ASS_sentiment_Analysis.ipynb

Assignment sentiment_Analysis.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "import numpy as np\nimport pandas as pd ",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "tweets=pd.read_csv(\"E:/text mining/Tweets.txt\",error_bad_lines=False,sep=\";\")\ntweets.head()",
      "execution_count": 6,
      "outputs": [
        {
          "data": {
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>X</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>234 tweets with \"loser\"  I feel sorry for Rosi...</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>tweets with \"dumb\" or \"dummy\" You must admit t...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>204 tweets with \"terrible\" I loved beating the...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>183 tweets with \"stupid\" @michellemalkin You w...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>.</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                                                   X\n0  234 tweets with \"loser\"  I feel sorry for Rosi...\n1  tweets with \"dumb\" or \"dummy\" You must admit t...\n2  204 tweets with \"terrible\" I loved beating the...\n3  183 tweets with \"stupid\" @michellemalkin You w...\n4                                                  ."
          },
          "execution_count": 6,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "tweets = [X.strip() for X in tweets.X] \ntweets = [X for X in tweets if X] \ntweets[0:10]",
      "execution_count": 7,
      "outputs": [
        {
          "data": {
            "text/plain": "['234 tweets with \"loser\"  I feel sorry for Rosie \\'s new partner in love whose parents are devastated at the thought of their daughter being with @Rosie--a true loser. — Donald J. Trump (@realDonaldTrump) December 14, 2011 222.',\n 'tweets with \"dumb\" or \"dummy\" You must admit that Bryant Gumbel is one of the dumbest racists around - an arrogant dope with no talent. Failed at CBS etc-why still on TV? — Donald J. Trump (@realDonaldTrump) August 21, 2013 .',\n '204 tweets with \"terrible\" I loved beating these two terrible human beings. I would never recommend that anyone use her lawyer, he is a total loser! — Donald J. Trump (@realDonaldTrump) May 23, 2013 .',\n '183 tweets with \"stupid\" @michellemalkin You were born stupid! — Donald J. Trump (@realDonaldTrump) March 22, 2013',\n '.',\n '156 tweets with \"weak\" There is no longer a Bernie Sanders \"political revolution.\" He is turning out to be a weak and somewhat pathetic figure,wants it all to end! — Donald J. Trump (@realDonaldTrump) July 24, 2016',\n '.',\n '117 tweets with \"dope\" or \"dopey\" Dopey  @Lord_Sugar I\\'m worth $8 billion and you\\'re worth peanuts...without my show nobody would even know who you are. — Donald J. Trump (@realDonaldTrump) December 7, 2012',\n '.',\n '115 tweets with \"dishonest\" A dishonest slob of a reporter, who doesn\\'t understand my sarcasm when talking about him or his wife, wrote a foolish & boring Trump \"hit\" — Donald J. Trump (@realDonaldTrump) February 15, 2014 .']"
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "import scipy\nnlp = spacy.load('en_core_web_md') ",
      "execution_count": 12,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "##Part Of Speech Tagging\none_block = tweets[20]\ndoc_block = nlp(one_block)\nspacy.displacy.render(doc_block, style='ent', jupyter=True)",
      "execution_count": 13,
      "outputs": [
        {
          "data": {
            "text/html": "<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\">\n<mark class=\"entity\" style=\"background: #e4e7d2; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    37\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">CARDINAL</span>\n</mark>\n tweets with &quot;disgusting&quot; \n<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    Barney Frank\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n</mark>\n looked disgusting--nipples protruding--in his blue shirt before \n<mark class=\"entity\" style=\"background: #7aecec; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    Congress\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n</mark>\n. Very very disrespectful. — \n<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    Donald J. Trump\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n</mark>\n (\n<mark class=\"entity\" style=\"background: #7aecec; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    @realDonaldTrump\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n</mark>\n) \n<mark class=\"entity\" style=\"background: #bfe1d9; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n    December 21, 2011\n    <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">DATE</span>\n</mark>\n.</div></span>",
