Added phoneme frequency percentage in plot

dataset_analysis/PhonemeCoverage.ipynb

@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -94,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -120,17 +120,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      " 76%|███████▋  | 84/110 [00:05<00:01, 15.92it/s][WARNING] fount 1 utterances containing language switches on lines 1\n",
+      " 76%|███████▋  | 84/110 [00:06<00:01, 13.58it/s][WARNING] fount 1 utterances containing language switches on lines 1\n",
       "[WARNING] extra phones may appear in the \"de\" phoneset\n",
       "[WARNING] language switch flags have been kept (applying \"keep-flags\" policy)\n",
-      "100%|██████████| 110/110 [00:07<00:00, 15.16it/s]\n"
+      "100%|██████████| 110/110 [00:07<00:00, 13.77it/s]\n"
      ]
     }
    ],
@@ -152,14 +152,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Dataset contains 39 different ipa phonemes.\n"
+      "Dataset contains 39 different ipa phonemes.\n",
+      "Dataset consists of 2620 phonemes\n"
      ]
     }
    ],
@@ -175,12 +176,15 @@
     "sorted_d.pop(' ', None)\n",
     "sorted_d.pop('ˈ', None)\n",
     "\n",
-    "print(\"Dataset contains \" + str(len(sorted_d)) + \" different ipa phonemes.\")"
+    "phonemesSum = len(phonemeString.replace(\" \",\"\"))\n",
+    "\n",
+    "print(\"Dataset contains \" + str(len(sorted_d)) + \" different ipa phonemes.\")\n",
+    "print(\"Dataset consists of \" + str(phonemesSum) + \" phonemes\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -206,12 +210,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAC2AAAAtHCAYAAADZF5EIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAgAElEQVR4nOydd7gdVbXAfysJAULvPQTpVXoRhQCKgDRB0Yciodh7BxSN2FFBfaCgiBGUJ1UERFTKBZHepdfQSyihhhSy3h9rLpm7zz7nzMyZc2bOvev3ffMlM/fsMrPb2muvvbaoKo7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOE57RlWdAcdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxnH7BDbAdx3Ecx3Ecx3Ecx3Ecx3Ecx3Ecx3Ecx3Ecx3Ecx3Ecx3Ey4gbYjuM4juM4juM4juM4juM4juM4juM4juM4juM4juM4juM4GXEDbMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxHMdxnIy4AbbjOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOI7jOE5G3ADbcRzHcRzHcRzHcRzHcRzHcRzHcRzHcRzHcRzHcRzHcRwnI26A7TiO4xRGRCaJiAbXhKrz5TiO4zj9jogsJiKfEZEzReQ+EXleRN4Ixtxbqs7nSEFEBoJvP1B1nhxnJCIiEyPzj4lV56sKROSjwXf4cdV5akcd+tKRXoci7z656jw5Ti8QkalB3Z9SdZ4cx