notebook about market analysis

notebooks/markets_analysis.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,16 +15,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "fpmms = pd.read_parquet('../data/fpmms.parquet')"
+    "fpmms = pd.read_parquet('../data/all_fpmms.parquet')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -48,63 +48,69 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>id</th>\n",
        "      <th>currentAnswer</th>\n",
+       "      <th>id</th>\n",
        "      <th>title</th>\n",
+       "      <th>market_creator</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>0x0020d13c89140b47e10db54cbd53852b90bc1391</td>\n",
        "      <td>No</td>\n",
-       "      <td>Will the Francis Scott Key Bridge in Baltimore...</td>\n",
+       "      <td>0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5</td>\n",
+       "      <td>Will the first floating offshore wind research...</td>\n",
+       "      <td>quickstart</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07</td>\n",
        "      <td>No</td>\n",
-       "      <td>Will FC Saarbrucken reach the final of the Ger...</td>\n",
+       "      <td>0x0020d13c89140b47e10db54cbd53852b90bc1391</td>\n",
+       "      <td>Will the Francis Scott Key Bridge in Baltimore...</td>\n",
+       "      <td>quickstart</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c</td>\n",
-       "      <td>Yes</td>\n",
-       "      <td>Will the pro-life activists convicted for 'con...</td>\n",
+       "      <td>No</td>\n",
+       "      <td>0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07</td>\n",
+       "      <td>Will FC Saarbrucken reach the final of the Ger...</td>\n",
+       "      <td>quickstart</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>0x005e3f7a90585acbec807425a750fbba1d0c2b5c</td>\n",
        "      <td>Yes</td>\n",
-       "      <td>Will Apple announce the release of a new M4 ch...</td>\n",
+       "      <td>0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c</td>\n",
+       "      <td>Will the pro-life activists convicted for 'con...</td>\n",
+       "      <td>quickstart</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>0x0094fa304017d5c2b355790e2976f769ea600492</td>\n",
-       "      <td>No</td>\n",
-       "      <td>Will the Hisense U8K be considered a top-tier ...</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>0x005e3f7a90585acbec807425a750fbba1d0c2b5c</td>\n",
+       "      <td>Will Apple announce the release of a new M4 ch...</td>\n",
+       "      <td>quickstart</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "                                           id currentAnswer  \\\n",
-       "0  0x0020d13c89140b47e10db54cbd53852b90bc1391            No   \n",
-       "1  0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07            No   \n",
-       "2  0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c           Yes   \n",
-       "3  0x005e3f7a90585acbec807425a750fbba1d0c2b5c           Yes   \n",
-       "4  0x0094fa304017d5c2b355790e2976f769ea600492            No   \n",
+       "  currentAnswer                                          id  \\\n",
+       "0            No  0x0017cd58d6a7ee1451388c7d5b1051b4c0a041f5   \n",
+       "1            No  0x0020d13c89140b47e10db54cbd53852b90bc1391   \n",
+       "2            No  0x003ae5e007cc38b3f86b0ed7c82f938a1285ac07   \n",
+       "3           Yes  0x004c8d4c619dc6b9caa940f5ea7ef699ae85359c   \n",
+       "4           Yes  0x005e3f7a90585acbec807425a750fbba1d0c2b5c   \n",
        "\n",
-       "                                               title  \n",
-       "0  Will the Francis Scott Key Bridge in Baltimore...  \n",
-       "1  Will FC Saarbrucken reach the final of the Ger...  \n",
-       "2  Will the pro-life activists convicted for 'con...  \n",
-       "3  Will Apple announce the release of a new M4 ch...  \n",
-       "4  Will the Hisense U8K be considered a top-tier ...  "
+       "                                               title market_creator  \n",
+       "0  Will the first floating offshore wind research...     quickstart  \n",
+       "1  Will the Francis Scott Key Bridge in Baltimore...     quickstart  \n",
+       "2  Will FC Saarbrucken reach the final of the Ger...     quickstart  \n",
+       "3  Will the pro-life activists convicted for 'con...     quickstart  \n",
+       "4  Will Apple announce the release of a new M4 ch...     quickstart  "
       ]
      },
-     "execution_count": 3,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -113,6 +119,108 @@
     "fpmms.head()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "currentAnswer\n",
+       "No       2583\n",
+       "Yes      1833\n",
+       "no          1\n",
+       "False       1\n",
+       "IND         1\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fpmms.currentAnswer.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "market_creator\n",
+       "quickstart    4252\n",
+       "pearl          167\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fpmms.market_creator.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 4419 entries, 0 to 4418\n",
+      "Data columns (total 4 columns):\n",
+      " #   Column          Non-Null Count  Dtype \n",
+      "---  ------          --------------  ----- \n",
+      " 0   currentAnswer   4419 non-null   object\n",
+      " 1   id              4419 non-null   object\n",
+      " 2   title           4419 non-null   object\n",
+      " 3   market_creator  4419 non-null   object\n",
+      "dtypes: object(4)\n",
+      "memory usage: 138.2+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "fpmms.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "currentAnswer\n",
+       "No       2495\n",
+       "Yes      1746\n",
+       "no          1\n",
+       "False       1\n",
+       "IND         1\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fpmms.currentAnswer.value_counts()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,