            "text/plain": "<IPython.core.display.HTML object>"
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "for token in doc_block[0:20]:\n    print(token, token.pos_)",
      "execution_count": 14,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "37 NUM\ntweets NOUN\nwith ADP\n\" PUNCT\ndisgusting ADJ\n\" PUNCT\nBarney PROPN\nFrank PROPN\nlooked VERB\ndisgusting ADJ\n-- PUNCT\nnipples NOUN\nprotruding VERB\n-- PUNCT\nin ADP\nhis PRON\nblue ADJ\nshirt NOUN\nbefore ADP\nCongress PROPN\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "#Filtering for nouns and verbs only\nnouns_verbs = [token.text for token in doc_block if token.pos_ in ('NOUN', 'VERB')]\nprint(nouns_verbs[5:25])",
      "execution_count": 16,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "[]\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "from sklearn.feature_extraction.text import CountVectorizer\n#Counting tokens again\ncv = CountVectorizer()\n\nX = cv.fit_transform(nouns_verbs)\nsum_words = X.sum(axis=0)\nwords_freq = [(word, sum_words[0, idx]) for word, idx in cv.vocabulary_.items()]\nwords_freq =sorted(words_freq, key = lambda x: x[1], reverse=True)\nwf_df = pd.DataFrame(words_freq)\nwf_df.columns = ['word', 'count']\n\nwf_df[0:15]",
      "execution_count": 18,
      "outputs": [
        {
          "data": {
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>word</th>\n      <th>count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>tweets</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>looked</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>nipples</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>protruding</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>shirt</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "         word  count\n0      tweets      1\n1      looked      1\n2     nipples      1\n3  protruding      1\n4       shirt      1"
          },
          "execution_count": 18,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "##Visualizing results\n#Barchart for top 10 nouns + verbs\nwf_df[0:10].plot.bar(x='word', figsize=(12,8), title='Top verbs and nouns');",
      "execution_count": 19,
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 864x576 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "# Emotion Mining"
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "#Sentiment analysis\nafinn = pd.read_csv('E:/AA Lalit/55615/Afinn (1).csv' , sep=',', encoding='latin-1')\nafinn.shape",
      "execution_count": 29,
      "outputs": [
        {
          "data": {
            "text/plain": "(2477, 2)"
          },
          "execution_count": 29,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "from itertools import islice\n\ndef take(n, iterable):\n    \"Return first n items of the iterable as a list\"\n    return list(islice(iterable, n))",
      "execution_count": 30,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "affinity_scores = afinn.set_index('word')['value'].to_dict()\ntake(20, affinity_scores.items())",
      "execution_count": 31,
      "outputs": [
        {
          "data": {
            "text/plain": "[('abandon', -2),\n ('abandoned', -2),\n ('abandons', -2),\n ('abducted', -2),\n ('abduction', -2),\n ('abductions', -2),\n ('abhor', -3),\n ('abhorred', -3),\n ('abhorrent', -3),\n ('abhors', -3),\n ('abilities', 2),\n ('ability', 2),\n ('aboard', 1),\n ('absentee', -1),\n ('absentees', -1),\n ('absolve', 2),\n ('absolved', 2),\n ('absolves', 2),\n ('absolving', 2),\n ('absorbed', 1)]"
          },
          "execution_count": 31,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "from nltk import tokenize\nsentences = tokenize.sent_tokenize(\" \".join(tweets))\nsentences[5:15]",
      "execution_count": 32,
      "outputs": [
        {
          "data": {
            "text/plain": "['I would never recommend that anyone use her lawyer, he is a total loser!',\n '— Donald J. Trump (@realDonaldTrump) May 23, 2013 .',\n '183 tweets with \"stupid\" @michellemalkin You were born stupid!',\n '— Donald J. Trump (@realDonaldTrump) March 22, 2013 .',\n '156 tweets with \"weak\" There is no longer a Bernie Sanders \"political revolution.\"',\n 'He is turning out to be a weak and somewhat pathetic figure,wants it all to end!',\n '— Donald J. Trump (@realDonaldTrump) July 24, 2016 .',\n '117 tweets with \"dope\" or \"dopey\" Dopey  @Lord_Sugar I\\'m worth $8 billion and you\\'re worth peanuts...without my show nobody would even know who you are.',\n '— Donald J. Trump (@realDonaldTrump) December 7, 2012 .',\n '115 tweets with \"dishonest\" A dishonest slob of a reporter, who doesn\\'t understand my sarcasm when talking about him or his wife, wrote a foolish & boring Trump \"hit\" — Donald J. Trump (@realDonaldTrump) February 15, 2014 .']"