3EGKTo++7heL+og6zq9RUSmBGU+teo8Ob3D+2DHcZzhgYgsJyIvp/rz+0Vk/qrz5ThOf+EG2I7jOI7jOI7jODVCRD4BPAr8L/A+YA1gCXz+5jiO4wAisiTww9Sj54AfVJQdx3Ecx3Ecx3Ecx3Ecx3GcvkNVnwaOST1aHfhqRdlxHKdP8QV8x3GcYYCITIjstm51zRCRp0TkHhE5X0Qmi8hOIuLjguM4juNUiIgcCfwaWKTqvDiO4zi15QfAUqn776nqi1VlxnEcJw8i8pVAR3Vu1XlynOFKk9MLB6+5IrJaSekc2UoXXUYajlMEEbk9qI97V50nx3Ecx3Ecp3b8FHgmdX+4iIyvKjOO4/QfbmjnOI4zMlkAWA5YC9gd+DZwMfCAiHxZRMZUmTnHcRzHGYmIyGbA5MifFHgEuA24NXXd07PM9RlNDA0mVJ0vp3f4UcDOcEVE1gUOTT16Gjihouz0BBGZGrTnKVXnyXGcjtgruG8wwE4cBbgB5whGRAaCOjBQdZ6GIQIc1HEkIqXE4zhlIyKrA+unHs0A/llRdhzHcRzHcWpH2eso/aqTV9WXgWNTj8YBR1WUHcdx+hA3wHYcx3HSTMB2+F0jImtWnBfHcRzHGWl8icY52g+BpVV1VVV9q6punLo+UEEeHcdxnGr5LjA6dX+sqr5eVWYcx3HyICLLAG9LPXoDuKCi7DiOAweWcCLiDkApnrQdp2TCDT//UtXXKsmJ4ziO4ziOU3d+BaRPGPxw4gjDcRynLW6A7TiOM3x5laFeMtPXfcALLcJuBlwsIit3O5OO4ziO40Cy6L1H8PhMVT1CVZ+vIk+O4zhOvRCRTYF9Uo9ewhYHHMdx+oU9GLomcZWqPltVZhzHYTywU4dxHFxGRhynC+wd3P+1klw4juM4juM4tUdVX2LoKYOjge9UlB3HcfqMMVVnwHEcx+kaN6jqxFY/SI7h+yDwBWDp4M/jgTOBbbqSO8dxHMdx0qwLLBI8O72KjDiO4zi15euApO5PTY7I7AvazU8dxxkRhN5I3RjOcXrPC8ASqfuDgX8ViUhEFmPo5jCA54Eli2XNccpBRJZm6IkLc4HzK8qO4zjDEFWV9r9yHMdx+owTga8xT/+6r4isrqoPVJgnx3H6APeA7TiOM4JR1QdU9fvAhsB1kZ9sLSLv73G2HMdxHGckMj7y7J6e58JxHMepJSKyKrBv8PjEKvLiOI5TBBEZB7wreHxuFXlxnBHOacH93iKyRPSX7dkfWDB1fxdwc8G4HKdMdse8Fg5ylapOqyozjuM4juM4Tv1R1YeAi1OPRmGODB3HcVriBtiO4zgOqvoUppR8KvLnj/c4O47jOI4zElks8uzVnufCcRzHqSufYagRyfWq+t+qMuM4jlOAnRlqqHmHe5FynEq4Brgzdb8AZkhdhIOD+98XjMdxymbv4N5PXHAcx3Ecx3Gy8Lvg/iARWbSSnDiO0ze4AbbjOI4DQOIB4ujIn96eeClyHMdxHKd7LBB5pj3PheM4jlM7RGQMcEDw+Mwq8uI4jtMBewX3bgznONURGkoflDcCEdkA2Dz1aA5wSieZcpwyEJEFaTxxwcccx3Ecx3EcJwsXADNS9wsBfmK84zgtGVN1BhzHcZxacQ5wTPBsfmB94PqikYrIfMCWwHrA0sBsYBpwL3Cdqr5RNO4WaS6epLk8sAzmLe6Z5Lq+V0cOJosRmyT5GA08CzwKXKmqXfFsmrz7FsBy2LvPn6Q7+O5PdiPdIA/jsUWYVbGJycvA/dhxjy/kiGdd7PutAIzF3uEB7PvN6UK+BdgQWB37dkthHminAVOx71d6umUgImOxb74ylu8lgJnAS9g3uzPxdl9GWssmaS2bXG9gZfM0cI2qvlRGOnVCRJYDNsXqxbLYRsZpzHvn53uQh/FYe1gVWAT77k8Dp6vqaxnCLwusg9XvxZnXNp8HHsf641e6lPf5gG2SvK+QPH4WuAO4oRvjQJN8rA2sjZXh0lgbmYb1y9eq6uu9yEcVJJuptgJWxOrxAti7PwPcrKqP9SgfawJvxfqqhYFZwFOqOiwW6kVkGWBr4C3Y+72IfeNrVfXhLqW5FiZjLcu8cesZrF5fp6qzu5FukIdxmNy1JrAkpmt4EbhMVe9oE3Z0Em5DrG4uislMr2Fj2KPAQ8ADqjq3W+/QCXWQH0RkFDZObYjVBcX62Qcx+WtWN9MvSvLtNsPqwIrAfNi4dDdWf3vSLydj7EZY+S2DjbHPAk8AV3drfMzBuzHZPs1ZZUWeGKlsi/XNy2Pv/xTwX+BWVR1xG4L6tU2VQdIuN8baxLJYn/wk8Aj27jMrzF5TRtp8KNCzLJU8fhq4SVVvzRHPopj+YG1sjvAq1v