{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "import glob"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configuration\n",
    "\n",
    "*input_dir:* The path to the directory containg annoted seed words. Please make sure to use a '/' (slash) in the end. For example: `path/to/annotated/seed_words/`.\n",
    "\n",
    "*output_dir:* The path to the directory where you want to save selected seed words. Please make sure to use a '/' (slash) in the end. For example: `path/to/output/`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_dir = \"results/annotated/\"\n",
    "output_dir = \"results/selected/\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Directory Setup (Optional)\n",
    "Creates directories according to the configuration if not already created manually."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not os.path.exists(input_dir):\n",
    "    os.makedirs(input_dir)\n",
    "if not os.path.exists(output_dir):\n",
    "    os.makedirs(output_dir)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Seed Word Selection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load annoteted seed words"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "annotation_file_names = glob.glob(\"{}*.csv\".format(input_dir))\n",
    "print(\"found {} annotations\".format(len(annotation_file_names)))\n",
    "annotations = []\n",
    "for annotation_file_name in annotation_file_names:\n",
    "    annotations.append(pd.read_csv(annotation_file_name, index_col=\"word\"))\n",
    "print(\"loaded {} annotations\".format(len(annotations)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Select seed words\n",
    "This is based on a majority vote."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "annotations_df = pd.concat(annotations, axis=1).fillna(\"neutral\")\n",
    "pos_words = []\n",
    "neg_words = []\n",
    "neu_words = []\n",
    "for w, row in annotations_df.mode(axis=1).iterrows():\n",
    "    row = row.dropna()\n",
    "    if len(row) > 1:\n",
    "        continue\n",
    "    if row[0] == \"positive\":\n",
    "        pos_words.append(w)\n",
    "    elif row[0] == \"negative\":\n",
    "        neg_words.append(w)\n",
    "    elif row[0] == \"neutral\":\n",
    "        neu_words.append(w)\n",
    "print(\"number of positive:\", len(pos_words))\n",
    "print(\"number of negative:\", len(neg_words))\n",
    "print(\"number of neutral:\", len(neu_words))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Save selected seed words"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"{}positive.txt\".format(output_dir), mode=\"wt\", encoding=\"utf-8\") as pos_file:\n",
    "    pos_file.write(\"\\n\".join(pos_words))\n",
    "with open(\"{}negative.txt\".format(output_dir), mode=\"wt\", encoding=\"utf-8\") as neg_file:\n",
    "    neg_file.write(\"\\n\".join(neg_words))\n",
    "with open(\"{}neutral.txt\".format(output_dir), mode=\"wt\", encoding=\"utf-8\") as neu_file:\n",
    "    neu_file.write(\"\\n\".join(neu_words))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}