python-pour-finance/11-Quantopian-Avancé/04-Projet-Analyse-Sentiment-Stock.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Analyse de Sentiments\n",
    "\n",
    "Regardez la vidéo pour plus de détails."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Code final\n",
    "Voici le code final:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Cette section est uniquement importable dans le backtester\n",
    "from quantopian.algorithm import attach_pipeline, pipeline_output\n",
    "\n",
    "# Importations générales de pipeline\n",
    "from quantopian.pipeline import Pipeline\n",
    "from quantopian.pipeline.factors import AverageDollarVolume\n",
    "\n",
    "\n",
    "# Utiliser l'échantillon gratuit dans votre algo de pipeline\n",
    "from quantopian.pipeline.data.sentdex import sentiment_free as sentdex\n",
    "\n",
    "# pour calculer l'impact\n",
    "from quantopian.pipeline.factors import CustomFactor\n",
    "import numpy as np\n",
    "\n",
    "\n",
    "def initialize(context):\n",
    "    # Planifier notre fonction de rééquilibrage au début de chaque semaine.\n",
    "    schedule_function(my_rebalance, date_rules.every_day())\n",
    "\n",
    "    \n",
    "    attach_pipeline(make_pipeline(), \"pipeline\")\n",
    "\n",
    "# Calcul du sentiment m sur la longueur de la fenêtre\n",
    "class AvgSentiment(CustomFactor):\n",
    "    def compute(self, today, assets, out, impact):\n",
    "        np.mean(impact, axis=0, out=out)\n",
    "    \n",
    "def make_pipeline():\n",
    "\n",
    "    # Éliminez les actions à un penny et les titres peu liquides.\n",
    "    dollar_volume = AverageDollarVolume(window_length=30)\n",
    "    is_liquid = dollar_volume.top(500)\n",
    "    \n",
    "    # Calcul du sentiment moyen\n",
    "    avg_sentiment = AvgSentiment(inputs=[sentdex.sentiment_signal], window_length=10)\n",
    "\n",
    "    return Pipeline(columns={\n",
    "            'sentiment':avg_sentiment\n",
    "        }, screen=is_liquid)\n",
    "            \n",
    "\n",
    "    \n",
    "def before_trading_start(context, data):\n",
    "    portfo = pipeline_output('pipeline')\n",
    "    context.something = portfo['sentiment'] \n",
    "    \n",
    "    # Actions avec un sentiment > 0\n",
    "    context.longs = portfo[portfo['sentiment'] > 0].index.tolist()\n",
    "    \n",
    "    # Actions avec un sentiment < 0\n",
    "    context.shorts = portfo[portfo['sentiment'] < 0].index.tolist()\n",
    "\n",
    "    context.long_weight, context.short_weight = my_compute_weights(context)\n",
    "\n",
    "    \n",
    "def my_compute_weights(context):\n",
    "\n",
    "    # Calculer des pondérations cibles égales pour nos positions longues et nos positions courtes.\n",
    "    if len(context.longs)==0:\n",
    "        long_weight = 0\n",
    "    else:\n",
    "        long_weight = 0.5/len(context.longs)\n",
    "    \n",
    "    if len(context.shorts)==0:\n",
    "        short_weight = 0\n",
    "    else:\n",
    "        short_weight = -0.5/len(context.shorts)\n",
    " \n",
    "    return long_weight, short_weight\n",
    "\n",
    "\n",
    "def my_rebalance(context, data):\n",
    "\n",
    "    for security in context.portfolio.positions:\n",
    "        if security not in context.longs and security not in context.shorts and data.can_trade(security):\n",
    "            order_target_percent(security, 0)\n",
    "\n",
    "    for security in context.longs:\n",
    "        if data.can_trade(security):\n",
    "            order_target_percent(security, context.long_weight)\n",
    "\n",
    "    for security in context.shorts:\n",
    "        if data.can_trade(security):\n",
    "            order_target_percent(security, context.short_weight)\n",
    "            \n",
    "    print(context.something)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.5",
   "language": "python",
   "name": "py35"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}