7/U6Z8mIz3uwePa2cMJyKrYN9jVWAcNiY9jX2Pp7uQ3qAMsSY2/izJPPnxIaw8uy7/pPRIg3PFUdi7/72dDJvUxXWBDbD8L4r1mTOA6Vjf8aCqTu1W/jslqZ+bYuW+DNZ/vITJcvdh86WujoUV6E5PBX7IvDXCzURkI1W9LUcchwT3F6rq01athxd1kPd7RTKebgGshI1xiwIvYO96p6re2SJ4WXkoPL9MeBfWhw9yl6reVyAfS2Hz+5Wwcp+B9Wk3JsfTd50qy6MmawxvweaLq2CnaEzDdJhX90IXWxW91l+KyBKYznhNbAxcGNPJDMpB1/Xqe5fQ/mNx9lS+K4Nez0frorvvlDroNuogMySy7caYXLkctg7wKnCbql5SMM5lsbWF1bC1qdeAh7H6mHmeLSKrMW/eviBWzx4GLi+zb0vqwlpY37Y0Nn7OwcbQZ4FbejU/Gcn6pW7Qi/mnqr4qIhcB7009/giNnrEdx3Hmoap++eWXX371+QVMwITL9DVQMK5XInHt1uS3kyK/nZD6+/LAzzGBN/zd4PUCcCywVAnfYQzwUeDf2ESqWZpzMYPyLwHzl/S9J6X+Pj/wRWyxrFkeZmIG7+uWVAcWTN7nqjbvrsDtwNeBhQqkM9CqngH7Jd+2WdqvY95wVm6RxvzA57BFrlb15gfAuJK+3+ZJvp5q8+1eAs4Gtuxmm86R79GYN8SLMAVKq7wrZsz0c2CTgnXsq8ANSRtqlsZs4ArsGNrRGeNeLgmXjufcEr7PCZH8rZ8j/BLAt4Gb2rzzG0m9/zgwX4F8Tg3im5L623zAJ4HbWqQ/oUm8iwAfAv6AKbHa1Y85yXscCowtqY6Ox5QSz7dI9zngJ8AyqXCTsr5nhjysBfw68p3Da0bSlnbuUfudkqFMWl1TMqbzfuCfWP/bbmyYDCxa8H3C+Can/rYQcBhm/BRNvybfdEi+g7gHgt8NBH+fmHznN1rEfQfWJqWEd10R688favM+LwF/ASYWTGdyq7LCFmfOaVG/ot8zCbsZcBKt5cT09SLwL+ALNJEjaN/Os1yZvxU9kB+SutU0j5iS+Ttt8vAK5uVwlTLaWkntdSHge7Qen15J6shqWb9HzjysBPwUuKtN+c3CZJsPUEL7LZjXU4M83VFSvOsDZxCfAw5ejwNHkpo70KZvaJHeQBBuoMnvJpTQlqN5qrpN0ULuyxlP0TII32Vy6m+LJPE+2eLdp2Pj7YQq2kLkfYbFfChnHV0ROB4bW5rl4R7ggDbpbIS1/1Yy4lXAtiWV1XZB3I8T9Kk09hFFrklF2h62sHp1i3jnAtcCu5b0PdbCxrhW7U2xhfk/FamzSTpTgvimBn/fFZOvmumRot8zCbsD8GfM+CJL2UwDzsf0dks3ibPT8ldy9E/AO7ETJV7IUA5/ANYpUAaTWuWRLutOm6T/4eRv5wbPf54j3rFJmabD75X87eIwzYxxTg3CTcmanyCeyUXSbxJXT/SFkfgmdzNcJB4B3od5+2slFyrWfx9HC91u0bKhg/llEM/JQbgf5szn9sDfadRVpq/bgANJjWVklHXrUh5N0q58jSF5/4NorQudlZTR9mW8dwffa0qQr6kdxNUz/SVmjPle4ERMbmyVnmJy0O3Al4GFC6Y5OYw3+Hvu9h/5VlOCv3dVvsuSx0iYiZFwE1N/76mOhxro7ktqiz3VbTTJQx10hOOxMaFZeQ5E4pwS/GZq8Pd3AZfSXOc9B9tY23StG9vc+RHgljb1+gQK2gpgY8e2wI+xdt1qDB+8HsXk8PEF02xXHrXV2UbKvcg1ORXLine truncated
+      "image/png": "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 truncated
       "text/plain": [
        "<Figure size 3600x3600 with 1 Axes>"
       ]
@@ -242,7 +246,8 @@
     "plt.xlabel('occurrences', fontsize=50)\n",
     "\n",
     "for i, v in enumerate(y):\n",
-    "    plt.text(v + 2, i + .2, str(v), fontsize=20)\n",
+    "    #plt.text(v + 2, i + .2, str(v), fontsize=20)\n",
+    "    plt.text(v + 2, i + .2, str(v) + \" (\" + str(round(100/phonemesSum * v,2)) + \"%)\", fontsize=20)\n",
     "    \n",
     "plt.show()"
    ]