{ "cells": [ { "cell_type": "markdown", "id": "908dc123-5278-4d13-827a-7588ac3127cb", "metadata": {}, "source": [ "# 10 Scikit-learn" ] }, { "cell_type": "markdown", "id": "d6a701f8-6b4b-466c-ac62-aeb73146cfcc", "metadata": {}, "source": [ "Sklearn is the most famous Python package in terms of machine learning." ] }, { "cell_type": "code", "execution_count": 2, "id": "63a71d52-d7ed-4f64-912d-e3913ba989b0", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 5, "id": "fd7d6467-dd85-451a-97ff-dc47f66b0705", "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv('./smsspamcollection.tsv', sep='\\t')" ] }, { "cell_type": "code", "execution_count": 6, "id": "d870e691-5e75-46c8-a909-6227a05f2b42", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "

	label	message	length	punct
0	ham	Go until jurong point, crazy.. Available only ...	111	9
1	ham	Ok lar... Joking wif u oni...	29	6
2	spam	Free entry in 2 a wkly comp to win FA Cup fina...	155	6
3	ham	U dun say so early hor... U c already then say...	49	6
4	ham	Nah I don't think he goes to usf, he lives aro...	61	2

\n", "

" ], "text/plain": [ " label message length punct\n", "0 ham Go until jurong point, crazy.. Available only ... 111 9\n", "1 ham Ok lar... Joking wif u oni... 29 6\n", "2 spam Free entry in 2 a wkly comp to win FA Cup fina... 155 6\n", "3 ham U dun say so early hor... U c already then say... 49 6\n", "4 ham Nah I don't think he goes to usf, he lives aro... 61 2" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] }, { "cell_type": "markdown", "id": "ee4220f0-2d95-4193-ad6c-66c26ac7281a", "metadata": {}, "source": [ "Checking missing values:" ] }, { "cell_type": "code", "execution_count": 7, "id": "9c6ec3e0-04be-41e2-8df4-779f694835bb", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "label 0\n", "message 0\n", "length 0\n", "punct 0\n", "dtype: int64" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "markdown", "id": "f2a62681-a001-4410-a30f-359264cc2221", "metadata": {}, "source": [ "Checking dataframe length:" ] }, { "cell_type": "code", "execution_count": 9, "id": "30270a51-85fc-488c-bf0f-8fea5dfa67d9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "5572" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(df)" ] }, { "cell_type": "markdown", "id": "7d6ae4dc-1a4f-417c-a19e-ab80a18c54ae", "metadata": {}, "source": [ "Checking binary output labels:" ] }, { "cell_type": "code", "execution_count": 11, "id": "a15bb57d-8b1c-4241-b317-6aceb6c8aab1", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['ham', 'spam'], dtype=object)" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['label'].unique()" ] }, { "cell_type": "markdown", "id": "5b960d35-75d0-416e-99d3-83deed5675ca", "metadata": {}, "source": [ "Checking the occurrences for each label:" ] }, { "cell_type": "code", "execution_count": 13, "id": "d16125c8-deb0-420d-9c0a-862873b4a803", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "label\n", "ham 4825\n", "spam 747\n", "Name: count, dtype: int64" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['label'].value_counts()" ] }, { "cell_type": "code", "execution_count": 14, "id": "48066261-ee5e-4321-87b0-b7d69b43d7c5", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split" ] }, { "cell_type": "code", "execution_count": 16, "id": "cdb40015-17db-42db-b8b8-7090d2cf3482", "metadata": {}, "outputs": [], "source": [ "X = df[['length', 'punct']]\n", "y = df['label']\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)" ] }, { "cell_type": "code", "execution_count": 17, "id": "74f92f21-2d14-4600-9310-86e7eac2b0f0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(3900, 2)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_train.shape" ] }, { "cell_type": "code", "execution_count": 19, "id": "a62ff3ad-502b-4c5a-bffe-7c232139103b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1672, 2)" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_test.shape" ] }, { "cell_type": "code", "execution_count": 20, "id": "df655827-628a-4025-8402-b76005a462c3", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1672,)" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_test.shape" ] }, { "cell_type": "code", "execution_count": 21, "id": "9a46a122-a861-4a0b-b0ae-682ceb7fdf41", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(3900,)" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_train.shape" ] }, { "cell_type": "code", "execution_count": 22, "id": "479f17e9-28ee-4ac7-b335-09fd3db24880", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "3245 ham\n", "944 ham\n", "1044 ham\n", "2484 ham\n", "812 ham\n", " ... \n", "2505 ham\n", "2525 spam\n", "4975 ham\n", "650 spam\n", "4463 ham\n", "Name: label, Length: 1672, dtype: object" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_test" ] }, { "cell_type": "code", "execution_count": 23, "id": "33d580ee-1f08-4c5b-9532-8d0116db0087", "metadata": {}, "outputs": [], "source": [ "from sklearn.linear_model import LogisticRegression" ] }, { "cell_type": "code", "execution_count": 28, "id": "57e8397d-6825-4508-96cc-03465b22ad98", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

LogisticRegression()

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.

