Last active
July 16, 2021 16:50
-
-
Save kmehant/fb29dcfb54dd19a9736c058dae0a56b4 to your computer and use it in GitHub Desktop.
Mehant_LogisticRegression.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"name": "411843_Mehant_LogisticRegression.ipynb", | |
"provenance": [], | |
"collapsed_sections": [], | |
"include_colab_link": true | |
}, | |
"kernelspec": { | |
"display_name": "Python 3", | |
"name": "python3" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "view-in-github", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"<a href=\"https://colab.research.google.com/gist/kmehant/fb29dcfb54dd19a9736c058dae0a56b4/411843_mehant_logisticregression.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "EephMyPHGbnD", | |
"outputId": "03311919-8df5-4998-f751-4448d8b6c6e3" | |
}, | |
"source": [ | |
"\n", | |
"\"\"\"\n", | |
"Import python modules\n", | |
"\"\"\"\n", | |
"\n", | |
"import pandas as pd\n", | |
"import numpy as np\n", | |
"\n", | |
"from sklearn.feature_extraction.text import CountVectorizer\n", | |
"from sklearn.model_selection import train_test_split\n", | |
"from sklearn.linear_model import LogisticRegression\n", | |
"from sklearn.metrics import confusion_matrix, classification_report\n", | |
"from sklearn.preprocessing import LabelEncoder\n", | |
"\n", | |
"import matplotlib.pyplot as plt\n", | |
"import os\n", | |
"import re\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Create a pandas dataframe\n", | |
"\"\"\"\n", | |
"\n", | |
"columns = ['target', 'review']\n", | |
"df = pd.DataFrame(columns=columns)\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Import data into dataframes and perform cleaning\n", | |
"\"\"\"\n", | |
"\n", | |
"for pos_file in os.listdir('/content/drive/MyDrive/data/pos'):\n", | |
" f = open('/content/drive/MyDrive/data/pos/' + pos_file, \"r\")\n", | |
" file_data = f.read()\n", | |
" # clean data\n", | |
" file_data = re.sub(r'[^a-zA-Z0-9_\\s]+', '', file_data)\n", | |
" file_data = file_data.strip()\n", | |
" # append at the end of the dataframe\n", | |
" df.loc[len(df.index)] = [1, file_data]\n", | |
"\n", | |
"\n", | |
"for neg_file in os.listdir('/content/drive/MyDrive/data/neg'):\n", | |
" f = open('/content/drive/MyDrive/data/neg/' + neg_file, \"r\")\n", | |
" file_data = f.read()\n", | |
" # clean data\n", | |
" file_data = re.sub(r'[^a-zA-Z0-9_\\s]+', '', file_data)\n", | |
" file_data = file_data.strip()\n", | |
" # append at the end of the dataframe\n", | |
" df.loc[len(df.index)] = [0, file_data]\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Split the data into test and train data\n", | |
"\"\"\"\n", | |
"\n", | |
"x = df.review.values\n", | |
"y = df.target.values\n", | |
"x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.20, random_state=20)\n", | |
"\n", | |
"y_train = y_train.astype(int)\n", | |
"y_test = y_test.astype(int)\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Create a count vectorizer\n", | |
"\"\"\"\n", | |
"\n", | |
"vectorizer = CountVectorizer(stop_words=['is','are','and','in','the'])\n", | |
"vectorizer.fit(x_train)\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Transform text (independent feature) into numerical type using count vectorizer\n", | |
"\"\"\"\n", | |
"\n", | |
"X_train = vectorizer.transform(x_train)\n", | |
"X_test = vectorizer.transform(x_test)\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Create a logistic regression model\n", | |
"\"\"\"\n", | |
"\n", | |
"classifier = LogisticRegression(max_iter=100)\n", | |
"classifier.fit(X_train, y_train)\n", | |
"\n", | |
"\n", | |
"\"\"\"\n", | |
"Compute testing accuracy\n", | |
"\"\"\"\n", | |
"\n", | |
"score = classifier.score(X_test, y_test)\n", | |
"\n", | |
"print(\"Accuracy: \", (score*100), '%', sep='')\n" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": [ | |
"Accuracy: 84.0%\n" | |
], | |
"name": "stdout" | |
}, | |
{ | |
"output_type": "stream", | |
"text": [ | |
"/usr/local/lib/python3.6/dist-packages/sklearn/linear_model/_logistic.py:940: ConvergenceWarning: lbfgs failed to converge (status=1):\n", | |
"STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n", | |
"\n", | |
"Increase the number of iterations (max_iter) or scale the data as shown in:\n", | |
" https://scikit-learn.org/stable/modules/preprocessing.html\n", | |
"Please also refer to the documentation for alternative solver options:\n", | |
" https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n", | |
" extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)\n" | |
], | |
"name": "stderr" | |
} | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"id": "9jNX44DCPcDr", | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"outputId": "b5a4d6f3-0137-4110-8296-417e70b196cc" | |
}, | |
"source": [ | |
"\"\"\"\n", | |
"Logistic regression vectorized implementation\n", | |
"\"\"\"\n", | |
"\n", | |
"def h_theta(z):\n", | |
" return 1/ (1 + np.exp(-z))\n", | |
"\n", | |
"def costFn(theta, x, y):\n", | |
" h_theta_x = h_theta(np.dot(x, theta))\n", | |
" cost = (-y * np.log(h_theta_x)) - ((1 - y) * np.log(1 - h_theta_x))\n", | |
" j_theta = 1/m * sum(cost)\n", | |
" deviation = 1 / m * np.dot(x.transpose(), (h_theta_x - y))\n", | |
" return j_theta[0], deviation\n", | |
"\n", | |
"def gradientDescent(x,y,theta,alpha,num_iters):\n", | |
" for i in range(num_iters):\n", | |
" cost, dev = costFn(theta, x, y)\n", | |
" theta = theta - (alpha * dev)\n", | |
" return theta\n", | |
"\n", | |
"def predictClass(theta,x):\n", | |
" predictions = x.dot(theta)\n", | |
" return predictions > 0\n", | |
"\n", | |
"m = X_train.shape[0]\n", | |
"n = df.shape[1] - 1\n", | |
"\n", | |
"X_train = X_train.toarray()\n", | |
"X_train = np.array(X_train)\n", | |
"\n", | |
"x = []\n", | |
"maxx = 0\n", | |
"for i in range(X_train.shape[0]):\n", | |
" maxx = max(maxx, np.sum(X_train[i]))\n", | |
"for i in range(X_train.shape[0]):\n", | |
" x.append([1, (np.sum(X_train[i]) / maxx)])\n", | |
"x = np.asarray(x)\n", | |
"\n", | |
"y = np.asarray(y_train)\n", | |
"y = y.reshape(m, 1)\n", | |
"x = x.reshape(m, 2)\n", | |
"\n", | |
"theta = np.zeros((n + 1,1))\n", | |
"cost, deviation = costFn(theta,x,y)\n", | |
"\n", | |
"theta = gradientDescent(x, y, theta, 0.1, 1000)\n", | |
"\n", | |
"y_pred = predictClass(theta, x)\n", | |
"\n", | |
"print(\"training Accuracy: \", (sum(y_pred == y)[0] / m) * 100,\"%\", sep='')\n" | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": [ | |
"training Accuracy: 55.875%\n" | |
], | |
"name": "stdout" | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment