From b75a427aad2d625c955ac96a1b1ec75baf637f82 Mon Sep 17 00:00:00 2001
From: Tim Diller <tim@dillerdigital.com>
Date: Fri, 15 May 2026 09:38:04 -0500
Subject: [PATCH] simplify the function to create particles

goal is to leave lots of room for student improvements
in class.

also, introduce missingness in the data
---
 particlecloud/util.py | 67 +++++++++++++++++++++----------------------
 1 file changed, 33 insertions(+), 34 deletions(-)

diff --git a/particlecloud/util.py b/particlecloud/util.py
index f590b06..54987ae 100644
--- a/particlecloud/util.py
+++ b/particlecloud/util.py
@@ -1,47 +1,46 @@
 import random
+import sys
 
-from particlecloud.stuff import Particle
+import numpy as np
 
 
-PARTICLE_FILE_COLUMN_NAMES = [
-    "number", "mass", "vx", "vy", "vz", "px", "py", "pz",
+FILE_COLUMN_NAMES = [
+    "n", "m", "v1", "v2", "v3", "p1", "p2", "p3",
 ]
 
-def make_particles(n=10):
-    particles = []
-    for i in range(n):
-        particles.append(
-            Particle(
-                mass=random.gauss(mu=3., sigma=0.5),
-                velocity=(
-                    random.gauss(mu=0., sigma=1.5),
-                    random.gauss(mu=0., sigma=1.5),
-                    random.gauss(mu=0., sigma=1.5),
-                ),
-                position=(
-                    random.gauss(mu=0., sigma=25),
-                    random.gauss(mu=0., sigma=25),
-                    random.gauss(mu=0., sigma=25),
+
+def write_data_file(filename, n=20, missing_values=False):
+    """Write a csv file with data
+    """
+
+    with open(filename, "w") as fp:
+        fp.write(", ".join(FILE_COLUMN_NAMES) + ",\n")
+        for i in range(n):
+            vals = []
+            vals.append(random.gauss(3., 0.5))
+            vals.extend(
+                (
+                    random.gauss(0., 25),
+                    random.gauss(0., 25),
+                    random.gauss(0., 25),
                 )
             )
-        )
-    return particles
-
-
-def write_particles_file(filename, n=10):
-    """Write a csv file with particle data
-    """
-    particles = make_particles(n=n)
-    with open(filename, "w") as fp:
-        fp.write(", ".join(PARTICLE_FILE_COLUMN_NAMES) + ",\n")
-        for i, p in enumerate(particles):
-            vals = []
-            vals.append(p.mass)
-            vals.extend(p.velocity)
-            vals.extend(p.position)
+            vals.extend(
+                (
+                    random.gauss(0., 1.5),
+                    random.gauss(0., 1.5),
+                    random.gauss(0., 1.5),
+                )
+            )
+            if missing_values:
+                if random.randint(0,10) < 1:
+                    idx = random.randint(1, len(vals))
+                    vals[idx] = np.nan
             line = f"{i}, " + ", ".join(f"{v:7.5f}" for v in vals) + ",\n"
             fp.write(line)
 
 
 if __name__ == '__main__':
-    write_particles_file("sample_data.csv")
+    missing_values = sys.argv[-1] == '-m'
+
+    write_data_file("sample_data.csv", n=20, missing_values=True)