │ int32 ║╟───┼──────────────────────╢║ B │ int32 ║╟───┼──────────────────────╢║ C │ float32 ║╟───┼──────────────────────╢║ D │ int32 ║╚═══╧══════════════════════╝
Creating a DataFrame by passing a dictionary of objects with the same length
Node
Browser
Node
const dfd = require("danfojs-node")dates = new dfd.date_range({ start: '2017-01-01', end: "2020-01-01", period: 4, freq: "Y" })console.log(dates);obj_data = {'A': dates,'B': ["bval1", "bval2", "bval3", "bval4"],'C': [10, 20, 30, 40],'D': [1.2, 3.45, 60.1, 45],'E': ["test", "train", "test", "train"]}df = new dfd.DataFrame(obj_data)df.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>dates = new dfd.date_range({ start: '2017-01-01', end: "2020-01-01", period: 4, freq: "Y" })console.log(dates);obj_data = {'A': dates,'B': ["bval1", "bval2", "bval3", "bval4"],'C': [10, 20, 30, 40],'D': [1.2, 3.45, 60.1, 45],'E': ["test", "train", "test", "train"]}df = new dfd.DataFrame(obj_data)df.print()</script></body></html>
//output in console╔═══╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C │ D │ E ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ 1/1/2017, 1:0... │ bval1 │ 10 │ 1.2 │ test ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ 1/1/2018, 1:0... │ bval2 │ 20 │ 3.45 │ train ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ 1/1/2019, 1:0... │ bval3 │ 30 │ 60.1 │ test ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ 1/1/2020, 1:0... │ bval4 │ 40 │ 45 │ train ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
The columns of the resulting DataFrame have different dtypes.
df.ctypes.print()
//output╔═══╤══════════════════════╗║ │ 0 ║╟───┼──────────────────────╢║ A │ string ║╟───┼──────────────────────╢║ B │ string ║╟───┼──────────────────────╢║ C │ int32 ║╟───┼──────────────────────╢║ D │ float32 ║╟───┼──────────────────────╢║ E │ string ║╚═══╧══════════════════════╝
Creating a DataFrame by passing an array of arrays. Index and column labels are automatically generated for you.
Node
Browser
Node
const dfd = require("danfojs-node")arr_data = [["bval1", 10, 1.2, "test"],["bval2", 20, 3.45, "train"],["bval3", 30, 60.1, "train"],["bval4", 35, 3.2, "test"]]df = new dfd.DataFrame(arr_data)df.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>arr_data = [["bval1", 10, 1.2, "test"],["bval2", 20, 3.45, "train"],["bval3", 30, 60.1, "train"],["bval4", 35, 3.2, "test"]]df = new dfd.DataFrame(arr_data)df.print()</script></body></html>
//output in console╔═══╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ 0 │ 1 │ 2 │ 3 ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ bval1 │ 10 │ 1.2 │ test ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ bval2 │ 20 │ 3.45 │ train ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ bval3 │ 30 │ 60.1 │ train ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ bval4 │ 35 │ 3.2 │ test ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
Here is how to view the top and bottom rows of the frame above:
df.head(2).print()df.tail(2).print()
//output from head╔═══╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ 0 │ 1 │ 2 │ 3 ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ bval1 │ 10 │ 1.2 │ test ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ bval2 │ 20 │ 3.45 │ train ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝//output from tail╔═══╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ 0 │ 1 │ 2 │ 3 ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ bval3 │ 30 │ 60.1 │ train ║╟───┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ bval4 │ 35 │ 3.2 │ test ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
Display the index, columns:
JavaScript
Browser
JavaScript
const dfd = require("danfojs-node")dates = new dfd.date_range({ start: '2017-01-01', end: "2020-01-01", period: 4, freq: "Y" })obj_data = {'A': dates,'B': ["bval1", "bval2", "bval3", "bval4"],'C': [10, 20, 30, 40],'D': [1.2, 3.45, 60.1, 45],'E': ["test", "train", "test", "train"]}df = new dfd.DataFrame(obj_data)console.log(df.index);console.log(df.columns);
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>dates = new dfd.date_range({ start: '2017-01-01', end: "2020-01-01", period: 4, freq: "Y" })obj_data = {'A': dates,'B': ["bval1", "bval2", "bval3", "bval4"],'C': [10, 20, 30, 40],'D': [1.2, 3.45, 60.1, 45],'E': ["test", "train", "test", "train"]}df = new dfd.DataFrame(obj_data)console.log(df.index);console.log(df.columns);</script></body></html>
//output[ 0, 1, 2, 3 ][ 'A', 'B', 'C', 'D', 'E' ]
DataFrame.tensor returns a Tensorflow tensor representation of the underlying data. Note that Tensorflow tensors have one dtype for the entire array, while danfo DataFrames have one dtype per column.