" ], "text/plain": [ "LogisticRegression()" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lr_model = LogisticRegression(solver='lbfgs')\n", "\n", "lr_model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 29, "id": "64531d16-a5a2-480b-ae26-f53e81369f4d", "metadata": {}, "outputs": [], "source": [ "from sklearn import metrics" ] }, { "cell_type": "code", "execution_count": 31, "id": "dac0be91-54ee-4414-8834-fdce4377d7ee", "metadata": {}, "outputs": [], "source": [ "predictions = lr_model.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 32, "id": "8607038a-8fbf-430b-a602-4c96767e9055", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1404, 44],\n", " [ 219, 5]])" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "metrics.confusion_matrix(y_test, predictions)" ] }, { "cell_type": "code", "execution_count": 33, "id": "54e318fe-7147-4e81-b816-4e22c63493fd", "metadata": {}, "outputs": [], "source": [ "df = pd.DataFrame(metrics.confusion_matrix(y_test, predictions), index=['ham', 'spam'], columns=['ham', 'spam'])" ] }, { "cell_type": "code", "execution_count": 34, "id": "8c32990c-47c1-4dc3-b988-2c78696e29bf", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "

	ham	spam
ham	1404	44
spam	219	5

\n", "

" ], "text/plain": [ " ham spam\n", "ham 1404 44\n", "spam 219 5" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 35, "id": "e21a5967-2adf-4ae0-a71e-4f1df25dc907", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " ham 0.87 0.97 0.91 1448\n", " spam 0.10 0.02 0.04 224\n", "\n", " accuracy 0.84 1672\n", " macro avg 0.48 0.50 0.48 1672\n", "weighted avg 0.76 0.84 0.80 1672\n", "\n" ] } ], "source": [ "print(metrics.classification_report(y_test, predictions))" ] }, { "cell_type": "code", "execution_count": 36, "id": "9037a8fe-ac39-422d-897d-b02bc4964e2b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.8427033492822966\n" ] } ], "source": [ "print(metrics.accuracy_score(y_test, predictions))" ] }, { "cell_type": "code", "execution_count": 37, "id": "d749c3d7-314f-41aa-ad4a-026c2b6d1329", "metadata": {}, "outputs": [], "source": [ "from sklearn.naive_bayes import MultinomialNB" ] }, { "cell_type": "code", "execution_count": 40, "id": "e1451a3c-bbd1-4102-ba19-378bf13fa222", "metadata": {}, "outputs": [], "source": [ "nb_model = MultinomialNB()" ] }, { "cell_type": "code", "execution_count": 41, "id": "526df92e-6b56-413d-8973-447842d2a6d3", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

MultinomialNB()

" ], "text/plain": [ "MultinomialNB()" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nb_model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 42, "id": "c5d4e8e8-4c1d-4352-b72e-0002db302068", "metadata": {}, "outputs": [], "source": [ "predictions = nb_model.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 43, "id": "f086e6c8-f00b-41cd-92fd-7385e6fb4c52", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " ham 0.87 0.99 0.92 1448\n", " spam 0.00 0.00 0.00 224\n", "\n", " accuracy 0.86 1672\n", " macro avg 0.43 0.50 0.46 1672\n", "weighted avg 0.75 0.86 0.80 1672\n", "\n" ] } ], "source": [ "print(metrics.classification_report(y_test, predictions))" ] }, { "cell_type": "code", "execution_count": 44, "id": "4feff554-a4f9-4e1d-b0e1-358f902dd28b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.8600478468899522\n" ] } ], "source": [ "print(metrics.accuracy_score(y_test, predictions))" ] }, { "cell_type": "code", "execution_count": 45, "id": "0ff01904-4cf6-4f79-b033-29dfe4a57474", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "

	ham	spam
ham	1438	10
spam	224	0

\n", "

" ], "text/plain": [ " ham spam\n", "ham 1438 10\n", "spam 224 0" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.DataFrame(metrics.confusion_matrix(y_test, predictions), index=['ham', 'spam'], columns=['ham', 'spam'])\n", "df" ] }, { "cell_type": "code", "execution_count": 46, "id": "a2c5cbe4-fd5b-4e81-91d1-d0f5cb03459e", "metadata": {}, "outputs": [], "source": [ "from sklearn.svm import SVC" ] }, { "cell_type": "code", "execution_count": 47, "id": "98e53aef-b745-4e75-9aa1-c23e76f31cd7", "metadata": {}, "outputs": [], "source": [ "svc_model = SVC()" ] }, { "cell_type": "code", "execution_count": 49, "id": "208e916e-3978-44ad-87c4-457c686a5361", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

SVC()

" ], "text/plain": [ "SVC()" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "svc_model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 51, "id": "184bb22a-fd2e-4861-8438-1965cc950cc2", "metadata": {}, "outputs": [], "source": [ "predictions = svc_model.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 52, "id": "8ac8f1eb-3aad-47f2-a631-cf6e2fd2bf01", "metadata": {}, "outputs": [ { "data": { "text/html": [ "

\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "

	ham	spam
ham	1420	28
spam	186	38

\n", "

" ], "text/plain": [ " ham spam\n", "ham 1420 28\n", "spam 186 38" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.DataFrame(metrics.confusion_matrix(y_test, predictions), index=['ham', 'spam'], columns=['ham', 'spam'])\n", "df" ] }, { "cell_type": "code", "execution_count": null, "id": "7c513616-047d-49c7-938e-3a6281a5ac2a", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.11.4" } }, "nbformat": 4, "nbformat_minor": 5 }