{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Machine Learning with scikit-learn" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import sklearn" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 1. the iris dataset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The iris is a classic data set in the field of data recognition." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "from sklearn import datasets\n", "iris = datasets.load_iris()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "sklearn.utils._bunch.Bunch" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(iris)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ ".. _iris_dataset:\n", "\n", "Iris plants dataset\n", "--------------------\n", "\n", "**Data Set Characteristics:**\n", "\n", " :Number of Instances: 150 (50 in each of three classes)\n", " :Number of Attributes: 4 numeric, predictive attributes and the class\n", " :Attribute Information:\n", " - sepal length in cm\n", " - sepal width in cm\n", " - petal length in cm\n", " - petal width in cm\n", " - class:\n", " - Iris-Setosa\n", " - Iris-Versicolour\n", " - Iris-Virginica\n", " \n", " :Summary Statistics:\n", "\n", " ============== ==== ==== ======= ===== ====================\n", " Min Max Mean SD Class Correlation\n", " ============== ==== ==== ======= ===== ====================\n", " sepal length: 4.3 7.9 5.84 0.83 0.7826\n", " sepal width: 2.0 4.4 3.05 0.43 -0.4194\n", " petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\n", " petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\n", " ============== ==== ==== ======= ===== ====================\n", "\n", " :Missing Attribute Values: None\n", " :Class Distribution: 33.3% for each of 3 classes.\n", " :Creator: R.A. Fisher\n", " :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n", " :Date: July, 1988\n", "\n", "The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\n", "from Fisher's paper. Note that it's the same as in R, but not as in the UCI\n", "Machine Learning Repository, which has two wrong data points.\n", "\n", "This is perhaps the best known database to be found in the\n", "pattern recognition literature. Fisher's paper is a classic in the field and\n", "is referenced frequently to this day. (See Duda & Hart, for example.) The\n", "data set contains 3 classes of 50 instances each, where each class refers to a\n", "type of iris plant. One class is linearly separable from the other 2; the\n", "latter are NOT linearly separable from each other.\n", "\n", ".. topic:: References\n", "\n", " - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\n", " Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\n", " Mathematical Statistics\" (John Wiley, NY, 1950).\n", " - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\n", " (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\n", " - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\n", " Structure and Classification Rule for Recognition in Partially Exposed\n", " Environments\". IEEE Transactions on Pattern Analysis and Machine\n", " Intelligence, Vol. PAMI-2, No. 1, 67-71.\n", " - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\". IEEE Transactions\n", " on Information Theory, May 1972, 431-433.\n", " - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al\"s AUTOCLASS II\n", " conceptual clustering system finds 3 classes in the data.\n", " - Many, many more ...\n" ] } ], "source": [ "print(iris.DESCR)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us take a look at the data." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "numpy.ndarray" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data = iris.data\n", "type(data)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(150, 4)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The data is a two dimensional array, of 150 rows and 4 columns." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "numpy.ndarray" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ydata = iris.target\n", "type(ydata)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(150,)" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ydata.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let us see how many different target values we have." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 1, 2])" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.unique(ydata)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "There are three different values for the target." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 2. finding the clusters in the data set" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "from sklearn import cluster" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In running the k-means algorithm, we have to given the number of clusters." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "k_means = cluster.KMeans(n_clusters=3, n_init='auto')" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\jan\\miniconda3\\lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1436: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n", " warnings.warn(\n" ] }, { "data": { "text/html": [ "
KMeans(n_clusters=3, n_init='auto')
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": [ "KMeans(n_clusters=3, n_init='auto')" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "k_means.fit(data)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To see how good the labeling of the data points along the three clusters is, we look at the first ten points." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "numpy.ndarray" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(k_means.labels_)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(150,)" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "k_means.labels_.shape" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2])" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "k_means.labels_[::10]" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0 0 0 0 0 1 1 1 1 1 2 2 2 2 2]\n" ] } ], "source": [ "print(ydata[::10])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 3. dimension reduction" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The data set is four dimensional. To make a two dimensional plot, we apply the principal component analysis." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The code comes from page 149 on the book by\n", "Gavin Hackeling: *Mastering Machine Learning with scikit-learn.\n", "Apply effective learning algorithms to real-world problems\n", "using scikit-learn.