Morten Hjorth-Jensen
364 lines
14 KiB
Plaintext
364 lines
14 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Perceptron #"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"{'data': array([[5.1, 3.5, 1.4, 0.2],\n",
|
||
" [4.9, 3. , 1.4, 0.2],\n",
|
||
" [4.7, 3.2, 1.3, 0.2],\n",
|
||
" [4.6, 3.1, 1.5, 0.2],\n",
|
||
" [5. , 3.6, 1.4, 0.2],\n",
|
||
" [5.4, 3.9, 1.7, 0.4],\n",
|
||
" [4.6, 3.4, 1.4, 0.3],\n",
|
||
" [5. , 3.4, 1.5, 0.2],\n",
|
||
" [4.4, 2.9, 1.4, 0.2],\n",
|
||
" [4.9, 3.1, 1.5, 0.1],\n",
|
||
" [5.4, 3.7, 1.5, 0.2],\n",
|
||
" [4.8, 3.4, 1.6, 0.2],\n",
|
||
" [4.8, 3. , 1.4, 0.1],\n",
|
||
" [4.3, 3. , 1.1, 0.1],\n",
|
||
" [5.8, 4. , 1.2, 0.2],\n",
|
||
" [5.7, 4.4, 1.5, 0.4],\n",
|
||
" [5.4, 3.9, 1.3, 0.4],\n",
|
||
" [5.1, 3.5, 1.4, 0.3],\n",
|
||
" [5.7, 3.8, 1.7, 0.3],\n",
|
||
" [5.1, 3.8, 1.5, 0.3],\n",
|
||
" [5.4, 3.4, 1.7, 0.2],\n",
|
||
" [5.1, 3.7, 1.5, 0.4],\n",
|
||
" [4.6, 3.6, 1. , 0.2],\n",
|
||
" [5.1, 3.3, 1.7, 0.5],\n",
|
||
" [4.8, 3.4, 1.9, 0.2],\n",
|
||
" [5. , 3. , 1.6, 0.2],\n",
|
||
" [5. , 3.4, 1.6, 0.4],\n",
|
||
" [5.2, 3.5, 1.5, 0.2],\n",
|
||
" [5.2, 3.4, 1.4, 0.2],\n",
|
||
" [4.7, 3.2, 1.6, 0.2],\n",
|
||
" [4.8, 3.1, 1.6, 0.2],\n",
|
||
" [5.4, 3.4, 1.5, 0.4],\n",
|
||
" [5.2, 4.1, 1.5, 0.1],\n",
|
||
" [5.5, 4.2, 1.4, 0.2],\n",
|
||
" [4.9, 3.1, 1.5, 0.2],\n",
|
||
" [5. , 3.2, 1.2, 0.2],\n",
|
||
" [5.5, 3.5, 1.3, 0.2],\n",
|
||
" [4.9, 3.6, 1.4, 0.1],\n",
|
||
" [4.4, 3. , 1.3, 0.2],\n",
|
||
" [5.1, 3.4, 1.5, 0.2],\n",
|
||
" [5. , 3.5, 1.3, 0.3],\n",
|
||
" [4.5, 2.3, 1.3, 0.3],\n",
|
||
" [4.4, 3.2, 1.3, 0.2],\n",
|
||
" [5. , 3.5, 1.6, 0.6],\n",
|
||
" [5.1, 3.8, 1.9, 0.4],\n",
|
||
" [4.8, 3. , 1.4, 0.3],\n",
|
||
" [5.1, 3.8, 1.6, 0.2],\n",
|
||
" [4.6, 3.2, 1.4, 0.2],\n",
|
||
" [5.3, 3.7, 1.5, 0.2],\n",
|
||
" [5. , 3.3, 1.4, 0.2],\n",
|
||
" [7. , 3.2, 4.7, 1.4],\n",
|
||
" [6.4, 3.2, 4.5, 1.5],\n",
|
||
" [6.9, 3.1, 4.9, 1.5],\n",
|
||
" [5.5, 2.3, 4. , 1.3],\n",
|
||
" [6.5, 2.8, 4.6, 1.5],\n",
|
||
" [5.7, 2.8, 4.5, 1.3],\n",
|
||
" [6.3, 3.3, 4.7, 1.6],\n",
|
||
" [4.9, 2.4, 3.3, 1. ],\n",
|
||
" [6.6, 2.9, 4.6, 1.3],\n",
|
||
" [5.2, 2.7, 3.9, 1.4],\n",
|
||
" [5. , 2. , 3.5, 1. ],\n",
|
||
" [5.9, 3. , 4.2, 1.5],\n",
|
||
" [6. , 2.2, 4. , 1. ],\n",
|
||
" [6.1, 2.9, 4.7, 1.4],\n",
|
||
" [5.6, 2.9, 3.6, 1.3],\n",
|
||
" [6.7, 3.1, 4.4, 1.4],\n",
|
||
" [5.6, 3. , 4.5, 1.5],\n",
|
||
" [5.8, 2.7, 4.1, 1. ],\n",
|
||
" [6.2, 2.2, 4.5, 1.5],\n",
|
||
" [5.6, 2.5, 3.9, 1.1],\n",
|
||
" [5.9, 3.2, 4.8, 1.8],\n",
|
||
" [6.1, 2.8, 4. , 1.3],\n",
|
||
" [6.3, 2.5, 4.9, 1.5],\n",
|
||
" [6.1, 2.8, 4.7, 1.2],\n",
|
||
" [6.4, 2.9, 4.3, 1.3],\n",
|
||
" [6.6, 3. , 4.4, 1.4],\n",
|
||
" [6.8, 2.8, 4.8, 1.4],\n",
|
||
" [6.7, 3. , 5. , 1.7],\n",
|
||
" [6. , 2.9, 4.5, 1.5],\n",
|
||
" [5.7, 2.6, 3.5, 1. ],\n",
|
||
" [5.5, 2.4, 3.8, 1.1],\n",
|
||
" [5.5, 2.4, 3.7, 1. ],\n",
|
||
" [5.8, 2.7, 3.9, 1.2],\n",
|
||
" [6. , 2.7, 5.1, 1.6],\n",
|
||
" [5.4, 3. , 4.5, 1.5],\n",
|
||
" [6. , 3.4, 4.5, 1.6],\n",
|
||
" [6.7, 3.1, 4.7, 1.5],\n",
|
||
" [6.3, 2.3, 4.4, 1.3],\n",
|
||
" [5.6, 3. , 4.1, 1.3],\n",
|
||
" [5.5, 2.5, 4. , 1.3],\n",
|
||
" [5.5, 2.6, 4.4, 1.2],\n",
|
||