For df, our DataFrame of all floating-point values, DataFrame.tensoris fast and doesn’t require copying data.
Node
Browser
Node
const dfd = require("danfojs-node")json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)console.log(df.tensor);//ordf.tensor.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)console.log(df.tensor);//ordf.tensor.print()</script></body></html>
//outputTensor {kept: false,isDisposedInternal: false,shape: [ 4, 4 ],dtype: 'float32',size: 16,strides: [ 4 ],dataId: {},id: 0,rankType: '2'}Tensor[[0.4612, 4.2828302, -1.5089999, -1.1352 ],[0.5112, -0.22863 , -3.39059 , 1.1632 ],[0.6911, -0.82863 , -1.5059 , 2.1352 ],[0.4692, -1.28863 , 4.5058999 , 4.1631999]]
Note
DataFrame.tensor does not include the index or column labels in the output.
describe() shows a quick statistic summary of your data:
Node
Browser
Node
const dfd = require("danfojs-node")json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df.describe().print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df.describe().print()</script></body></html>
//output in console╔════════╤═══════════════════╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C │ D ║╟────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ count │ 4 │ 4 │ 4 │ 4 ║╟────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ mean │ 0.533175 │ 0.484235 │ -0.474898 │ 1.5816 ║╟────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ std │ 0.107543 │ 2.569317 │ 3.437147 │ 2.200545 ║╟────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ min │ 0.4612 │ -1.28863 │ -3.39059 │ -1.1352 ║╟────────┼───────────────────┼───────────────────┼───────────────────┼───────────────────╢║ median │ 0.4902 │ -0.52863 │ -1.50745 │ 1.6492 ║╚════════╧═══════════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
Sorting by values (Defaults to ascending):
Node
Browser
Node
const dfd = require("danfojs")let data = {"A": [-20, 30, 47.3, NaN],"B": [34, -4, 5, 6] ,"C": [20, 2, 3, 30] }let df = new dfd.DataFrame(data)df.sort_values({by: "C", inplace: true})df.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>let data = {"A": [-20, 30, 47.3, NaN],"B": [34, -4, 5, 6] ,"C": [20, 2, 3, 30] }let df = new dfd.DataFrame(data)df.sort_values({by: "C", inplace: true})df.print()</script></body></html>
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ 30 │ -4 │ 2 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ 47.3 │ 5 │ 3 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ -20 │ 34 │ 20 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
Selecting a single column, which yields a Series, equivalent to df.A:
Node
Browser
Node
const dfd = require("danfojs-node")json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df['A'].print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>json_data = [{ A: 0.4612, B: 4.28283, C: -1.509, D: -1.1352 },{ A: 0.5112, B: -0.22863, C: -3.39059, D: 1.1632 },{ A: 0.6911, B: -0.82863, C: -1.5059, D: 2.1352 },{ A: 0.4692, B: -1.28863, C: 4.5059, D: 4.1632 }]df = new dfd.DataFrame(json_data)df['A'].print()</script></body></html>
//output╔═══╤══════════════════════╗║ │ A ║╟───┼──────────────────────╢║ 0 │ 0.4612 ║╟───┼──────────────────────╢║ 1 │ 0.5112 ║╟───┼──────────────────────╢║ 2 │ 0.6911 ║╟───┼──────────────────────╢║ 3 │ 0.4692 ║╚═══╧══════════════════════╝
For getting a cross-section using a label:
const dfd = require("danfojs")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data, {index: ["a", "b", "c", "d"]})df.print()let sub_df = df.loc({rows: ["a", "c"]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ a │ Apples │ 21 │ 200 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ b │ Mango │ 5 │ 300 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ c │ Banana │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ d │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝Shape: (2,3)╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ a │ Apples │ 21 │ 200 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ c │ Banana │ 30 │ 40 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
Selecting on a multi-axis by label:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10],"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)df.print()let sub_df = df.loc({ rows: [0,1], columns: ["Name", "Price"] })sub_df.print()
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ Apples │ 21 │ 200 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ Mango │ 5 │ 300 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ Banana │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝Shape: (2,2)╔═══╤═══════════════════╤═══════════════════╗║ │ Name │ Price ║╟───┼───────────────────┼───────────────────╢║ 0 │ Apples │ 200 ║╟───┼───────────────────┼───────────────────╢║ 1 │ Mango │ 300 ║╚═══╧═══════════════════╧═══════════════════╝
Showing label slicing, both endpoints are included:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10],"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)df.print()let sub_df = df.loc({ rows: ["0:2"], columns: ["Name", "Price"] })sub_df.print()
