adding working polars command-line tool

Author: noahgift

README.md

@@ -990,6 +990,14 @@ pub async fn complete_prompt(prompt: &str) -> Result<String, Box<dyn std::error:
 
 ```
 
+### Command-line Data Science with Rust (Action Items)
+
+
+1. go into `dscli`
+2. Figure the way to make Polars work with `linfa`
+3. How can I make a kmeans cluster using Polars
+
+
 ### Containerized Actix Continuous Delivery to AWS App Runner
 
 1. cd into `webdocker`

dscli/Cargo.toml

@@ -0,0 +1,10 @@
+[package]
+name = "dscli"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+clap = {version="4.0.32", features=["derive"]}
+polars = "0.26.1"

dscli/Makefile

@@ -0,0 +1,13 @@
+format:
+	cargo fmt --quiet
+
+lint:
+	cargo clippy --quiet
+
+test:
+	cargo test --quiet
+
+run:
+	cargo run 
+
+all: format lint test run

dscli/src/data/global-life-expt-2022.csv

@@ -0,0 +1,21 @@
+/*
+A library that provides introspects global life expectancy data using Polars
+*/
+
+use polars::prelude::*;
+pub const CSV_FILE: &str = "src/data/global-life-expt-2022.csv";
+
+//read in a csv file
+pub fn read_csv(path: &str) -> DataFrame {
+    CsvReader::from_path(path).unwrap().finish().unwrap()
+}
+
+//print "n" rows of a dataframe
+pub fn print_df(df: &DataFrame, n: usize) {
+    println!("{:?}", df.head(Some(n)));
+}
+
+//do kmeans clustering of 2018, 2019, 2020 in the dataframe
+//returns a dataframe with the cluster column added
+//TBD for next time
+//pub fn cluster(df: &DataFrame) -> DataFrame {

dscli/src/lib.rs

@@ -0,0 +1,39 @@
+/* Life-expectancy CLI that uses Polars and Clap
+*/
+
+use clap::Parser;
+use dscli::CSV_FILE;
+
+#[derive(Parser)]
+//add extended help
+#[clap(
+    version = "1.0",
+    author = "Noah Gift",
+    about = "A data science CLI that uses Polars and Clap",
+    after_help = "Example: cargo run -- print --rows 3"
+)]
+struct Cli {
+    #[clap(subcommand)]
+    command: Option<Commands>,
+}
+
+#[derive(Parser)]
+enum Commands {
+    Print {
+        #[clap(long, default_value = CSV_FILE)]
+        path: String,
+        #[clap(long, default_value = "10")]
+        rows: usize,
+    },
+}
+
+fn main() {
+    let args = Cli::parse();
+    match args.command {
+        Some(Commands::Print { path, rows }) => {
+            let df = dscli::read_csv(&path);
+            dscli::print_df(&df, rows);
+        }
+        None => println!("No command given"),
+    }
+}