          },
          "execution_count": 32,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "sent_df = pd.DataFrame(sentences, columns=['sentence'])\nsent_df",
      "execution_count": 33,
      "outputs": [
        {
          "data": {
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>sentence</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>234 tweets with \"loser\"  I feel sorry for Rosi...</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>— Donald J. Trump (@realDonaldTrump) December ...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Failed at CBS etc-why still on TV?</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>— Donald J. Trump (@realDonaldTrump) August 21...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>204 tweets with \"terrible\" I loved beating the...</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>89</th>\n      <td>I study cowards and stupid people \"@MrMarin88:...</td>\n    </tr>\n    <tr>\n      <th>90</th>\n      <td>Only stupid people Pigs get slaughtered … again.</td>\n    </tr>\n    <tr>\n      <th>91</th>\n      <td>Ft Lauderdale plaintiffs must pay me close to ...</td>\n    </tr>\n    <tr>\n      <th>92</th>\n      <td>Many journalists are honest and great - but so...</td>\n    </tr>\n    <tr>\n      <th>93</th>\n      <td>They should.be weeded out!</td>\n    </tr>\n  </tbody>\n</table>\n<p>94 rows × 1 columns</p>\n</div>",
            "text/plain": "                                             sentence\n0   234 tweets with \"loser\"  I feel sorry for Rosi...\n1   — Donald J. Trump (@realDonaldTrump) December ...\n2                  Failed at CBS etc-why still on TV?\n3   — Donald J. Trump (@realDonaldTrump) August 21...\n4   204 tweets with \"terrible\" I loved beating the...\n..                                                ...\n89  I study cowards and stupid people \"@MrMarin88:...\n90   Only stupid people Pigs get slaughtered … again.\n91  Ft Lauderdale plaintiffs must pay me close to ...\n92  Many journalists are honest and great - but so...\n93                         They should.be weeded out!\n\n[94 rows x 1 columns]"
          },
          "execution_count": 33,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "from itertools import islice\n\ndef take(n, iterable):\n    \"Return first n items of the iterable as a list\"\n    return list(islice(iterable, n))",
      "execution_count": 34,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "#Custom function :score each word in a sentence in lemmatised form, \n#but calculate the score for the whole original sentence.\nnlp = spacy.load('en_core_web_md')\nsentiment_lexicon = affinity_scores\n\ndef calculate_sentiment(text: str = None) -> float:\n    sent_score = 0\n    if text:\n        sentence = nlp(text)\n        for word in sentence:\n            sent_score += sentiment_lexicon.get(word.lemma_, 0)\n    return sent_score",
      "execution_count": 36,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "# test that it works\ncalculate_sentiment(text = 'very sad')",
      "execution_count": 37,
      "outputs": [
        {
          "data": {
            "text/plain": "-2"
          },
          "execution_count": 37,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "sent_df['sentiment_value'] = sent_df['sentence'].apply(calculate_sentiment)",
      "execution_count": 38,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "# how many words are in the sentence?\nsent_df['word_count'] = sent_df['sentence'].str.split().apply(len)\nsent_df['word_count'].head(10)",
      "execution_count": 39,
      "outputs": [
        {
          "data": {
            "text/plain": "0    29\n1    34\n2     7\n3     9\n4    12\n5    14\n6     9\n7     9\n8     9\n9    13\nName: word_count, dtype: int64"
          },
          "execution_count": 39,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "sent_df.sort_values(by='sentiment_value').tail(10)",
      "execution_count": 40,
      "outputs": [
        {
          "data": {
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>sentence</th>\n      <th>sentiment_value</th>\n      <th>word_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>65</th>\n      <td>31 tweets implying \"autism\" is caused by vacci...</td>\n      <td>2</td>\n      <td>30</td>\n    </tr>\n    <tr>\n      <th>73</th>\n      <td>Retaliation It makes me feel so good to hit \"s...</td>\n      <td>3</td>\n      <td>22</td>\n    </tr>\n    <tr>\n      <th>25</th>\n      <td>Good night.</td>\n      <td>3</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>92</th>\n      <td>Many journalists are honest and great - but so...</td>\n      <td>3</td>\n      <td>15</td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>I already know the winners.</td>\n      <td>4</td>\n      <td>5</td>\n    </tr>\n    <tr>\n      <th>59</th>\n      <td>Like the @nytimes story which has become a joke!