Skip to content

Commit

Permalink
Small edits
Browse files Browse the repository at this point in the history
  • Loading branch information
@Shobhit-Bandhu
Shobhit-Bandhu committed Dec 17, 2023
1 parent 2fa5e86 commit 6115a2b
Showing 1 changed file with 83 additions and 195 deletions.
278 changes: 83 additions & 195 deletions Stock News Sentiment Analysis/Model/stock_news_sentiment_analysis.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
"import pandas as pd \n",
"import matplotlib.pyplot as plt \n",
"import seaborn as sns\n",
"import regex\n",
"import nltk\n",
"\n",
"plt.style.use('ggplot')"
]
Expand Down Expand Up @@ -96,7 +96,7 @@
}
],
"source": [
"path = 'Data/Sentiment_Stock_data.csv'\n",
"path = '../Dataset/Sentiment_Stock_data.csv'\n",
"\n",
"df = pd.read_csv(path)\n",
"\n",
Expand Down Expand Up @@ -659,205 +659,51 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 18,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "NameError",
"evalue": "name 'nltk' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[18], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mnltk\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcorpus\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m stopwords\n\u001b[0;32m----> 3\u001b[0m \u001b[43mnltk\u001b[49m\u001b[38;5;241m.\u001b[39mdownload(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mstopwords\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
"\u001b[0;31mNameError\u001b[0m: name 'nltk' is not defined"
]
}
],
"source": [
"from nltk.corpus import stopwords"
"from nltk.corpus import stopwords\n",
"\n",
"nltk.download('stopwords')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['i',\n",
" 'me',\n",
" 'my',\n",
" 'myself',\n",
" 'we',\n",
" 'our',\n",
" 'ours',\n",
" 'ourselves',\n",
" 'you',\n",
" \"you're\",\n",
" \"you've\",\n",
" \"you'll\",\n",
" \"you'd\",\n",
" 'your',\n",
" 'yours',\n",
" 'yourself',\n",
" 'yourselves',\n",
" 'he',\n",
" 'him',\n",
" 'his',\n",
" 'himself',\n",
" 'she',\n",
" \"she's\",\n",
" 'her',\n",
" 'hers',\n",
" 'herself',\n",
" 'it',\n",
" \"it's\",\n",
" 'its',\n",
" 'itself',\n",
" 'they',\n",
" 'them',\n",
" 'their',\n",
" 'theirs',\n",
" 'themselves',\n",
" 'what',\n",
" 'which',\n",
" 'who',\n",
" 'whom',\n",
" 'this',\n",
" 'that',\n",
" \"that'll\",\n",
" 'these',\n",
" 'those',\n",
" 'am',\n",
" 'is',\n",
" 'are',\n",
" 'was',\n",
" 'were',\n",
" 'be',\n",
" 'been',\n",
" 'being',\n",
" 'have',\n",
" 'has',\n",
" 'had',\n",
" 'having',\n",
" 'do',\n",
" 'does',\n",
" 'did',\n",
" 'doing',\n",
" 'a',\n",
" 'an',\n",
" 'the',\n",
" 'and',\n",
" 'but',\n",
" 'if',\n",
" 'or',\n",
" 'because',\n",
" 'as',\n",
" 'until',\n",
" 'while',\n",
" 'of',\n",
" 'at',\n",
" 'by',\n",
" 'for',\n",
" 'with',\n",
" 'about',\n",
" 'against',\n",
" 'between',\n",
" 'into',\n",
" 'through',\n",
" 'during',\n",
" 'before',\n",
" 'after',\n",
" 'above',\n",
" 'below',\n",
" 'to',\n",
" 'from',\n",
" 'up',\n",
" 'down',\n",
" 'in',\n",
" 'out',\n",
" 'on',\n",
" 'off',\n",
" 'over',\n",
" 'under',\n",
" 'again',\n",
" 'further',\n",
" 'then',\n",
" 'once',\n",
" 'here',\n",
" 'there',\n",
" 'when',\n",
" 'where',\n",
" 'why',\n",
" 'how',\n",
" 'all',\n",
" 'any',\n",
" 'both',\n",
" 'each',\n",
" 'few',\n",
" 'more',\n",
" 'most',\n",
" 'other',\n",
" 'some',\n",
" 'such',\n",
" 'no',\n",
" 'nor',\n",
" 'not',\n",
" 'only',\n",
" 'own',\n",
" 'same',\n",
" 'so',\n",
" 'than',\n",
" 'too',\n",
" 'very',\n",
" 's',\n",
" 't',\n",
" 'can',\n",
" 'will',\n",
" 'just',\n",
" 'don',\n",
" \"don't\",\n",
" 'should',\n",
" \"should've\",\n",
" 'now',\n",
" 'd',\n",
" 'll',\n",
" 'm',\n",
" 'o',\n",
" 're',\n",
" 've',\n",
" 'y',\n",
" 'ain',\n",
" 'aren',\n",
" \"aren't\",\n",
" 'couldn',\n",
" \"couldn't\",\n",
" 'didn',\n",
" \"didn't\",\n",
" 'doesn',\n",
" \"doesn't\",\n",
" 'hadn',\n",
" \"hadn't\",\n",
" 'hasn',\n",
" \"hasn't\",\n",
" 'haven',\n",
" \"haven't\",\n",
" 'isn',\n",
" \"isn't\",\n",
" 'ma',\n",
" 'mightn',\n",
" \"mightn't\",\n",
" 'mustn',\n",
" \"mustn't\",\n",
" 'needn',\n",
" \"needn't\",\n",
" 'shan',\n",
" \"shan't\",\n",
" 'shouldn',\n",
" \"shouldn't\",\n",
" 'wasn',\n",
" \"wasn't\",\n",
" 'weren',\n",
" \"weren't\",\n",
" 'won',\n",
" \"won't\",\n",
" 'wouldn',\n",
" \"wouldn't\"]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
"ename": "LookupError",
