node-pandas 1.0.4 → 2.0.0

package/README.md

@@ -11,10 +11,12 @@ An [npm package](https://www.npmjs.com/package/node-pandas) that incorporates mi
 > For now, you can 
 >
 > + create Series(using 1D array), DataFrame(using 2D array or file `readCsv()`)
+> + access Series object using exactly an array like syntax (indexing, looping etc.)
 > + view columns, index
 > + save DataFrame in a CSV file `toCsv()`
 > + access elements using indices/column names
 > + view contents in pretty tabular form on console
+> + access DataFrame's columns using column names
 
 ## Installation
 
@@ -41,6 +43,12 @@ An [npm package](https://www.npmjs.com/package/node-pandas) that incorporates mi
 
 4.  [Example 4 - Accessing columns (Retrieving columns using column name)](#df-ex4) - `df.fullName -> ["R A", "B R", "P K"]`
 
+5.  [Example 5 - Selecting specific columns using select()](#df-ex5)
+
+6.  [Example 6 - Filtering DataFrame rows using filter()](#df-ex6)
+
+7.  [Example 7 - Grouping and aggregating data using groupBy()](#df-ex7)
+
 <hr>
 
 ## Getting started
@@ -65,7 +73,7 @@ NodeSeries [
   -3,
   0,
   5,
-  _data: [ 1, 9, 2, 6, 7, -8, 4, -3, 0, 5 ] ]
+]
 > 
 > s.show
 ┌─────────┬────────┐
@@ -111,21 +119,18 @@ undefined
 ...     ['Wes McKinney', 3, 'Pandas'],
 ...     ['Ken Thompson', 1, 'B language']
 ... ], columns)
-NodeDataFrame {
+NodeDataFrame [
+  [ 'Guido Van Rossum', 6, 'Python' ],
+  [ 'Ryan Dahl', 5, 'Node.js' ],
+  [ 'Anders Hezlsberg', 7, 'TypeScript' ],
+  [ 'Wes McKinney', 3, 'Pandas' ],
+  [ 'Ken Thompson', 1, 'B language' ],
   columns: [ 'full_name', 'user_id', 'technology' ],
   index: [ 0, 1, 2, 3, 4 ],
-  _data:
-   [ { full_name: 'Guido Van Rossum',
-       user_id: 6,
-       technology: 'Python' },
-     { full_name: 'Ryan Dahl', user_id: 5, technology: 'Node.js' },
-     { full_name: 'Anders Hezlsberg',
-       user_id: 7,
-       technology: 'TypeScript' },
-     { full_name: 'Wes McKinney', user_id: 3, technology: 'Pandas' },
-     { full_name: 'Ken Thompson',
-       user_id: 1,
-       technology: 'B language' } ] }
+  rows: 5,
+  cols: 3,
+  out: true
+]
 > 
 > df.show
 ┌─────────┬────────────────────┬─────────┬──────────────┐
@@ -181,37 +186,52 @@ Now have a look the below statements executed on Node REPL.
 undefined
 > 
 > df = pd.readCsv("/Users/hygull/Projects/NodeJS/node-pandas/docs/csvs/devs.csv")
-NodeDataFrame {
+NodeDataFrame [
+  {
+    fullName: 'Ken Thompson',
+    Profession: 'C developer',
+    Language: 'C',
+    DevId: 1122
+  },
+  {
+    fullName: 'Ron Wilson',
+    Profession: 'Ruby developer',
+    Language: 'Ruby',
+    DevId: 4433
+  },
+  {
+    fullName: 'Jeff Thomas',
+    Profession: 'Java developer',
+    Language: 'Java',
+    DevId: 8899
+  },
+  {
+    fullName: 'Rishikesh Agrawani',
+    Profession: 'Python developer',
+    Language: 'Python',
+    DevId: 6677
+  },
+  {
+    fullName: 'Kylie Dwine',
+    Profession: 'C++',
+    Language: 'C++ Developer',
+    DevId: 11
+  },
+  {
+    fullName: 'Briella Brown',
+    Profession: 'JavaScirpt developer',
+    Language: 'JavaScript',
+    DevId: 8844
+  },
   columns: [ 'fullName', 'Profession', 'Language', 'DevId' ],
-  index: [ '0', '1', '2', '3', '4', '5' ],
-  _data:
-   [ { fullName: 'Ken Thompson',
-       Profession: 'C developer',
-       Language: 'C',
