added some statistical evaluation

Project/simple_approach/simple_twitter_learning.ipynb

@@ -2412,6 +2412,86 @@
     "display(testlist)\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* exactly correct labeled sentences:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.21221374045801528\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (sum([1 if sample[1]['teacher'] == sample[1]['predict'] else 0 for sample in testlist.iterrows()]) / testlist.shape[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* mean squared error:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.02218067, 0.02490165, 0.00302656])"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "teacher_sentiments = np.array([sample[1]['teacher_sentiment'] for sample in testlist.iterrows()])\n",
+    "predicted_sentiments = np.array([sample[1]['predicted_sentiment'] for sample in testlist.iterrows()])\n",
+    "\n",
+    "mean_squared_error = ((teacher_sentiments - predicted_sentiments)**2).mean(axis=0)\n",
+    "display(mean_squared_error)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* by an overall variance of:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Variance teacher:  [0.02183094 0.02513847 0.00285735]\n",
+      "Variance prediction:  [0.00863898 0.00919997 0.00082446]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Variance teacher: \", np.var(teacher_sentiments, axis=0))\n",
+    "print(\"Variance prediction: \", np.var(predicted_sentiments, axis=0))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 35,
@@ -2541,13 +2621,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9c34c24b4df140f9ab22ded811cf8f89",
+       "model_id": "8a4248b8f8d147a58cdc02f4be7fbe03",
        "version_major": 2,
        "version_minor": 0
       },
@@ -2561,12 +2641,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7fb503b1cbb9472da347289cc130f838",
+       "model_id": "525901f072994db2a57e654faa5b9b39",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "VBox(children=(Button(description='get smiley', icon='check', style=ButtonStyle(), tooltip='Click me'), Output…"
+       "VBox(children=(Button(description='get emoji', icon='check', style=ButtonStyle(), tooltip='Click me'), Output(…"
       ]
      },
      "metadata": {},
@@ -2578,7 +2658,7 @@
     "\n",
     "t = widgets.Text()\n",
     "b = widgets.Button(\n",
-    "    description='get smiley',\n",
+    "    description='get emoji',\n",
     "    disabled=False,\n",
     "    button_style='', # 'success', 'info', 'warning', 'danger' or ''\n",
     "    tooltip='Click me',\n",
@@ -2593,7 +2673,7 @@
     "    with out:\n",
     "        pred = clf.predict(vectorizer.transform([t.value]))\n",
     "        \n",
-    "        display(Markdown(\"# \" + str(sent2emoji(pred, lookup_emojis))))\n",
+    "        display(Markdown(\"# \" + str(sent2emoji(pred, lookup_emojis)[0])))\n",
     "\n",
     "b.on_click(handle_submit)\n",
     "    \n",
@@ -2627,10 +2707,8 @@
    ]
   },
   {
-   "cell_type": "code",
+   "cell_type": "markdown",
-   "execution_count": null,
    "metadata": {},
-   "outputs": [],
    "source": []
   }
  ],