"evalue": "\n**********************************************************************\n Resource \u001b[93mstopwords\u001b[0m not found.\n Please use the NLTK Downloader to obtain the resource:\n\n \u001b[31m>>> import nltk\n >>> nltk.download('stopwords')\n \u001b[0m\n For more information see: https://www.nltk.org/data.html\n\n Attempted to load \u001b[93mcorpora/stopwords\u001b[0m\n\n Searched in:\n - '/root/nltk_data'\n - '/root/anaconda3/envs/py310/nltk_data'\n - '/root/anaconda3/envs/py310/share/nltk_data'\n - '/root/anaconda3/envs/py310/lib/nltk_data'\n - '/usr/share/nltk_data'\n - '/usr/local/share/nltk_data'\n - '/usr/lib/nltk_data'\n - '/usr/local/lib/nltk_data'\n**********************************************************************\n",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mLookupError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/corpus/util.py:84\u001b[0m, in \u001b[0;36mLazyCorpusLoader.__load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 84\u001b[0m root \u001b[38;5;241m=\u001b[39m \u001b[43mnltk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfind\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msubdir\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mzip_name\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 85\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mLookupError\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/data.py:583\u001b[0m, in \u001b[0;36mfind\u001b[0;34m(resource_name, paths)\u001b[0m\n\u001b[1;32m 582\u001b[0m resource_not_found \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mmsg\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 583\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mLookupError\u001b[39;00m(resource_not_found)\n",
"\u001b[0;31mLookupError\u001b[0m: \n**********************************************************************\n Resource \u001b[93mstopwords\u001b[0m not found.\n Please use the NLTK Downloader to obtain the resource:\n\n \u001b[31m>>> import nltk\n >>> nltk.download('stopwords')\n \u001b[0m\n For more information see: https://www.nltk.org/data.html\n\n Attempted to load \u001b[93mcorpora/stopwords.zip/stopwords/\u001b[0m\n\n Searched in:\n - '/root/nltk_data'\n - '/root/anaconda3/envs/py310/nltk_data'\n - '/root/anaconda3/envs/py310/share/nltk_data'\n - '/root/anaconda3/envs/py310/lib/nltk_data'\n - '/usr/share/nltk_data'\n - '/usr/local/share/nltk_data'\n - '/usr/lib/nltk_data'\n - '/usr/local/lib/nltk_data'\n**********************************************************************\n",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mLookupError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m stop_words \u001b[38;5;241m=\u001b[39m \u001b[43mstopwords\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwords\u001b[49m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124menglish\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m stop_words\n",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/corpus/util.py:121\u001b[0m, in \u001b[0;36mLazyCorpusLoader.__getattr__\u001b[0;34m(self, attr)\u001b[0m\n\u001b[1;32m 118\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m attr \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m__bases__\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 119\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLazyCorpusLoader object has no attribute \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__bases__\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 121\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__load\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 122\u001b[0m \u001b[38;5;66;03m# This looks circular, but its not, since __load() changes our\u001b[39;00m\n\u001b[1;32m 123\u001b[0m \u001b[38;5;66;03m# __class__ to something new:\u001b[39;00m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, attr)\n",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/corpus/util.py:86\u001b[0m, in \u001b[0;36mLazyCorpusLoader.__load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 84\u001b[0m root \u001b[38;5;241m=\u001b[39m nltk\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mfind(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubdir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mzip_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 85\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mLookupError\u001b[39;00m:\n\u001b[0;32m---> 86\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m 88\u001b[0m \u001b[38;5;66;03m# Load the corpus.