" [6.1, 3. , 4.6, 1.4],\n",
|
||
" [5.8, 2.6, 4. , 1.2],\n",
|
||
" [5. , 2.3, 3.3, 1. ],\n",
|
||
" [5.6, 2.7, 4.2, 1.3],\n",
|
||
" [5.7, 3. , 4.2, 1.2],\n",
|
||
" [5.7, 2.9, 4.2, 1.3],\n",
|
||
" [6.2, 2.9, 4.3, 1.3],\n",
|
||
" [5.1, 2.5, 3. , 1.1],\n",
|
||
" [5.7, 2.8, 4.1, 1.3],\n",
|
||
" [6.3, 3.3, 6. , 2.5],\n",
|
||
" [5.8, 2.7, 5.1, 1.9],\n",
|
||
" [7.1, 3. , 5.9, 2.1],\n",
|
||
" [6.3, 2.9, 5.6, 1.8],\n",
|
||
" [6.5, 3. , 5.8, 2.2],\n",
|
||
" [7.6, 3. , 6.6, 2.1],\n",
|
||
" [4.9, 2.5, 4.5, 1.7],\n",
|
||
" [7.3, 2.9, 6.3, 1.8],\n",
|
||
" [6.7, 2.5, 5.8, 1.8],\n",
|
||
" [7.2, 3.6, 6.1, 2.5],\n",
|
||
" [6.5, 3.2, 5.1, 2. ],\n",
|
||
" [6.4, 2.7, 5.3, 1.9],\n",
|
||
" [6.8, 3. , 5.5, 2.1],\n",
|
||
" [5.7, 2.5, 5. , 2. ],\n",
|
||
" [5.8, 2.8, 5.1, 2.4],\n",
|
||
" [6.4, 3.2, 5.3, 2.3],\n",
|
||
" [6.5, 3. , 5.5, 1.8],\n",
|
||
" [7.7, 3.8, 6.7, 2.2],\n",
|
||
" [7.7, 2.6, 6.9, 2.3],\n",
|
||
" [6. , 2.2, 5. , 1.5],\n",
|
||
" [6.9, 3.2, 5.7, 2.3],\n",
|
||
" [5.6, 2.8, 4.9, 2. ],\n",
|
||
" [7.7, 2.8, 6.7, 2. ],\n",
|
||
" [6.3, 2.7, 4.9, 1.8],\n",
|
||
" [6.7, 3.3, 5.7, 2.1],\n",
|
||
" [7.2, 3.2, 6. , 1.8],\n",
|
||
" [6.2, 2.8, 4.8, 1.8],\n",
|
||
" [6.1, 3. , 4.9, 1.8],\n",
|
||
" [6.4, 2.8, 5.6, 2.1],\n",
|
||
" [7.2, 3. , 5.8, 1.6],\n",
|
||
" [7.4, 2.8, 6.1, 1.9],\n",
|
||
" [7.9, 3.8, 6.4, 2. ],\n",
|
||
" [6.4, 2.8, 5.6, 2.2],\n",
|
||
" [6.3, 2.8, 5.1, 1.5],\n",
|
||
" [6.1, 2.6, 5.6, 1.4],\n",
|
||
" [7.7, 3. , 6.1, 2.3],\n",
|
||
" [6.3, 3.4, 5.6, 2.4],\n",
|
||
" [6.4, 3.1, 5.5, 1.8],\n",
|
||
" [6. , 3. , 4.8, 1.8],\n",
|
||
" [6.9, 3.1, 5.4, 2.1],\n",
|
||
" [6.7, 3.1, 5.6, 2.4],\n",
|
||
" [6.9, 3.1, 5.1, 2.3],\n",
|
||
" [5.8, 2.7, 5.1, 1.9],\n",
|
||
" [6.8, 3.2, 5.9, 2.3],\n",
|
||
" [6.7, 3.3, 5.7, 2.5],\n",
|
||
" [6.7, 3. , 5.2, 2.3],\n",
|
||
" [6.3, 2.5, 5. , 1.9],\n",
|
||
" [6.5, 3. , 5.2, 2. ],\n",
|
||
" [6.2, 3.4, 5.4, 2.3],\n",
|
||
" [5.9, 3. , 5.1, 1.8]]), 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
|
||
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
|
||
" 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
|
||
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
|
||
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
|
||
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
|
||
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]), 'frame': None, 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'), 'DESCR': '.. _iris_dataset:\\n\\nIris 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\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature. Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day. (See Duda & Hart, for example.) The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant. One class is linearly separable from the other 2; the\\nlatter 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 ...', 'feature_names': ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'], 'filename': '/opt/anaconda3/lib/python3.8/site-packages/sklearn/datasets/data/iris.csv'}\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Load required libraries\n",
|
||
"from sklearn import datasets\n",
|
||
"from sklearn.preprocessing import StandardScaler\n",
|
||
