From cd6167f80a71c1bb42aa8a8e28559fdfe4399afc Mon Sep 17 00:00:00 2001
From: Carsten <carsten.draschner@gmail.com>
Date: Tue, 26 Jun 2018 23:05:27 +0200
Subject: [PATCH] merge prediction optimization

---
 Project/Tools/User_Interface.ipynb | 54 ++++++++++++++++++------------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/Project/Tools/User_Interface.ipynb b/Project/Tools/User_Interface.ipynb
index 42edc2b..05efedc 100644
--- a/Project/Tools/User_Interface.ipynb
+++ b/Project/Tools/User_Interface.ipynb
@@ -139,7 +139,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "#sys.path.append(\"..\")\n",
@@ -151,7 +153,9 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "tmp_dict = clf_naive.prepareData()"
@@ -167,8 +171,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "def merged_prediction(msg , split = 0.5 , number = 8, target_emojis = top_emojis):\n",
@@ -178,10 +184,23 @@
     "    number_naive = round((1-split)*number)\n",
     "    \n",
     "    #predict emojis with the naive approach\n",
-    "    prediction_naive = clf_naive.predict(sentence = msg, lookup= tmp_dict, n = number_naive)\n",
+    "    prediction_naive , prediction_naive_values = clf_naive.predict(sentence = msg, lookup= tmp_dict, n = number_naive)\n",
+    "\n",
+    "    #filter 0 values\n",
+    "    tmp1 = []\n",
+    "    tmp2 = []\n",
+    "    epsilon = 0.0001\n",
+    "\n",
+    "    for i in range(len(prediction_naive)):\n",
+    "        if(abs(prediction_naive_values[i]) > epsilon):\n",
+    "            tmp1.append(prediction_naive[i])\n",
+    "            tmp2.append(prediction_naive[i])\n",
+    "\n",
+    "    prediction_naive = tmp1\n",
+    "    prediction_naive_values = tmp2\n",
     "    \n",
     "    if(len(prediction_naive) < number_naive):\n",
-    "        print(\"only few matches\")\n",
+    "        #print(\"only few matches\")\n",
     "        number_advanced = number - len(prediction_naive)\n",
     "        \n",
     "    #print(number, number_advanced, number_naive)\n",
@@ -222,10 +241,11 @@
     "    #p = ed.sentiment_vector_to_emoji(sent,n_results = 8, custom_target_emojis=top_emojis)\n",
     "    \n",
     "    #merged prediction\n",
-    "    p = merged_prediction(msg = current_message, target_emojis=top_emojis)\n",
-    "    \n",
-    "    predictions = p\n",
-    "    update_descriptions()"
+    "    if(current_message != \"\"):\n",
+    "        p = merged_prediction(msg = current_message, target_emojis=top_emojis)\n",
+    "\n",
+    "        predictions = p\n",
+    "        update_descriptions()"
    ]
   },
   {
@@ -527,13 +547,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9b6fd63901c84db9a5a2d10399053cb3",
+       "model_id": "3b8a6a311c1e4a1bb2b711d59246577a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -543,16 +563,6 @@
      },
      "metadata": {},
      "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "8 4 4\n",
-      "8 4 4\n",
-      "8 4 4\n",
-      "8 4 4\n"
-     ]
     }
    ],
    "source": [