\u001b[39;00m\n\u001b[1;32m 89\u001b[0m corpus \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m__reader_cls(root, \u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m__args, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m__kwargs)\n",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/corpus/util.py:81\u001b[0m, in \u001b[0;36mLazyCorpusLoader.__load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 79\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 81\u001b[0m root \u001b[38;5;241m=\u001b[39m \u001b[43mnltk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfind\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msubdir\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__name\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 82\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mLookupError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/py310/lib/python3.10/site-packages/nltk/data.py:583\u001b[0m, in \u001b[0;36mfind\u001b[0;34m(resource_name, paths)\u001b[0m\n\u001b[1;32m 581\u001b[0m sep \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m*\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m*\u001b[39m \u001b[38;5;241m70\u001b[39m\n\u001b[1;32m 582\u001b[0m resource_not_found \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mmsg\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00msep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 583\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mLookupError\u001b[39;00m(resource_not_found)\n",
"\u001b[0;31mLookupError\u001b[0m: \n**********************************************************************\n Resource \u001b[93mstopwords\u001b[0m not found.\n Please use the NLTK Downloader to obtain the resource:\n\n \u001b[31m>>> import nltk\n >>> nltk.download('stopwords')\n \u001b[0m\n For more information see: https://www.nltk.org/data.html\n\n Attempted to load \u001b[93mcorpora/stopwords\u001b[0m\n\n Searched in:\n - '/root/nltk_data'\n - '/root/anaconda3/envs/py310/nltk_data'\n - '/root/anaconda3/envs/py310/share/nltk_data'\n - '/root/anaconda3/envs/py310/lib/nltk_data'\n - '/usr/share/nltk_data'\n - '/usr/local/share/nltk_data'\n - '/usr/lib/nltk_data'\n - '/usr/local/lib/nltk_data'\n**********************************************************************\n"
]
}
],
"source": [
Expand Down Expand Up @@ -1483,11 +1329,23 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 5,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'textblob'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtextblob\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Word \n",
"\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'textblob'"
]
}
],
"source": [
"from textblob import Word"
"from textblob import Word "
]
},
{
Expand All @@ -1502,6 +1360,36 @@
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: WordCloud in /root/anaconda3/envs/py310/lib/python3.10/site-packages (1.9.3)\n",
"Requirement already satisfied: numpy>=1.6.1 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from WordCloud) (1.26.2)\n",
"Requirement already satisfied: pillow in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from WordCloud) (10.1.0)\n",
"Requirement already satisfied: matplotlib in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from WordCloud) (3.8.2)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (1.2.0)\n",
"Requirement already satisfied: cycler>=0.10 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (4.46.0)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (1.4.5)\n",
"Requirement already satisfied: packaging>=20.0 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (23.2)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (3.1.1)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from matplotlib->WordCloud) (2.8.2)\n",
"Requirement already satisfied: six>=1.5 in /root/anaconda3/envs/py310/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib->WordCloud) (1.16.0)\n",
"\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
"\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"import wordcloud"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down

0 comments on commit 6115a2b

Please sign in to comment.