* Packt publishing, 2014." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "from sklearn.decomposition import PCA" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "data = datasets.load_iris()" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "y = data.target\n", "X = data.data" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "# dimension reduction\n", "pca = PCA(n_components=2)\n", "reduced_X = pca.fit_transform(X)" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "# assemble and plot the reduced data\n", "red_x, red_y = [], []\n", "blue_x, blue_y = [], []\n", "green_x, green_y = [], []\n", "for i in range(len(reduced_X)):\n", " if y[i] == 0:\n", " red_x.append(reduced_X[i][0])\n", " red_y.append(reduced_X[i][1])\n", " elif y[i] == 1:\n", " blue_x.append(reduced_X[i][0])\n", " blue_y.append(reduced_X[i][1])\n", " else:\n", " green_x.append(reduced_X[i][0])\n", " green_y.append(reduced_X[i][1])" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(red_x, red_y, c='r', marker='x')\n", "plt.scatter(blue_x, blue_y, c='b', marker='D')\n", "plt.scatter(green_x, green_y, c='g', marker='.')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 4. nearest neighbors" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "iris = datasets.load_iris()\n", "iris_X = iris.data\n", "iris_y = iris.target" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [], "source": [ "np.random.seed(0)\n", "indices = np.random.permutation(len(iris_X))\n", "iris_X_train = iris_X[indices[:-10]]\n", "iris_y_train = iris_y[indices[:-10]]\n", "iris_X_test = iris_X[indices[-10:]]\n", "iris_y_test = iris_y[indices[-10:]]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we will be running the classification algorithm." ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
KNeighborsClassifier()
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": [ "KNeighborsClassifier()" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.neighbors import KNeighborsClassifier\n", "knn = KNeighborsClassifier()\n", "knn.fit(iris_X_train, iris_y_train)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we can predict and verify." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 2, 1, 0, 0, 0, 2, 1, 2, 0])" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "knn.predict(iris_X_test)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 1, 1, 0, 0, 0, 2, 1, 2, 0])" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "iris_y_test" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 5. regression and cross validation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Another data set is used to illustrate regression." ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "# boston = datasets.load_boston()\n", "# print(boston.DESCR)\n", "# The Boston dataset was removed for ethical concerns." ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ ".. _california_housing_dataset:\n", "\n", "California Housing dataset\n", "--------------------------\n", "\n", "**Data Set Characteristics:**\n", "\n", " :Number of Instances: 20640\n", "\n", " :Number of Attributes: 8 numeric, predictive attributes and the target\n", "\n", " :Attribute Information:\n", " - MedInc median income in block group\n", " - HouseAge median house age in block group\n", " - AveRooms average number of rooms per household\n", " - AveBedrms average number of bedrooms per household\n", " - Population block group population\n", " - AveOccup average number of household members\n", " - Latitude block group latitude\n", " - Longitude block group longitude\n", "\n", " :Missing Attribute Values: None\n", "\n", "This dataset was obtained from the StatLib repository.\n", "https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html\n", "\n", "The target variable is the median house value for California districts,\n", "expressed in hundreds of thousands of dollars ($100,000).\n", "\n", "This dataset was derived from the 1990 U.S. census, using one row per census\n", "block group. A block group is the smallest geographical unit for which the U.S.\n", "Census Bureau publishes sample data (a block group typically has a population\n", "of 600 to 3,000 people).\n", "\n", "A household is a group of people residing within a home. Since the average\n", "number of rooms and bedrooms in this dataset are provided per household, these\n", "columns may take surprisingly large values for block groups with few households\n", "and many empty houses, such as vacation resorts.\n", "\n", "It can be downloaded/loaded using the\n", ":func:`sklearn.datasets.fetch_california_housing` function.\n", "\n", ".. topic:: References\n", "\n", " - Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions,\n", " Statistics and Probability Letters, 33 (1997) 291-297\n", "\n" ] } ], "source": [ "from sklearn.datasets import fetch_california_housing\n", "housing = fetch_california_housing()\n", "print(housing.DESCR)" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import cross_val_predict\n", "from sklearn import linear_model" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "lr = linear_model.LinearRegression()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The target variable is the median house value for California districts,\n", "expressed in hundreds of thousands of dollars ($100,000)." ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [], "source": [ "y = housing.target" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The ``cross_val_predict`` returns an array of the same\n", "size as ``y`` where each entry is a prediction\n", "obtained by cross validation." ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [], "source": [ "predicted = cross_val_predict(lr, housing.data, y, cv=10)" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig, ax = plt.subplots()\n", "ax.scatter(y, predicted, edgecolors=(0, 0, 0))\n", "ax.plot([y.min(), y.max()], [y.min(), y.max()], \\\n", " 'k--', lw=4)\n", "ax.set_xlabel('Measured')\n", "ax.set_ylabel('Predicted')\n", "plt.show()" ] } ], "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": "3.10.10" }, "latex_envs": { "LaTeX_envs_menu_present": true, "autocomplete": true, "bibliofile": "biblio.bib", "cite_by": "apalike", "current_citInitial": 1, "eqLabelWithNumbers": true, "eqNumInitial": 1, "hotkeys": { "equation": "Ctrl-E", "itemize": "Ctrl-I" }, "labels_anchors": false, "latex_user_defs": false, "report_style_numbering": false, "user_envs_cfg": false } }, "nbformat": 4, "nbformat_minor": 4 }