Scribd Logo
Upload

Welcome to Scribd!

  • 5 views

    Machine Learning

    Uploaded by

    2021pcecscharul037
    The document compares the k-means and EM clustering algorithms. It loads iris data and clusters it using both algorithms. It plots the real labels and predicted clusters from each algorithm for comparison. It comments on the quality of clustering from each.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Machine Learning

    Uploaded by

    2021pcecscharul037
    5 views8 pages
    The document compares the k-means and EM clustering algorithms. It loads iris data and clusters it using both algorithms. It plots the real labels and predicted clusters from each algorithm for comparison. It comments on the quality of clustering from each.

    Original Title

    machine learning

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document compares the k-means and EM clustering algorithms. It loads iris data and clusters it using both algorithms. It plots the real labels and predicted clusters from each algorithm for comparison. It comments on the quality of clustering from each.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    5 views8 pages

    Machine Learning

    Uploaded by

    2021pcecscharul037
    The document compares the k-means and EM clustering algorithms. It loads iris data and clusters it using both algorithms. It plots the real labels and predicted clusters from each algorithm for comparison. It comments on the quality of clustering from each.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 8

    Candidate elimination

    import numpy as np

    import pandas as pd

    data = pd.read_csv('2.csv')

    concepts = np.array(data.iloc[:,0:-1])

    target = np.array(data.iloc[:,-1])

    def learn(concepts, target):

    specific_h = concepts[0].copy()

    print("initialization of specific_h \n",specific_h)

    general_h = [["?" for i in range(len(specific_h))] for i in range(len(specific_h))]

    print("initialization of general_h \n", general_h)

    for i, h in enumerate(concepts):

    if target[i] == "yes":

    print("If instance is Positive ")

    for x in range(len(specific_h)):

    if h[x]!= specific_h[x]:

    specific_h[x] ='?'

    general_h[x][x] ='?'

    if target[i] == "no":

    print("If instance is Negative ")

    for x in range(len(specific_h)):

    if h[x]!= specific_h[x]:

    general_h[x][x] = specific_h[x]

    else:

    general_h[x][x] = '?'

    print(" step {}".format(i+1))

    print(specific_h)
    print(general_h)

    print("\n")

    print("\n")

    indices = [i for i, val in enumerate(general_h) if val == ['?', '?', '?', '?', '?', '?']]

    for i in indices:

    general_h.remove(['?', '?', '?', '?', '?', '?'])

    return specific_h, general_h

    s_final, g_final = learn(concepts, target)

    print("Final Specific_h:", s_final, sep="\n")

    print("Final General_h:", g_final, sep="\n")

    output

    initialization of specific_h

    ['sunny' 'warm' 'normal' 'strong' 'warm' 'same']

    initialization of general_h

    [['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'],

    ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?']]

    If instance is Positive

    step 1

    ['sunny' 'warm' 'normal' 'strong' 'warm' 'same']

    [['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'],

    ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?']]

    If instance is Positive

    step 2

    ['sunny' 'warm' '?' 'strong' 'warm' 'same']

    [['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'],
    ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?']]

    If instance is Negative

    step 3

    ['sunny' 'warm' '?' 'strong' 'warm' 'same']

    [['sunny', '?', '?', '?', '?', '?'], ['?', 'warm', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'],

    ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', 'same']]

    If instance is Positive

    step 4

    ['sunny' 'warm' '?' 'strong' '?' '?']

    [['sunny', '?', '?', '?', '?', '?'], ['?', 'warm', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'],

    ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?'], ['?', '?', '?', '?', '?', '?']]

    Final Specific_h:

    ['sunny' 'warm' '?' 'strong' '?' '?']

    Final General_h:

    [['sunny', '?', '?', '?', '?', '?'], ['?', 'warm', '?', '?', '?', '?']]
    Write a program to implement the naïve Bayesian classifier for a sampletraining data set stored as
    a .CSV file. Compute the accuracy of the classifier, considering few test data sets.
    Assuming a set of documents that need to be classified, use the naïve BayesianClassifier model to
    perform this task. Built-in Java classes/API can be used towrite the program. Calculate the accuracy,
    precision, and recall for your dataset
    Apply EM algorithm to cluster a set of data stored in a .CSV file. Use the samedata set for clustering
    using k-Means algorithm. Compare the results of thesetwo algorithms and comment on the quality
    of clustering. You can addJava/Python ML library classes/API in the program.

    from sklearn.cluster import KMeans

    from sklearn import preprocessing

    from sklearn.mixture import GaussianMixture

    from sklearn.datasets import load_iris

    import sklearn.metrics as sm

    import pandas as pd

    import numpy as np

    import matplotlib.pyplot as plt

    dataset=load_iris()

    # print(dataset)

    X=pd.DataFrame(dataset.data)
    X.columns=['Sepal_Length','Sepal_Width','Petal_Length','Petal_Width']

    y=pd.DataFrame(dataset.target)

    y.columns=['Targets']

    # print(X)

    plt.figure(figsize=(14,7))

    colormap=np.array(['red','lime','black'])

    # REAL PLOT

    plt.subplot(1,3,1)

    plt.scatter(X.Petal_Length,X.Petal_Width,c=colormap[y.Targets],s=40)

    plt.title('Real')

    # K-PLOT

    plt.subplot(1,3,2)

    model=KMeans(n_clusters=3)

    model.fit(X)

    predY=np.choose(model.labels_,[0,1,2]).astype(np.int64)

    plt.scatter(X.Petal_Length,X.Petal_Width,c=colormap[predY],s=40)

    plt.title('KMeans')

    # GMM PLOT

    scaler=preprocessing.StandardScaler()

    scaler.fit(X)

    xsa=scaler.transform(X)

    xs=pd.DataFrame(xsa,columns=X.columns)

    gmm=GaussianMixture(n_components=3)

    gmm.fit(xs)

    y_cluster_gmm=gmm.predict(xs)

    plt.subplot(1,3,3)

    plt.scatter(X.Petal_Length,X.Petal_Width,c=colormap[y_cluster_gmm],s=40)
    plt.title('GMM Classification')

    You might also like