-       DevId: 1122 },
-     { fullName: 'Ron Wilson',
-       Profession: 'Ruby developer',
-       Language: 'Ruby',
-       DevId: 4433 },
-     { fullName: 'Jeff Thomas',
-       Profession: 'Java developer',
-       Language: 'Java',
-       DevId: 8899 },
-     { fullName: 'Rishikesh Agrawani',
-       Profession: 'Python developer',
-       Language: 'Python',
-       DevId: 6677 },
-     { fullName: 'Kylie Dwine',
-       Profession: 'C++',
-       Language: 'C++ Developer',
-       DevId: 11 },
-     { fullName: 'Briella Brown',
-       Profession: 'JavaScript developer',
-       Language: 'JavaScript',
-       DevId: 8844 } ] }
+  index: [ 0, 1, 2, 3, 4, 5 ],
+  rows: 6,
+  cols: 4,
+  out: true
+]
 > 
 > df.index
-[ '0', '1', '2', '3', '4', '5' ]
+[ 0, 1, 2, 3, 4, 5 ]
 > 
 > df.columns
 [ 'fullName', 'Profession', 'Language', 'DevId' ]
@@ -253,59 +273,48 @@ undefined
 > 
 > df = pd.readCsv("./docs/csvs/devs.csv")
 NodeDataFrame [
-  { fullName: 'Ken Thompson',
+  {
+    fullName: 'Ken Thompson',
     Profession: 'C developer',
     Language: 'C',
-    DevId: 1122 },
-  { fullName: 'Ron Wilson',
+    DevId: 1122
+  },
+  {
+    fullName: 'Ron Wilson',
     Profession: 'Ruby developer',
     Language: 'Ruby',
-    DevId: 4433 },
-  { fullName: 'Jeff Thomas',
+    DevId: 4433
+  },
+  {
+    fullName: 'Jeff Thomas',
     Profession: 'Java developer',
     Language: 'Java',
-    DevId: 8899 },
-  { fullName: 'Rishikesh Agrawani',
+    DevId: 8899
+  },
+  {
+    fullName: 'Rishikesh Agrawani',
     Profession: 'Python developer',
     Language: 'Python',
-    DevId: 6677 },
-  { fullName: 'Kylie Dwine',
+    DevId: 6677
+  },
+  {
+    fullName: 'Kylie Dwine',
     Profession: 'C++',
     Language: 'C++ Developer',
-    DevId: 11 },
-  { fullName: 'Briella Brown',
-    Profession: 'JavaScript developer',
+    DevId: 11
+  },
+  {
+    fullName: 'Briella Brown',
+    Profession: 'JavaScirpt developer',
     Language: 'JavaScript',
-    DevId: 8844 },
+    DevId: 8844
+  },
   columns: [ 'fullName', 'Profession', 'Language', 'DevId' ],
-  index: [ '0', '1', '2', '3', '4', '5' ],
-  _data: [ { fullName: 'Ken Thompson',
-      Profession: 'C developer',
-      Language: 'C',
-      DevId: 1122 },
-    { fullName: 'Ron Wilson',
-      Profession: 'Ruby developer',
-      Language: 'Ruby',
-      DevId: 4433 },
-    { fullName: 'Jeff Thomas',
-      Profession: 'Java developer',
-      Language: 'Java',
-      DevId: 8899 },
-    { fullName: 'Rishikesh Agrawani',
-      Profession: 'Python developer',
-      Language: 'Python',
-      DevId: 6677 },
-    { fullName: 'Kylie Dwine',
-      Profession: 'C++',
-      Language: 'C++ Developer',
-      DevId: 11 },
-    { fullName: 'Briella Brown',
-      Profession: 'JavaScript developer',
-      Language: 'JavaScript',
-      DevId: 8844 } ],
+  index: [ 0, 1, 2, 3, 4, 5 ],
   rows: 6,
   cols: 4,
-  out: true ]
+  out: true
+]
 > 
 > df.cols
 4
@@ -314,7 +323,7 @@ NodeDataFrame [
 > df.columns
 [ 'fullName', 'Profession', 'Language', 'DevId' ]
 > df.index
-[ '0', '1', '2', '3', '4', '5' ]
+[ 0, 1, 2, 3, 4, 5 ]
 > 
 > df.toCsv("/Users/hygull/Desktop/newDevs.csv")
 undefined
@@ -361,38 +370,300 @@ df.show // View DataFrame in tabular form
 └─────────┴──────────────────────┴────────────────────────┴─────────────────┴───────┘
 */
 
