def mainDecisionTreeImplementation(decisiontreemodel, linPCA,
training_dataframe, pca_option):
df = pd.read_csv("BreastCancerData.csv")
column_titles = None
column_titles = processing.processData(df, column_titles)
column_titles = np.array(column_titles)
training_data = []
final_validation = []
processing.splitData(training_dataframe, .8, training_data,
final_validation)
training_data = np.array(training_data)
final_validation = np.array(final_validation)
features = []
labels = []
features, labels = processing.createFeatures_Labels(training_data)
np.transpose(labels)
features_data = None
labels_data = None
features_data, labels_data = processing.convertToDataFrame(
features, labels, column_titles)
if (pca_option == 'no'):
# print('model without PCA')
DT_STD_means.append(
DecisionTree(features_data, labels_data, decisiontreemodel))
elif (pca_option == 'both'):
DT_STD_means.append(
DecisionTree(features_data, labels_data, decisiontreemodel))
features_data_PCA = processing.linearPCAReduction(
features_data, linPCA)
features_df_PCA = pd.DataFrame(
features_data_PCA,
columns=column_titles[1:(features_data_PCA.shape[1] + 1)])
# print('Decision Tree model with PCA')
DT_PCA_means.append(
DecisionTree(features_df_PCA, labels_data, decisiontreemodel))
else:
features_data_PCA = processing.linearPCAReduction(
features_data, linPCA)
features_df_PCA = pd.DataFrame(
features_data_PCA,
columns=column_titles[1:(features_data_PCA.shape[1] + 1)])
# print('Decision Tree model with PCA')
DT_PCA_means.append(
DecisionTree(features_df_PCA, labels_data, decisiontreemodel))
def PolynomialSVMTest(pca_option):
import SVM
SVM.SVMSimulation(SVM.svm_poly, processing.linear_pca,
processing.overall_training_data, pca_option)
processing.final_validation = np.array(processing.final_validation)
FV_features = []
FV_labels = []
FV_features, FV_labels = processing.createFeatures_Labels(
processing.final_validation)
FV_features_data = None
FV_labels_data = None
FV_features_data, FV_labels_data = processing.convertToDataFrame(
FV_features, FV_labels, processing.column_titles)
global SVM_POLY_final_predictions
if(pca_option == 'yes' or pca_option == 'both'):
transformed_FV = processing.linear_pca.transform(FV_features_data)
final_predictions = SVM.svm_poly.predict(transformed_FV)
SVM_GAUS_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('POLYNOMIAL SVM MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('POLYNOMIAL SVM MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('POLYNOMIAL SVM MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
else:
final_predictions = SVM.svm_poly.predict(FV_features_data)
SVM_GAUS_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('POLYNOMIAL SVM MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('POLYNOMIAL SVM MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('POLYNOMIAL SVM MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
def NeuralNetworkTest(pca_option):
import NN
NN.NeuralNetworkSimulation(
NN.nn, processing.linear_pca, processing.overall_training_data, pca_option)
processing.final_validation = np.array(processing.final_validation)
FV_features = []
FV_labels = []
FV_features, FV_labels = processing.createFeatures_Labels(
processing.final_validation)
FV_features_data = None
FV_labels_data = None
FV_features_data, FV_labels_data = processing.convertToDataFrame(
FV_features, FV_labels, processing.column_titles)
global NN_final_predictions
if(pca_option == 'yes' or pca_option == 'both'):
transformed_FV = processing.linear_pca.transform(FV_features_data)
final_predictions = NN.nn.predict(transformed_FV)
NN_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('NEURAL NETWORK MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('NEURAL NETWORK MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('NEURAL NETWORK MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
else:
final_predictions = NN.nn.predict(FV_features_data)
NN_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('NEURAL NETWORK MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('NEURAL NETWORK MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('NEURAL NETWORK MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
def RandomForestTest(pca_option):
import RF
RF.RandomForestSimulation(
RF.rf, processing.linear_pca, processing.overall_training_data, pca_option)
processing.final_validation = np.array(processing.final_validation)
FV_features = []
FV_labels = []
FV_features, FV_labels = processing.createFeatures_Labels(
processing.final_validation)
FV_features_data = None
FV_labels_data = None
FV_features_data, FV_labels_data = processing.convertToDataFrame(
FV_features, FV_labels, processing.column_titles)
global RF_final_predictions
if(pca_option == 'yes' or pca_option == 'both'):
transformed_FV = processing.linear_pca.transform(FV_features_data)
final_predictions = RF.rf.predict(transformed_FV)
RF_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('RANDOM FOREST MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('RANDOM FOREST MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('RANDOM FOREST MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
else:
final_predictions = RF.rf.predict(FV_features_data)
RF_final_predictions = final_predictions
accuracy = metrics.accuracy_score(final_predictions, FV_labels)
precision = metrics.precision_score(
FV_labels, final_predictions, average='micro')
recall = metrics.recall_score(
FV_labels, final_predictions, average='micro')
print('RANDOM FOREST MODEL FINAL TEST DATA ACCURACY: ', 100 * accuracy)
print('RANDOM FOREST MODEL FINAL TEST DATA PRECISION: ', 100 * precision)
print('RANDOM FOREST MODEL FINAL TEST DATA RECALL: ', 100 * recall)
print()
return accuracy, precision, recall
def mainNeuralNetworkImplementation(nnmodel, linPCA, training_dataframe, pca_option):
df = pd.read_csv("BreastCancerData.csv")
column_titles = None
column_titles = processing.processData(df, column_titles)
column_titles = np.array(column_titles)
training_data = []
final_validation = []
processing.splitData(training_dataframe, .8,
training_data, final_validation)
training_data = np.array(training_data)
final_validation = np.array(final_validation)
features = []
labels = []
features, labels = processing.createFeatures_Labels(training_data)
np.transpose(labels)
features_data = None
labels_data = None
features_data, labels_data = processing.convertToDataFrame(
features, labels, column_titles)
if(pca_option == 'both'):
#print('Random Forest model without PCA')
NN_STD_means.append(NeuralNetwork(
features_data, labels_data, nnmodel))
# print()
features_data_PCA = processing.linearPCAReduction(
features_data, linPCA)
features_df_PCA = pd.DataFrame(
features_data_PCA, columns=column_titles[1:(features_data_PCA.shape[1] + 1)])
#print('Random Forest model with PCA')
NN_PCA_means.append(NeuralNetwork(
features_df_PCA, labels_data, nnmodel))
elif(pca_option == 'yes'):
features_data_PCA = processing.linearPCAReduction(
features_data, linPCA)
features_df_PCA = pd.DataFrame(
features_data_PCA, columns=column_titles[1:(features_data_PCA.shape[1] + 1)])
#print('Random Forest model with PCA')
NN_PCA_means.append(NeuralNetwork(
features_df_PCA, labels_data, nnmodel))
else:
NN_STD_means.append(NeuralNetwork(
features_data, labels_data, nnmodel))