From 48e89cda68619146ec0aa24099494f86a7ce3070 Mon Sep 17 00:00:00 2001
From: Jonas Weinz <s6jowein@uni-bonn.de>
Date: Thu, 31 May 2018 15:23:57 +0200
Subject: [PATCH] improved output and threshold

---
 Project/naive_approach/naive_approach.ipynb | 98 ++++++++++++++++-----
 1 file changed, 77 insertions(+), 21 deletions(-)

diff --git a/Project/naive_approach/naive_approach.ipynb b/Project/naive_approach/naive_approach.ipynb
index c3b8249..e7e6f2c 100644
--- a/Project/naive_approach/naive_approach.ipynb
+++ b/Project/naive_approach/naive_approach.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 149,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,7 +15,10 @@
     "from nltk.stem import PorterStemmer\n",
     "from nltk.tokenize import sent_tokenize, word_tokenize\n",
     "from nltk.corpus import wordnet\n",
-    "import math"
+    "import math\n",
+    "import pprint\n",
+    "\n",
+    "pp=pprint.PrettyPrinter(indent=4)"
    ]
   },
   {
@@ -270,11 +273,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 130,
    "metadata": {},
    "outputs": [],
    "source": [
-    "result = evaluate_sentence(\"car soccer surf\")"
+    "result = evaluate_sentence(\"I like playing soccer\")"
    ]
   },
   {
@@ -286,7 +289,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 107,
+   "execution_count": 131,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -304,7 +307,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 108,
+   "execution_count": 139,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -312,33 +315,86 @@
     "max_val = np.argsort([-np.max(x) for x in result])\n",
     "avg =  np.argsort([-np.mean(x) for x in result])\n",
     "\n",
-    "t = 0.7\n",
-    "threshold = np.argsort([-len(np.where(x>t)[0]) for x in result])\n"
+    "t = 0.9\n",
+    "threshold = np.argsort([-len(np.where(x>t)[0]) / (x.shape[0] * x.shape[1]) for x in result])\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 109,
+   "execution_count": 156,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def print_best_results(sorted_indices, n=10):\n",
+    "    pp.pprint([lookup[x] + \" -- \" + str(table.iloc[x]['description']) for x in sorted_indices[:10]])\n",
+    "    pp.pprint([result[x] for x in sorted_indices[:10]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 157,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/markdown": [
-       "# 🏉⚾🎳🔥🏐🎱💏🧾🚗🚘"
-      ],
-      "text/plain": [
-       "<IPython.core.display.Markdown object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[   '⚽ -- SOCCER BALL',\n",
+      "    '🏉 -- RUGBY FOOTBALL',\n",
+      "    '🏈 -- AMERICAN FOOTBALL',\n",
+      "    '🎴 -- FLOWER PLAYING CARDS',\n",
+      "    '🃏 -- PLAYING CARD BLACK JOKER',\n",
+      "    '🇮 -- REGIONAL INDICATOR SYMBOL LETTER I',\n",
+      "    '\\U0001f91f -- I LOVE YOU HAND SIGN',\n",
+      "    '📧 -- E-MAIL SYMBOL',\n",
+      "    '📭 -- OPEN MAILBOX WITH LOWERED FLAG',\n",
+      "    '📥 -- INBOX TRAY']\n",
+      "[   array([[0.25      , 0.28571429, 0.58333333, 1.        ],\n",
+      "       [0.26666667, 0.10526316, 0.1       , 0.1       ]]),\n",
+      "    array([[0.25      , 0.28571429, 0.58333333, 0.84615385],\n",
+      "       [0.26666667, 0.3       , 0.60869565, 0.96      ]]),\n",
+      "    array([[0.33333333, 0.125     , 0.11764706, 0.11764706],\n",
+      "       [0.26666667, 0.3       , 0.60869565, 0.96      ]]),\n",
+      "    array([[0.23529412, 0.0952381 , 0.09090909, 0.09090909],\n",
+      "       [0.25      , 0.47619048, 1.        , 0.58333333],\n",
+      "       [0.30769231, 0.33333333, 0.57142857, 0.7       ]]),\n",
+      "    array([[0.25      , 0.47619048, 1.        , 0.58333333],\n",
+      "       [0.53333333, 0.22222222, 0.21052632, 0.21052632],\n",
+      "       [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n",
+      "       [0.28571429, 0.11111111, 0.10526316, 0.10526316]]),\n",
+      "    array([[0.        , 0.        , 0.        , 0.        ],\n",
+      "       [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n",
+      "       [0.4       , 0.26666667, 0.25      , 0.25      ],\n",
+      "       [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n",
+      "       [1.        , 0.26666667, 0.25      , 0.25      ]]),\n",
+      "    array([[1.        , 0.26666667, 0.25      , 0.25      ],\n",
+      "       [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n",
+      "       [0.        , 0.        , 0.        , 0.        ],\n",
+      "       [0.28571429, 0.11111111, 0.10526316, 0.10526316],\n",
+      "       [0.33333333, 0.23529412, 0.22222222, 0.22222222]]),\n",
+      "    array([[0.28571429, 0.31578947, 0.45454545, 0.5       ],\n",
+      "       [0.4       , 0.26666667, 0.25      , 0.25      ]]),\n",
+      "    array([[0.30769231, 0.11764706, 0.11111111, 0.11111111],\n",
+      "       [0.26666667, 0.10526316, 0.1       , 0.1       ],\n",
+      "       [0.        , 0.        , 0.        , 0.        ],\n",
+      "       [0.22222222, 0.14285714, 0.13333333, 0.13333333],\n",
+      "       [0.26666667, 0.10526316, 0.1       , 0.1       ]]),\n",
+      "    array([[0.        , 0.        , 0.        , 0.        ],\n",
+      "       [0.26666667, 0.10526316, 0.1       , 0.1       ]])]\n"
+     ]
     }
    ],
    "source": [
-    "def print_best_results(sorted_indices, n=10):\n",
-    "    print([lookup[x] + \" -- \" + table.iloc[]])"
+    "print_best_results(threshold)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": null,