-console.log(df['fullName']) // Access Column name fullname
+console.log(df['fullName'])
 /*
-    [
-        'Ken Thompson',
-        'Ron Wilson',
-        'Jeff Thomas',
-        'Rishikesh Agrawani',
-        'Kylie Dwine',
-        'Briella Brown'
+    NodeSeries [
+      'Ken Thompson',
+      'Ron Wilson',
+      'Jeff Thomas',
+      'Rishikesh Agrawani',
+      'Kylie Dwine',
+      'Briella Brown'
     ]
 */
 
-console.log(df.Language) // df['Language']
+console.log(df.DevId)
+/* 
+    NodeSeries [ 1122, 4433, 8899, 6677, 11, 8844 ]
+*/
+
+let languages = df.Language
+console.log(languages) 
 /*
-    [ 'C', 'Ruby', 'Java', 'Python', 'C++ Developer', 'JavaScript' ]
+    NodeSeries [
+      'C',
+      'Ruby',
+      'Java',
+      'Python',
+      'C++ Developer',
+      'JavaScript'
+    ]
 */
 
-console.log(df.Profession) 
+console.log(languages[0], '&', languages[1]) // C & Ruby
+
+
+let professions = df.Profession
+console.log(professions) 
 /*
-    [
-        'C developer',
-        'Ruby developer',
-        'Java developer',
-        'Python developer',
-        'C++',
-        'JavaScirpt developer'
+    NodeSeries [
+      'C developer',
+      'Ruby developer',
+      'Java developer',
+      'Python developer',
+      'C++',
+      'JavaScirpt developer'
     ]
 */
 