"from sklearn.linear_model import Perceptron\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"from sklearn.metrics import accuracy_score\n",
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"\n",
|
||
"# Load the iris dataset\n",
|
||
"iris = datasets.load_iris()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"This data sets consists of 3 different types of irises’ (Setosa, Versicolour, and Virginica) petal and sepal length, stored in a 150x4 numpy.ndarray. The rows being the samples and the columns being: Sepal Length, Sepal Width, Petal Length and Petal Width. See\n",
|
||
"https://scikit-learn.org/stable/auto_examples/datasets/plot_iris_dataset.html"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 45,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"(100, 4)\n",
|
||
"[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
|
||
" 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Create our X and y data\n",
|
||
"X = iris.data[0:100,:]\n",
|
||
"y = iris.target[0:100]\n",
|
||
"\n",
|
||
"print(X.shape)\n",
|
||
"print(y)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 1. Data Processing ##"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"(75, 4)\n",
|
||
"(75,)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Split the data into 75% training data and 25% testing data\n",
|
||
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(X_train.shape)\n",
|
||
"print(y_train.shape)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 47,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Train the scaler, which standarizes all the features to have mean=0 and unit variance\n",
|
||
"sc = StandardScaler()\n",
|
||
"sc.fit(X_train)\n",
|
||
"\n",
|
||
"# Apply the scaler to the X training data\n",
|
||
"X_train_std = sc.transform(X_train)\n",
|
||
"\n",
|
||
"# Apply the SAME scaler to the X test data\n",
|
||
"X_test_std = sc.transform(X_test)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 2. Model Training ##"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 48,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"Perceptron(eta0=0.1)"
|
||
]
|
||
},
|
||
"execution_count": 48,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Create a perceptron instance with a learning rate of 0.1\n",
|
||
"perceptron = Perceptron(eta0=0.1)\n",
|
||
"\n",
|
||
"# Train the perceptron\n",
|
||
"perceptron.fit(X_train_std, y_train)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# 3. Model Testing #"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 49,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[1 0 1 1 0 0 0 1 1 0 1 1 0 1 0 1 1 1 0 0 0 0 0 1 0]\n",
|
||
"[1 0 1 1 0 0 0 1 1 0 1 1 0 1 0 1 1 1 0 0 0 0 0 1 0]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Apply the trained perceptron on the X data to make predicts for the y test data\n",
|
||
"y_pred = perceptron.predict(X_test_std)\n",
|
||
"\n",
|
||
"\n",
|
||
"# Print the predicted labels\n",
|
||
"print(y_pred)\n",
|
||
"\n",
|
||
"# Print the true labels\n",
|
||
"print(y_test)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": []
|
||
}
|
||
],
|
||
"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": "3.8.3"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
}
|