Removed Dataset and uploaded code files

Data Science/Parkinsons Disease/Code/Merging Data.ipynb

@@ -0,0 +1,82 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "e1c31b44-419d-4547-9d26-fec1bceb737d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "4f5943d5-30b4-4623-820b-73b423c249e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##pip install openpyxl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "5c64e683-8a95-4f69-b0ff-a67d969e4e9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "All CSV files merged successfully into CSV/PD.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "# folder path containing the CSV files\n",
+    "folder_path = 'CSV/PD'\n",
+    "\n",
+    "# Initialize an empty DataFrame to store all the data\n",
+    "PD_subjects = pd.DataFrame()\n",
+    "\n",
+    "# Loop through all the CSV files in the folder\n",
+    "for filename in os.listdir(folder_path):\n",
+    "    if filename.endswith('.csv'):\n",
+    "        file_path = os.path.join(folder_path, filename)\n",
+    "        # Read the CSV file\n",
+    "        data = pd.read_csv(file_path)\n",
+    "        # Append the data to the merged DataFrame\n",
+    "        PD_subjects = pd.concat([PD_subjects, data], ignore_index=True)\n",
+    "\n",
+    "# Export the merged DataFrame to an Excel file\n",
+    "output_path = 'CSV/PD.csv'\n",
+    "PD_subjects.to_csv(output_path, index=False)\n",
+    "print(f\"All CSV files merged successfully into {output_path}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}

Data Science/Parkinsons Disease/Code/txt_to_csv.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "1ac3f519-e490-4269-8afd-6a7ea704ede6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "304ed7d1-9057-43e0-b8c2-babeb6e967bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ParserError",
+     "evalue": "Error tokenizing data. C error: Expected 26 fields in line 161, saw 30\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mParserError\u001b[0m                               Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[9], line 10\u001b[0m\n\u001b[0;32m      7\u001b[0m input_file_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(folder_path, txt_file)\n\u001b[0;32m      8\u001b[0m output_file_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(output_folder_path, txt_file\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.txt\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.csv\u001b[39m\u001b[38;5;124m'\u001b[39m))\n\u001b[1;32m---> 10\u001b[0m df \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[43minput_file_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdelimiter\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;130;43;01m\\t\u001b[39;49;00m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m \n\u001b[0;32m     11\u001b[0m df\u001b[38;5;241m.\u001b[39mto_csv(output_file_path, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m     12\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mConverted \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtxt_file\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutput_file_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1026\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   1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[0;32m   1014\u001b[0m     dialect,\n\u001b[0;32m   1015\u001b[0m     delimiter,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1022\u001b[0m     dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[0;32m   1023\u001b[0m )\n\u001b[0;32m   1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[1;32m-> 1026\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;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:626\u001b[0m, in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    623\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n\u001b[0;32m    625\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m parser:\n\u001b[1;32m--> 626\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnrows\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1923\u001b[0m, in \u001b[0;36mTextFileReader.read\u001b[1;34m(self, nrows)\u001b[0m\n\u001b[0;32m   1916\u001b[0m nrows \u001b[38;5;241m=\u001b[39m validate_integer(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnrows\u001b[39m\u001b[38;5;124m\"\u001b[39m, nrows)\n\u001b[0;32m   1917\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1918\u001b[0m     \u001b[38;5;66;03m# error: \"ParserBase\" has no attribute \"read\"\u001b[39;00m\n\u001b[0;32m   1919\u001b[0m     (\n\u001b[0;32m   1920\u001b[0m         index,\n\u001b[0;32m   1921\u001b[0m         columns,\n\u001b[0;32m   1922\u001b[0m         col_dict,\n\u001b[1;32m-> 1923\u001b[0m     ) \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[attr-defined]\u001b[39;49;00m\n\u001b[0;32m   1924\u001b[0m \u001b[43m        \u001b[49m\u001b[43mnrows\u001b[49m\n\u001b[0;32m   1925\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1926\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m   1927\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclose()\n",
+      "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\io\\parsers\\c_parser_wrapper.py:234\u001b[0m, in \u001b[0;36mCParserWrapper.read\u001b[1;34m(self, nrows)\u001b[0m\n\u001b[0;32m    232\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m    233\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlow_memory:\n\u001b[1;32m--> 234\u001b[0m         chunks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_reader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_low_memory\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnrows\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    235\u001b[0m         \u001b[38;5;66;03m# destructive to chunks\u001b[39;00m\n\u001b[0;32m    236\u001b[0m         data \u001b[38;5;241m=\u001b[39m _concatenate_chunks(chunks)\n",
+      "File \u001b[1;32mparsers.pyx:838\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader.read_low_memory\u001b[1;34m()\u001b[0m\n",
+      "File \u001b[1;32mparsers.pyx:905\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._read_rows\u001b[1;34m()\u001b[0m\n",
+      "File \u001b[1;32mparsers.pyx:874\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._tokenize_rows\u001b[1;34m()\u001b[0m\n",
+      "File \u001b[1;32mparsers.pyx:891\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._check_tokenize_status\u001b[1;34m()\u001b[0m\n",
+      "File \u001b[1;32mparsers.pyx:2061\u001b[0m, in \u001b[0;36mpandas._libs.parsers.raise_parser_error\u001b[1;34m()\u001b[0m\n",
+      "\u001b[1;31mParserError\u001b[0m: Error tokenizing data. C error: Expected 26 fields in line 161, saw 30\n"
+     ]
+    }
+   ],
+   "source": [
+    "folder_path = 'Dataset/'\n",
+    "output_folder_path = 'CSV files/'\n",
+    "\n",
+    "txt_files = [f for f in os.listdir(folder_path) if f.endswith('.txt')]\n",
+    "\n",
+    "for txt_file in txt_files:\n",
+    "    input_file_path = os.path.join(folder_path, txt_file)\n",
+    "    output_file_path = os.path.join(output_folder_path, txt_file.replace('.txt', '.csv'))\n",
+    "    \n",
+    "    df = pd.read_csv(input_file_path, delimiter=' ') \n",
+    "    df.to_csv(output_file_path, index=False)\n",
+    "    print(f\"Converted {txt_file} to {output_file_path}\")\n",
+    "\n",
+    "print(\"All files converted successfully!\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}

