ml.py

from numpy import genfromtxt
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import datasets, svm
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score

def main():
    features_train = genfromtxt("Abalone_train.csv", delimiter=',' ,usecols = (0,1,2,3,4,5,6,7), skip_header=1)
    labels_train = genfromtxt("Abalone_train.csv", delimiter=',' ,usecols = (8), skip_header=1)

    features_test = genfromtxt("Abalone_test.csv", delimiter=',' ,usecols = (0,1,2,3,4,5,6,7), skip_header=1)
    labels_test = genfromtxt("Abalone_test.csv", delimiter=',' ,usecols = (8), skip_header=1)
    
    ## SUPPORT VECTOR MACHINE 
    print("Training SVM...")
    clfSVM = svm.SVC(kernel='rbf', gamma=0.5, C=100)
    clfSVM.fit(features_train, labels_train)
    print("Training SVM completed. Now testing.")
    svmPredict = clfSVM.predict(features_test)
    svmConfusion = confusion_matrix(labels_test, svmPredict)
    svmAccuracy  = accuracy_score(labels_test, svmPredict)
    print("Accuracy : " + str(svmAccuracy))
    print(svmConfusion)
    plt.matshow(svmConfusion)
    plt.title("SVM Confusion Matrix")
    plt.show()

    ## ENSEMBLE LEARNING
    print("Training ensemble learning...")
    clfEnsemble = GradientBoostingClassifier()
    clfEnsemble.fit(features_train, labels_train)
    print("Training ensemble completed. Now testing.")
    ensemblePredict = clfEnsemble.predict(features_test)
    ensembleConfusion = confusion_matrix(labels_test, ensemblePredict)
    ensembleAccuracy  = accuracy_score(labels_test, ensemblePredict)
    print("Accuracy : " + str(ensembleAccuracy))
    print(ensembleConfusion)
    plt.matshow(ensembleConfusion)
    plt.title("Ensemble Confusion Matrix")
    plt.show()

    ## DECISION TREE CLASSIFIER
    print("Training tree classifier...")
    clfTree = tree.DecisionTreeClassifier()
    clfTree.fit(features_train, labels_train)
    print("Training tree classifier completed. Now testing")
    treePredict = clfTree.predict(features_test)
    treeConfusion = confusion_matrix(labels_test, treePredict)
    treeAccuracy = accuracy_score(labels_test, treePredict)
    print("Accuracy : " + str(treeAccuracy))
    print(treeConfusion)
    plt.matshow(treeConfusion)
    plt.title("Tree Confusion Matrix")
    plt.show()

    ## RANDOM FOREST CLASSIFIER
    print("Training random forest classifier")
    clfRandom = RandomForestClassifier()
    clfRandom.fit(features_train, labels_train)
    print("Training random forest classifier completed. Now testing")
    randomPredict = clfRandom.predict(features_test)
    randomConfusion = confusion_matrix(labels_test, randomPredict)
    randomAccuracy = accuracy_score(labels_test, randomPredict)
    print("Accuracy : " + str(randomAccuracy))
    print(randomConfusion)
    plt.matshow(randomConfusion)
    plt.title("Random Forest Confusion Matrix")
    plt.show()

if __name__ == "__main__":
    main()