{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "lzBc7Vwg8l_w" }, "outputs": [], "source": [ "# Importing Libraries\n", "import numpy as np\n", "import pandas as pd\n", "\n", "# Import dataset\n", "dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter = '\\t')" ] }, { "cell_type": "code", "source": [ "# library to clean data\n", "import re\n", "\n", "# Natural Language Tool Kit\n", "import nltk\n", "\n", "nltk.download('stopwords')\n", "\n", "# to remove stopword\n", "from nltk.corpus import stopwords\n", "\n", "# for Stemming propose\n", "from nltk.stem.porter import PorterStemmer\n", "\n", "# Initialize empty array\n", "# to append clean text\n", "corpus = []\n", "\n", "# 1000 (reviews) rows to clean\n", "for i in range(0, 1000):\n", "\n", "\t# column : \"Review\", row ith\n", "\treview = re.sub('[^a-zA-Z]', ' ', dataset['Review'][i])\n", "\n", "\t# convert all cases to lower cases\n", "\treview = review.lower()\n", "\n", "\t# split to array(default delimiter is \" \")\n", "\treview = review.split()\n", "\n", "\t# creating PorterStemmer object to\n", "\t# take main stem of each word\n", "\tps = PorterStemmer()\n", "\n", "\t# loop for stemming each word\n", "\t# in string array at ith row\n", "\treview = [ps.stem(word) for word in review\n", "\t\t\t\tif not word in set(stopwords.words('english'))]\n", "\n", "\t# rejoin all string array elements\n", "\t# to create back into a string\n", "\treview = ' '.join(review)\n", "\n", "\t# append each string to create\n", "\t# array of clean text\n", "\tcorpus.append(review)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "PWD4G-Kh86do", "outputId": "59b39470-89bf-4466-f9f1-de11dca5114e" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package stopwords to /root/nltk_data...\n", "[nltk_data] Package stopwords is already up-to-date!\n" ] } ] }, { "cell_type": "code", "source": [ "# Creating the Bag of Words model\n", "from sklearn.feature_extraction.text import CountVectorizer\n", "\n", "# To extract max 1500 feature.\n", "# \"max_features\" is attribute to\n", "# experiment with to get better results\n", "cv = CountVectorizer(max_features = 1500)\n", "\n", "# X contains corpus (dependent variable)\n", "X = cv.fit_transform(corpus).toarray()\n", "\n", "# y contains answers if review\n", "# is positive or negative\n", "y = dataset.iloc[:, 1].values" ], "metadata": { "id": "P7MAkjaO88Zp" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Splitting the dataset into\n", "# the Training set and Test set\n", "from sklearn.model_selection import train_test_split\n", "\n", "# experiment with \"test_size\"\n", "# to get better results\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)" ], "metadata": { "id": "t0rmp-4l8-GU" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "# Fitting Random Forest Classification\n", "# to the Training set\n", "from sklearn.ensemble import RandomForestClassifier\n", "\n", "# n_estimators can be said as number of\n", "# trees, experiment with n_estimators\n", "# to get better results\n", "model = RandomForestClassifier(n_estimators = 501,\n", "\t\t\t\t\t\t\tcriterion = 'entropy')\n", "\n", "model.fit(X_train, y_train)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 74 }, "id": "TQnRMDwY8_BM", "outputId": "a4653f6e-9ad4-4273-ed2b-8d8aa97a505b" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "RandomForestClassifier(criterion='entropy', n_estimators=501)" ], "text/html": [ "
RandomForestClassifier(criterion='entropy', n_estimators=501)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ] }, "metadata": {}, "execution_count": 9 } ] }, { "cell_type": "code", "source": [ "# Predicting the Test set results\n", "y_pred = model.predict(X_test)\n", "\n", "y_pred" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "KjrLCFtC9AXl", "outputId": "9a81aeb7-8b11-46e5-9c4a-77820729d593" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "array([0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0,\n", " 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0,\n", " 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0,\n", " 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0,\n", " 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0,\n", " 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1,\n", " 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0,\n", " 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1,\n", " 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1,\n", " 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1,\n", " 0, 0, 0, 1, 0, 0, 1, 1])" ] }, "metadata": {}, "execution_count": 10 } ] }, { "cell_type": "code", "source": [ "# Making the Confusion Matrix\n", "from sklearn.metrics import confusion_matrix\n", "\n", "cm = confusion_matrix(y_test, y_pred)\n", "\n", "cm" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "HIrqSoXY9Bpf", "outputId": "7f00bb75-92a7-4fcb-e112-510c84db469d" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "array([[102, 28],\n", " [ 41, 79]])" ] }, "metadata": {}, "execution_count": 11 } ] } ] }