Data Science/Parkinsons Disease/Data Format.txt

@@ -0,0 +1,71 @@
+Data format:
+------------
+
+Each line contains 19 columns:
+
+Column      1:   Time (in seconds)
+Columns   2-9:   Vertical ground reaction force (VGRF, in Newton) on each of 8
+	  	  sensors located under the left foot
+Columns 10-17:   VGRF on each of the 8 sensors located under the right foot
+Column     18:   Total force under the left foot
+Column     19:   Total force under the right foot.
+
+When a person is comfortably standing with both legs parallel to each
+other, sensor locations inside the insole can be described (according
+to the Infotronic website; http://www.infotronic.nl/) as lying
+approximately at the following (X,Y) coordinates, assuming that the
+origin (0,0) is just between the legs and the person is facing towards
+the positive side of the Y axis:
+
+Sensor       X      Y
+----------------------------
+L1         -500   -800
+L2         -700   -400
+L3         -300   -400
+L4         -700      0
+L5         -300      0
+L6         -700    400
+L7         -300    400
+L8         -500    800
+
+R1          500   -800
+R2          700   -400
+R3          300   -400
+R4          700      0
+R5          300      0
+R6          700    400
+R7          300    400
+R8          500    800
+
+The X and Y numbers are in an arbitrary coordinate system reflecting
+the relative (arbitrarily scaled) positions of the sensors within each
+insole. During walking, the sensors inside each insole remain at the
+same relative position, but the two feet are no longer parallel to
+each other. Thus, this coordinate system enables a calculation of a
+proxy for the location of the center of pressure (COP) under each
+foot.
+
+
+Data file names:
+----------------
+These follow a common convention, e.g., GaCo01_02.txt  or  JuPt03_06.txt,
+where
+
+Ga, Ju or Si – indicate the study from which the data originated:
+    Ga - Galit Yogev et al (dual tasking in PD; Eur J Neuro, 2005)
+    Ju – Hausdorff et al (RAS in PD; Eur J Neuro, 2007)
+    Si - Silvi Frenkel-Toledo et al (Treadmill walking in PD; Mov Disorders,
+          2005)
+
+Co or Pt: Control subject or a PD Patient
+
+01: Subject number in the group
+
+A walk number of 10  (for the "Ga" study) indicates a dual-task walking,
+where the subject was engaged in serial-7 subtraction while walking.
+
+A walk number of 01 refers to a usual, normal walk. 
+
+.txt: file name extension
+
+The sampling rate was 100 Hz.