readme and test

Cargo.lock

@@ -31,17 +31,6 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
-[[package]]
-name = "getrandom"
-version = "0.2.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "190092ea657667030ac6a35e305e62fc4dd69fd98ac98631e5d3a2b1575a12b5"
-dependencies = [
- "cfg-if",
- "libc",
- "wasi",
-]
-
 [[package]]
 name = "heck"
 version = "0.4.1"
@@ -85,17 +74,6 @@ dependencies = [
  "scopeguard",
 ]
 
-[[package]]
-name = "lyagushka"
-version = "0.1.0"
-dependencies = [
- "atty",
- "pyo3",
- "rand",
- "serde",
- "serde_json",
-]
-
 [[package]]
 name = "memoffset"
 version = "0.9.0"
@@ -134,12 +112,6 @@ dependencies = [
  "windows-targets",
 ]
 
-[[package]]
-name = "ppv-lite86"
-version = "0.2.17"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
-
 [[package]]
 name = "proc-macro2"
 version = "1.0.78"
@@ -149,6 +121,16 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "pyagushka"
+version = "0.1.0"
+dependencies = [
+ "atty",
+ "pyo3",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "pyo3"
 version = "0.20.2"
@@ -219,36 +201,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rand"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
-dependencies = [
- "libc",
- "rand_chacha",
- "rand_core",
-]
-
-[[package]]
-name = "rand_chacha"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
-dependencies = [
- "ppv-lite86",
- "rand_core",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
-dependencies = [
- "getrandom",
-]
-
 [[package]]
 name = "redox_syscall"
 version = "0.4.1"
@@ -336,12 +288,6 @@ version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
 
-[[package]]
-name = "wasi"
-version = "0.11.0+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
-
 [[package]]
 name = "winapi"
 version = "0.3.9"

Cargo.toml

@@ -1,15 +1,18 @@
 [package]
-name = "lyagushka"
+name = "pyagushka"
 version = "0.1.0"
 edition = "2021"
 
 [lib]
-name = "lyagushka"
+name = "pyagushka"
 crate-type = ["cdylib"]
 
 [dependencies]
 atty = "0.2.14"
 pyo3 = "0.20.2"
-rand = "0.8.5"
 serde = { version = "1.0.196", features = ["derive"] }
 serde_json = "1.0.113"
+
+[features]
+extension-module = ["pyo3/extension-module"]
+default = ["extension-module"]

readme.md

@@ -0,0 +1,61 @@
+# lyagushka
+
+(Russian лягушка: frog)
+
+Cluster and Gap Analysis Tool inspired by Fatum Project's 'Zhaba' algorithm (Russian 'жаба': toad) that finds attractor clusters in lists of integers.
+
+This Rust command-line tool analyzes a dataset of integers to identify clusters of closely grouped points and significant gaps between these clusters. It calculates z-scores for each cluster or gap to measure their statistical significance relative to the dataset's mean distance. The analysis results, including clusters, gaps, and their z-scores, are output as a JSON string.
+
+## Features
+
+- **Cluster Identification**: Identifies groups of points that are closely spaced together based on a customizable threshold.
+- **Gap Detection**: Detects significant gaps between clusters, providing insights into the dataset's distribution.
+- **Z-Score Calculation**: Calculates z-scores for both clusters and gaps, offering a statistical measure of their deviation from the mean distance.
+- **Flexible Input**: Accepts input data either from a file specified as a command-line argument or piped directly into stdin.
+- **JSON Output**: Outputs the analysis results in a readable JSON format, making it easy to interpret or use in further processing.
+
+## Usage
+
+### From a File
+
+To analyze a dataset from a file, provide the filename as an argument along with two additional parameters: the factor for adjusting clustering and gap detection thresholds, and the minimum cluster size.
+
+```sh
+cargo run -- filename.txt 0.5 2
+```
+
+### From Stdin
+
+Alternatively, you can pipe a list of integers into the tool, followed by the factor and minimum cluster size.
+
+```sh
+echo "1\n2\n10\n20" | cargo run -- 0.5 2
+```
+
+#### Parameters
+
+*  `filename.txt` (optional): A file containing a newline-separated list of integers to analyze. If not provided, the program expects input from stdin.
+*  `factor`: A floating-point value used to fine-tune the sensitivity of cluster and gap detection. Lower values result in tighter clusters and wider gaps, while higher values do the opposite.
+*  `min_cluster_size`: An integer specifying the minimum number of contiguous points required to be considered a cluster.
+
+### Output
+
+The tool outputs a JSON string that includes details about the identified clusters and gaps, along with their respective z-scores. Here's an example of the JSON output format:
+
+```json
+
+[
+  {
+    "span_length": 1.0,
+    "num_elements": 2,
+    "centroid": 1.5,
+    "z_score": -1.23
+  },
+  {
+    "span_length": 8.0,
+    "num_elements": 0,
+    "centroid": 6.0,
+    "z_score": 2.45
+  }
+]
+```

src/lib.rs

@@ -167,7 +167,7 @@ fn lyagushka(_py: Python, int_list: &PyList, factor: f32, min_cluster_size: usiz
 
 
 #[pymodule]
-fn lyagushka_module(_py: Python, m: &PyModule) -> PyResult<()> {
+fn pyagushka(_py: Python, m: &PyModule) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(lyagushka, m)?)?;
     Ok(())
 }

test.py

@@ -0,0 +1,13 @@
+from pyagushka import lyagushka
+from randonautentropy import rndo
+import json
+
+random_data = []
+
+with open('random_values.txt', 'r') as file:
+    for line in file:
+        random_data.append(int(line.strip()))
+
+anomalies = json.loads(lyagushka(random_data, 1.0, 5))
+
+print(anomalies)