{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# XML cutter and midi formatter \n",
    "This script is prepared to parse a folder full of xml files, cut them to a certain length , *if desired* (according to a specific measure criteria) and output then a midi file with thiss new length.\n",
    "\n",
    "Afterwards, we are able to process these new midi files by using jSymbolic GUI if we want to include these features in our analyses. This notebook allso provides code for that purpose.\n",
    "\n",
    "To install `musif`:\n",
    "1. [Download](https://raw.githubusercontent.com/DIDONEproject/musif/main/docs/source/Cutter_and_midi_extractor.ipynb) this notebook.\n",
    "2. Start `jupyter` in your Anaconda environment.\n",
    "3. Open this script.\n",
    "4. Run the following cell by clicking on it and pressing Ctrl+Enter.\n",
    "\n",
    "https://musescore.org/es/download\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install musif"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import subprocess\n",
    "import sys\n",
    "from math import floor\n",
    "from os import path\n",
    "from pathlib import Path\n",
    "\n",
    "from music21.stream.base import Measure, Score\n",
    "from musif.common._utils import read_dicts_from_csv\n",
    "\n",
    "import musif.extract.constants as C\n",
    "from musif.extract.extract import parse_filename\n",
    "from musif.logs import perr, pinfo, pwarn\n",
    "\n",
    "sys.path.append(os.path.abspath('.'))\n",
    "from feature_extraction.custom_conf import CustomConf\n",
    "from musif.config import ExtractConfiguration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import glob\n",
    "\n",
    "\n",
    "class CustomConf(ExtractConfiguration):\n",
    "    def __init__(self, *args, **kwargs):\n",
    "        super().__init__(*args, **kwargs)\n",
    "        self._load_metadata()\n",
    "\n",
    "    def _load_metadata(self) -> None:\n",
    "        self.scores_metadata = {\n",
    "            path.basename(file): read_dicts_from_csv(file)\n",
    "            for file in glob(path.join(self.metadata_dir, \"*.csv\")) # type: ignore\n",
    "        }\n",
    "        if not self.scores_metadata:\n",
    "            print(\n",
    "                \"\\nMetadata could not be loaded properly!! Check metadata path in config file.\\n\"\n",
    "            )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define specific functions for our script"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def cut_by_measures_by_measure(cfg, data):\n",
    "    score: Score = data[C.DATA_SCORE]\n",
    "    last_measure = 1000000\n",
    "    for metadata in cfg.scores_metadata[last_measure]:\n",
    "        if metadata[\"FileName\"] == data[\"FileName\"]:\n",
    "            last_measure = floor(float(metadata.get(cfg.end_of_theme_a, last_measure)))\n",
    "            if last_measure == 0:\n",
    "                name = data['file'].name\n",
    "                pwarn(f'Last measure for {name} fil was found to be 0! Remember to update metadata before extraction ;) Setting last measure to the end of the score.\\n')\n",
    "                last_measure = 1000000\n",
    "            break\n",
    "\n",
    "    remove_everything_after_measure(score, last_measure)\n",
    "\n",
    "def remove_everything_after_measure(score, last_measure):\n",
    "    for part in score.parts:\n",
    "        read_measures = 0\n",
    "        elements_to_remove = []\n",
    "        for measure in part.getElementsByClass(Measure):\n",
    "            read_measures += 1\n",
    "            if read_measures > last_measure:\n",
    "                elements_to_remove.append(measure)\n",
    "        part.remove(targetOrList=elements_to_remove)\n",
    "\n",
    "def save_xml(data, new_filename):\n",
    "    new_filename = str(new_filename) + '.xml'\n",
    "    data[C.DATA_SCORE].write('musicxml', fp=f'{new_filename}')\n",
    "    \n",
    "def save_to_midi(filename):\n",
    "    filename = str(filename)\n",
    "    new_filename = filename + '.mid'\n",
    "    if path.exists(new_filename):\n",
    "            pinfo(f\"{filename} already exists as MIDI, skipping it!\")\n",
    "            return\n",
    "    cmd = [\"mscore\", \"-fo\", new_filename, filename + '.xml']\n",
    "    pinfo(f\"Converting {filename} to MIDI\")\n",
    "    try:\n",
    "        subprocess.run(\n",
    "            cmd,\n",
    "            stdout=subprocess.DEVNULL,\n",
    "            timeout=120,\n",
    "        )\n",
    "    except subprocess.TimeoutExpired:\n",
    "        pwarn(\n",
    "            f\"Continuing because time expired for file {filename}! Try running:\\n\"\n",
    "            + \"\".join(cmd)\n",
    "        ) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from musif.config import ExtractConfiguration\n",
    "\n",
    "custom_config = \"config.yml\"\n",
    "\n",
    "cfg = CustomConf(\n",
    "    None,\n",
    "    metadata_dir = \"your/metadata/dir\"\n",
    "    expand_repeats = False,\n",
    "    remove_unpitched_objects = True)\n",
    "data_path = 'data/xml/'\n",
    "data_path_cutted = Path('data/xml/cutted_themeA/')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for filename in sorted(Path(data_path).glob(f\"*.xml\")):\n",
    "        data = {}\n",
    "        new_filename = data_path_cutted / Path(filename.stem + '_cutted')\n",
    "        if path.exists(str(new_filename) + '.xml'):\n",
    "            pinfo(f\"{filename} already exists as cutted xml, skipping it!\")\n",
    "            continue\n",
    "        score = parse_filename(\n",
    "            filename,\n",
    "            None,\n",
    "            expand_repeats=cfg.expand_repeats,\n",
    "            export_dfs_to = None,\n",
    "            remove_unpitched_objects=cfg.remove_unpitched_objects,\n",
    "        )\n",
    "        data[C.DATA_SCORE] = score\n",
    "        data[C.DATA_FILE] = filename\n",
    "        \n",
    "        cut_by_measures_by_measure(cfg, data)\n",
    "        data_path_cutted.mkdir(exist_ok=True)\n",
    "        try:        \n",
    "            save_xml(data, new_filename)\n",
    "        except Exception as e:\n",
    "            perr(f'There was an error saving score {filename} to xml: {e}. Skipping it!')\n",
    "            continue\n",
    "        try:        \n",
    "            save_to_midi(new_filename)\n",
    "        except Exception as e:\n",
    "            perr(f'There was an error saving score {filename} to midi: {e}. Skipping it!')\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "--- In this part, we are free to use jSymbolic GUI to extract features from our recent created midi files. Afterwards, just run the following cell in order to join jSymbolic data to musif's extraction---\n",