</td>\n      <td>4</td>\n      <td>9</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>117 tweets with \"dope\" or \"dopey\" Dopey  @Lord...</td>\n      <td>4</td>\n      <td>25</td>\n    </tr>\n    <tr>\n      <th>51</th>\n      <td>28 tweets with \"goofy\" When Mitt Romney asked ...</td>\n      <td>4</td>\n      <td>31</td>\n    </tr>\n    <tr>\n      <th>80</th>\n      <td>It is always important to WIN!</td>\n      <td>6</td>\n      <td>6</td>\n    </tr>\n    <tr>\n      <th>81</th>\n      <td>I am a very calm person but love tweeting abou...</td>\n      <td>7</td>\n      <td>15</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                                             sentence  sentiment_value  \\\n65  31 tweets implying \"autism\" is caused by vacci...                2   \n73  Retaliation It makes me feel so good to hit \"s...                3   \n25                                        Good night.                3   \n92  Many journalists are honest and great - but so...                3   \n24                        I already know the winners.                4   \n59   Like the @nytimes story which has become a joke!                4   \n12  117 tweets with \"dope\" or \"dopey\" Dopey  @Lord...                4   \n51  28 tweets with \"goofy\" When Mitt Romney asked ...                4   \n80                     It is always important to WIN!                6   \n81  I am a very calm person but love tweeting abou...                7   \n\n    word_count  \n65          30  \n73          22  \n25           2  \n92          15  \n24           5  \n59           9  \n12          25  \n51          31  \n80           6  \n81          15  "
          },
          "execution_count": 40,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "# Sentiment score of the whole review\nsent_df['sentiment_value'].describe()",
      "execution_count": 41,
      "outputs": [
        {
          "data": {
            "text/plain": "count    94.000000\nmean     -1.404255\nstd       3.785425\nmin     -15.000000\n25%      -3.000000\n50%       0.000000\n75%       0.000000\nmax       7.000000\nName: sentiment_value, dtype: float64"
          },
          "execution_count": 41,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "# Sentiment score of the whole review\nsent_df[sent_df['sentiment_value']<=0].head()",
      "execution_count": 42,
      "outputs": [
        {
          "data": {
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>sentence</th>\n      <th>sentiment_value</th>\n      <th>word_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>234 tweets with \"loser\"  I feel sorry for Rosi...</td>\n      <td>-6</td>\n      <td>29</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>— Donald J. Trump (@realDonaldTrump) December ...</td>\n      <td>-13</td>\n      <td>34</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Failed at CBS etc-why still on TV?</td>\n      <td>-2</td>\n      <td>7</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>— Donald J. Trump (@realDonaldTrump) August 21...</td>\n      <td>0</td>\n      <td>9</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>204 tweets with \"terrible\" I loved beating the...</td>\n      <td>-3</td>\n      <td>12</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                                            sentence  sentiment_value  \\\n0  234 tweets with \"loser\"  I feel sorry for Rosi...               -6   \n1  — Donald J. Trump (@realDonaldTrump) December ...              -13   \n2                 Failed at CBS etc-why still on TV?               -2   \n3  — Donald J. Trump (@realDonaldTrump) August 21...                0   \n4  204 tweets with \"terrible\" I loved beating the...               -3   \n\n   word_count  \n0          29  \n1          34  \n2           7  \n3           9  \n4          12  "
          },
          "execution_count": 42,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "import seaborn as sns\nimport matplotlib.pyplot as plt\nplt.figure(figsize=(15, 10))\nsns.distplot(sent_df['sentiment_value']);",
      "execution_count": 43,
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": "C:\\Users\\HP\\anaconda3\\lib\\site-packages\\seaborn\\distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n  warnings.warn(msg, FutureWarning)\n"
        },
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 1080x720 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "sent_df.plot.scatter(x='word_count', y='sentiment_value', figsize=(8,8), title='Sentence sentiment value to sentence word count');",
      "execution_count": 44,
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 576x576 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.8.5",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "ASS_sentiment_Analysis.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 4
}