k-means clustering

Project/Tools/kmeans_on_Emojis.ipynb

@@ -0,0 +1,206 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import numpy as np\n",
+    "from sklearn.cluster import KMeans\n",
+    "sys.path.append(\"..\")\n",
+    "\n",
+    "from Tools.Emoji_Distance import sentiment_vector_to_emoji\n",
+    "from Tools.Emoji_Distance import emoji_to_sentiment_vector\n",
+    "from Tools.Emoji_Distance import dataframe_to_dictionary\n",
+    "\n",
+    "def emoji2sent(emoji_arr):\n",
+    "    return np.array([emoji_to_sentiment_vector(e) for e in emoji_arr])\n",
+    "\n",
+    "def sent2emoji(sent_arr, custom_target_emojis=None):\n",
+    "    return [sentiment_vector_to_emoji(s, custom_target_emojis=custom_target_emojis) for s in sent_arr]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data , data_only_emoticons, list_sentiment_vectors , list_emojis , list_sentiment_emoticon_vectors , list_emoticon_emojis = dataframe_to_dictionary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0.46813021, 0.24716181, 0.28470797],\n",
+       "       [0.72967448, 0.05173769, 0.21858783],\n",
+       "       [0.34310532, 0.43648208, 0.2204126 ],\n",
+       "       [0.75466009, 0.0529057 , 0.19243421],\n",
+       "       [0.70401758, 0.05932203, 0.23666039],\n",
+       "       [0.57697579, 0.12699863, 0.29602558],\n",
+       "       [0.22289823, 0.59126106, 0.18584071],\n",
+       "       [0.49837557, 0.0805718 , 0.42105263],\n",
+       "       [0.44415243, 0.11169514, 0.44415243],\n",
+       "       [0.5634451 , 0.09927679, 0.33727811]])"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "array_sentiment_vectors = np.array(list_sentiment_emoticon_vectors)\n",
+    "array_sentiment_vectors[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "kmeans = KMeans(n_clusters=5, random_state=0).fit(array_sentiment_vectors)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0.43555605, 0.2777192 , 0.28672476],\n",
+       "       [0.21254481, 0.57576584, 0.21168936],\n",
+       "       [0.56669216, 0.13017252, 0.30313532],\n",
+       "       [0.33453667, 0.45309312, 0.21237021],\n",
+       "       [0.71664806, 0.06648547, 0.21686647]])"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "centers = kmeans.cluster_centers_\n",
+    "centers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🙇\n",
+      "😿\n",
+      "😄\n",
+      "😭\n",
+      "😍\n"
+     ]
+    }
+   ],
+   "source": [
+    "for center in centers:\n",
+    "    print(sentiment_vector_to_emoji(center))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* only most used emojis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "top_emojis = [('😂', 10182),\n",
+    " ('😭', 3893),\n",
+    " ('😍', 2866),\n",
+    " ('😩', 1647),\n",
+    " ('😊', 1450),\n",
+    " ('😘', 1151),\n",
+    " ('🙏', 1089),\n",
+    " ('🙌', 1003),\n",
+    " ('😉', 752),\n",
+    " ('😁', 697),\n",
+    " ('😅', 651),\n",
+    " ('😎', 606),\n",
+    " ('😢', 544),\n",
+    " ('😒', 539),\n",
+    " ('😏', 478),\n",
+    " ('😌', 434),\n",
+    " ('😔', 415),\n",
+    " ('😋', 397),\n",
+    " ('😀', 392),\n",
+    " ('😤', 368)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "😂\n",
+      "😒\n",
+      "😁\n",
+      "😭\n",
+      "😍\n"
+     ]
+    }
+   ],
+   "source": [
+    "for center in centers:\n",
+    "    print(sentiment_vector_to_emoji(center, custom_target_emojis=top_emojis))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.6.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}