added intro analysis

src/notebooks/intro_analysis.ipynb

@@ -23,13 +23,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "archetype_data = pd.read_csv('../../data/enriched/persona_identification/archetype_predictions_joined.csv')\n",
     "\n",
-    "character_data = pd.read_csv('../../data/MovieSummaries/alex_character_processed.csv')\n",
+    "character_data = pd.read_csv('../../data/MovieSummaries/character_processed.csv')\n",
     "\n",
     "character_data = character_data.rename(columns={\n",
     "    'Wikipedia movie ID': \"wikipedia_movie_id\",\n",
@@ -196212,7 +196212,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now let's look on how the average number of как бля короче распределены эти ебаные архетипы по ебаным фильмам нахуй"
+    "Every movie on average contains a lot of different characters with a lot of different archetypes. The distribution of the how many unique archetypes every movie has"
    ]
   },
   {
@@ -220782,72 +220782,6 @@
     "fig.show()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# should do on unique!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from plotly.subplots import make_subplots\n",
-    "fig = make_subplots(\n",
-    "    rows=4, cols=1, \n",
-    "    specs=[\n",
-    "        [{\"type\": \"pie\"}], [{\"type\": \"pie\"}],\n",
-    "        [{\"type\": \"pie\"}], [{\"type\": \"pie\"}]\n",
-    "    ])\n",
-    "\n",
-    "fig.add_trace(\n",
-    "    go.Pie(\n",
-    "        labels=data.archetype.value_counts().index, \n",
-    "        values=data.archetype.value_counts(),\n",
-    "        legendgroup=\"1\",\n",
-    "    ),\n",
-    "    row=1, col=1\n",
-    ")\n",
-    "\n",
-    "fig.add_trace(\n",
-    "    go.Pie(\n",
-    "        labels=data.actor_gender.value_counts().index, \n",
-    "        values=data.actor_gender.value_counts(),\n",
-    "        legendgroup=\"2\",\n",
-    "    ),\n",
-    "    row=2, col=1\n",
-    ")\n",
-    "\n",
-    "fig.add_trace(\n",
-    "    go.Pie(\n",
-    "        labels=data.race.value_counts().index, \n",
-    "        values=data.race.value_counts(),\n",
-    "        legendgroup=\"3\",\n",
-    "    ),\n",
-    "    row=3, col=1\n",
-    ")\n",
-    "\n",
-    "fig.update_layout(\n",
-    "    height=1000,\n",
-    "    autosize=False,\n",
-    "    legend_tracegroupgap = 180,\n",
-    "    margin=dict(t=0, b=0, l=0, r=0),\n",
-    ")\n",
-    "\n",
-    "\n",
-    "fig.show()\n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,