-console.log(df.DevId)
-/* 
-    [ 1122, 4433, 8899, 6677, 11, 8844 ]
+// Iterate like arrays
+for(let profession of professions) {
+    console.log(profession)
+}
+/*
+    C developer
+    Ruby developer
+    Java developer
+    Python developer
+    C++
+    JavaScirpt developer
+*/
+```
+
+<hr>
+
+<h3 id='df-ex5'><code>Example 5 - Selecting specific columns using select()</code></h3>
+
+> **Note:** The `select()` method returns a new DataFrame containing only the specified columns.
+
+```javascript
+const pd = require("node-pandas")
+
+// Create a DataFrame with employee data
+const df = pd.DataFrame([
+    ['Rishikesh Agrawani', 32, 'Engineering'],
+    ['Hemkesh Agrawani', 30, 'Marketing'],
+    ['Malinikesh Agrawani', 28, 'Sales']
+], ['name', 'age', 'department'])
+
+df.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┐
+│ (index) │        name          │ age │  department  │
+├─────────┼──────────────────────┼─────┼──────────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│
+│    1    │  'Hemkesh Agrawani'  │ 30  │  'Marketing' │
+│    2    │ 'Malinikesh Agrawani'│ 28  │   'Sales'    │
+└─────────┴──────────────────────┴─────┴──────────────┘
+*/
+
+// Select a single column
+const nameOnly = df.select(['name'])
+nameOnly.show
+/*
+┌─────────┬──────────────────────┐
+│ (index) │        name          │
+├─────────┼──────────────────────┤
+│    0    │ 'Rishikesh Agrawani' │
+│    1    │  'Hemkesh Agrawani'  │
+│    2    │ 'Malinikesh Agrawani'│
+└─────────┴──────────────────────┘
+*/
+
+// Select multiple columns
+const nameAndAge = df.select(['name', 'age'])
+nameAndAge.show
+/*
+┌─────────┬──────────────────────┬─────┐
+│ (index) │        name          │ age │
+├─────────┼──────────────────────┼─────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │
+│    1    │  'Hemkesh Agrawani'  │ 30  │
+│    2    │ 'Malinikesh Agrawani'│ 28  │
+└─────────┴──────────────────────┴─────┘
+*/
+
+// Original DataFrame remains unchanged
+console.log(df.columns) // ['name', 'age', 'department']
+```
+
+<hr>
+
+<h3 id='df-ex6'><code>Example 6 - Filtering DataFrame rows using filter()</code></h3>
+
+> **Note:** The `filter()` method returns a new DataFrame containing only rows that match the condition. Multiple filters can be chained together.
+
+```javascript
+const pd = require("node-pandas")
+
+// Create a DataFrame with employee data
+const df = pd.DataFrame([
+    ['Rishikesh Agrawani', 32, 'Engineering'],
+    ['Hemkesh Agrawani', 30, 'Marketing'],
+    ['Malinikesh Agrawani', 28, 'Sales']
+], ['name', 'age', 'department'])
+
+df.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┐
+│ (index) │        name          │ age │  department  │
+├─────────┼──────────────────────┼─────┼──────────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│
+│    1    │  'Hemkesh Agrawani'  │ 30  │  'Marketing' │
+│    2    │ 'Malinikesh Agrawani'│ 28  │   'Sales'    │
+└─────────┴──────────────────────┴─────┴──────────────┘
+*/
+
+// Filter rows where age is greater than 28
+const over28 = df.filter(row => row.age > 28)
+over28.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┐
+│ (index) │        name          │ age │  department  │
+├─────────┼──────────────────────┼─────┼──────────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│
+│    1    │  'Hemkesh Agrawani'  │ 30  │  'Marketing' │
+└─────────┴──────────────────────┴─────┴──────────────┘
+*/
+
+// Filter rows where department is 'Engineering'
+const engineering = df.filter(row => row.department === 'Engineering')
+engineering.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┐
+│ (index) │        name          │ age │  department  │
+├─────────┼──────────────────────┼─────┼──────────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│
+└─────────┴──────────────────────┴─────┴──────────────┘
+*/
+
+// Chain multiple filters together
+const result = df
+    .filter(row => row.age > 28)
+    .filter(row => row.department !== 'Sales')
+result.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┐
+│ (index) │        name          │ age │  department  │
+├─────────┼──────────────────────┼─────┼──────────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│
+│    1    │  'Hemkesh Agrawani'  │ 30  │  'Marketing' │
+└─────────┴──────────────────────┴─────┴──────────────┘
+*/
+```
+
+<hr>
+