    "\n",
    "Download: https://sourceforge.net/projects/jmir/files/jSymbolic/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Merging musif data with jSymbolic extracted csv\n",
    "Now, if we want to merge jSymbolic data with our extracted musif df:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "ename": "PermissionError",
     "evalue": "[Errno 13] Permission denied: '.'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mPermissionError\u001b[0m                           Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[2], line 4\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mpd\u001b[39;00m\n\u001b[0;32m      3\u001b[0m path_to_musif_df \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m----> 4\u001b[0m df_musif \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_to_musif_df\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlow_memory\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[0;32m      6\u001b[0m path_to_jsymbollic_extracted_csv \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mextracted_feature_values.csv\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m      7\u001b[0m df_jSymbolic \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(path_to_jsymbollic_extracted_csv, low_memory\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n",
      "File \u001b[1;32mc:\\Anaconda3\\envs\\musicai\\lib\\site-packages\\pandas\\io\\parsers\\readers.py:948\u001b[0m, in \u001b[0;36mread_csv\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[0;32m    935\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[0;32m    936\u001b[0m     dialect,\n\u001b[0;32m    937\u001b[0m     delimiter,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    944\u001b[0m     dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[0;32m    945\u001b[0m )\n\u001b[0;32m    946\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[1;32m--> 948\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Anaconda3\\envs\\musicai\\lib\\site-packages\\pandas\\io\\parsers\\readers.py:611\u001b[0m, in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    608\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m    610\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[1;32m--> 611\u001b[0m parser \u001b[38;5;241m=\u001b[39m TextFileReader(filepath_or_buffer, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwds)\n\u001b[0;32m    613\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[0;32m    614\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
      "File \u001b[1;32mc:\\Anaconda3\\envs\\musicai\\lib\\site-packages\\pandas\\io\\parsers\\readers.py:1448\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[1;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[0;32m   1445\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m   1447\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1448\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Anaconda3\\envs\\musicai\\lib\\site-packages\\pandas\\io\\parsers\\readers.py:1705\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[1;34m(self, f, engine)\u001b[0m\n\u001b[0;32m   1703\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[0;32m   1704\u001b[0m         mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m-> 1705\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1706\u001b[0m \u001b[43m    \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1707\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1708\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1709\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1710\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1711\u001b[0m \u001b[43m    \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1712\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1713\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1714\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1715\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1716\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
      "File \u001b[1;32mc:\\Anaconda3\\envs\\musicai\\lib\\site-packages\\pandas\\io\\common.py:863\u001b[0m, in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    858\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m    859\u001b[0m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[0;32m    860\u001b[0m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[0;32m    861\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[0;32m    862\u001b[0m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[1;32m--> 863\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[0;32m    864\u001b[0m \u001b[43m            \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    865\u001b[0m \u001b[43m            \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    866\u001b[0m \u001b[43m            \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    867\u001b[0m \u001b[43m            \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    868\u001b[0m \u001b[43m            \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    869\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    870\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    871\u001b[0m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[0;32m    872\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
      "\u001b[1;31mPermissionError\u001b[0m: [Errno 13] Permission denied: '.'"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "path_to_musif_df = '.'\n",
    "df_musif = pd.read_csv(path_to_musif_df, low_memory=False)\n",
    "\n",
    "path_to_jsymbollic_extracted_csv = 'extracted_feature_values.csv'\n",
    "df_jSymbolic = pd.read_csv(path_to_jsymbollic_extracted_csv, low_memory=False)\n",
    "df_jSymbolic.rename(columns={'Unnamed: 0': 'FileName'})\n",
    "# -- here you must process the FileName column so both values in musif's df and in j_Symbolic match\n",
    "df_jSymbolic.columns = ['js_' + i for i in df_jSymbolic.columns] \n",
    "df_jSymbolic.rename(columns={'js_Unnamed: 0': 'FileName'}, inplace=True)\n",
    "df_jSymbolic['FileName'] = [i.replace('/Users/carlosvaquero/Downloads/midi_partial/', '').replace('.mid', '.xml') for i in df_jSymbolic['FileName']]\n",
    "\n",
    "# \n",
    "\n",
    "df_total = pd.merge(df_musif, df_jSymbolic, on='FileName')\n",
    "\n",
    "df_total.to_csv('total.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "musicai",
   "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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}