Merge pull request #19 from tkphd/script

Use argparse to add --output flag to plotting script

episodes/06-expansion.md

@@ -119,7 +119,7 @@ curl -O https://ocaisa.github.io/hpc-workflows/files/plot_terse_amdahl_results.p
 The script `plot_terse_amdahl_results.py` needs a command line that looks like:
 
 ```bash
-python plot_terse_amdahl_results.py <output jpeg filename> <1st input file> <2nd input file> ...
+python plot_terse_amdahl_results.py --output <output image filename> <1st input file> <2nd input file> ...
 ```
 
 Let's introduce that into our `generate_run_files` rule:
@@ -129,7 +129,7 @@ rule generate_run_files:
     output: "p_{parallel_proportion}_runs.txt"
     input:  expand("p_{{parallel_proportion}}/runs/amdahl_run_{count}.json", count=NTASK_SIZES)
     shell:
-        "python plot_terse_amdahl_results.py {output} {input}"
+        "python plot_terse_amdahl_results.py --output {output} {input}"
 ```
 
 ::: challenge
@@ -146,7 +146,7 @@ rule generate_run_files:
     envmodules:
       "matplotlib"
     shell:
-        "python plot_terse_amdahl_results.py {output} {input}"
+        "python plot_terse_amdahl_results.py --output {output} {input}"
 ```
 
 ::::::
@@ -188,6 +188,7 @@ snakemake --profile cluster_profile/ p_0.8_scalability.jpg
 :::
 
 ::: challenge
+
 ## Bonus round
 
 Create a final rule that can be called directly and generates a scaling plot for

episodes/files/plot_terse_amdahl_results.py

@@ -1,15 +1,34 @@
-import sys
+#!/usr/bin/env python3
+import argparse
 import json
+import matplotlib
 import matplotlib.pyplot as plt
 import numpy as np
 
-def process_files(file_list, output="plot.jpg"):
+matplotlib.use('AGG')
+
+description = """
+Plot results of an Amdahl scaling study,
+assuming the '--terse' output flag was used.
+"""
+
+def process_files(output, file_list):
     value_tuples=[]
     for filename in file_list:
       # Open the JSON file and load data
-      with open(filename, 'r') as file:
-        data = json.load(file)
-      value_tuples.append((data['nproc'], data['execution_time']))
+      try:
+          with open(filename, 'r') as file:
+              data = json.load(file)
+          value_tuples.append((data['nproc'], data['execution_time']))
+      except FileNotFoundError:
+          print(f"Error: File {filename} not found.")
+          return
+      except json.JSONDecodeError:
+          print(f"Error: File {filename} is not a valid JSON.")
+          return
+      except KeyError:
+          print(f"Error: Missing required data in file {filename}.")
+          return
 
     # Sort the tuples
     sorted_list = sorted(value_tuples)
@@ -22,9 +41,10 @@ def process_files(file_list, output="plot.jpg"):
 
     # Adding the y=1/x line
     x_line = np.linspace(1, max(x), 100)  # Create x values for the line
-    y_line = (y[0]/x[0]) / x_line  # Calculate corresponding (scaled) y values
+    y_line = (y[0] / x[0]) / x_line       # Calculate corresponding (scaled) y values
 
-    plt.plot(x_line, y_line, linestyle='--', color='red', label='Perfect scaling')
+    plt.plot(x_line, y_line, linestyle='--',
+             color='red', label='Perfect scaling')
 
     # Adding title and labels
     plt.title("Scaling plot")
@@ -34,16 +54,27 @@ def process_files(file_list, output="plot.jpg"):
     # Show the legend
     plt.legend()
 
-    # Save the plot to a JPEG file
-    plt.savefig(output, format='jpeg')
+    # Save the plot to the specified file
+    plt.savefig(output, dpi=400, bbox_inches="tight")
 
 if __name__ == "__main__":
-    # The first command-line argument is the script name itself, so we skip it
-    output = sys.argv[1]
-    filenames = sys.argv[2:]
+    parser = argparse.ArgumentParser(
+        description=description,
+        epilog="Brought to you by HPC Carpentry"
+    )
+
+    parser.add_argument(
+        "--output",
+        help="Image file to write (PNG or JPG)",
+        required=True
+    )
+
+    parser.add_argument(
+        "inputs",
+        help="Amdahl terse output files (JSON)",
+        nargs="+"
+    )
 
-    if filenames:
-        process_files(filenames, output=output)
-    else:
-        print("No files provided.")
+    args = parser.parse_args()
 
+    process_files(args.output, args.inputs)