+<h3 id='df-ex7'><code>Example 7 - Grouping and aggregating data using groupBy()</code></h3>
+
+> **Note:** The `groupBy()` method groups rows by one or more columns and allows aggregation using methods like `mean()`, `sum()`, `count()`, `min()`, and `max()`.
+
+```javascript
+const pd = require("node-pandas")
+
+// Create a DataFrame with employee data including departments
+const df = pd.DataFrame([
+    ['Rishikesh Agrawani', 32, 'Engineering', 95000],
+    ['Hemkesh Agrawani', 30, 'Marketing', 75000],
+    ['Malinikesh Agrawani', 28, 'Sales', 65000],
+    ['Alice Johnson', 29, 'Engineering', 92000],
+    ['Bob Smith', 31, 'Marketing', 78000],
+    ['Carol White', 27, 'Sales', 62000]
+], ['name', 'age', 'department', 'salary'])
+
+df.show
+/*
+┌─────────┬──────────────────────┬─────┬──────────────┬────────┐
+│ (index) │        name          │ age │  department  │ salary │
+├─────────┼──────────────────────┼─────┼──────────────┼────────┤
+│    0    │ 'Rishikesh Agrawani' │ 32  │ 'Engineering'│ 95000  │
+│    1    │  'Hemkesh Agrawani'  │ 30  │  'Marketing' │ 75000  │
+│    2    │ 'Malinikesh Agrawani'│ 28  │   'Sales'    │ 65000  │
+│    3    │   'Alice Johnson'    │ 29  │ 'Engineering'│ 92000  │
+│    4    │    'Bob Smith'       │ 31  │  'Marketing' │ 78000  │
+│    5    │    'Carol White'     │ 27  │   'Sales'    │ 62000  │
+└─────────┴──────────────────────┴─────┴──────────────┴────────┘
+*/
+
+// Single-column grouping: Group by department and calculate mean salary
+const avgSalaryByDept = df.groupBy('department').mean('salary')
+avgSalaryByDept.show
+/*
+┌─────────┬──────────────┬──────────────┐
+│ (index) │  department  │ salary_mean  │
+├─────────┼──────────────┼──────────────┤
+│    0    │ 'Engineering'│   93500      │
+│    1    │  'Marketing' │   76500      │
+│    2    │   'Sales'    │   63500      │
+└─────────┴──────────────┴──────────────┘
+*/
+
+// Group by department and calculate sum of salaries
+const totalSalaryByDept = df.groupBy('department').sum('salary')
+totalSalaryByDept.show
+/*
+┌─────────┬──────────────┬──────────────┐
+│ (index) │  department  │ salary_sum   │
+├─────────┼──────────────┼──────────────┤
+│    0    │ 'Engineering'│   187000     │
+│    1    │  'Marketing' │   153000     │
+│    2    │   'Sales'    │   127000     │
+└─────────┴──────────────┴──────────────┘
+*/
+
+// Group by department and count employees
+const countByDept = df.groupBy('department').count()
+countByDept.show
+/*
+┌─────────┬──────────────┬───────┐
+│ (index) │  department  │ count │
+├─────────┼──────────────┼───────┤
+│    0    │ 'Engineering'│   2   │
+│    1    │  'Marketing' │   2   │
+│    2    │   'Sales'    │   2   │
+└─────────┴──────────────┴───────┘
+*/
+
+// Group by department and find minimum age
+const minAgeByDept = df.groupBy('department').min('age')
+minAgeByDept.show
+/*
+┌─────────┬──────────────┬──────────┐
+│ (index) │  department  │ age_min  │
+├─────────┼──────────────┼──────────┤
+│    0    │ 'Engineering'│   29     │
+│    1    │  'Marketing' │   30     │
+│    2    │   'Sales'    │   27     │
+└─────────┴──────────────┴──────────┘
+*/
+
+// Group by department and find maximum age
+const maxAgeByDept = df.groupBy('department').max('age')
+maxAgeByDept.show
+/*
+┌─────────┬──────────────┬──────────┐
+│ (index) │  department  │ age_max  │
+├─────────┼──────────────┼──────────┤
+│    0    │ 'Engineering'│   32     │
+│    1    │  'Marketing' │   31     │
+│    2    │   'Sales'    │   28     │
+└─────────┴──────────────┴──────────┘
+*/
+
+// Multi-column grouping: Group by department and age range
+const groupedByDeptAndAge = df.groupBy(['department', 'age']).count()
+groupedByDeptAndAge.show
+/*
+┌─────────┬──────────────┬─────┬───────┐
+│ (index) │  department  │ age │ count │
+├─────────┼──────────────┼─────┼───────┤
+│    0    │ 'Engineering'│ 29  │   1   │
+│    1    │ 'Engineering'│ 32  │   1   │
+│    2    │  'Marketing' │ 30  │   1   │
+│    3    │  'Marketing' │ 31  │   1   │
+│    4    │   'Sales'    │ 27  │   1   │
+│    5    │   'Sales'    │ 28  │   1   │
+└─────────┴──────────────┴─────┴───────┘
 */
 ```
 
@@ -426,4 +697,5 @@ console.log(df.DevId)
 
 + [JavaScript getter](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Functions/set)
 
++ [JavaScript (enumerable, writable, configurable)](https://hashnode.com/post/what-are-enumerable-properties-in-javascript-ciljnbtqa000exx53n5nbkykx)