Scribd Logo
Upload

Welcome to Scribd!

  • 4 views

    BVH

    Uploaded by

    buiviethoangpltn
    bvh

    Copyright:

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

    BVH

    Uploaded by

    buiviethoangpltn
    4 views2 pages
    bvh

    Original Title

    bvh

    Copyright

    © © All Rights Reserved

    Available Formats

    TXT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    bvh

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    4 views2 pages

    BVH

    Uploaded by

    buiviethoangpltn
    bvh

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    of 2

    import numpy as np

    import pandas as pd
    import tensorflow as tf
    import sklearn.metrics as metrics
    from sklearn.preprocessing import normalize

    # for visualization
    import matplotlib.pyplot as plt
    import seaborn as sns
    import datetime as dt
    %matplotlib inline

    # Import Warnings
    import warnings
    warnings.simplefilter(action="ignore")

    # for data splitting, transforming and model training


    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    # import SVC classifier
    from sklearn.svm import SVC
    # import metrics to compute accuracy
    from sklearn.metrics import accuracy_score

    =============================================================
    def show_data(data):
    sns.pairplot(data,hue="diagnosis")
    plt.show()
    =============================================================
    def preprocessing_data():
    #data collection
    data = pd.read_csv('Breast.csv') # Load the Iris dataset into a Pandas
    DataFrame
    print(data.head())
    #print(data)
    print(data.describe())
    #data cleaning
    data.drop('id',axis=1,inplace=True) #dropping the id column as it is unecessary
    data.drop('Unnamed: 32',axis=1,inplace=True)
    # print(data)
    print(data.isna().sum())# Checking for missing values
    #data.dropna(inplace=True)

    print(data.duplicated().sum()) # Checking for dupliacted values


    data.drop_duplicates(inplace=True) # Remove dupliacted values
    print(data.info())

    #show data
    #show_data(data)

    train, test = train_test_split(data, test_size = 0.2) # the attribute


    test_size=0.2 splits the data into 80% and 20% ratio. train=80% and test=20%

    X_train=
    train[['radius_mean','texture_mean','perimeter_mean','area_mean','smoothness_mean',
    'compactness_mean','concavity_mean','concave points_mean',
    'symmetry_mean','fractal_dimension_mean','radius_se','texture_se','perimeter_se','a
    rea_se','smoothness_se','compactness_se','concavity_se','concave
    points_se','symmetry_se','fractal_dimension_se','radius_worst','texture_worst','per
    imeter_worst','area_worst','smoothness_worst','compactness_worst','concavity_worst'
    ,'concave points_worst','symmetry_worst','fractal_dimension_worst']] # taking the
    training data features
    y_train=train.diagnosis
    # output of our training data
    X_test=
    test[['radius_mean','texture_mean','perimeter_mean','area_mean','smoothness_mean','
    compactness_mean','concavity_mean','concave points_mean',
    'symmetry_mean','fractal_dimension_mean','radius_se','texture_se','perimeter_se','a
    rea_se','smoothness_se','compactness_se','concavity_se','concave
    points_se','symmetry_se','fractal_dimension_se','radius_worst','texture_worst','per
    imeter_worst','area_worst','smoothness_worst','compactness_worst','concavity_worst'
    ,'concave points_worst','symmetry_worst','fractal_dimension_worst']] # taking the
    training data features # taking test data features
    y_test=test.diagnosis

    #data transformation

    sc = StandardScaler()

    X_train = sc.fit_transform(X_train)
    X_test = sc.transform(X_test)

    # #data transformation

    return (X_train, X_test, y_train, y_test)


    ===================================================================================
    ============
    def SVM_Classifier(X_train, X_test, y_train, y_test):
    svc=SVC()

    # fit classifier to training set

    svc.fit(X_train,y_train)

    # make predictions on test set


    y_pred=svc.predict(X_test)

    # compute and print accuracy score


    print('Model accuracy score with default hyperparameters: {0:0.4f}'.
    format(accuracy_score(y_test, y_pred)))
    # Setting parameters of model KNN step by step
    ===================================================================================
    if __name__ == "__main__":
    (X_train, X_test, y_train, y_test)=preprocessing_data()
    SVM_Classifier(X_train, X_test, y_train, y_test)

    You might also like