make_viewframe_profiling.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import bioframe as bf\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "chr1     11925630\n",
      "chr2    177637758\n",
      "chr3     62259946\n",
      "chr4    202237397\n",
      "chr5    200931227\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "unique_chrom_names = [f'chr{i}' for i in range(1, 10001)]\n",
    "unique_chrom_lengths = np.random.randint(1_000_000, 250_000_000, size=10000)  # Random lengths between 1 million and 250 million\n",
    "unique_chrom_series = pd.Series(data=unique_chrom_lengths, index=unique_chrom_names)\n",
    "print(unique_chrom_series.head())\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "chromosomes = bf.make_viewframe(unique_chrom_series)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_plot(lp):\n",
    "    function_info = next(iter(lp.get_stats().timings.keys()))\n",
    "    filename = function_info[0]\n",
    "    start_line = function_info[1]\n",
    "    with open(filename, 'r') as f:\n",
    "        source_lines = f.readlines()\n",
    "    function_timings = next(iter(lp.get_stats().timings.values()))\n",
    "    line_numbers = [line_no for line_no, _, _ in function_timings]\n",
    "    times_ms = [time_ns / 1_000_000 for _, _, time_ns in function_timings]  # Convert nanoseconds to milliseconds\n",
    "    line_descriptions = [source_lines[line_no - start_line].strip() for line_no, _, _ in function_timings]\n",
    "    combined = list(zip(line_numbers, times_ms, line_descriptions))\n",
    "    top_3_lines = sorted(combined, key=lambda x: x[1], reverse=True)[:3]\n",
    "    plt.figure(figsize=(12, 8))\n",
    "    bars = plt.bar(line_numbers, times_ms, color='skyblue')\n",
    "    plt.xticks(line_numbers, [f'Line {ln}' for ln in line_numbers], rotation='vertical')\n",
    "    plt.ylabel('Time (milliseconds)')\n",
    "    plt.xlabel('Source Code Line Number')\n",
    "    plt.title('Profiling Results: Time Spent per Line')\n",
    "    plt.tight_layout()  # Adjust layout to make room for the rotated x-axis labels\n",
    "    plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "bioframe-setup",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}