//before slicing╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ Apples │ 21 │ 200 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ Mango │ 5 │ 300 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ Banana │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝//after slicingShape: (3,2)╔═══╤═══════════════════╤═══════════════════╗║ │ Name │ Price ║╟───┼───────────────────┼───────────────────╢║ 0 │ Apples │ 200 ║╟───┼───────────────────┼───────────────────╢║ 1 │ Mango │ 300 ║╟───┼───────────────────┼───────────────────╢║ 2 │ Banana │ 40 ║╚═══╧═══════════════════╧═══════════════════╝
Select via the position of the passed integers:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)let sub_df = df.iloc({rows: [1,3]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ Mango │ 5 │ 300 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
By integer slices:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)let sub_df = df.iloc({rows: ["1:3"]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ Mango │ 5 │ 300 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ Banana │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
By lists of integer position locations:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)let sub_df = df.iloc({rows: [1,3], columns: [0,2]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╗║ │ Name │ Price ║╟───┼───────────────────┼───────────────────╢║ 1 │ Mango │ 300 ║╟───┼───────────────────┼───────────────────╢║ 3 │ Pear │ 250 ║╚═══╧═══════════════════╧═══════════════════╝
For slicing rows explicitly:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)let sub_df = df.iloc({rows: ["2:3"], columns: [":"]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ Name │ Count │ Price ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ Banana │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Pear │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
For slicing columns explicitly:
const dfd = require("danfojs-node")let data = { "Name": ["Apples", "Mango", "Banana", "Pear"] ,"Count": [21, 5, 30, 10] ,"Price": [200, 300, 40, 250] }let df = new dfd.DataFrame(data)let sub_df = df.iloc({rows: [":"], columns: ["1:2"]})sub_df.print()
╔═══╤═══════════════════╤═══════════════════╗║ │ Count │ Price ║╟───┼───────────────────┼───────────────────╢║ 0 │ 21 │ 200 ║╟───┼───────────────────┼───────────────────╢║ 1 │ 5 │ 300 ║╟───┼───────────────────┼───────────────────╢║ 2 │ 30 │ 40 ║╟───┼───────────────────┼───────────────────╢║ 3 │ 10 │ 250 ║╚═══╧═══════════════════╧═══════════════════╝
Using a single column’s values to select data.
Node
Browser
Node
const dfd = require("danfojs-node")let data = [[1, 2, 3], [4, 5, 6], [20, 30, 40], [39, 89, 78]]let cols = ["A", "B", "C"]let df = new dfd.DataFrame(data, { columns: cols })df.print() //before querylet query_df = df.query({ "column": "B", "is": ">", "to": 5 })query_df.print() //after query
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>let data = [[1, 2, 3], [4, 5, 6], [20, 30, 40], [39, 89, 78]]let cols = ["A", "B", "C"]let df = new dfd.DataFrame(data, { columns: cols })df.print() //before querylet query_df = df.query({ "column": "B", "is": ">", "to": 5 })query_df.print() //after query</script></body></html>
//before query╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ 1 │ 2 │ 3 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ 4 │ 5 │ 6 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ 20 │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ 39 │ 89 │ 78 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝//after query╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ 20 │ 30 │ 40 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ 39 │ 89 │ 78 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
Selecting values from a DataFrame works on string columns:
let data = [{"A": ["Ng", "Yu", "Mo", "Ng"]},{"B": [34, 4, 5, 6]},{"C": [20, 20, 30, 40]}]let df = new dfd.DataFrame(data)df.print()let query_df = df.query({ column: "A", is: "==", to: "Ng"})query_df.print() //after query
╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ Ng │ 34 │ 20 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 1 │ Yu │ 4 │ 20 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 2 │ Mo │ 5 │ 30 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Ng │ 6 │ 40 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝//after query╔═══╤═══════════════════╤═══════════════════╤═══════════════════╗║ │ A │ B │ C ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 0 │ Ng │ 34 │ 20 ║╟───┼───────────────────┼───────────────────┼───────────────────╢║ 3 │ Ng │ 6 │ 40 ║╚═══╧═══════════════════╧═══════════════════╧═══════════════════╝
Setting a new column automatically aligns the data by the indexes.
Node
Browser
Node
const dfd = require("danfojs-node")let data = { "A": [30, 1, 2, 3] ,"B": [34, 4, 5, 6] ,"C": [20, 20, 30, 40] }let df = new dfd.DataFrame(data)df.print()let new_col = [1, 2, 3, 4]df.addColumn({ "column": "D", "value": new_col }); //happens inplacedf.print()
Browser
<!DOCTYPE html><html lang="en"><head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><!--danfojs CDN --><script src="https://cdn.jsdelivr.net/npm/[email protected]/lib/bundle.min.js"></script> <title>Document</title></head><body><script>let data = { "A": [30, 1, 2, 3] ,"B": [34, 4, 5, 6] ,"C": [20, 20, 30, 40] }let df = new dfd.DataFrame(data)df.print()let new_col = [1, 2, 3, 4]df.addColumn({ "column": "D", "value": new_col });