Add wordcloud

.ipynb_checkpoints/Wordcloud-checkpoint.ipynb

@@ -0,0 +1,227 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to\n",
+      "[nltk_data]     C:\\Users\\neha\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Importing packages\n",
+    "import pandas as pd\n",
+    "import string\n",
+    "import nltk\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "from nltk.corpus import stopwords\n",
+    "nltk.download(\"stopwords\")\n",
+    "stop_words = set(stopwords.words(\"english\"))\n",
+    "from wordcloud import WordCloud\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "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>review</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>One of the other reviewers has mentioned that ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>A wonderful little production. &lt;br /&gt;&lt;br /&gt;The...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>I thought this was a wonderful way to spend ti...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Basically there's a family where a little boy ...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Petter Mattei's \"Love in the Time of Money\" is...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                              review sentiment\n",
+       "0  One of the other reviewers has mentioned that ...  positive\n",
+       "1  A wonderful little production. <br /><br />The...  positive\n",
+       "2  I thought this was a wonderful way to spend ti...  positive\n",
+       "3  Basically there's a family where a little boy ...  negative\n",
+       "4  Petter Mattei's \"Love in the Time of Money\" is...  positive"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Loading Data \n",
+    "data = pd.read_csv(\"Dataset/IMDB Dataset.csv\")\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Remove punctuations\n",
+    "def remove_punct(text):\n",
+    "    text = text.lower()\n",
+    "    table=str.maketrans('','',string.punctuation)\n",
+    "    return text.translate(table)\n",
+    "\n",
+    "data[\"review\"]= data[\"review\"].apply(remove_punct,1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Tokenize and remove stop words\n",
+    "def tokenize_remove_stopwords(text):\n",
+    "    \n",
+    "    word_tokens = word_tokenize(text) # tokenization\n",
+    "    \n",
+    "    # remove stopwords\n",
+    "    filtered_sentence = []\n",
+    "    for w in word_tokens: \n",
+    "        if w not in stop_words: \n",
+    "            filtered_sentence.append(w) \n",
+    "    return filtered_sentence\n",
+    "\n",
+    "data[\"review\"]= data[\"review\"].apply(tokenize_remove_stopwords,1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert list to string\n",
+    "def convert_string(lst):\n",
+    "    lst = lst\n",
+    "    return ' '.join(lst)\n",
+    "data[\"review\"]= data[\"review\"].apply(convert_string,1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Word Cloud for all reviews\n",
+    "all_words = \" \".join([text for text in data[\"review\"]])\n",
+    "wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(all_words)\n",
+    "plt.figure(figsize=(10, 7))\n",
+    "plt.imshow(wordcloud, interpolation=\"bilinear\")\n",
+    "plt.axis(\"off\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Word Cloud for positive reviews\n",
+    "positive_words = \" \".join([text for text in data[\"review\"][data[\"sentiment\"]==\"positive\"]])\n",
+    "wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(positive_words)\n",
+    "plt.figure(figsize=(10, 7))\n",
+    "plt.imshow(wordcloud, interpolation=\"bilinear\")\n",
+    "plt.axis(\"off\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Word Cloud for negative reviews\n",
+    "negative_words = \" \".join([text for text in data[\"review\"][data[\"sentiment\"]==\"negative\"]])\n",
+    "wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(negative_words)\n",
+    "plt.figure(figsize=(10, 7))\n",
+    "plt.imshow(wordcloud, interpolation=\"bilinear\")\n",
+    "plt.axis(\"off\")\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "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": 4
+}