{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "import json\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Installing file system interface for s3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install s3fs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set up the bucket name and key by entering the\n",
    "bucket_name=*enter your bucket name*,\n",
    "and *in_key_name=prefix/path/file*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bucket_name='<your_bucket_name>'\n",
    "in_key_name='<prefix>/<path>/<file>'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Reading the file content from s3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s3 = boto3.resource('s3')\n",
    "obj = s3.Object(bucket_name,in_key_name)\n",
    "text=obj.get()['Body'].read().decode('utf-8')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Calling Comprehend API detect_sentiment for sentiment analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "client = boto3.client('comprehend')\n",
    "lst=[]\n",
    "for line in text.splitlines():\n",
    "    line_dict=json.loads(line)\n",
    "    line_dict['Sentiment']=client.detect_sentiment(Text=line_dict['text'],LanguageCode='en')['Sentiment']\n",
    "    lst.append(json.dumps(line_dict))\n",
    "joined_lines='\\n'.join(lst)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "slack_df = pd.read_json(joined_lines,lines=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "slack_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "slack_df[['text','Sentiment']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "slack_df[['text','Sentiment']].groupby(['Sentiment']).agg(['count'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "slack_df[['text','Sentiment']].groupby(['Sentiment']).agg(['count']).plot(kind='pie',subplots=True)"
   ]
  }
 ],
 "metadata": {
  "instance_type": "ml.t3.medium",
  "kernelspec": {
   "display_name": "Python 3 (Data Science)",
   "language": "python",
   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/datascience-1.0"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}